Mercurial > repos > mheinzl > hd
annotate hd.py @ 19:2e9f7ea7ae93 draft
planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/hd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a-dirty
author | mheinzl |
---|---|
date | Mon, 08 Oct 2018 05:56:04 -0400 |
parents | a8581bf627fd |
children | b084b6a8e3ac |
rev | line source |
---|---|
0
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
1 #!/usr/bin/env python |
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
2 |
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
3 # Hamming distance analysis of SSCSs |
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
4 # |
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
5 # Author: Monika Heinzl, Johannes-Kepler University Linz (Austria) |
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
6 # Contact: monika.heinzl@edumail.at |
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
7 # |
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
8 # Takes at least one TABULAR file with tags before the alignment to the SSCS and optionally a second TABULAR file as input. |
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
9 # The program produces a plot which shows a histogram of Hamming distances separated after family sizes, |
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
10 # a family size distribution separated after Hamming distances for all (sample_size=0) or a given sample of SSCSs or SSCSs, which form a DCS. |
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
11 # In additon, the tool produces HD and FSD plots for the difference between the HDs of both parts of the tags and for the chimeric reads |
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
12 # and finally a CSV file with the data of the plots. |
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
13 # It is also possible to perform the HD analysis with shortened tags with given sizes as input. |
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
14 # The tool can run on a certain number of processors, which can be defined by the user. |
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
15 |
19
2e9f7ea7ae93
planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/hd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a-dirty
mheinzl
parents:
18
diff
changeset
|
16 # USAGE: python hd.py --inputFile filename --inputName1 filename --inputFile2 filename2 --inputName2 filename2 --sample_size int/0 --sep "characterWhichSeparatesCSVFile" / |
2e9f7ea7ae93
planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/hd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a-dirty
mheinzl
parents:
18
diff
changeset
|
17 # --only_DCS True --FamilySize3 True --subset_tag True --nproc int --minFS int --maxFS int --nr_above_bars True/False --output_tabular outptufile_name_tabular --output_pdf outputfile_name_pdf |
0
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
18 |
19
2e9f7ea7ae93
planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/hd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a-dirty
mheinzl
parents:
18
diff
changeset
|
19 import argparse |
0
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
20 import itertools |
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
21 import operator |
19
2e9f7ea7ae93
planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/hd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a-dirty
mheinzl
parents:
18
diff
changeset
|
22 import sys |
2e9f7ea7ae93
planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/hd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a-dirty
mheinzl
parents:
18
diff
changeset
|
23 from collections import Counter |
0
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
24 from functools import partial |
19
2e9f7ea7ae93
planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/hd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a-dirty
mheinzl
parents:
18
diff
changeset
|
25 from multiprocessing.pool import Pool |
2e9f7ea7ae93
planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/hd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a-dirty
mheinzl
parents:
18
diff
changeset
|
26 |
2e9f7ea7ae93
planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/hd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a-dirty
mheinzl
parents:
18
diff
changeset
|
27 import matplotlib.pyplot as plt |
2e9f7ea7ae93
planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/hd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a-dirty
mheinzl
parents:
18
diff
changeset
|
28 import numpy |
0
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
29 from matplotlib.backends.backend_pdf import PdfPages |
19
2e9f7ea7ae93
planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/hd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a-dirty
mheinzl
parents:
18
diff
changeset
|
30 |
2e9f7ea7ae93
planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/hd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a-dirty
mheinzl
parents:
18
diff
changeset
|
31 plt.switch_backend('agg') |
0
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
32 |
19
2e9f7ea7ae93
planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/hd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a-dirty
mheinzl
parents:
18
diff
changeset
|
33 |
2e9f7ea7ae93
planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/hd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a-dirty
mheinzl
parents:
18
diff
changeset
|
34 def plotFSDwithHD2(familySizeList1, maximumXFS, minimumXFS, originalCounts, |
2e9f7ea7ae93
planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/hd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a-dirty
mheinzl
parents:
18
diff
changeset
|
35 title_file1, subtitle, pdf, relative=False, diff=True): |
1
7414792e1cb8
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 90ee23e393deb06fa5c15e3778fa23c39a25f7ce
mheinzl
parents:
0
diff
changeset
|
36 if diff is False: |
7414792e1cb8
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 90ee23e393deb06fa5c15e3778fa23c39a25f7ce
mheinzl
parents:
0
diff
changeset
|
37 colors = ["#e6194b", "#3cb44b", "#ffe119", "#0082c8", "#f58231", "#911eb4"] |
19
2e9f7ea7ae93
planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/hd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a-dirty
mheinzl
parents:
18
diff
changeset
|
38 labels = ["HD=1", "HD=2", "HD=3", "HD=4", "HD=5-8", "HD>8"] |
1
7414792e1cb8
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 90ee23e393deb06fa5c15e3778fa23c39a25f7ce
mheinzl
parents:
0
diff
changeset
|
39 else: |
7414792e1cb8
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 90ee23e393deb06fa5c15e3778fa23c39a25f7ce
mheinzl
parents:
0
diff
changeset
|
40 colors = ["#93A6AB", "#403C14", "#731E41", "#BAB591", "#085B6F", "#E8AA35", "#726C66"] |
7414792e1cb8
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 90ee23e393deb06fa5c15e3778fa23c39a25f7ce
mheinzl
parents:
0
diff
changeset
|
41 if relative is True: |
7414792e1cb8
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 90ee23e393deb06fa5c15e3778fa23c39a25f7ce
mheinzl
parents:
0
diff
changeset
|
42 labels = ["d=0", "d=0.1", "d=0.2", "d=0.3", "d=0.4", "d=0.5-0.8", "d>0.8"] |
7414792e1cb8
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 90ee23e393deb06fa5c15e3778fa23c39a25f7ce
mheinzl
parents:
0
diff
changeset
|
43 else: |
19
2e9f7ea7ae93
planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/hd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a-dirty
mheinzl
parents:
18
diff
changeset
|
44 labels = ["d=0", "d=1", "d=2", "d=3", "d=4", "d=5-8", "d>8"] |
1
7414792e1cb8
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 90ee23e393deb06fa5c15e3778fa23c39a25f7ce
mheinzl
parents:
0
diff
changeset
|
45 |
7414792e1cb8
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 90ee23e393deb06fa5c15e3778fa23c39a25f7ce
mheinzl
parents:
0
diff
changeset
|
46 fig = plt.figure(figsize=(6, 7)) |
7414792e1cb8
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 90ee23e393deb06fa5c15e3778fa23c39a25f7ce
mheinzl
parents:
0
diff
changeset
|
47 ax = fig.add_subplot(111) |
7414792e1cb8
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 90ee23e393deb06fa5c15e3778fa23c39a25f7ce
mheinzl
parents:
0
diff
changeset
|
48 plt.subplots_adjust(bottom=0.1) |
7414792e1cb8
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 90ee23e393deb06fa5c15e3778fa23c39a25f7ce
mheinzl
parents:
0
diff
changeset
|
49 p1 = numpy.bincount(numpy.concatenate((familySizeList1))) |
7414792e1cb8
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 90ee23e393deb06fa5c15e3778fa23c39a25f7ce
mheinzl
parents:
0
diff
changeset
|
50 maximumY = numpy.amax(p1) |
7414792e1cb8
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 90ee23e393deb06fa5c15e3778fa23c39a25f7ce
mheinzl
parents:
0
diff
changeset
|
51 |
7414792e1cb8
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 90ee23e393deb06fa5c15e3778fa23c39a25f7ce
mheinzl
parents:
0
diff
changeset
|
52 if len(range(minimumXFS, maximumXFS)) == 0: |
7414792e1cb8
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 90ee23e393deb06fa5c15e3778fa23c39a25f7ce
mheinzl
parents:
0
diff
changeset
|
53 range1 = range(minimumXFS - 1, minimumXFS + 2) |
7414792e1cb8
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 90ee23e393deb06fa5c15e3778fa23c39a25f7ce
mheinzl
parents:
0
diff
changeset
|
54 else: |
7414792e1cb8
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 90ee23e393deb06fa5c15e3778fa23c39a25f7ce
mheinzl
parents:
0
diff
changeset
|
55 range1 = range(0, maximumXFS + 2) |
7414792e1cb8
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 90ee23e393deb06fa5c15e3778fa23c39a25f7ce
mheinzl
parents:
0
diff
changeset
|
56 counts = plt.hist(familySizeList1, label=labels, |
7414792e1cb8
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 90ee23e393deb06fa5c15e3778fa23c39a25f7ce
mheinzl
parents:
0
diff
changeset
|
57 color=colors, stacked=True, |
19
2e9f7ea7ae93
planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/hd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a-dirty
mheinzl
parents:
18
diff
changeset
|
58 rwidth=0.8, alpha=1, align="left", |
2e9f7ea7ae93
planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/hd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a-dirty
mheinzl
parents:
18
diff
changeset
|
59 edgecolor="None", bins=range1) |
1
7414792e1cb8
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 90ee23e393deb06fa5c15e3778fa23c39a25f7ce
mheinzl
parents:
0
diff
changeset
|
60 plt.legend(loc='upper right', fontsize=14, frameon=True, bbox_to_anchor=(1.45, 1)) |
7414792e1cb8
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 90ee23e393deb06fa5c15e3778fa23c39a25f7ce
mheinzl
parents:
0
diff
changeset
|
61 |
19
2e9f7ea7ae93
planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/hd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a-dirty
mheinzl
parents:
18
diff
changeset
|
62 # plt.title(title_file1, fontsize=12) |
1
7414792e1cb8
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 90ee23e393deb06fa5c15e3778fa23c39a25f7ce
mheinzl
parents:
0
diff
changeset
|
63 plt.suptitle(subtitle, y=1, x=0.5, fontsize=14) |
2
316fbf91dd12
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit f9d5547849dabb59a33a5e998bda4730323d62a9
mheinzl
parents:
1
diff
changeset
|
64 plt.xlabel("Family size", fontsize=14) |
316fbf91dd12
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit f9d5547849dabb59a33a5e998bda4730323d62a9
mheinzl
parents:
1
diff
changeset
|
65 plt.ylabel("Absolute Frequency", fontsize=14) |
1
7414792e1cb8
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 90ee23e393deb06fa5c15e3778fa23c39a25f7ce
mheinzl
parents:
0
diff
changeset
|
66 |
7414792e1cb8
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 90ee23e393deb06fa5c15e3778fa23c39a25f7ce
mheinzl
parents:
0
diff
changeset
|
67 ticks = numpy.arange(0, maximumXFS + 1, 1) |
7414792e1cb8
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 90ee23e393deb06fa5c15e3778fa23c39a25f7ce
mheinzl
parents:
0
diff
changeset
|
68 ticks1 = map(str, ticks) |
7414792e1cb8
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 90ee23e393deb06fa5c15e3778fa23c39a25f7ce
mheinzl
parents:
0
diff
changeset
|
69 if maximumXFS >= 20: |
7414792e1cb8
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 90ee23e393deb06fa5c15e3778fa23c39a25f7ce
mheinzl
parents:
0
diff
changeset
|
70 ticks1[len(ticks1) - 1] = ">=20" |
7414792e1cb8
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 90ee23e393deb06fa5c15e3778fa23c39a25f7ce
mheinzl
parents:
0
diff
changeset
|
71 plt.xticks(numpy.array(ticks), ticks1) |
7414792e1cb8
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 90ee23e393deb06fa5c15e3778fa23c39a25f7ce
mheinzl
parents:
0
diff
changeset
|
72 [l.set_visible(False) for (i, l) in enumerate(ax.get_xticklabels()) if i % 5 != 0] |
7414792e1cb8
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 90ee23e393deb06fa5c15e3778fa23c39a25f7ce
mheinzl
parents:
0
diff
changeset
|
73 |
7414792e1cb8
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 90ee23e393deb06fa5c15e3778fa23c39a25f7ce
mheinzl
parents:
0
diff
changeset
|
74 plt.xlim((0, maximumXFS + 1)) |
7414792e1cb8
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 90ee23e393deb06fa5c15e3778fa23c39a25f7ce
mheinzl
parents:
0
diff
changeset
|
75 if len(numpy.concatenate(familySizeList1)) != 0: |
7414792e1cb8
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 90ee23e393deb06fa5c15e3778fa23c39a25f7ce
mheinzl
parents:
0
diff
changeset
|
76 plt.ylim((0, max(numpy.bincount(numpy.concatenate(familySizeList1))) * 1.1)) |
7414792e1cb8
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 90ee23e393deb06fa5c15e3778fa23c39a25f7ce
mheinzl
parents:
0
diff
changeset
|
77 |
7414792e1cb8
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 90ee23e393deb06fa5c15e3778fa23c39a25f7ce
mheinzl
parents:
0
diff
changeset
|
78 plt.ylim((0, maximumY * 1.2)) |
7414792e1cb8
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 90ee23e393deb06fa5c15e3778fa23c39a25f7ce
mheinzl
parents:
0
diff
changeset
|
79 legend = "\nmax. family size: \nabsolute frequency: \nrelative frequency: " |
7414792e1cb8
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 90ee23e393deb06fa5c15e3778fa23c39a25f7ce
mheinzl
parents:
0
diff
changeset
|
80 plt.text(0.15, -0.08, legend, size=12, transform=plt.gcf().transFigure) |
7414792e1cb8
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 90ee23e393deb06fa5c15e3778fa23c39a25f7ce
mheinzl
parents:
0
diff
changeset
|
81 |
11
7adc48c8a03d
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 8d9bdadb5e154dadc455720c99700afbd9aafae9
mheinzl
parents:
10
diff
changeset
|
82 count = numpy.bincount(originalCounts) # original counts |
19
2e9f7ea7ae93
planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/hd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a-dirty
mheinzl
parents:
18
diff
changeset
|
83 legend1 = "{}\n{}\n{:.5f}".format(max(originalCounts), count[len(count) - 1], float(count[len(count) - 1]) / sum(count)) |
1
7414792e1cb8
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 90ee23e393deb06fa5c15e3778fa23c39a25f7ce
mheinzl
parents:
0
diff
changeset
|
84 plt.text(0.5, -0.08, legend1, size=12, transform=plt.gcf().transFigure) |
19
2e9f7ea7ae93
planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/hd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a-dirty
mheinzl
parents:
18
diff
changeset
|
85 legend3 = "singletons\n{:,}\n{:.5f}".format(int(counts[0][len(counts[0]) - 1][1]), float(counts[0][len(counts[0]) - 1][1]) / sum(counts[0][len(counts[0]) - 1])) |
1
7414792e1cb8
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 90ee23e393deb06fa5c15e3778fa23c39a25f7ce
mheinzl
parents:
0
diff
changeset
|
86 plt.text(0.7, -0.08, legend3, transform=plt.gcf().transFigure, size=12) |
7414792e1cb8
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 90ee23e393deb06fa5c15e3778fa23c39a25f7ce
mheinzl
parents:
0
diff
changeset
|
87 plt.grid(b=True, which='major', color='#424242', linestyle=':') |
7414792e1cb8
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 90ee23e393deb06fa5c15e3778fa23c39a25f7ce
mheinzl
parents:
0
diff
changeset
|
88 |
7414792e1cb8
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 90ee23e393deb06fa5c15e3778fa23c39a25f7ce
mheinzl
parents:
0
diff
changeset
|
89 pdf.savefig(fig, bbox_inches="tight") |
7414792e1cb8
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 90ee23e393deb06fa5c15e3778fa23c39a25f7ce
mheinzl
parents:
0
diff
changeset
|
90 plt.close("all") |
19
2e9f7ea7ae93
planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/hd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a-dirty
mheinzl
parents:
18
diff
changeset
|
91 |
2e9f7ea7ae93
planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/hd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a-dirty
mheinzl
parents:
18
diff
changeset
|
92 |
2e9f7ea7ae93
planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/hd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a-dirty
mheinzl
parents:
18
diff
changeset
|
93 def plotHDwithFSD(list1, maximumX, minimumX, subtitle, lenTags, title_file1, pdf, xlabel, relative=False, nr_above_bars=True): |
1
7414792e1cb8
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 90ee23e393deb06fa5c15e3778fa23c39a25f7ce
mheinzl
parents:
0
diff
changeset
|
94 if relative is True: |
7414792e1cb8
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 90ee23e393deb06fa5c15e3778fa23c39a25f7ce
mheinzl
parents:
0
diff
changeset
|
95 step = 0.1 |
7414792e1cb8
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 90ee23e393deb06fa5c15e3778fa23c39a25f7ce
mheinzl
parents:
0
diff
changeset
|
96 else: |
7414792e1cb8
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 90ee23e393deb06fa5c15e3778fa23c39a25f7ce
mheinzl
parents:
0
diff
changeset
|
97 step = 1 |
7414792e1cb8
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 90ee23e393deb06fa5c15e3778fa23c39a25f7ce
mheinzl
parents:
0
diff
changeset
|
98 |
7414792e1cb8
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 90ee23e393deb06fa5c15e3778fa23c39a25f7ce
mheinzl
parents:
0
diff
changeset
|
99 fig = plt.figure(figsize=(6, 8)) |
7414792e1cb8
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 90ee23e393deb06fa5c15e3778fa23c39a25f7ce
mheinzl
parents:
0
diff
changeset
|
100 plt.subplots_adjust(bottom=0.1) |
7414792e1cb8
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 90ee23e393deb06fa5c15e3778fa23c39a25f7ce
mheinzl
parents:
0
diff
changeset
|
101 con_list1 = numpy.concatenate(list1) |
7414792e1cb8
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 90ee23e393deb06fa5c15e3778fa23c39a25f7ce
mheinzl
parents:
0
diff
changeset
|
102 p1 = numpy.array([v for k, v in sorted(Counter(con_list1).iteritems())]) |
7414792e1cb8
