Mercurial > repos > johnheap > vapper

comparison Tryp_G.py @ 0:36cb22bd911d draft

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
planemo upload for repository https://github.com/johnheap/VAPPER-Galaxy
author johnheap
date Wed, 04 Jul 2018 16:39:13 -0400
parents
children 4432e4183ebd
comparison
equal deleted inserted replaced
-1:000000000000 0:36cb22bd911d
1 """
2 * Copyright 2018 University of Liverpool
3 * Author: John Heap, Computational Biology Facility, UoL
4 * Based on original scripts of Sara Silva Pereira, Institute of Infection and Global Health, UoL
5 *
6 * Licensed under the Apache License, Version 2.0 (the "License");
7 * you may not use this file except in compliance with the License.
8 * You may obtain a copy of the License at
9 *
10 * http://www.apache.org/licenses/LICENSE-2.0
11 *
12 * Unless required by applicable law or agreed to in writing, software
13 * distributed under the License is distributed on an "AS IS" BASIS,
14 * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
15 * See the License for the specific language governing permissions and
16 * limitations under the License.
17 *
18 """
19
20 import subprocess
21 import re
22 import os
23 import sys
24 import shutil
25 import pandas as pd
26 import numpy as np
27 import matplotlib as mpl
28 mpl.use('Agg')
29 import matplotlib.pyplot as plt
30 from matplotlib.mlab import PCA
31 import seaborn as sns
32
33 # some globals for convenience
34
35 pList = ['P1', 'P2', 'P3', 'P4', 'P5', 'P6', 'P7', 'P8', 'P9', 'P10', 'P11', 'P12', 'P13', 'P14', 'P15']
36
37 quietString = "" #" >>"+os.path.dirname(os.path.realpath(__file__))+"/log/Vap_log.txt 2>&1"
38
39 def assembleWithVelvet(name, kmers, inslen, covcut, fastq1name,fastq2name):
40 #argString = "velveth " + name + "_k65 65 -shortPaired -fastq " + name + "_R1.fastq " + name + "_R2.fastq"
41 argString = "velveth " + name + "_k"+ kmers+" "+ kmers + " -shortPaired -fastq " + fastq1name+" "+fastq2name+quietString
42 print(argString)
43 returncode = subprocess.call(argString, shell=True)
44 if returncode != 0:
45 return "Error in velveth"
46 argString = "velvetg " + name + "_k"+kmers+" -exp_cov auto -ins_length "+inslen+" -cov_cutoff "+covcut+" -clean yes -ins_length_sd 50 -min_pair_count 20"+quietString
47 #argString = "velvetg " + name + "_k65 -exp_cov auto -ins_length 400 -cov_cutoff 5 -clean yes -ins_length_sd 50 -min_pair_count 20"+quietString
48 print(argString)
49 returncode = subprocess.call(argString, shell = True)
50 if returncode != 0:
51 return "Error in velvetg"
52 shutil.copyfile(name + "_k"+kmers+"//contigs.fa",name + ".fa") # my $namechange = "mv ".$input."_k65/contigs.fa ".$input.".fa";
53 return "ok"
54
55 def contigTranslation(name):
56 argString = "transeq " + name + ".fa " + name + "_6frame.fas -frame=6 " #+quietString
57 print(argString)
58 returncode = subprocess.call(argString, shell=True)
59 #subprocess.call('ls -l *.fa', shell = True)
60 #sys.exit(1)
61 #if returncode != 0:
62 # return "Error in Transeq"
63 #return 'ok'
64
65
66 def HMMerMotifSearch(name):
67 motifs = ['1', '2a', '2b', '3', '4a', '4b', '4c', '5', '6', '7', '8a', '8b', '9a', '9b',
68 '9c', '10a', '10b', '11a', '11b', '12', '13a', '13b', '13c', '13d', '14', '15a', '15b', '15c']
69 lineCounts = []
70 compoundList = []
71 dir_path = os.path.dirname(os.path.realpath(__file__))
72 phylopath = dir_path + "/data/Motifs/Phylotype"
73 for m in motifs:
74 argString = "hmmsearch " + phylopath + m + ".hmm " + name + "_6frame.fas > Phy" + m + ".out" # +quietString
75 # argString = "hmmsearch "+phylopath + m + ".hmm " + dir_path+"/data/Test_6frame.fas > Phy" + m + ".out"
76 #print(argString)
77 subprocess.call(argString, shell=True)
78
79 hmmResult = open("Phy" + m + ".out", 'r')
80 tempout = open(dir_path + "/data/" + "Phy" + m + ".txt", 'w')
81 #regex = r"NODE_[0-9]{1,7}_length_[0-9]{1,7}_cov_[0-9]{1,10}.[0-9]{1,7}_[0-9]{1,2}"
82 n = 0
83 outList = []
84 for l in range(0,14):
85 hmmResult.readline() #hacky? miss out the first 14 lines. data we want starts on line 15
86
87
88 for line in hmmResult:
89 if re.search(r"inclusion", line):
90 #print("inclusion threshold reached")
91 break
92 if len(line) <= 1:
93 #print("end of data")
94 break
95 m = line[60:-1]
96 #print(m)
97 #tempout.write(m.group() + "\n")
98 outList.append("" + m + "\n")
99 n += 1
100 compoundList.append(outList)
101 lineCounts.append(n)
102 hmmResult.close()
103
104
105 print(lineCounts)
106 motifGroups = [['1'], ['2a', '2b'], ['3'], ['4a', '4b', '4c'], ['5'], ['6'], ['7'], ['8a', '8b'], ['9a', '9b',
107 '9c'],
108 ['10a', '10b'], ['11a', '11b'], ['12'], ['13a', '13b', '13c', '13d'], ['14'], ['15a', '15b', '15c']]
109 concatGroups = [1, 2, 1, 3, 1, 1, 1, 2, 3, 2, 2, 1, 4, 1, 3]
110 countList = []
111 countIndex = 0
112 totalCount = 0
113
114 for c in concatGroups:
115 a = []
116 for n in range(0, c):
117 a = a + compoundList.pop(0)
118 t = set(a)
119 countList.append(len(t))
120 totalCount += len(t)
121 countList.append(totalCount)
122 #print(countList)
123 #print("--------")
124 return countList
125
126 """
127 def HMMerMotifSearch(name):
128 motifs = ['1', '2a', '2b', '3', '4a', '4b', '4c', '5', '6', '7', '8a', '8b', '9a', '9b',
129 '9c', '10a', '10b', '11a', '11b', '12', '13a', '13b', '13c', '13d', '14', '15a', '15b', '15c']
130 lineCounts = []
131 compoundList = []
132 dir_path = os.path.dirname(os.path.realpath(__file__))
133 phylopath = dir_path+"/data/Motifs/Phylotype"
134 for m in motifs:
135 argString = "hmmsearch "+phylopath + m + ".hmm " + name + "_6frame.fas > Phy" + m + ".out" #+quietString
136 #argString = "hmmsearch "+phylopath + m + ".hmm " + dir_path+"/data/Test_6frame.fas > Phy" + m + ".out"
137 print(argString)
138 subprocess.call(argString, shell=True)
139
140 hmmResult = open("Phy" + m + ".out", 'r')
141 tempout = open(dir_path+"/data/"+"Phy" + m + ".txt", 'w')
142 regex = r"NODE_[0-9]{1,7}_length_[0-9]{1,7}_cov_[0-9]{1,10}.[0-9]{1,7}_[0-9]{1,2}"
143 n = 0
144 outList = []
145 for line in hmmResult:
146 m = re.search(regex, line)
147 if m:
148 tempout.write(m.group() + "\n")
149 outList.append(""+m.group()+"\n")
150 n += 1
151 if re.search(r"inclusion", line):
152 print("inclusion threshold reached")
153 break
154 compoundList.append(outList)
155 lineCounts.append(n)
156 hmmResult.close()
157 #tempout.close()
158 print(lineCounts)
159 motifGroups = [['1'], ['2a', '2b'], ['3'], ['4a', '4b', '4c'], ['5'], ['6'], ['7'], ['8a', '8b'], ['9a', '9b',
160 '9c'],
161 ['10a', '10b'], ['11a', '11b'], ['12'], ['13a', '13b', '13c', '13d'], ['14'], ['15a', '15b', '15c']]
162 concatGroups = [1, 2, 1, 3, 1, 1, 1, 2, 3, 2, 2, 1, 4, 1, 3]
163 countList = []
164 countIndex = 0
165 totalCount = 0
166
167 for c in concatGroups:
168 a = []
169 for n in range(0, c):
170 a = a + compoundList.pop(0)
171 t = set(a)
172 countList.append(len(t))