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 90ee23e393deb06fa5c15e3778fa23c39a25f7ce
mheinzl
parents:
0
diff
changeset
|
103 maximumY = numpy.amax(p1) |
7414792e1cb8
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 90ee23e393deb06fa5c15e3778fa23c39a25f7ce
mheinzl
parents:
0
diff
changeset
|
104 |
7414792e1cb8
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 90ee23e393deb06fa5c15e3778fa23c39a25f7ce
mheinzl
parents:
0
diff
changeset
|
105 if relative is True: # relative difference |
7414792e1cb8
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 90ee23e393deb06fa5c15e3778fa23c39a25f7ce
mheinzl
parents:
0
diff
changeset
|
106 bin1 = numpy.arange(-1, maximumX + 0.2, 0.1) |
7414792e1cb8
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 90ee23e393deb06fa5c15e3778fa23c39a25f7ce
mheinzl
parents:
0
diff
changeset
|
107 else: |
7414792e1cb8
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 90ee23e393deb06fa5c15e3778fa23c39a25f7ce
mheinzl
parents:
0
diff
changeset
|
108 bin1 = maximumX + 1 |
7414792e1cb8
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 90ee23e393deb06fa5c15e3778fa23c39a25f7ce
mheinzl
parents:
0
diff
changeset
|
109 |
7414792e1cb8
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 90ee23e393deb06fa5c15e3778fa23c39a25f7ce
mheinzl
parents:
0
diff
changeset
|
110 counts = plt.hist(list1, bins=bin1, edgecolor='black', linewidth=1, |
7414792e1cb8
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 90ee23e393deb06fa5c15e3778fa23c39a25f7ce
mheinzl
parents:
0
diff
changeset
|
111 label=["FS=1", "FS=2", "FS=3", "FS=4", "FS=5-10", |
7414792e1cb8
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 90ee23e393deb06fa5c15e3778fa23c39a25f7ce
mheinzl
parents:
0
diff
changeset
|
112 "FS>10"], rwidth=0.8, |
7414792e1cb8
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 90ee23e393deb06fa5c15e3778fa23c39a25f7ce
mheinzl
parents:
0
diff
changeset
|
113 color=["#808080", "#FFFFCC", "#FFBF00", "#DF0101", "#0431B4", "#86B404"], |
7414792e1cb8
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 90ee23e393deb06fa5c15e3778fa23c39a25f7ce
mheinzl
parents:
0
diff
changeset
|
114 stacked=True, alpha=1, |
7414792e1cb8
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 90ee23e393deb06fa5c15e3778fa23c39a25f7ce
mheinzl
parents:
0
diff
changeset
|
115 align="left", |
7414792e1cb8
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 90ee23e393deb06fa5c15e3778fa23c39a25f7ce
mheinzl
parents:
0
diff
changeset
|
116 range=(0, maximumX + 1)) |
7414792e1cb8
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 90ee23e393deb06fa5c15e3778fa23c39a25f7ce
mheinzl
parents:
0
diff
changeset
|
117 plt.legend(loc='upper right', fontsize=14, frameon=True, bbox_to_anchor=(1.45, 1)) |
7414792e1cb8
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 90ee23e393deb06fa5c15e3778fa23c39a25f7ce
mheinzl
parents:
0
diff
changeset
|
118 bins = counts[1] # width of bins |
7414792e1cb8
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 90ee23e393deb06fa5c15e3778fa23c39a25f7ce
mheinzl
parents:
0
diff
changeset
|
119 counts = numpy.array(map(int, counts[0][5])) |
7414792e1cb8
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 90ee23e393deb06fa5c15e3778fa23c39a25f7ce
mheinzl
parents:
0
diff
changeset
|
120 plt.suptitle(subtitle, y=1, x=0.5, fontsize=14) |
19
2e9f7ea7ae93
planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/hd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a-dirty
mheinzl
parents:
18
diff
changeset
|
121 # plt.title(title_file1, fontsize=12) |
2
316fbf91dd12
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit f9d5547849dabb59a33a5e998bda4730323d62a9
mheinzl
parents:
1
diff
changeset
|
122 plt.xlabel(xlabel, fontsize=14) |
316fbf91dd12
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit f9d5547849dabb59a33a5e998bda4730323d62a9
mheinzl
parents:
1
diff
changeset
|
123 plt.ylabel("Absolute Frequency", fontsize=14) |
1
7414792e1cb8
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 90ee23e393deb06fa5c15e3778fa23c39a25f7ce
mheinzl
parents:
0
diff
changeset
|
124 |
7414792e1cb8
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 90ee23e393deb06fa5c15e3778fa23c39a25f7ce
mheinzl
parents:
0
diff
changeset
|
125 plt.grid(b=True, which='major', color='#424242', linestyle=':') |
7414792e1cb8
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 90ee23e393deb06fa5c15e3778fa23c39a25f7ce
mheinzl
parents:
0
diff
changeset
|
126 plt.axis((minimumX - step, maximumX + step, 0, numpy.amax(counts) + sum(counts) * 0.1)) |
7414792e1cb8
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 90ee23e393deb06fa5c15e3778fa23c39a25f7ce
mheinzl
parents:
0
diff
changeset
|
127 plt.xticks(numpy.arange(0, maximumX + step, step)) |
7414792e1cb8
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 90ee23e393deb06fa5c15e3778fa23c39a25f7ce
mheinzl
parents:
0
diff
changeset
|
128 |
7414792e1cb8
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 90ee23e393deb06fa5c15e3778fa23c39a25f7ce
mheinzl
parents:
0
diff
changeset
|
129 plt.ylim((0, maximumY * 1.2)) |
7414792e1cb8
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 90ee23e393deb06fa5c15e3778fa23c39a25f7ce
mheinzl
parents:
0
diff
changeset
|
130 |
14
883e6381ba29
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 38f5c032262361131c645812dd3dc639be6a5f4e
mheinzl
parents:
13
diff
changeset
|
131 if nr_above_bars is True: |
883e6381ba29
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 38f5c032262361131c645812dd3dc639be6a5f4e
mheinzl
parents:
13
diff
changeset
|
132 bin_centers = -0.4 * numpy.diff(bins) + bins[:-1] |
883e6381ba29
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 38f5c032262361131c645812dd3dc639be6a5f4e
mheinzl
parents:
13
diff
changeset
|
133 for x_label, label in zip(counts, bin_centers): # labels for values |
883e6381ba29
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 38f5c032262361131c645812dd3dc639be6a5f4e
mheinzl
parents:
13
diff
changeset
|
134 if x_label == 0: |
883e6381ba29
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 38f5c032262361131c645812dd3dc639be6a5f4e
mheinzl
parents:
13
diff
changeset
|
135 continue |
883e6381ba29
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 38f5c032262361131c645812dd3dc639be6a5f4e
mheinzl
parents:
13
diff
changeset
|
136 else: |
883e6381ba29
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 38f5c032262361131c645812dd3dc639be6a5f4e
mheinzl
parents:
13
diff
changeset
|
137 plt.annotate("{:,}\n{:.3f}".format(x_label, float(x_label) / sum(counts), 1), |
883e6381ba29
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 38f5c032262361131c645812dd3dc639be6a5f4e
mheinzl
parents:
13
diff
changeset
|
138 xy=(label, x_label + len(con_list1) * 0.01), |
19
2e9f7ea7ae93
planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/hd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a-dirty
mheinzl
parents:
18
diff
changeset
|
139 xycoords="data", color="#000066", fontsize=10) |
2e9f7ea7ae93
planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/hd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a-dirty
mheinzl
parents:
18
diff
changeset
|
140 |
1
7414792e1cb8
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 90ee23e393deb06fa5c15e3778fa23c39a25f7ce
mheinzl
parents:
0
diff
changeset
|
141 legend = "sample size= {:,} against {:,}".format(sum(counts), lenTags) |
7414792e1cb8
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 90ee23e393deb06fa5c15e3778fa23c39a25f7ce
mheinzl
parents:
0
diff
changeset
|
142 plt.text(0.14, -0.01, legend, size=12, transform=plt.gcf().transFigure) |
7414792e1cb8
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 90ee23e393deb06fa5c15e3778fa23c39a25f7ce
mheinzl
parents:
0
diff
changeset
|
143 |
7414792e1cb8
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 90ee23e393deb06fa5c15e3778fa23c39a25f7ce
mheinzl
parents:
0
diff
changeset
|
144 pdf.savefig(fig, bbox_inches="tight") |
7414792e1cb8
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 90ee23e393deb06fa5c15e3778fa23c39a25f7ce
mheinzl
parents:
0
diff
changeset
|
145 plt.close("all") |
7414792e1cb8
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 90ee23e393deb06fa5c15e3778fa23c39a25f7ce
mheinzl
parents:
0
diff
changeset
|
146 plt.clf() |
7414792e1cb8
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 90ee23e393deb06fa5c15e3778fa23c39a25f7ce
mheinzl
parents:
0
diff
changeset
|
147 |
19
2e9f7ea7ae93
planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/hd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a-dirty
mheinzl
parents:
18
diff
changeset
|
148 |
2e9f7ea7ae93
planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/hd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a-dirty
mheinzl
parents:
18
diff
changeset
|
149 def plotHDwithinSeq_Sum2(sum1, sum1min, sum2, sum2min, min_value, lenTags, title_file1, pdf): |
1
7414792e1cb8
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 90ee23e393deb06fa5c15e3778fa23c39a25f7ce
mheinzl
parents:
0
diff
changeset
|
150 fig = plt.figure(figsize=(6, 8)) |
7414792e1cb8
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 90ee23e393deb06fa5c15e3778fa23c39a25f7ce
mheinzl
parents:
0
diff
changeset
|
151 plt.subplots_adjust(bottom=0.1) |
7414792e1cb8
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 90ee23e393deb06fa5c15e3778fa23c39a25f7ce
mheinzl
parents:
0
diff
changeset
|
152 |
19
2e9f7ea7ae93
planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/hd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a-dirty
mheinzl
parents:
18
diff
changeset
|
153 ham_partial = [sum1, sum1min, sum2, sum2min, numpy.array(min_value)] # new hd within tags |
1
7414792e1cb8
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 90ee23e393deb06fa5c15e3778fa23c39a25f7ce
mheinzl
parents:
0
diff
changeset
|
154 |
19
2e9f7ea7ae93
planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/hd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a-dirty
mheinzl
parents:
18
diff
changeset
|
155 maximumX = numpy.amax(numpy.concatenate(ham_partial)) |
2e9f7ea7ae93
planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/hd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a-dirty
mheinzl
parents:
18
diff
changeset
|
156 minimumX = numpy.amin(numpy.concatenate(ham_partial)) |
2e9f7ea7ae93
planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/hd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a-dirty
mheinzl
parents:
18
diff
changeset
|
157 maximumY = numpy.amax(numpy.array(numpy.concatenate(map(lambda (x): numpy.bincount(x), ham_partial)))) |
1
7414792e1cb8
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 90ee23e393deb06fa5c15e3778fa23c39a25f7ce
mheinzl
parents:
0
diff
changeset
|
158 |
7414792e1cb8
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 90ee23e393deb06fa5c15e3778fa23c39a25f7ce
mheinzl
parents:
0
diff
changeset
|
159 if len(range(minimumX, maximumX)) == 0: |
7414792e1cb8
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 90ee23e393deb06fa5c15e3778fa23c39a25f7ce
mheinzl
parents:
0
diff
changeset
|
160 range1 = minimumX |
7414792e1cb8
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 90ee23e393deb06fa5c15e3778fa23c39a25f7ce
mheinzl
parents:
0
diff
changeset
|
161 else: |
7414792e1cb8
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 90ee23e393deb06fa5c15e3778fa23c39a25f7ce
mheinzl
parents:
0
diff
changeset
|
162 range1 = range(minimumX, maximumX + 2) |
7414792e1cb8
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 90ee23e393deb06fa5c15e3778fa23c39a25f7ce
mheinzl
parents:
0
diff
changeset
|
163 |
19
2e9f7ea7ae93
planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/hd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a-dirty
mheinzl
parents:
18
diff
changeset
|
164 plt.hist(ham_partial, align="left", rwidth=0.8, stacked=False, label=[ "HD a", "HD b'", "HD b", "HD a'", "HD a+b"], bins=range1, color=["#58ACFA", "#0404B4", "#FE642E", "#B40431", "#585858"], edgecolor='black', linewidth=1) |
2e9f7ea7ae93
planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/hd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a-dirty
mheinzl
parents:
18
diff
changeset
|
165 |
1
7414792e1cb8
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 90ee23e393deb06fa5c15e3778fa23c39a25f7ce
mheinzl
parents:
0
diff
changeset
|
166 plt.legend(loc='upper right', fontsize=14, frameon=True, bbox_to_anchor=(1.55, 1)) |
7414792e1cb8
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 90ee23e393deb06fa5c15e3778fa23c39a25f7ce
mheinzl
parents:
0
diff
changeset
|
167 plt.suptitle('Hamming distances within tags', fontsize=14) |
19
2e9f7ea7ae93
planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/hd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a-dirty
mheinzl
parents:
18
diff
changeset
|
168 # plt.title(title_file1, fontsize=12) |
14
883e6381ba29
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 38f5c032262361131c645812dd3dc639be6a5f4e
mheinzl
parents:
13
diff
changeset
|
169 plt.xlabel("HD", fontsize=14) |
2
316fbf91dd12
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit f9d5547849dabb59a33a5e998bda4730323d62a9
mheinzl
parents:
1
diff
changeset
|
170 plt.ylabel("Absolute Frequency", fontsize=14) |
1
7414792e1cb8
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 90ee23e393deb06fa5c15e3778fa23c39a25f7ce
mheinzl
parents:
0
diff
changeset
|
171 plt.grid(b=True, which='major', color='#424242', linestyle=':') |
7414792e1cb8
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 90ee23e393deb06fa5c15e3778fa23c39a25f7ce
mheinzl
parents:
0
diff
changeset
|
172 |
19
2e9f7ea7ae93
planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/hd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a-dirty
mheinzl
parents:
18
diff
changeset
|
173 plt.axis((minimumX - 1, maximumX + 1, 0, maximumY * 1.2)) |
2
316fbf91dd12
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit f9d5547849dabb59a33a5e998bda4730323d62a9
mheinzl
parents:
1
diff
changeset
|
174 plt.xticks(numpy.arange(0, maximumX + 1, 1.0)) |
19
2e9f7ea7ae93
planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/hd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a-dirty
mheinzl
parents:
18
diff
changeset
|
175 # plt.ylim(0, maximumY * 1.2) |
1
7414792e1cb8
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 90ee23e393deb06fa5c15e3778fa23c39a25f7ce
mheinzl
parents:
0
diff
changeset
|
176 |
19
2e9f7ea7ae93
planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/hd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a-dirty
mheinzl
parents:
18
diff
changeset
|
177 legend = "sample size= {:,} against {:,}".format(sum(ham_partial[4]), lenTags) |
1
7414792e1cb8
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 90ee23e393deb06fa5c15e3778fa23c39a25f7ce
mheinzl
parents:
0
diff
changeset
|
178 plt.text(0.14, -0.01, legend, size=12, transform=plt.gcf().transFigure) |
7414792e1cb8
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 90ee23e393deb06fa5c15e3778fa23c39a25f7ce
mheinzl
parents:
0
diff
changeset
|
179 pdf.savefig(fig, bbox_inches="tight") |
7414792e1cb8
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 90ee23e393deb06fa5c15e3778fa23c39a25f7ce
mheinzl
parents:
0
diff
changeset
|
180 plt.close("all") |
7414792e1cb8
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 90ee23e393deb06fa5c15e3778fa23c39a25f7ce
mheinzl
parents:
0
diff
changeset
|
181 plt.clf() |
7414792e1cb8
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 90ee23e393deb06fa5c15e3778fa23c39a25f7ce
mheinzl
parents:
0
diff
changeset
|
182 |
19
2e9f7ea7ae93
planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/hd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a-dirty
mheinzl
parents:
18
diff
changeset
|
183 |
1
7414792e1cb8
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 90ee23e393deb06fa5c15e3778fa23c39a25f7ce
mheinzl
parents:
0
diff
changeset
|
184 def createTableFSD2(list1, diff=True): |
7414792e1cb8
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 90ee23e393deb06fa5c15e3778fa23c39a25f7ce
mheinzl
parents:
0
diff
changeset
|
185 selfAB = numpy.concatenate(list1) |
7414792e1cb8
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 90ee23e393deb06fa5c15e3778fa23c39a25f7ce
mheinzl
parents:
0
diff
changeset
|
186 uniqueFS = numpy.unique(selfAB) |
7414792e1cb8
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 90ee23e393deb06fa5c15e3778fa23c39a25f7ce
mheinzl
parents:
0
diff
changeset
|
187 nr = numpy.arange(0, len(uniqueFS), 1) |
7414792e1cb8
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 90ee23e393deb06fa5c15e3778fa23c39a25f7ce
mheinzl
parents:
0
diff
changeset
|
188 if diff is False: |
7414792e1cb8
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 90ee23e393deb06fa5c15e3778fa23c39a25f7ce
mheinzl
parents:
0
diff
changeset
|
189 count = numpy.zeros((len(uniqueFS), 6)) |
7414792e1cb8
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 90ee23e393deb06fa5c15e3778fa23c39a25f7ce
mheinzl
parents:
0
diff
changeset
|
190 else: |
7414792e1cb8
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 90ee23e393deb06fa5c15e3778fa23c39a25f7ce
mheinzl
parents:
0
diff
changeset
|
191 count = numpy.zeros((len(uniqueFS), 7)) |
7414792e1cb8
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 90ee23e393deb06fa5c15e3778fa23c39a25f7ce
mheinzl
parents:
0
diff
changeset
|
192 |
7414792e1cb8
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 90ee23e393deb06fa5c15e3778fa23c39a25f7ce
mheinzl
parents:
0
diff
changeset
|
193 state = 1 |
7414792e1cb8
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 90ee23e393deb06fa5c15e3778fa23c39a25f7ce
mheinzl
parents:
0
diff
changeset
|
194 for i in list1: |
7414792e1cb8
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 90ee23e393deb06fa5c15e3778fa23c39a25f7ce
mheinzl
parents:
0
diff
changeset
|
195 counts = list(Counter(i).items()) |
7414792e1cb8
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 90ee23e393deb06fa5c15e3778fa23c39a25f7ce
mheinzl
parents:
0
diff
changeset
|
196 hd = [item[0] for item in counts] |
7414792e1cb8
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 90ee23e393deb06fa5c15e3778fa23c39a25f7ce
mheinzl
parents:
0
diff
changeset
|
197 c = [item[1] for item in counts] |
7414792e1cb8
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 90ee23e393deb06fa5c15e3778fa23c39a25f7ce
mheinzl
parents:
0
diff
changeset
|
198 table = numpy.column_stack((hd, c)) |
7414792e1cb8
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 90ee23e393deb06fa5c15e3778fa23c39a25f7ce
mheinzl
parents:
0
diff
changeset
|
199 if len(table) == 0: |
7414792e1cb8
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 90ee23e393deb06fa5c15e3778fa23c39a25f7ce
mheinzl
parents:
0
diff
changeset
|
200 state = state + 1 |
7414792e1cb8
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 90ee23e393deb06fa5c15e3778fa23c39a25f7ce
mheinzl
parents:
0
diff
changeset
|
201 continue |
7414792e1cb8
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 90ee23e393deb06fa5c15e3778fa23c39a25f7ce
mheinzl
parents:
0
diff
changeset
|
202 else: |
7414792e1cb8
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 90ee23e393deb06fa5c15e3778fa23c39a25f7ce
mheinzl
parents:
0
diff
changeset
|
203 if state == 1: |
19
2e9f7ea7ae93
planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/hd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a-dirty
mheinzl
parents:
18
diff
changeset
|
204 for i, l in zip(uniqueFS, nr): |
1
7414792e1cb8
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 90ee23e393deb06fa5c15e3778fa23c39a25f7ce
mheinzl
parents:
0
diff
changeset
|
205 for j in table: |
7414792e1cb8
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 90ee23e393deb06fa5c15e3778fa23c39a25f7ce
mheinzl
parents:
0
diff
changeset
|
206 if j[0] == uniqueFS[l]: |
7414792e1cb8
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 90ee23e393deb06fa5c15e3778fa23c39a25f7ce
mheinzl
parents:
0
diff
changeset
|
207 count[l, 0] = j[1] |
7414792e1cb8
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 90ee23e393deb06fa5c15e3778fa23c39a25f7ce
mheinzl
parents:
0
diff
changeset
|
208 if state == 2: |
7414792e1cb8
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 90ee23e393deb06fa5c15e3778fa23c39a25f7ce
mheinzl
parents:
0
diff
changeset
|
209 for i, l in zip(uniqueFS, nr): |
7414792e1cb8
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 90ee23e393deb06fa5c15e3778fa23c39a25f7ce
mheinzl
parents:
0
diff
changeset
|
210 for j in table: |
7414792e1cb8
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 90ee23e393deb06fa5c15e3778fa23c39a25f7ce
mheinzl
parents:
0
diff
changeset
|
211 if j[0] == uniqueFS[l]: |
7414792e1cb8
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 90ee23e393deb06fa5c15e3778fa23c39a25f7ce
mheinzl
parents:
0
diff
changeset
|
212 count[l, 1] = j[1] |
7414792e1cb8
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 90ee23e393deb06fa5c15e3778fa23c39a25f7ce
mheinzl
parents:
0
diff
changeset
|
213 |
7414792e1cb8
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 90ee23e393deb06fa5c15e3778fa23c39a25f7ce
mheinzl
parents:
0
diff
changeset
|
214 if state == 3: |
7414792e1cb8
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 90ee23e393deb06fa5c15e3778fa23c39a25f7ce
mheinzl
parents:
0
diff
changeset
|
215 for i, l in zip(uniqueFS, nr): |
7414792e1cb8
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 90ee23e393deb06fa5c15e3778fa23c39a25f7ce
mheinzl
parents:
0
diff
changeset
|
216 for j in table: |
7414792e1cb8
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 90ee23e393deb06fa5c15e3778fa23c39a25f7ce
mheinzl
parents:
0
diff
changeset
|
217 if j[0] == uniqueFS[l]: |
7414792e1cb8
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 90ee23e393deb06fa5c15e3778fa23c39a25f7ce
mheinzl
parents:
0
diff
changeset
|
218 count[l, 2] = j[1] |
7414792e1cb8
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 90ee23e393deb06fa5c15e3778fa23c39a25f7ce
mheinzl
parents:
0
diff
changeset
|
219 |
7414792e1cb8
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 90ee23e393deb06fa5c15e3778fa23c39a25f7ce
mheinzl
parents:
0
diff
changeset
|
220 if state == 4: |
7414792e1cb8
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 90ee23e393deb06fa5c15e3778fa23c39a25f7ce
mheinzl
parents:
0
diff
changeset
|
221 for i, l in zip(uniqueFS, nr): |
7414792e1cb8
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 90ee23e393deb06fa5c15e3778fa23c39a25f7ce
mheinzl
parents:
0
diff
changeset
|
222 for j in table: |
7414792e1cb8
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 90ee23e393deb06fa5c15e3778fa23c39a25f7ce
mheinzl
parents:
0
diff
changeset
|
223 if j[0] == uniqueFS[l]: |
7414792e1cb8
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 90ee23e393deb06fa5c15e3778fa23c39a25f7ce
mheinzl
parents:
0
diff
changeset
|
224 count[l, 3] = j[1] |
7414792e1cb8
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 90ee23e393deb06fa5c15e3778fa23c39a25f7ce
mheinzl
parents:
0
diff
changeset
|
225 |
7414792e1cb8
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 90ee23e393deb06fa5c15e3778fa23c39a25f7ce
mheinzl
parents:
0
diff
changeset
|
226 if state == 5: |
7414792e1cb8
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 90ee23e393deb06fa5c15e3778fa23c39a25f7ce
mheinzl
parents:
0
diff
changeset
|
227 for i, l in zip(uniqueFS, nr): |
7414792e1cb8
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 90ee23e393deb06fa5c15e3778fa23c39a25f7ce
mheinzl
parents:
0
diff
changeset
|
228 for j in table: |
7414792e1cb8
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 90ee23e393deb06fa5c15e3778fa23c39a25f7ce
mheinzl
parents:
0
diff
changeset
|
229 if j[0] == uniqueFS[l]: |
7414792e1cb8
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 90ee23e393deb06fa5c15e3778fa23c39a25f7ce
mheinzl
parents:
0
diff
changeset
|
230 count[l, 4] = j[1] |
7414792e1cb8
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 90ee23e393deb06fa5c15e3778fa23c39a25f7ce
mheinzl
parents:
0
diff
changeset
|
231 |
7414792e1cb8
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 90ee23e393deb06fa5c15e3778fa23c39a25f7ce
mheinzl
parents:
0
diff
changeset
|
232 if state == 6: |
7414792e1cb8
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 90ee23e393deb06fa5c15e3778fa23c39a25f7ce
mheinzl
parents:
0
diff
changeset
|
233 for i, l in zip(uniqueFS, nr): |
7414792e1cb8
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 90ee23e393deb06fa5c15e3778fa23c39a25f7ce
mheinzl
parents:
0
diff
changeset
|
234 for j in table: |
7414792e1cb8
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 90ee23e393deb06fa5c15e3778fa23c39a25f7ce
mheinzl
parents:
0
diff
changeset
|
235 if j[0] == uniqueFS[l]: |
7414792e1cb8
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 90ee23e393deb06fa5c15e3778fa23c39a25f7ce
mheinzl
parents:
0
diff
changeset
|
236 count[l, 5] = j[1] |
7414792e1cb8
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 90ee23e393deb06fa5c15e3778fa23c39a25f7ce
mheinzl
parents:
0
diff
changeset
|
237 |
7414792e1cb8
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 90ee23e393deb06fa5c15e3778fa23c39a25f7ce
mheinzl
parents:
0
diff
changeset
|
238 if state == 7: |
7414792e1cb8
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 90ee23e393deb06fa5c15e3778fa23c39a25f7ce
mheinzl
parents:
0
diff
changeset
|
239 for i, l in zip(uniqueFS, nr): |
7414792e1cb8
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 90ee23e393deb06fa5c15e3778fa23c39a25f7ce
mheinzl
parents:
0
diff
changeset
|
240 for j in table: |
7414792e1cb8
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 90ee23e393deb06fa5c15e3778fa23c39a25f7ce
mheinzl
parents:
0
diff
changeset
|
241 if j[0] == uniqueFS[l]: |
7414792e1cb8
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 90ee23e393deb06fa5c15e3778fa23c39a25f7ce
mheinzl
parents:
0
diff
changeset
|
242 count[l, 6] = j[1] |
7414792e1cb8
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 90ee23e393deb06fa5c15e3778fa23c39a25f7ce
mheinzl
parents:
0
diff
changeset
|
243 state = state + 1 |
7414792e1cb8
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 90ee23e393deb06fa5c15e3778fa23c39a25f7ce
mheinzl
parents:
0
diff
changeset
|
244 |
7414792e1cb8
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 90ee23e393deb06fa5c15e3778fa23c39a25f7ce
mheinzl
parents:
0
diff
changeset
|
245 sumRow = count.sum(axis=1) |
7414792e1cb8
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 90ee23e393deb06fa5c15e3778fa23c39a25f7ce
mheinzl
parents:
0
diff
changeset
|
246 sumCol = count.sum(axis=0) |
7414792e1cb8
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 90ee23e393deb06fa5c15e3778fa23c39a25f7ce
mheinzl
parents:
0
diff
changeset
|
247 |
7414792e1cb8
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 90ee23e393deb06fa5c15e3778fa23c39a25f7ce
mheinzl
parents:
0
diff
changeset
|
248 uniqueFS = uniqueFS.astype(str) |
7414792e1cb8
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 90ee23e393deb06fa5c15e3778fa23c39a25f7ce
mheinzl
parents:
0
diff
changeset
|
249 if uniqueFS[len(uniqueFS) - 1] == "20": |
7414792e1cb8
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 90ee23e393deb06fa5c15e3778fa23c39a25f7ce
mheinzl
parents:
0
diff
changeset
|
250 uniqueFS[len(uniqueFS) - 1] = ">20" |
7414792e1cb8
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 90ee23e393deb06fa5c15e3778fa23c39a25f7ce
mheinzl
parents:
0
diff
changeset
|
251 |
7414792e1cb8
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 90ee23e393deb06fa5c15e3778fa23c39a25f7ce
mheinzl
parents:
0
diff
changeset
|
252 first = ["FS={}".format(i) for i in uniqueFS] |
7414792e1cb8
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 90ee23e393deb06fa5c15e3778fa23c39a25f7ce
mheinzl
parents:
0
diff
changeset
|
253 final = numpy.column_stack((first, count, sumRow)) |
7414792e1cb8
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 90ee23e393deb06fa5c15e3778fa23c39a25f7ce
mheinzl
parents:
0
diff
changeset
|
254 |
7414792e1cb8
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 90ee23e393deb06fa5c15e3778fa23c39a25f7ce
mheinzl
parents:
0
diff
changeset
|
255 return (final, sumCol) |
7414792e1cb8
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 90ee23e393deb06fa5c15e3778fa23c39a25f7ce
mheinzl
parents:
0
diff
changeset
|
256 |
19
2e9f7ea7ae93
planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/hd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a-dirty
mheinzl
parents:
18
diff
changeset
|
257 |
2e9f7ea7ae93
planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/hd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a-dirty
mheinzl
parents:
18
diff
changeset
|
258 def createFileFSD2(summary, sumCol, overallSum, output_file, name, sep, rel=False, diff=True): |
1
7414792e1cb8
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 90ee23e393deb06fa5c15e3778fa23c39a25f7ce
mheinzl
parents:
0
diff
changeset
|
259 output_file.write(name) |
7414792e1cb8
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 90ee23e393deb06fa5c15e3778fa23c39a25f7ce
mheinzl
parents:
0
diff
changeset
|
260 output_file.write("\n") |
7414792e1cb8
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 90ee23e393deb06fa5c15e3778fa23c39a25f7ce
mheinzl
parents:
0
diff
changeset
|
261 if diff is False: |
19
2e9f7ea7ae93
planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/hd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a-dirty
mheinzl
parents:
18
diff
changeset
|
262 output_file.write("{}HD=1{}HD=2{}HD=3{}HD=4{}HD=5-8{}HD>8{}sum{}\n".format(sep, sep, sep, sep, sep, sep, sep, sep)) |
1
7414792e1cb8
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 90ee23e393deb06fa5c15e3778fa23c39a25f7ce
mheinzl
parents:
0
diff
changeset
|
263 else: |
7414792e1cb8
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 90ee23e393deb06fa5c15e3778fa23c39a25f7ce
mheinzl
parents:
0
diff
changeset
|
264 if rel is False: |
19
2e9f7ea7ae93
planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/hd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a-dirty
mheinzl
parents:
18
diff
changeset
|
265 output_file.write("{}diff=0{}diff=1{}diff=2{}diff=3{}diff=4{}diff=5-8{}diff>8{}sum{}\n".format(sep, sep, sep, sep, sep, sep, sep, sep, sep)) |
1
7414792e1cb8
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 90ee23e393deb06fa5c15e3778fa23c39a25f7ce
mheinzl
parents:
0
diff
changeset
|
266 else: |
19
2e9f7ea7ae93
planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/hd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a-dirty
mheinzl
parents:
18
diff
changeset
|
267 output_file.write("{}diff=0{}diff=0.1{}diff=0.2{}diff=0.3{}diff=0.4{}diff=0.5-0.8{}diff>0.8{}sum{}\n".format(sep, sep, sep, sep, sep, sep, sep, sep, sep)) |
1
7414792e1cb8
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 90ee23e393deb06fa5c15e3778fa23c39a25f7ce
mheinzl
parents:
0
diff
changeset
|
268 |
7414792e1cb8
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 90ee23e393deb06fa5c15e3778fa23c39a25f7ce
mheinzl
parents:
0
diff
changeset
|
269 for item in summary: |
7414792e1cb8
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 90ee23e393deb06fa5c15e3778fa23c39a25f7ce
mheinzl
parents:
0
diff
changeset
|
270 for nr in item: |
7414792e1cb8
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 90ee23e393deb06fa5c15e3778fa23c39a25f7ce
mheinzl
parents:
0
diff
changeset
|
271 if "FS" not in nr and "diff" not in nr: |
7414792e1cb8
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 90ee23e393deb06fa5c15e3778fa23c39a25f7ce
mheinzl
parents:
0
diff
changeset
|
272 nr = nr.astype(float) |
7414792e1cb8
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 90ee23e393deb06fa5c15e3778fa23c39a25f7ce
mheinzl
parents:
0
diff
changeset
|
273 nr = nr.astype(int) |
19
2e9f7ea7ae93
planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/hd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a-dirty
mheinzl
parents:
18
diff
changeset
|
274 output_file.write("{}{}".format(nr, sep)) |
1
7414792e1cb8
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 90ee23e393deb06fa5c15e3778fa23c39a25f7ce
mheinzl
parents:
0
diff
changeset
|
275 output_file.write("\n") |
7414792e1cb8
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 90ee23e393deb06fa5c15e3778fa23c39a25f7ce
mheinzl
parents:
0
diff
changeset
|
276 output_file.write("sum{}".format(sep)) |
7414792e1cb8
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 90ee23e393deb06fa5c15e3778fa23c39a25f7ce
mheinzl
parents:
0
diff
changeset
|
277 sumCol = map(int, sumCol) |
7414792e1cb8
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 90ee23e393deb06fa5c15e3778fa23c39a25f7ce
mheinzl
parents:
0
diff
changeset
|
278 for el in sumCol: |
19
2e9f7ea7ae93
planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/hd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a-dirty
mheinzl
parents:
18
diff
changeset
|
279 output_file.write("{}{}".format(el, sep)) |
2e9f7ea7ae93
planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/hd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a-dirty
mheinzl
parents:
18
diff
changeset
|
280 output_file.write("{}{}".format(overallSum.astype(int), sep)) |
1
7414792e1cb8
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 90ee23e393deb06fa5c15e3778fa23c39a25f7ce
mheinzl
parents:
0
diff
changeset
|
281 output_file.write("\n\n") |
7414792e1cb8
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 90ee23e393deb06fa5c15e3778fa23c39a25f7ce
mheinzl
parents:
0
diff
changeset
|
282 |
19
2e9f7ea7ae93
planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/hd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a-dirty
mheinzl
parents:
18
diff
changeset
|
283 |
1
7414792e1cb8
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 90ee23e393deb06fa5c15e3778fa23c39a25f7ce
mheinzl
parents:
0
diff
changeset
|
284 def createTableHD(list1, row_label): |
7414792e1cb8
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 90ee23e393deb06fa5c15e3778fa23c39a25f7ce
mheinzl
parents:
0
diff
changeset
|
285 selfAB = numpy.concatenate(list1) |
7414792e1cb8
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 90ee23e393deb06fa5c15e3778fa23c39a25f7ce
mheinzl
parents:
0
diff
changeset
|
286 uniqueHD = numpy.unique(selfAB) |
7414792e1cb8
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 90ee23e393deb06fa5c15e3778fa23c39a25f7ce
mheinzl
parents:
0
diff
changeset
|
287 nr = numpy.arange(0, len(uniqueHD), 1) |
7414792e1cb8
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 90ee23e393deb06fa5c15e3778fa23c39a25f7ce
mheinzl
parents:
0
diff
changeset
|
288 count = numpy.zeros((len(uniqueHD), 6)) |
7414792e1cb8
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 90ee23e393deb06fa5c15e3778fa23c39a25f7ce
mheinzl
parents:
0
diff
changeset
|
289 state = 1 |
7414792e1cb8
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 90ee23e393deb06fa5c15e3778fa23c39a25f7ce
mheinzl
parents:
0
diff
changeset
|
290 for i in list1: |
7414792e1cb8
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 90ee23e393deb06fa5c15e3778fa23c39a25f7ce
mheinzl
parents:
0
diff
changeset
|
291 counts = list(Counter(i).items()) |
7414792e1cb8
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 90ee23e393deb06fa5c15e3778fa23c39a25f7ce
mheinzl
parents:
0
diff
changeset
|
292 hd = [item[0] for item in counts] |
7414792e1cb8
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 90ee23e393deb06fa5c15e3778fa23c39a25f7ce
mheinzl
parents:
0
diff
changeset
|
293 c = [item[1] for item in counts] |
7414792e1cb8
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 90ee23e393deb06fa5c15e3778fa23c39a25f7ce
mheinzl
parents:
0
diff
changeset
|
294 table = numpy.column_stack((hd, c)) |
7414792e1cb8
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 90ee23e393deb06fa5c15e3778fa23c39a25f7ce
mheinzl
parents:
0
diff
changeset
|
295 if len(table) == 0: |
7414792e1cb8
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 90ee23e393deb06fa5c15e3778fa23c39a25f7ce
mheinzl
parents:
0
diff
changeset
|
296 state = state + 1 |
7414792e1cb8
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 90ee23e393deb06fa5c15e3778fa23c39a25f7ce
mheinzl
parents:
0
diff
changeset
|
297 continue |
7414792e1cb8
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 90ee23e393deb06fa5c15e3778fa23c39a25f7ce
mheinzl
parents:
0
diff
changeset
|
298 else: |
7414792e1cb8
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 90ee23e393deb06fa5c15e3778fa23c39a25f7ce
mheinzl
parents:
0
diff
changeset
|
299 if state == 1: |
19
2e9f7ea7ae93
planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/hd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a-dirty
mheinzl
parents:
18
diff
changeset
|
300 for i, l in zip(uniqueHD, nr): |
1
7414792e1cb8
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 90ee23e393deb06fa5c15e3778fa23c39a25f7ce
mheinzl
parents:
0
diff
changeset
|
301 for j in table: |
7414792e1cb8
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 90ee23e393deb06fa5c15e3778fa23c39a25f7ce
mheinzl
parents:
0
diff
changeset
|
302 if j[0] == uniqueHD[l]: |
7414792e1cb8
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 90ee23e393deb06fa5c15e3778fa23c39a25f7ce
mheinzl
parents:
0
diff
changeset
|
303 count[l, 0] = j[1] |
7414792e1cb8
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 90ee23e393deb06fa5c15e3778fa23c39a25f7ce
mheinzl
parents:
0
diff
changeset
|
304 if state == 2: |
7414792e1cb8
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 90ee23e393deb06fa5c15e3778fa23c39a25f7ce
mheinzl
parents:
0
diff
changeset
|
305 for i, l in zip(uniqueHD, nr): |
7414792e1cb8
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 90ee23e393deb06fa5c15e3778fa23c39a25f7ce
mheinzl
parents:
0
diff
changeset
|
306 for j in table: |
7414792e1cb8
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 90ee23e393deb06fa5c15e3778fa23c39a25f7ce
mheinzl
parents:
0
diff
changeset
|
307 if j[0] == uniqueHD[l]: |
7414792e1cb8
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 90ee23e393deb06fa5c15e3778fa23c39a25f7ce
mheinzl
parents:
0
diff
changeset
|
308 count[l, 1] = j[1] |
7414792e1cb8
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 90ee23e393deb06fa5c15e3778fa23c39a25f7ce
mheinzl
parents:
0
diff
changeset
|
309 |
7414792e1cb8
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 90ee23e393deb06fa5c15e3778fa23c39a25f7ce
mheinzl
parents:
0
diff
changeset
|
310 if state == 3: |
7414792e1cb8
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 90ee23e393deb06fa5c15e3778fa23c39a25f7ce
mheinzl
parents:
0
diff
changeset
|
311 for i, l in zip(uniqueHD, nr): |
7414792e1cb8
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 90ee23e393deb06fa5c15e3778fa23c39a25f7ce
mheinzl
parents:
0
diff
changeset
|
312 for j in table: |
7414792e1cb8
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 90ee23e393deb06fa5c15e3778fa23c39a25f7ce
mheinzl
parents:
0
diff
changeset
|
313 if j[0] == uniqueHD[l]: |
7414792e1cb8
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 90ee23e393deb06fa5c15e3778fa23c39a25f7ce
mheinzl
parents:
0
diff
changeset
|
314 count[l, 2] = j[1] |
7414792e1cb8
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 90ee23e393deb06fa5c15e3778fa23c39a25f7ce
mheinzl
parents:
0
diff
changeset
|
315 |
7414792e1cb8
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 90ee23e393deb06fa5c15e3778fa23c39a25f7ce
mheinzl
parents:
0
diff
changeset
|
316 if state == 4: |
7414792e1cb8
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 90ee23e393deb06fa5c15e3778fa23c39a25f7ce
mheinzl
parents:
0
diff
changeset
|
317 for i, l in zip(uniqueHD, nr): |
7414792e1cb8
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 90ee23e393deb06fa5c15e3778fa23c39a25f7ce
mheinzl
parents:
0
diff
changeset
|
318 for j in table: |
7414792e1cb8
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 90ee23e393deb06fa5c15e3778fa23c39a25f7ce
mheinzl
parents:
0
diff
changeset
|
319 if j[0] == uniqueHD[l]: |
7414792e1cb8
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 90ee23e393deb06fa5c15e3778fa23c39a25f7ce
mheinzl
parents:
0
diff
changeset
|
320 count[l, 3] = j[1] |
7414792e1cb8
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 90ee23e393deb06fa5c15e3778fa23c39a25f7ce
mheinzl
parents:
0
diff
changeset
|
321 |
7414792e1cb8
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 90ee23e393deb06fa5c15e3778fa23c39a25f7ce
mheinzl
parents:
0
diff
changeset
|
322 if state == 5: |
7414792e1cb8
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 90ee23e393deb06fa5c15e3778fa23c39a25f7ce
mheinzl
parents:
0
diff
changeset
|
323 for i, l in zip(uniqueHD, nr): |
7414792e1cb8
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 90ee23e393deb06fa5c15e3778fa23c39a25f7ce
mheinzl
parents:
0
diff
changeset
|
324 for j in table: |
7414792e1cb8
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 90ee23e393deb06fa5c15e3778fa23c39a25f7ce
mheinzl
parents:
0
diff
changeset
|
325 if j[0] == uniqueHD[l]: |
7414792e1cb8
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 90ee23e393deb06fa5c15e3778fa23c39a25f7ce
mheinzl
parents:
0
diff
changeset
|
326 count[l, 4] = j[1] |
7414792e1cb8
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 90ee23e393deb06fa5c15e3778fa23c39a25f7ce
mheinzl
parents:
0
diff
changeset
|
327 |
7414792e1cb8
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 90ee23e393deb06fa5c15e3778fa23c39a25f7ce
mheinzl
parents:
0
diff
changeset
|
328 if state == 6: |
7414792e1cb8
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 90ee23e393deb06fa5c15e3778fa23c39a25f7ce
mheinzl
parents:
0
diff
changeset
|
329 for i, l in zip(uniqueHD, nr): |
7414792e1cb8
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 90ee23e393deb06fa5c15e3778fa23c39a25f7ce
mheinzl
parents:
0
diff
changeset
|
330 for j in table: |
7414792e1cb8
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 90ee23e393deb06fa5c15e3778fa23c39a25f7ce
mheinzl
parents:
0
diff
changeset
|
331 if j[0] == uniqueHD[l]: |
7414792e1cb8
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 90ee23e393deb06fa5c15e3778fa23c39a25f7ce
mheinzl
parents:
0
diff
changeset
|
332 count[l, 5] = j[1] |
7414792e1cb8
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 90ee23e393deb06fa5c15e3778fa23c39a25f7ce
mheinzl
parents:
0
diff
changeset
|
333 state = state + 1 |
7414792e1cb8
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 90ee23e393deb06fa5c15e3778fa23c39a25f7ce
mheinzl
parents:
0
diff
changeset
|
334 |
7414792e1cb8
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 90ee23e393deb06fa5c15e3778fa23c39a25f7ce
mheinzl
parents:
0
diff
changeset
|
335 sumRow = count.sum(axis=1) |
7414792e1cb8
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 90ee23e393deb06fa5c15e3778fa23c39a25f7ce
mheinzl
parents:
0
diff
changeset
|
336 sumCol = count.sum(axis=0) |
19
2e9f7ea7ae93
planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/hd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a-dirty
mheinzl
parents:
18
diff
changeset
|
337 first = ["{}{}".format(row_label, i) for i in uniqueHD] |
1
7414792e1cb8
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 90ee23e393deb06fa5c15e3778fa23c39a25f7ce
mheinzl
parents:
0
diff
changeset
|
338 final = numpy.column_stack((first, count, sumRow)) |
7414792e1cb8
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 90ee23e393deb06fa5c15e3778fa23c39a25f7ce
mheinzl
parents:
0
diff
changeset
|
339 |
7414792e1cb8
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 90ee23e393deb06fa5c15e3778fa23c39a25f7ce
mheinzl
parents:
0
diff
changeset
|
340 return (final, sumCol) |
7414792e1cb8
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 90ee23e393deb06fa5c15e3778fa23c39a25f7ce
mheinzl
parents:
0
diff
changeset
|
341 |
19
2e9f7ea7ae93
planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/hd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a-dirty
mheinzl
parents:
18
diff
changeset
|
342 |
1
7414792e1cb8
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 90ee23e393deb06fa5c15e3778fa23c39a25f7ce
mheinzl
parents:
0
diff
changeset
|
343 def createTableHDwithTags(list1): |
7414792e1cb8
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 90ee23e393deb06fa5c15e3778fa23c39a25f7ce
mheinzl
parents:
0
diff
changeset
|
344 selfAB = numpy.concatenate(list1) |
7414792e1cb8
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 90ee23e393deb06fa5c15e3778fa23c39a25f7ce
mheinzl
parents:
0
diff
changeset
|
345 uniqueHD = numpy.unique(selfAB) |
7414792e1cb8
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 90ee23e393deb06fa5c15e3778fa23c39a25f7ce
mheinzl
parents:
0
diff
changeset
|
346 nr = numpy.arange(0, len(uniqueHD), 1) |
19
2e9f7ea7ae93
planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/hd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a-dirty
mheinzl
parents:
18
diff
changeset
|
347 count = numpy.zeros((len(uniqueHD), 5)) |
1
7414792e1cb8
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 90ee23e393deb06fa5c15e3778fa23c39a25f7ce
mheinzl
parents:
0
diff
changeset
|
348 |
7414792e1cb8
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 90ee23e393deb06fa5c15e3778fa23c39a25f7ce
mheinzl
parents:
0
diff
changeset
|
349 state = 1 |
7414792e1cb8
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 90ee23e393deb06fa5c15e3778fa23c39a25f7ce
mheinzl
parents:
0
diff
changeset
|
350 for i in list1: |
7414792e1cb8
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 90ee23e393deb06fa5c15e3778fa23c39a25f7ce
mheinzl
parents:
0
diff
changeset
|
351 counts = list(Counter(i).items()) |
7414792e1cb8
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 90ee23e393deb06fa5c15e3778fa23c39a25f7ce
mheinzl
parents:
0
diff
changeset
|
352 hd = [item[0] for item in counts] |
7414792e1cb8
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 90ee23e393deb06fa5c15e3778fa23c39a25f7ce
mheinzl
parents:
0
diff
changeset
|
353 c = [item[1] for item in counts] |
7414792e1cb8
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 90ee23e393deb06fa5c15e3778fa23c39a25f7ce
mheinzl
parents:
0
diff
changeset
|
354 table = numpy.column_stack((hd, c)) |
7414792e1cb8
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 90ee23e393deb06fa5c15e3778fa23c39a25f7ce
mheinzl
parents:
0
diff
changeset
|
355 if len(table) == 0: |
7414792e1cb8
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 90ee23e393deb06fa5c15e3778fa23c39a25f7ce
mheinzl
parents:
0
diff
changeset
|
356 state = state + 1 |
7414792e1cb8
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 90ee23e393deb06fa5c15e3778fa23c39a25f7ce
mheinzl
parents:
0
diff
changeset
|
357 continue |
7414792e1cb8
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 90ee23e393deb06fa5c15e3778fa23c39a25f7ce
mheinzl
parents:
0
diff
changeset
|
358 else: |
7414792e1cb8
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 90ee23e393deb06fa5c15e3778fa23c39a25f7ce
mheinzl
parents:
0
diff
changeset
|
359 if state == 1: |
19
2e9f7ea7ae93
planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/hd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a-dirty
mheinzl
parents:
18
diff
changeset
|
360 for i, l in zip(uniqueHD, nr): |
1
7414792e1cb8
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 90ee23e393deb06fa5c15e3778fa23c39a25f7ce
mheinzl
parents:
0
diff
changeset
|
361 for j in table: |
7414792e1cb8
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 90ee23e393deb06fa5c15e3778fa23c39a25f7ce
mheinzl
parents:
0
diff
changeset
|
362 if j[0] == uniqueHD[l]: |
7414792e1cb8
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 90ee23e393deb06fa5c15e3778fa23c39a25f7ce
mheinzl
parents:
0
diff
changeset
|
363 count[l, 0] = j[1] |
7414792e1cb8
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 90ee23e393deb06fa5c15e3778fa23c39a25f7ce
mheinzl
parents:
0
diff
changeset
|
364 if state == 2: |
7414792e1cb8
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 90ee23e393deb06fa5c15e3778fa23c39a25f7ce
mheinzl
parents:
0
diff
changeset
|
365 for i, l in zip(uniqueHD, nr): |
7414792e1cb8
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 90ee23e393deb06fa5c15e3778fa23c39a25f7ce
mheinzl
parents:
0
diff
changeset
|
366 for j in table: |
7414792e1cb8
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 90ee23e393deb06fa5c15e3778fa23c39a25f7ce
mheinzl
parents:
0
diff
changeset
|
367 if j[0] == uniqueHD[l]: |
7414792e1cb8
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 90ee23e393deb06fa5c15e3778fa23c39a25f7ce
mheinzl
parents:
0
diff
changeset
|
368 count[l, 1] = j[1] |
7414792e1cb8
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 90ee23e393deb06fa5c15e3778fa23c39a25f7ce
mheinzl
parents:
0
diff
changeset
|
369 if state == 3: |
7414792e1cb8
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 90ee23e393deb06fa5c15e3778fa23c39a25f7ce
mheinzl
parents:
0
diff
changeset
|
370 for i, l in zip(uniqueHD, nr): |
7414792e1cb8
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 90ee23e393deb06fa5c15e3778fa23c39a25f7ce
mheinzl
parents:
0
diff
changeset
|
371 for j in table: |
7414792e1cb8
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 90ee23e393deb06fa5c15e3778fa23c39a25f7ce
mheinzl
parents:
0
diff
changeset
|
372 if j[0] == uniqueHD[l]: |
7414792e1cb8
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 90ee23e393deb06fa5c15e3778fa23c39a25f7ce
mheinzl
parents:
0
diff
changeset
|
373 count[l, 2] = j[1] |
19
2e9f7ea7ae93
planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/hd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a-dirty
mheinzl
parents:
18
diff
changeset
|
374 if state == 4: |
2e9f7ea7ae93
planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/hd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a-dirty
mheinzl
parents:
18
diff
changeset
|
375 for i, l in zip(uniqueHD, nr): |
2e9f7ea7ae93
planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/hd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a-dirty
mheinzl
parents:
18
diff
changeset
|
376 for j in table: |
2e9f7ea7ae93
planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/hd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a-dirty
mheinzl
parents:
18
diff
changeset
|
377 if j[0] == uniqueHD[l]: |
2e9f7ea7ae93
planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/hd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a-dirty
mheinzl
parents:
18
diff
changeset
|
378 count[l, 3] = j[1] |
2e9f7ea7ae93
planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/hd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a-dirty
mheinzl
parents:
18
diff
changeset
|
379 if state == 5: |
2e9f7ea7ae93
planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/hd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a-dirty
mheinzl
parents:
18
diff
changeset
|
380 for i, l in zip(uniqueHD, nr): |
2e9f7ea7ae93
planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/hd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a-dirty
mheinzl
parents:
18
diff
changeset
|
381 for j in table: |
2e9f7ea7ae93
planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/hd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a-dirty
mheinzl
parents:
18
diff
changeset
|
382 if j[0] == uniqueHD[l]: |
2e9f7ea7ae93
planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/hd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a-dirty
mheinzl
parents:
18
diff
changeset
|
383 count[l, 4] = j[1] |
2e9f7ea7ae93
planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/hd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a-dirty
mheinzl
parents:
18
diff
changeset
|
384 |
1
7414792e1cb8
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 90ee23e393deb06fa5c15e3778fa23c39a25f7ce
mheinzl
parents:
0
diff
changeset
|
385 state = state + 1 |
7414792e1cb8
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 90ee23e393deb06fa5c15e3778fa23c39a25f7ce
mheinzl
parents:
0
diff
changeset
|
386 |
7414792e1cb8
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 90ee23e393deb06fa5c15e3778fa23c39a25f7ce
mheinzl
parents:
0
diff
changeset
|
387 sumRow = count.sum(axis=1) |
7414792e1cb8
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 90ee23e393deb06fa5c15e3778fa23c39a25f7ce
mheinzl
parents:
0
diff
changeset
|
388 sumCol = count.sum(axis=0) |
7414792e1cb8
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 90ee23e393deb06fa5c15e3778fa23c39a25f7ce
mheinzl
parents:
0
diff
changeset
|
389 first = ["HD={}".format(i) for i in uniqueHD] |
7414792e1cb8
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 90ee23e393deb06fa5c15e3778fa23c39a25f7ce
mheinzl
parents:
0
diff
changeset
|
390 final = numpy.column_stack((first, count, sumRow)) |
7414792e1cb8
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 90ee23e393deb06fa5c15e3778fa23c39a25f7ce
mheinzl
parents:
0
diff
changeset
|
391 |
7414792e1cb8
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 90ee23e393deb06fa5c15e3778fa23c39a25f7ce
mheinzl
parents:
0
diff
changeset
|
392 return (final, sumCol) |
7414792e1cb8
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 90ee23e393deb06fa5c15e3778fa23c39a25f7ce
mheinzl
parents:
0
diff
changeset
|
393 |
19
2e9f7ea7ae93
planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/hd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a-dirty
mheinzl
parents:
18
diff
changeset
|
394 |
2e9f7ea7ae93
planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/hd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a-dirty
mheinzl
parents:
18
diff
changeset
|
395 def createFileHD(summary, sumCol, overallSum, output_file, name, sep): |
1
7414792e1cb8
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 90ee23e393deb06fa5c15e3778fa23c39a25f7ce
mheinzl
parents:
0
diff
changeset
|
396 output_file.write(name) |
7414792e1cb8
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 90ee23e393deb06fa5c15e3778fa23c39a25f7ce
mheinzl
parents:
0
diff
changeset
|
397 output_file.write("\n") |
19
2e9f7ea7ae93
planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/hd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a-dirty
mheinzl
parents:
18
diff
changeset
|
398 output_file.write("{}FS=1{}FS=2{}FS=3{}FS=4{}FS=5-10{}FS>10{}sum{}\n".format(sep, sep, sep, sep, sep, sep, sep, sep)) |
1
7414792e1cb8
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 90ee23e393deb06fa5c15e3778fa23c39a25f7ce
mheinzl
parents:
0
diff
changeset
|
399 for item in summary: |
7414792e1cb8
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 90ee23e393deb06fa5c15e3778fa23c39a25f7ce
mheinzl
parents:
0
diff
changeset
|
400 for nr in item: |
7414792e1cb8
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 90ee23e393deb06fa5c15e3778fa23c39a25f7ce
mheinzl
parents:
0
diff
changeset
|
401 if "HD" not in nr and "diff" not in nr: |
7414792e1cb8
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 90ee23e393deb06fa5c15e3778fa23c39a25f7ce
mheinzl
parents:
0
diff
changeset
|
402 nr = nr.astype(float) |
7414792e1cb8
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 90ee23e393deb06fa5c15e3778fa23c39a25f7ce
mheinzl
parents:
0
diff
changeset
|
403 nr = nr.astype(int) |
19
2e9f7ea7ae93
planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/hd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a-dirty
mheinzl
parents:
18
diff
changeset
|
404 output_file.write("{}{}".format(nr, sep)) |
1
7414792e1cb8
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 90ee23e393deb06fa5c15e3778fa23c39a25f7ce
mheinzl
parents:
0
diff
changeset
|
405 output_file.write("\n") |
7414792e1cb8
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 90ee23e393deb06fa5c15e3778fa23c39a25f7ce
mheinzl
parents:
0
diff
changeset
|
406 output_file.write("sum{}".format(sep)) |
7414792e1cb8
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 90ee23e393deb06fa5c15e3778fa23c39a25f7ce
mheinzl
parents:
0
diff
changeset
|
407 sumCol = map(int, sumCol) |
7414792e1cb8
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 90ee23e393deb06fa5c15e3778fa23c39a25f7ce
mheinzl
parents:
0
diff
changeset
|
408 for el in sumCol: |
19
2e9f7ea7ae93
planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/hd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a-dirty
mheinzl
parents:
18
diff
changeset
|
409 output_file.write("{}{}".format(el, sep)) |
2e9f7ea7ae93
planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/hd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a-dirty
mheinzl
parents:
18
diff
changeset
|
410 output_file.write("{}{}".format(overallSum.astype(int), sep)) |
1
7414792e1cb8
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 90ee23e393deb06fa5c15e3778fa23c39a25f7ce
mheinzl
parents:
0
diff
changeset
|
411 output_file.write("\n\n") |
7414792e1cb8
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 90ee23e393deb06fa5c15e3778fa23c39a25f7ce
mheinzl
parents:
0
diff
changeset
|
412 |
19
2e9f7ea7ae93
planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/hd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a-dirty
mheinzl
parents:
18
diff
changeset
|
413 |
2e9f7ea7ae93
planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/hd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a-dirty
mheinzl
parents:
18
diff
changeset
|
414 def createFileHDwithinTag(summary, sumCol, overallSum, output_file, name, sep): |
1
7414792e1cb8
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 90ee23e393deb06fa5c15e3778fa23c39a25f7ce
mheinzl
parents:
0
diff
changeset
|
415 output_file.write(name) |
7414792e1cb8
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 90ee23e393deb06fa5c15e3778fa23c39a25f7ce
mheinzl
parents:
0
diff
changeset
|
416 output_file.write("\n") |
19
2e9f7ea7ae93
planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/hd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a-dirty
mheinzl
parents:
18
diff
changeset
|
417 output_file.write("{}HD a{}HD b'{}HD b{}HD a'{}HD a+b{}sum{}\n".format(sep, sep, sep, sep, sep, sep, sep)) |
1
7414792e1cb8
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 90ee23e393deb06fa5c15e3778fa23c39a25f7ce
mheinzl
parents:
0
diff
changeset
|
418 for item in summary: |
7414792e1cb8
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 90ee23e393deb06fa5c15e3778fa23c39a25f7ce
mheinzl
parents:
0
diff
changeset
|
419 for nr in item: |
7414792e1cb8
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 90ee23e393deb06fa5c15e3778fa23c39a25f7ce
mheinzl
parents:
0
diff
changeset
|
420 if "HD" not in nr: |
7414792e1cb8
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 90ee23e393deb06fa5c15e3778fa23c39a25f7ce
mheinzl
parents:
0
diff
changeset
|
421 nr = nr.astype(float) |
7414792e1cb8
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 90ee23e393deb06fa5c15e3778fa23c39a25f7ce
mheinzl
parents:
0
diff
changeset
|
422 nr = nr.astype(int) |
19
2e9f7ea7ae93
planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/hd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a-dirty
mheinzl
parents:
18
diff
changeset
|
423 output_file.write("{}{}".format(nr, sep)) |
1
7414792e1cb8
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 90ee23e393deb06fa5c15e3778fa23c39a25f7ce
mheinzl
parents:
0
diff
changeset
|
424 output_file.write("\n") |
7414792e1cb8
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 90ee23e393deb06fa5c15e3778fa23c39a25f7ce
mheinzl
parents:
0
diff
changeset
|
425 output_file.write("sum{}".format(sep)) |
7414792e1cb8
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 90ee23e393deb06fa5c15e3778fa23c39a25f7ce
mheinzl
parents:
0
diff
changeset
|
426 sumCol = map(int, sumCol) |
7414792e1cb8
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 90ee23e393deb06fa5c15e3778fa23c39a25f7ce
mheinzl
parents:
0
diff
changeset
|
427 for el in sumCol: |
19
2e9f7ea7ae93
planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/hd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a-dirty
mheinzl
parents:
18
diff
changeset
|
428 output_file.write("{}{}".format(el, sep)) |
2e9f7ea7ae93
planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/hd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a-dirty
mheinzl
parents:
18
diff
changeset
|
429 output_file.write("{}{}".format(overallSum.astype(int), sep)) |
1
7414792e1cb8
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 90ee23e393deb06fa5c15e3778fa23c39a25f7ce
mheinzl
parents:
0
diff
changeset
|
430 output_file.write("\n\n") |
19
2e9f7ea7ae93
planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/hd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a-dirty
mheinzl
parents:
18
diff
changeset
|
431 |
2e9f7ea7ae93
planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/hd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a-dirty
mheinzl
parents:
18
diff
changeset
|
432 |
0
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
433 def hamming(array1, array2): |
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
434 res = 99 * numpy.ones(len(array1)) |
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
435 i = 0 |
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
436 array2 = numpy.unique(array2) # remove duplicate sequences to decrease running time |
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
437 for a in array1: |
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
438 dist = numpy.array([sum(itertools.imap(operator.ne, a, b)) for b in array2]) # fastest |
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
439 res[i] = numpy.amin(dist[dist > 0]) # pick min distance greater than zero |
19
2e9f7ea7ae93
planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/hd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a-dirty
mheinzl
parents:
18
diff
changeset
|
440 # print(i) |
0
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
441 i += 1 |
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
442 return res |
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
443 |
19
2e9f7ea7ae93
planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/hd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a-dirty
mheinzl
parents:
18
diff
changeset
|
444 |
0
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
445 def hamming_difference(array1, array2, mate_b): |
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
446 array2 = numpy.unique(array2) # remove duplicate sequences to decrease running time |
19
2e9f7ea7ae93
planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/hd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a-dirty
mheinzl
parents:
18
diff
changeset
|
447 array1_half = numpy.array([i[0:(len(i)) / 2] for i in array1]) # mate1 part1 |
2e9f7ea7ae93
planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/hd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a-dirty
mheinzl
parents:
18
diff
changeset
|
448 array1_half2 = numpy.array([i[len(i) / 2:len(i)] for i in array1]) # mate1 part 2 |
0
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
449 |
19
2e9f7ea7ae93
planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/hd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a-dirty
mheinzl
parents:
18
diff
changeset
|
450 array2_half = numpy.array([i[0:(len(i)) / 2] for i in array2]) # mate2 part1 |
0
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
451 array2_half2 = numpy.array([i[len(i) / 2:len(i)] for i in array2]) # mate2 part2 |
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
452 |
19
2e9f7ea7ae93
planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/hd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a-dirty
mheinzl
parents:
18
diff
changeset
|
453 # diff11 = 999 * numpy.ones(len(array2)) |
2e9f7ea7ae93
planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/hd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a-dirty
mheinzl
parents:
18
diff
changeset
|
454 # relativeDiffList = 999 * numpy.ones(len(array2)) |
2e9f7ea7ae93
planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/hd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a-dirty
mheinzl
parents:
18
diff
changeset
|
455 # ham1 = 999 * numpy.ones(len(array2)) |
2e9f7ea7ae93
planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/hd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a-dirty
mheinzl
parents:
18
diff
changeset
|
456 # ham2 = 999 * numpy.ones(len(array2)) |
2e9f7ea7ae93
planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/hd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a-dirty
mheinzl
parents:
18
diff
changeset
|
457 # min_valueList = 999 * numpy.ones(len(array2)) |
2e9f7ea7ae93
planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/hd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a-dirty
mheinzl
parents:
18
diff
changeset
|
458 # min_tagsList = 999 * numpy.ones(len(array2)) |
2e9f7ea7ae93
planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/hd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a-dirty
mheinzl
parents:
18
diff
changeset
|
459 # diff11_zeros = 999 * numpy.ones(len(array2)) |
2e9f7ea7ae93
planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/hd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a-dirty
mheinzl
parents:
18
diff
changeset
|
460 # min_tagsList_zeros = 999 * numpy.ones(len(array2)) |
2e9f7ea7ae93
planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/hd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a-dirty
mheinzl
parents:
18
diff
changeset
|
461 |
8
e2596a4e1c56
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 24e245e913368abc55281d3bf22b2e1b8d60d26a
mheinzl
parents:
7
diff
changeset
|
462 diff11 = [] |
e2596a4e1c56
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 24e245e913368abc55281d3bf22b2e1b8d60d26a
mheinzl
parents:
7
diff
changeset
|
463 relativeDiffList = [] |
e2596a4e1c56
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 24e245e913368abc55281d3bf22b2e1b8d60d26a
mheinzl
parents:
7
diff
changeset
|
464 ham1 = [] |
e2596a4e1c56
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 24e245e913368abc55281d3bf22b2e1b8d60d26a
mheinzl
parents:
7
diff
changeset
|
465 ham2 = [] |
14
883e6381ba29
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 38f5c032262361131c645812dd3dc639be6a5f4e
mheinzl
parents:
13
diff
changeset
|
466 ham1min = [] |
883e6381ba29
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 38f5c032262361131c645812dd3dc639be6a5f4e
mheinzl
parents:
13
diff
changeset
|
467 ham2min = [] |
8
e2596a4e1c56
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 24e245e913368abc55281d3bf22b2e1b8d60d26a
mheinzl
parents:
7
diff
changeset
|
468 min_valueList = [] |
e2596a4e1c56
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 24e245e913368abc55281d3bf22b2e1b8d60d26a
mheinzl
parents:
7
diff
changeset
|
469 min_tagsList = [] |
e2596a4e1c56
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 24e245e913368abc55281d3bf22b2e1b8d60d26a
mheinzl
parents:
7
diff
changeset
|
470 diff11_zeros = [] |
e2596a4e1c56
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 24e245e913368abc55281d3bf22b2e1b8d60d26a
mheinzl
parents:
7
diff
changeset
|
471 min_tagsList_zeros = [] |
19
2e9f7ea7ae93
planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/hd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a-dirty
mheinzl
parents:
18
diff
changeset
|
472 i = 0 # counter, only used to see how many HDs of tags were already calculated |
2e9f7ea7ae93
planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/hd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a-dirty
mheinzl
parents:
18
diff
changeset
|
473 if mate_b is False: # HD calculation for all a's |
0
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
474 half1_mate1 = array1_half |
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
475 half2_mate1 = array1_half2 |
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
476 half1_mate2 = array2_half |
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
477 half2_mate2 = array2_half2 |
19
2e9f7ea7ae93
planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/hd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a-dirty
mheinzl
parents:
18
diff
changeset
|
478 elif mate_b is True: # HD calculation for all b's |
0
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
479 half1_mate1 = array1_half2 |
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
480 half2_mate1 = array1_half |
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
481 half1_mate2 = array2_half2 |
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
482 half2_mate2 = array2_half |
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
483 |
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
484 for a, b, tag in zip(half1_mate1, half2_mate1, array1): |
19
2e9f7ea7ae93
planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/hd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a-dirty
mheinzl
parents:
18
diff
changeset
|
485 # exclude identical tag from array2, to prevent comparison to itself |
0
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
486 sameTag = numpy.where(array2 == tag) |
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
487 indexArray2 = numpy.arange(0, len(array2), 1) |
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
488 index_withoutSame = numpy.delete(indexArray2, sameTag) # delete identical tag from the data |
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
489 |
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
490 # all tags without identical tag |
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
491 array2_half_withoutSame = half1_mate2[index_withoutSame] |
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
492 array2_half2_withoutSame = half2_mate2[index_withoutSame] |
19
2e9f7ea7ae93
planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/hd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a-dirty
mheinzl
parents:
18
diff
changeset
|
493 # array2_withoutSame = array2[index_withoutSame] # whole tag (=not splitted into 2 halfs) |
0
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
494 |
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
495 dist = numpy.array([sum(itertools.imap(operator.ne, a, c)) for c in |
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
496 array2_half_withoutSame]) # calculate HD of "a" in the tag to all "a's" or "b" in the tag to all "b's" |
19
2e9f7ea7ae93
planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/hd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a-dirty
mheinzl
parents:
18
diff
changeset
|
497 min_index = numpy.where(dist == dist.min()) # get index of min HD |
0
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
498 min_value = dist[min_index] # get minimum HDs |
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
499 min_tag_half2 = array2_half2_withoutSame[min_index] # get all "b's" of the tag or all "a's" of the tag with minimum HD |
19
2e9f7ea7ae93
planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/hd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a-dirty
mheinzl
parents:
18
diff
changeset
|
500 # min_tag = array2_withoutSame[min_index] # get whole tag with min HD |
0
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
501 |
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
502 dist2 = numpy.array([sum(itertools.imap(operator.ne, b, e)) for e in |
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
503 min_tag_half2]) # calculate HD of "b" to all "b's" or "a" to all "a's" |
19
2e9f7ea7ae93
planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/hd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a-dirty
mheinzl
parents:
18
diff
changeset
|
504 for d, d2 in zip(min_value, dist2): |
0
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
505 if mate_b is True: # half2, corrects the variable of the HD from both halfs if it is a or b |
14
883e6381ba29
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 38f5c032262361131c645812dd3dc639be6a5f4e
mheinzl
parents:
13
diff
changeset
|
506 ham2.append(d) |
883e6381ba29
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 38f5c032262361131c645812dd3dc639be6a5f4e
mheinzl
parents:
13
diff
changeset
|
507 ham2min.append(d2) |
0
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
508 else: # half1, corrects the variable of the HD from both halfs if it is a or b |
14
883e6381ba29
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 38f5c032262361131c645812dd3dc639be6a5f4e
mheinzl
parents:
13
diff
changeset
|
509 ham1.append(d) |
883e6381ba29
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 38f5c032262361131c645812dd3dc639be6a5f4e
mheinzl
parents:
13
diff
changeset
|
510 ham1min.append(d2) |
19
2e9f7ea7ae93
planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/hd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a-dirty
mheinzl
parents:
18
diff
changeset
|
511 |
8
e2596a4e1c56
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 24e245e913368abc55281d3bf22b2e1b8d60d26a
mheinzl
parents:
7
diff
changeset
|
512 min_valueList.append(d + d2) |
e2596a4e1c56
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 24e245e913368abc55281d3bf22b2e1b8d60d26a
mheinzl
parents:
7
diff
changeset
|
513 min_tagsList.append(tag) |
0
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
514 difference1 = abs(d - d2) |
8
e2596a4e1c56
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 24e245e913368abc55281d3bf22b2e1b8d60d26a
mheinzl
parents:
7
diff
changeset
|
515 diff11.append(difference1) |
0
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
516 rel_difference = round(float(difference1) / (d + d2), 1) |
8
e2596a4e1c56
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 24e245e913368abc55281d3bf22b2e1b8d60d26a
mheinzl
parents:
7
diff
changeset
|
517 relativeDiffList.append(rel_difference) |
0
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
518 |
19
2e9f7ea7ae93
planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/hd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a-dirty
mheinzl
parents:
18
diff
changeset
|
519 # tags which have identical parts: |
0
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
520 if d == 0 or d2 == 0: |
8
e2596a4e1c56
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 24e245e913368abc55281d3bf22b2e1b8d60d26a
mheinzl
parents:
7
diff
changeset
|
521 min_tagsList_zeros.append(tag) |
0
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
522 difference1_zeros = abs(d - d2) |
8
e2596a4e1c56
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 24e245e913368abc55281d3bf22b2e1b8d60d26a
mheinzl
parents:
7
diff
changeset
|
523 diff11_zeros.append(difference1_zeros) |
e2596a4e1c56
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 24e245e913368abc55281d3bf22b2e1b8d60d26a
mheinzl
parents:
7
diff
changeset
|
524 i += 1 |
19
2e9f7ea7ae93
planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/hd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a-dirty
mheinzl
parents:
18
diff
changeset
|
525 |
2e9f7ea7ae93
planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/hd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a-dirty
mheinzl
parents:
18
diff
changeset
|
526 # print(i) |
2e9f7ea7ae93
planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/hd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a-dirty
mheinzl
parents:
18
diff
changeset
|
527 # diff11 = [st for st in diff11 if st != 999] |
2e9f7ea7ae93
planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/hd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a-dirty
mheinzl
parents:
18
diff
changeset
|
528 # ham1 = [st for st in ham1 if st != 999] |
2e9f7ea7ae93
planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/hd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a-dirty
mheinzl
parents:
18
diff
changeset
|
529 # ham2 = [st for st in ham2 if st != 999] |
2e9f7ea7ae93
planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/hd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a-dirty
mheinzl
parents:
18
diff
changeset
|
530 # min_valueList = [st for st in min_valueList if st != 999] |
2e9f7ea7ae93
planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/hd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a-dirty
mheinzl
parents:
18
diff
changeset
|
531 # min_tagsList = [st for st in min_tagsList if st != 999] |
2e9f7ea7ae93
planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/hd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a-dirty
mheinzl
parents:
18
diff
changeset
|
532 # relativeDiffList = [st for st in relativeDiffList if st != 999] |
2e9f7ea7ae93
planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/hd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a-dirty
mheinzl
parents:
18
diff
changeset
|
533 # diff11_zeros = [st for st in diff11_zeros if st != 999] |
2e9f7ea7ae93
planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/hd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a-dirty
mheinzl
parents:
18
diff
changeset
|
534 # min_tagsList_zeros = [st for st in min_tagsList_zeros if st != 999] |
2
316fbf91dd12
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit f9d5547849dabb59a33a5e998bda4730323d62a9
mheinzl
parents:
1
diff
changeset
|
535 |
14
883e6381ba29
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 38f5c032262361131c645812dd3dc639be6a5f4e
mheinzl
parents:
13
diff
changeset
|
536 return ([diff11, ham1, ham2, min_valueList, min_tagsList, relativeDiffList, diff11_zeros, min_tagsList_zeros, ham1min, ham2min]) |
0
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
537 |
19
2e9f7ea7ae93
planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/hd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a-dirty
mheinzl
parents:
18
diff
changeset
|
538 |
0
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
539 def readFileReferenceFree(file): |
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
540 with open(file, 'r') as dest_f: |
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
541 data_array = numpy.genfromtxt(dest_f, skip_header=0, delimiter='\t', comments='#', dtype='string') |
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
542 integers = numpy.array(data_array[:, 0]).astype(int) |
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
543 return(integers, data_array) |
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
544 |
19
2e9f7ea7ae93
planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/hd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a-dirty
mheinzl
parents:
18
diff
changeset
|
545 |
11
7adc48c8a03d
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 8d9bdadb5e154dadc455720c99700afbd9aafae9
mheinzl
parents:
10
diff
changeset
|
546 def hammingDistanceWithFS(fs, ham): |
7adc48c8a03d
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 8d9bdadb5e154dadc455720c99700afbd9aafae9
mheinzl
parents:
10
diff
changeset
|
547 fs = numpy.asarray(fs) |
0
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
548 maximum = max(ham) |
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
549 minimum = min(ham) |
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
550 ham = numpy.asarray(ham) |
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
551 |
11
7adc48c8a03d
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 8d9bdadb5e154dadc455720c99700afbd9aafae9
mheinzl
parents:
10
diff
changeset
|
552 singletons = numpy.where(fs == 1)[0] |
0
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
553 data = ham[singletons] |
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
554 |
11
7adc48c8a03d
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 8d9bdadb5e154dadc455720c99700afbd9aafae9
mheinzl
parents:
10
diff
changeset
|
555 hd2 = numpy.where(fs == 2)[0] |
0
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
556 data2 = ham[hd2] |
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
557 |
11
7adc48c8a03d
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 8d9bdadb5e154dadc455720c99700afbd9aafae9
mheinzl
parents:
10
diff
changeset
|
558 hd3 = numpy.where(fs == 3)[0] |
0
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
559 data3 = ham[hd3] |
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
560 |
11
7adc48c8a03d
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 8d9bdadb5e154dadc455720c99700afbd9aafae9
mheinzl
parents:
10
diff
changeset
|
561 hd4 = numpy.where(fs == 4)[0] |
0
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
562 data4 = ham[hd4] |
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
563 |
11
7adc48c8a03d
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 8d9bdadb5e154dadc455720c99700afbd9aafae9
mheinzl
parents:
10
diff
changeset
|
564 hd5 = numpy.where((fs >= 5) & (fs <= 10))[0] |
0
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
565 data5 = ham[hd5] |
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
566 |
11
7adc48c8a03d
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 8d9bdadb5e154dadc455720c99700afbd9aafae9
mheinzl
parents:
10
diff
changeset
|
567 hd6 = numpy.where(fs > 10)[0] |
0
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
568 data6 = ham[hd6] |
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
569 |
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
570 list1 = [data, data2, data3, data4, data5, data6] |
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
571 return(list1, maximum, minimum) |
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
572 |
19
2e9f7ea7ae93
planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/hd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a-dirty
mheinzl
parents:
18
diff
changeset
|
573 |
2e9f7ea7ae93
planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/hd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a-dirty
mheinzl
parents:
18
diff
changeset
|
574 def familySizeDistributionWithHD(fs, ham, diff=False, rel=True): |
0
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
575 hammingDistances = numpy.unique(ham) |
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
576 fs = numpy.asarray(fs) |
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
577 |
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
578 ham = numpy.asarray(ham) |
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
579 bigFamilies2 = numpy.where(fs > 19)[0] |
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
580 if len(bigFamilies2) != 0: |
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
581 fs[bigFamilies2] = 20 |
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
582 maximum = max(fs) |
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
583 minimum = min(fs) |
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
584 if diff is True: |
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
585 hd0 = numpy.where(ham == 0)[0] |
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
586 data0 = fs[hd0] |
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
587 |
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
588 if rel is True: |
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
589 hd1 = numpy.where(ham == 0.1)[0] |
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
590 else: |
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
591 hd1 = numpy.where(ham == 1)[0] |
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
592 data = fs[hd1] |
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
593 |
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
594 if rel is True: |
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
595 hd2 = numpy.where(ham == 0.2)[0] |
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
596 else: |
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
597 hd2 = numpy.where(ham == 2)[0] |
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
598 data2 = fs[hd2] |
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
599 |
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
600 if rel is True: |
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
601 hd3 = numpy.where(ham == 0.3)[0] |
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
602 else: |
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
603 hd3 = numpy.where(ham == 3)[0] |
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
604 data3 = fs[hd3] |
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
605 |
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
606 if rel is True: |
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
607 hd4 = numpy.where(ham == 0.4)[0] |
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
608 else: |
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
609 hd4 = numpy.where(ham == 4)[0] |
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
610 data4 = fs[hd4] |
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
611 |
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
612 if rel is True: |
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
613 hd5 = numpy.where((ham >= 0.5) & (ham <= 0.8))[0] |
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
614 else: |
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
615 hd5 = numpy.where((ham >= 5) & (ham <= 8))[0] |
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
616 data5 = fs[hd5] |
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
617 |
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
618 if rel is True: |
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
619 hd6 = numpy.where(ham > 0.8)[0] |
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
620 else: |
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
621 hd6 = numpy.where(ham > 8)[0] |
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
622 data6 = fs[hd6] |
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
623 |
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
624 if diff is True: |
19
2e9f7ea7ae93
planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/hd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a-dirty
mheinzl
parents:
18
diff
changeset
|
625 list1 = [data0, data, data2, data3, data4, data5, data6] |
0
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
626 else: |
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
627 list1 = [data, data2, data3, data4, data5, data6] |
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
628 |
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
629 return(list1, hammingDistances, maximum, minimum) |
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
630 |
19
2e9f7ea7ae93
planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/hd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a-dirty
mheinzl
parents:
18
diff
changeset
|
631 |
0
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
632 def make_argparser(): |
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
633 parser = argparse.ArgumentParser(description='Hamming distance analysis of duplex sequencing data') |
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
634 parser.add_argument('--inputFile', |
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
635 help='Tabular File with three columns: ab or ba, tag and family size.') |
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
636 parser.add_argument('--inputName1') |
19
2e9f7ea7ae93
planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/hd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a-dirty
mheinzl
parents:
18
diff
changeset
|
637 parser.add_argument('--inputFile2', default=None, |
0
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
638 help='Tabular File with three columns: ab or ba, tag and family size.') |
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
639 parser.add_argument('--inputName2') |
19
2e9f7ea7ae93
planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/hd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a-dirty
mheinzl
parents:
18
diff
changeset
|
640 parser.add_argument('--sample_size', default=1000, type=int, |
0
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
641 help='Sample size of Hamming distance analysis.') |
19
2e9f7ea7ae93
planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/hd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a-dirty
mheinzl
parents:
18
diff
changeset
|
642 parser.add_argument('--subset_tag', default=0, type=int, |
0
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
643 help='The tag is shortened to the given number.') |
19
2e9f7ea7ae93
planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/hd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a-dirty
mheinzl
parents:
18
diff
changeset
|
644 parser.add_argument('--nproc', default=4, type=int, |
0
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
645 help='The tool runs with the given number of processors.') |
19
2e9f7ea7ae93
planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/hd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a-dirty
mheinzl
parents:
18
diff
changeset
|
646 parser.add_argument('--only_DCS', action="store_false", |
0
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
647 help='Only tags of the DCSs are included in the HD analysis') |
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
648 |
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
649 parser.add_argument('--minFS', default=1, type=int, |
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
650 help='Only tags, which have a family size greater or equal than specified, are included in the HD analysis') |
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
651 parser.add_argument('--maxFS', default=0, type=int, |
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
652 help='Only tags, which have a family size smaller or equal than specified, are included in the HD analysis') |
19
2e9f7ea7ae93
planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/hd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a-dirty
mheinzl
parents:
18
diff
changeset
|
653 parser.add_argument('--nr_above_bars', action="store_true", |
14
883e6381ba29
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 38f5c032262361131c645812dd3dc639be6a5f4e
mheinzl
parents:
13
diff
changeset
|
654 help='If no, values above bars in the histrograms are removed') |
19
2e9f7ea7ae93
planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/hd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a-dirty
mheinzl
parents:
18
diff
changeset
|
655 |
2e9f7ea7ae93
planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/hd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a-dirty
mheinzl
parents:
18
diff
changeset
|
656 parser.add_argument('--output_tabular', default="data.tabular", type=str, |
2e9f7ea7ae93
planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/hd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a-dirty
mheinzl
parents:
18
diff
changeset
|
657 help='Name of the tabular file.') |
0
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
658 parser.add_argument('--output_pdf', default="data.pdf", type=str, |
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
659 help='Name of the pdf file.') |
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
660 parser.add_argument('--output_pdf2', default="data2.pdf", type=str, |
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
661 help='Name of the pdf file.') |
19
2e9f7ea7ae93
planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/hd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a-dirty
mheinzl
parents:
18
diff
changeset
|
662 parser.add_argument('--output_tabular2', default="data2.tabular", type=str, |
2e9f7ea7ae93
planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/hd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a-dirty
mheinzl
parents:
18
diff
changeset
|
663 help='Name of the tabular file.') |
0
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
664 |
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
665 return parser |
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
666 |
19
2e9f7ea7ae93
planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/hd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a-dirty
mheinzl
parents:
18
diff
changeset
|
667 |
0
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
668 def Hamming_Distance_Analysis(argv): |
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
669 parser = make_argparser() |
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
670 args = parser.parse_args(argv[1:]) |
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
671 |
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
672 file1 = args.inputFile |
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
673 name1 = args.inputName1 |
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
674 |
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
675 file2 = args.inputFile2 |
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
676 name2 = args.inputName2 |
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
677 |
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
678 index_size = args.sample_size |
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
679 title_savedFile_pdf = args.output_pdf |
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
680 title_savedFile_pdf2 = args.output_pdf2 |
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
681 |
19
2e9f7ea7ae93
planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/hd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a-dirty
mheinzl
parents:
18
diff
changeset
|
682 title_savedFile_csv = args.output_tabular |
2e9f7ea7ae93
planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/hd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a-dirty
mheinzl
parents:
18
diff
changeset
|
683 title_savedFile_csv2 = args.output_tabular2 |
0
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
684 |
19
2e9f7ea7ae93
planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/hd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a-dirty
mheinzl
parents:
18
diff
changeset
|
685 sep = "\t" |
0
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
686 onlyDuplicates = args.only_DCS |
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
687 minFS = args.minFS |
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
688 maxFS = args.maxFS |
14
883e6381ba29
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 38f5c032262361131c645812dd3dc639be6a5f4e
mheinzl
parents:
13
diff
changeset
|
689 nr_above_bars = args.nr_above_bars |
0
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
690 |
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
691 subset = args.subset_tag |
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
692 nproc = args.nproc |
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
693 |
19
2e9f7ea7ae93
planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/hd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a-dirty
mheinzl
parents:
18
diff
changeset
|
694 # input checks |
0
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
695 if index_size < 0: |
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
696 print("index_size is a negative integer.") |
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
697 exit(2) |
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
698 |
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
699 if nproc <= 0: |
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
700 print("nproc is smaller or equal zero") |
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
701 exit(3) |
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
702 |
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
703 if subset < 0: |
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
704 print("subset_tag is smaller or equal zero.") |
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
705 exit(5) |
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
706 |
19
2e9f7ea7ae93
planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/hd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a-dirty
mheinzl
parents:
18
diff
changeset
|
707 # PLOT |
0
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
708 plt.rcParams['axes.facecolor'] = "E0E0E0" # grey background color |
10
69aa17354a6e
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit f01678e9bfead9f9e1b54dd9ecf7141f057dd9de
mheinzl
parents:
9
diff
changeset
|
709 plt.rcParams['xtick.labelsize'] = 14 |
69aa17354a6e
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit f01678e9bfead9f9e1b54dd9ecf7141f057dd9de
mheinzl
parents:
9
diff
changeset
|
710 plt.rcParams['ytick.labelsize'] = 14 |
0
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
711 plt.rcParams['patch.edgecolor'] = "#000000" |
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
712 plt.rc('figure', figsize=(11.69, 8.27)) # A4 format |
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
713 |
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
714 if file2 != str(None): |
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
715 files = [file1, file2] |
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
716 name1 = name1.split(".tabular")[0] |
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
717 name2 = name2.split(".tabular")[0] |
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
718 names = [name1, name2] |
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
719 pdf_files = [title_savedFile_pdf, title_savedFile_pdf2] |
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
720 csv_files = [title_savedFile_csv, title_savedFile_csv2] |
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
721 else: |
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
722 files = [file1] |
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
723 name1 = name1.split(".tabular")[0] |
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
724 names = [name1] |
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
725 pdf_files = [title_savedFile_pdf] |
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
726 csv_files = [title_savedFile_csv] |
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
727 |
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
728 for f, name_file, pdf_f, csv_f in zip(files, names, pdf_files, csv_files): |
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
729 with open(csv_f, "w") as output_file, PdfPages(pdf_f) as pdf: |
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
730 print("dataset: ", name_file) |
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
731 integers, data_array = readFileReferenceFree(f) |
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
732 data_array = numpy.array(data_array) |
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
733 int_f = numpy.array(data_array[:, 0]).astype(int) |
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
734 data_array = data_array[numpy.where(int_f >= minFS)] |
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
735 integers = integers[integers >= minFS] |
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
736 |
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
737 # select family size for tags |
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
738 if maxFS > 0: |
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
739 int_f2 = numpy.array(data_array[:, 0]).astype(int) |
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
740 data_array = data_array[numpy.where(int_f2 <= maxFS)] |
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
741 integers = integers[integers <= maxFS] |
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
742 |
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
743 print("min FS", min(integers)) |
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
744 print("max FS", max(integers)) |
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
745 |
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
746 tags = data_array[:, 2] |
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
747 seq = data_array[:, 1] |
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
748 |
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
749 if onlyDuplicates is True: |
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
750 # find all unique tags and get the indices for ALL tags, but only once |
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
751 u, index_unique, c = numpy.unique(numpy.array(seq), return_counts=True, return_index=True) |
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
752 d = u[c > 1] |
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
753 |
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
754 # get family sizes, tag for duplicates |
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
755 duplTags_double = integers[numpy.in1d(seq, d)] |
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
756 duplTags = duplTags_double[0::2] # ab of DCS |
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
757 duplTagsBA = duplTags_double[1::2] # ba of DCS |
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
758 |
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
759 duplTags_tag = tags[numpy.in1d(seq, d)][0::2] # ab |
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
760 duplTags_seq = seq[numpy.in1d(seq, d)][0::2] # ab - tags |
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
761 |
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
762 data_array = numpy.column_stack((duplTags, duplTags_seq)) |
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
763 data_array = numpy.column_stack((data_array, duplTags_tag)) |
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
764 integers = numpy.array(data_array[:, 0]).astype(int) |
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
765 print("DCS in whole dataset", len(data_array)) |
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
766 |
19
2e9f7ea7ae93
planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/hd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a-dirty
mheinzl
parents:
18
diff
changeset
|
767 # HD analysis for a subset of the tag |
0
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
768 if subset > 0: |
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
769 tag1 = numpy.array([i[0:(len(i)) / 2] for i in data_array[:, 1]]) |
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
770 tag2 = numpy.array([i[len(i) / 2:len(i)] for i in data_array[:, 1]]) |
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
771 |
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
772 flanking_region_float = float((len(tag1[0]) - subset)) / 2 |
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
773 flanking_region = int(flanking_region_float) |
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
774 if flanking_region_float % 2 == 0: |
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
775 tag1_shorten = numpy.array([i[flanking_region:len(i) - flanking_region] for i in tag1]) |
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
776 tag2_shorten = numpy.array([i[flanking_region:len(i) - flanking_region] for i in tag2]) |
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
777 else: |
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
778 flanking_region_rounded = int(round(flanking_region, 1)) |
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
779 flanking_region_rounded_end = len(tag1[0]) - subset - flanking_region_rounded |
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
780 tag1_shorten = numpy.array( |
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
781 [i[flanking_region:len(i) - flanking_region_rounded_end] for i in tag1]) |
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
782 tag2_shorten = numpy.array( |
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
783 [i[flanking_region:len(i) - flanking_region_rounded_end] for i in tag2]) |
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
784 |
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
785 data_array_tag = numpy.array([i + j for i, j in zip(tag1_shorten, tag2_shorten)]) |
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
786 data_array = numpy.column_stack((data_array[:, 0], data_array_tag, data_array[:, 2])) |
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
787 |
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
788 print("length of tag= ", len(data_array[0, 1])) |
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
789 # select sample: if no size given --> all vs. all comparison |
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
790 if index_size == 0: |
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
791 result = numpy.arange(0, len(data_array), 1) |
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
792 else: |
19
2e9f7ea7ae93
planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/hd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a-dirty
mheinzl
parents:
18
diff
changeset
|
793 result = numpy.random.choice(len(integers), size=index_size, replace=False) # array of random sequences of size=index.size |
0
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
794 |
19
2e9f7ea7ae93
planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/hd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a-dirty
mheinzl
parents:
18
diff
changeset
|
795 # with open("index_result1_{}.pkl".format(app_f), "wb") as o: |
2e9f7ea7ae93
planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/hd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a-dirty
mheinzl
parents:
18
diff
changeset
|
796 # pickle.dump(result, o, pickle.HIGHEST_PROTOCOL) |
0
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
797 |
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
798 # comparison random tags to whole dataset |
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
799 result1 = data_array[result, 1] # random tags |
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
800 result2 = data_array[:, 1] # all tags |
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
801 print("size of the whole dataset= ", len(result2)) |
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
802 print("sample size= ", len(result1)) |
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
803 |
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
804 # HD analysis of whole tag |
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
805 proc_pool = Pool(nproc) |
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
806 chunks_sample = numpy.array_split(result1, nproc) |
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
807 ham = proc_pool.map(partial(hamming, array2=result2), chunks_sample) |
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
808 proc_pool.close() |
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
809 proc_pool.join() |
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
810 ham = numpy.concatenate(ham).astype(int) |
19
2e9f7ea7ae93
planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/hd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a-dirty
mheinzl
parents:
18
diff
changeset
|
811 # with open("HD_whole dataset_{}.txt".format(app_f), "w") as output_file1: |
2e9f7ea7ae93
planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/hd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a-dirty
mheinzl
parents:
18
diff
changeset
|
812 # for h, tag in zip(ham, result1): |
2e9f7ea7ae93
planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/hd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a-dirty
mheinzl
parents:
18
diff
changeset
|
813 # output_file1.write("{}\t{}\n".format(tag, h)) |
0
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
814 |
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
815 # HD analysis for chimeric reads |
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
816 proc_pool_b = Pool(nproc) |
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
817 diff_list_a = proc_pool_b.map(partial(hamming_difference, array2=result2, mate_b=False), chunks_sample) |
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
818 diff_list_b = proc_pool_b.map(partial(hamming_difference, array2=result2, mate_b=True), chunks_sample) |
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
819 proc_pool_b.close() |
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
820 proc_pool_b.join() |
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
821 diff = numpy.concatenate((numpy.concatenate([item[0] for item in diff_list_a]), |
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
822 numpy.concatenate([item_b[0] for item_b in diff_list_b]))).astype(int) |
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
823 HDhalf1 = numpy.concatenate((numpy.concatenate([item[1] for item in diff_list_a]), |
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
824 numpy.concatenate([item_b[1] for item_b in diff_list_b]))).astype(int) |
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
825 HDhalf2 = numpy.concatenate((numpy.concatenate([item[2] for item in diff_list_a]), |
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
826 numpy.concatenate([item_b[2] for item_b in diff_list_b]))).astype(int) |
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
827 minHDs = numpy.concatenate((numpy.concatenate([item[3] for item in diff_list_a]), |
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
828 numpy.concatenate([item_b[3] for item_b in diff_list_b]))).astype(int) |
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
829 minHD_tags = numpy.concatenate((numpy.concatenate([item[4] for item in diff_list_a]), |
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
830 numpy.concatenate([item_b[4] for item_b in diff_list_b]))) |
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
831 rel_Diff = numpy.concatenate((numpy.concatenate([item[5] for item in diff_list_a]), |
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
832 numpy.concatenate([item_b[5] for item_b in diff_list_b]))) |
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
833 diff_zeros = numpy.concatenate((numpy.concatenate([item[6] for item in diff_list_a]), |
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
834 numpy.concatenate([item_b[6] for item_b in diff_list_b]))).astype(int) |
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
835 minHD_tags_zeros = numpy.concatenate((numpy.concatenate([item[7] for item in diff_list_a]), |
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
836 numpy.concatenate([item_b[7] for item_b in diff_list_b]))) |
19
2e9f7ea7ae93
planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/hd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a-dirty
mheinzl
parents:
18
diff
changeset
|
837 HDhalf1min = numpy.concatenate((numpy.concatenate([item[8] for item in diff_list_a]), numpy.concatenate([item_b[8] for item_b in diff_list_b]))).astype(int) |
14
883e6381ba29
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 38f5c032262361131c645812dd3dc639be6a5f4e
mheinzl
parents:
13
diff
changeset
|
838 HDhalf2min = numpy.concatenate((numpy.concatenate([item[9] for item in diff_list_a]), |
883e6381ba29
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 38f5c032262361131c645812dd3dc639be6a5f4e
mheinzl
parents:
13
diff
changeset
|
839 numpy.concatenate([item_b[9] for item_b in diff_list_b]))).astype(int) |
0
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
840 |
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
841 lenTags = len(data_array) |
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
842 |
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
843 quant = numpy.array(data_array[result, 0]).astype(int) # family size for sample of tags |
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
844 seq = numpy.array(data_array[result, 1]) # tags of sample |
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
845 ham = numpy.asarray(ham) # HD for sample of tags |
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
846 |
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
847 if onlyDuplicates is True: # ab and ba strands of DCSs |
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
848 quant = numpy.concatenate((quant, duplTagsBA[result])) |
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
849 seq = numpy.tile(seq, 2) |
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
850 ham = numpy.tile(ham, 2) |
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
851 |
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
852 # prepare data for different kinds of plots |
2
316fbf91dd12
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit f9d5547849dabb59a33a5e998bda4730323d62a9
mheinzl
parents:
1
diff
changeset
|
853 # distribution of FSs separated after HD |
19
2e9f7ea7ae93
planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/hd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a-dirty
mheinzl
parents:
18
diff
changeset
|
854 familySizeList1, hammingDistances, maximumXFS, minimumXFS = familySizeDistributionWithHD(quant, ham, rel=False) |
0
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
855 list1, maximumX, minimumX = hammingDistanceWithFS(quant, ham) # histogram of HDs separated after FS |
19
2e9f7ea7ae93
planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/hd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a-dirty
mheinzl
parents:
18
diff
changeset
|
856 |
2e9f7ea7ae93
planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/hd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a-dirty
mheinzl
parents:
18
diff
changeset
|
857 # get FS for all tags with min HD of analysis of chimeric reads |
0
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
858 # there are more tags than sample size in the plot, because one tag can have multiple minimas |
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
859 seqDic = dict(zip(seq, quant)) |
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
860 lst_minHD_tags = [] |
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
861 for i in minHD_tags: |
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
862 lst_minHD_tags.append(seqDic.get(i)) |
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
863 |
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
864 # histogram with absolute and relative difference between HDs of both parts of the tag |
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
865 listDifference1, maximumXDifference, minimumXDifference = hammingDistanceWithFS(lst_minHD_tags, diff) |
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
866 listRelDifference1, maximumXRelDifference, minimumXRelDifference = hammingDistanceWithFS(lst_minHD_tags, |
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
867 rel_Diff) |
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
868 |
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
869 # family size distribution separated after the difference between HDs of both parts of the tag |
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
870 familySizeList1_diff, hammingDistances_diff, maximumXFS_diff, minimumXFS_diff = familySizeDistributionWithHD( |
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
871 lst_minHD_tags, diff, diff=True, rel=False) |
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
872 familySizeList1_reldiff, hammingDistances_reldiff, maximumXFS_reldiff, minimumXFS_reldiff = familySizeDistributionWithHD( |
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
873 lst_minHD_tags, rel_Diff, diff=True, rel=True) |
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
874 |
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
875 # chimeric read analysis: tags which have HD=0 in one of the halfs |
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
876 if len(minHD_tags_zeros) != 0: |
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
877 lst_minHD_tags_zeros = [] |
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
878 for i in minHD_tags_zeros: |
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
879 lst_minHD_tags_zeros.append(seqDic.get(i)) # get family size for tags of chimeric reads |
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
880 |
19
2e9f7ea7ae93
planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/hd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a-dirty
mheinzl
parents:
18
diff
changeset
|
881 # histogram with HD of non-identical half |
2e9f7ea7ae93
planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/hd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a-dirty
mheinzl
parents:
18
diff
changeset
|
882 listDifference1_zeros, maximumXDifference_zeros, minimumXDifference_zeros = hammingDistanceWithFS(lst_minHD_tags_zeros, diff_zeros) |
2e9f7ea7ae93
planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/hd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a-dirty
mheinzl
parents:
18
diff
changeset
|
883 # family size distribution of non-identical half |
2e9f7ea7ae93
planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/hd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a-dirty
mheinzl
parents:
18
diff
changeset
|
884 familySizeList1_diff_zeros, hammingDistances_diff_zeros, maximumXFS_diff_zeros, minimumXFS_diff_zeros = familySizeDistributionWithHD(lst_minHD_tags_zeros, diff_zeros, diff=False, rel=False) |
0
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
885 |
19
2e9f7ea7ae93
planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/hd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a-dirty
mheinzl
parents:
18
diff
changeset
|
886 # plot Hamming Distance with Family size distribution |
2e9f7ea7ae93
planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/hd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a-dirty
mheinzl
parents:
18
diff
changeset
|
887 plotHDwithFSD(list1=list1, maximumX=maximumX, minimumX=minimumX, pdf=pdf, subtitle="Hamming distance separated by family size", title_file1=name_file, lenTags=lenTags, xlabel="HD", nr_above_bars=nr_above_bars) |
2e9f7ea7ae93
planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/hd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a-dirty
mheinzl
parents:
18
diff
changeset
|
888 |
2e9f7ea7ae93
planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/hd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a-dirty
mheinzl
parents:
18
diff
changeset
|
889 # Plot FSD with separation after |
0
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
890 plotFSDwithHD2(familySizeList1, maximumXFS, minimumXFS, |
11
7adc48c8a03d
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 8d9bdadb5e154dadc455720c99700afbd9aafae9
mheinzl
parents:
10
diff
changeset
|
891 originalCounts=quant, subtitle="Family size distribution separated by Hamming distance", |
19
2e9f7ea7ae93
planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/hd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a-dirty
mheinzl
parents:
18
diff
changeset
|
892 pdf=pdf, relative=False, title_file1=name_file, diff=False) |
0
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
893 |
19
2e9f7ea7ae93
planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/hd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a-dirty
mheinzl
parents:
18
diff
changeset
|
894 # Plot HD within tags |
2e9f7ea7ae93
planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/hd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a-dirty
mheinzl
parents:
18
diff
changeset
|
895 plotHDwithinSeq_Sum2(HDhalf1, HDhalf1min, HDhalf2, HDhalf2min, minHDs, pdf=pdf, lenTags=lenTags, title_file1=name_file) |
2e9f7ea7ae93
planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/hd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a-dirty
mheinzl
parents:
18
diff
changeset
|
896 |
2e9f7ea7ae93
planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/hd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a-dirty
mheinzl
parents:
18
diff
changeset
|
897 # Plot difference between HD's separated after FSD |
0
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
898 plotHDwithFSD(listDifference1, maximumXDifference, minimumXDifference, pdf=pdf, |
2
316fbf91dd12
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit f9d5547849dabb59a33a5e998bda4730323d62a9
mheinzl
parents:
1
diff
changeset
|
899 subtitle="Delta Hamming distance within tags", |
0
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
900 title_file1=name_file, lenTags=lenTags, |
14
883e6381ba29
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 38f5c032262361131c645812dd3dc639be6a5f4e
mheinzl
parents:
13
diff
changeset
|
901 xlabel="absolute delta HD", relative=False, nr_above_bars=nr_above_bars) |
0
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
902 |
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
903 plotHDwithFSD(listRelDifference1, maximumXRelDifference, minimumXRelDifference, pdf=pdf, |
14
883e6381ba29
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 38f5c032262361131c645812dd3dc639be6a5f4e
mheinzl
parents:
13
diff
changeset
|
904 subtitle="Chimera Analysis: relative delta Hamming distances", |
0
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
905 title_file1=name_file, lenTags=lenTags, |
14
883e6381ba29
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 38f5c032262361131c645812dd3dc639be6a5f4e
mheinzl
parents:
13
diff
changeset
|
906 xlabel="relative delta HD", relative=True, nr_above_bars=nr_above_bars) |
0
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
907 |
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
908 # plots for chimeric reads |
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
909 if len(minHD_tags_zeros) != 0: |
19
2e9f7ea7ae93
planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/hd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a-dirty
mheinzl
parents:
18
diff
changeset
|
910 # HD |
0
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
911 plotHDwithFSD(listDifference1_zeros, maximumXDifference_zeros, minimumXDifference_zeros, pdf=pdf, |
2
316fbf91dd12
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit f9d5547849dabb59a33a5e998bda4730323d62a9
mheinzl
parents:
1
diff
changeset
|
912 subtitle="Hamming distance of the non-identical half of chimeras", |
19
2e9f7ea7ae93
planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/hd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a-dirty
mheinzl
parents:
18
diff
changeset
|
913 title_file1=name_file, lenTags=lenTags, xlabel="HD", relative=False, nr_above_bars=nr_above_bars) |
0
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
914 |
19
2e9f7ea7ae93
planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/hd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a-dirty
mheinzl
parents:
18
diff
changeset
|
915 # print all data to a CSV file |
2e9f7ea7ae93
planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/hd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a-dirty
mheinzl
parents:
18
diff
changeset
|
916 # HD |
0
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
917 summary, sumCol = createTableHD(list1, "HD=") |
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
918 overallSum = sum(sumCol) # sum of columns in table |
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
919 |
19
2e9f7ea7ae93
planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/hd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a-dirty
mheinzl
parents:
18
diff
changeset
|
920 # FSD |
0
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
921 summary5, sumCol5 = createTableFSD2(familySizeList1, diff=False) |
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
922 overallSum5 = sum(sumCol5) |
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
923 |
19
2e9f7ea7ae93
planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/hd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a-dirty
mheinzl
parents:
18
diff
changeset
|
924 # HD of both parts of the tag |
2e9f7ea7ae93
planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/hd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a-dirty
mheinzl
parents:
18
diff
changeset
|
925 summary9, sumCol9 = createTableHDwithTags([HDhalf1, HDhalf1min, HDhalf2, HDhalf2min, numpy.array(minHDs)]) |
0
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
926 overallSum9 = sum(sumCol9) |
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
927 |
19
2e9f7ea7ae93
planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/hd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a-dirty
mheinzl
parents:
18
diff
changeset
|
928 # HD |
0
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
929 # absolute difference |
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
930 summary11, sumCol11 = createTableHD(listDifference1, "diff=") |
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
931 overallSum11 = sum(sumCol11) |
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
932 # relative difference and all tags |
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
933 summary13, sumCol13 = createTableHD(listRelDifference1, "diff=") |
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
934 overallSum13 = sum(sumCol13) |
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
935 |
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
936 # chimeric reads |
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
937 if len(minHD_tags_zeros) != 0: |
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
938 # absolute difference and tags where at least one half has HD=0 |
18
a8581bf627fd
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit b09f6822cb5acf314c5034323501d6300fda25cc
mheinzl
parents:
17
diff
changeset
|
939 summary15, sumCol15 = createTableHD(listDifference1_zeros, "HD=") |
0
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
940 overallSum15 = sum(sumCol15) |
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
941 |
2
316fbf91dd12
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit f9d5547849dabb59a33a5e998bda4730323d62a9
mheinzl
parents:
1
diff
changeset
|
942 output_file.write("{}\n".format(name_file)) |
0
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
943 output_file.write("number of tags per file{}{:,} (from {:,}) against {:,}\n\n".format(sep, len( |
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
944 numpy.concatenate(list1)), lenTags, lenTags)) |
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
945 |
19
2e9f7ea7ae93
planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/hd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a-dirty
mheinzl
parents:
18
diff
changeset
|
946 # HD |
0
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
947 createFileHD(summary, sumCol, overallSum, output_file, |
2
316fbf91dd12
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit f9d5547849dabb59a33a5e998bda4730323d62a9
mheinzl
parents:
1
diff
changeset
|
948 "Hamming distance separated by family size", sep) |
19
2e9f7ea7ae93
planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/hd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a-dirty
mheinzl
parents:
18
diff
changeset
|
949 # FSD |
0
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
950 createFileFSD2(summary5, sumCol5, overallSum5, output_file, |
2
316fbf91dd12
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit f9d5547849dabb59a33a5e998bda4730323d62a9
mheinzl
parents:
1
diff
changeset
|
951 "Family size distribution separated by Hamming distance", sep, |
0
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
952 diff=False) |
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
953 |
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
954 count = numpy.bincount(quant) |
19
2e9f7ea7ae93
planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/hd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a-dirty
mheinzl
parents:
18
diff
changeset
|
955 # output_file.write("{}{}\n".format(sep, name_file)) |
18
a8581bf627fd
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit b09f6822cb5acf314c5034323501d6300fda25cc
mheinzl
parents:
17
diff
changeset
|
956 output_file.write("\n") |
0
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
957 output_file.write("max. family size:{}{}\n".format(sep, max(quant))) |
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
958 output_file.write("absolute frequency:{}{}\n".format(sep, count[len(count) - 1])) |
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
959 output_file.write( |
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
960 "relative frequency:{}{}\n\n".format(sep, float(count[len(count) - 1]) / sum(count))) |
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
961 |
19
2e9f7ea7ae93
planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/hd commit dfaab79252a858e8df16bbea3607ebf1b6962e5a-dirty
mheinzl
parents:
18
diff
changeset
|
962 # HD within tags |
0
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
963 output_file.write( |
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
964 "The hamming distances were calculated by comparing each half of all tags against the tag(s) with the minimum Hamming distance per half.\n" |
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
965 "It is possible that one tag can have the minimum HD from multiple tags, so the sample size in this calculation differs from the sample size entered by the user.\n") |
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
966 output_file.write( |
2
316fbf91dd12
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit f9d5547849dabb59a33a5e998bda4730323d62a9
mheinzl
parents:
1
diff
changeset
|
967 "actual number of tags with min HD = {:,} (sample size by user = {:,})\n".format( |
0
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
968 len(numpy.concatenate(listDifference1)), len(numpy.concatenate(list1)))) |
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
969 output_file.write("length of one part of the tag = {}\n\n".format(len(data_array[0, 1]) / 2)) |
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
970 |
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
971 createFileHDwithinTag(summary9, sumCol9, overallSum9, output_file, |
2
316fbf91dd12
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit f9d5547849dabb59a33a5e998bda4730323d62a9
mheinzl
parents:
1
diff
changeset
|
972 "Hamming distance of each half in the tag", sep) |
0
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
973 createFileHD(summary11, sumCol11, overallSum11, output_file, |
2
316fbf91dd12
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit f9d5547849dabb59a33a5e998bda4730323d62a9
mheinzl
parents:
1
diff
changeset
|
974 "Absolute delta Hamming distances within the tag", sep) |
0
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
975 createFileHD(summary13, sumCol13, overallSum13, output_file, |
14
883e6381ba29
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 38f5c032262361131c645812dd3dc639be6a5f4e
mheinzl
parents:
13
diff
changeset
|
976 "Chimera analysis: relative delta Hamming distances", sep) |
0
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
977 |
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
978 if len(minHD_tags_zeros) != 0: |
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
979 output_file.write( |
14
883e6381ba29
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 38f5c032262361131c645812dd3dc639be6a5f4e
mheinzl
parents:
13
diff
changeset
|
980 "Chimeras:\nAll tags were filtered: only those tags where at least one half is identical with the half of the min. tag are kept.\nSo the hamming distance of the non-identical half is compared.\n") |
0
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
981 createFileHD(summary15, sumCol15, overallSum15, output_file, |
2
316fbf91dd12
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit f9d5547849dabb59a33a5e998bda4730323d62a9
mheinzl
parents:
1
diff
changeset
|
982 "Hamming distances of non-zero half", sep) |
0
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
983 output_file.write("\n") |
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
984 |
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
985 |
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
986 if __name__ == '__main__': |
239c4448a163
planemo upload for repository https://github.com/monikaheinzl/galaxyProject/tree/master/tools/hd commit 6055f8c5c052f528ff85fb5e0d43b4500830637a
mheinzl
parents:
diff
changeset
|
987 sys.exit(Hamming_Distance_Analysis(sys.argv)) |