173 totalCount += len(t)
174 countList.append(totalCount)
175 print(countList)
176 print("--------")
177 return countList
178 """
179
180
181
182 def relativeFrequencyTable(countList, name, htmlresource):
183 relFreqList = []
184 c = float(countList[15])
185 if c == 0:
186 return [0,0,0,0,0, 0,0,0,0,0, 0,0,0,0,0]
187 for i in range(0, 15):
188 relFreqList.append(countList[i] / c)
189
190 data = {'Phylotype': pList, 'Relative Frequency': relFreqList}
191 relFreq_df = pd.DataFrame(data)
192 j_fname = htmlresource+"/" + name + "_relative_frequency.csv"
193 relFreq_df.to_csv(j_fname)
194 return relFreqList # 0-14 = p1-p15 counts [15] = total counts
195
196
197
198
199 def getDeviationFromMean(frequencyList, name, htmlresource):
200 devList = []
201 dir_path = os.path.dirname(os.path.realpath(__file__))
202 j_fname = dir_path + "/data/congodata.csv"
203 #j_fname = r"data/congodata.csv"
204 congo_df = pd.read_csv(j_fname) # we get the means from congo_df
205 for p in range(0, 15):
206 m = congo_df[pList[p]].mean()
207 dev = -(m - frequencyList[p])
208 devList.append(dev)
209
210 data = {'Phylotype': pList, 'Deviation from Mean': devList}
211 dev_df = pd.DataFrame(data)
212 j_fname = htmlresource+"/" + name + "_deviation_from_mean.csv"
213 dev_df.to_csv(j_fname)
214 return devList
215
216
217 def relativeFrequencyHeatMap(name, freqList, pdf, htmlresource):
218 localFreqList = freqList[:]
219 localFreqList.insert(0, name)
220 dir_path = os.path.dirname(os.path.realpath(__file__))
221 j_fname = dir_path+"/data/congodata.csv"
222 #print(dir_path)
223 congo_df = pd.read_csv(j_fname)
224 congo_df.drop('Colour', axis=1, inplace=True)
225 congo_df.loc[congo_df.index.max() + 1] = localFreqList
226 congo_df.set_index('Strain', inplace=True)
227
228 cg = sns.clustermap(congo_df, method='ward', cmap = "RdBu_r", col_cluster=False, yticklabels = congo_df.index.values)
229 plt.setp(cg.ax_heatmap.yaxis.get_ticklabels(), rotation=0, fontsize=8) # get y labels printed horizontally
230 ax=cg.ax_heatmap
231 title = "Variant Antigen Profiles of $\itTrypanosoma$ $\itcongolense$ estimated as the phylotype proportion across the\nsample cohort. "
232 title += "Dendrogram reflects the relationships amongst the VSG repertoires of each strain. "
233 title += "Strains\nwere isolated from multiple African countries as described in Silva Pereira et al. (2018)."
234 title += "\nData was produced with the 'Variant Antigen Profiler' (Silva Pereira and Jackson, 2018)."
235
236 #title = "Variant Antigen Profiles of Trypanosoma congolense estimated as the phylotype proportion across the sample cohort. Dendrogram reflects the relationships amongst the VSG repertoires of each strain. Strains were isolated from multiple African countries as described in Silva Pereira et al. (2018). Data was produced with the 'Variant Antigen Profiler' (Silva Pereira and Jackson, 2018)."
237 #ax.set_title(title, ha = "center", va = "bottom",wrap = "True")
238 #title = "Where is this!"
239 ax.text(-0.15,-0.05, title,va = "top",wrap = "True", transform = ax.transAxes )
240
241
242
243
244 # cg.dendrogram_col.linkage # linkage matrix for columns
245 # cg.dendrogram_row.linkage # linkage matrix for rows
246 #plt.savefig(r"results/" + name + "_heatmap.png")
247 plt.savefig(htmlresource+"/heatmap.png",bbox_inches='tight')
248 if pdf == 'PDF_Yes':
249 plt.savefig(htmlresource+"/heatmap.pdf", bbox_inches='tight')
250 #shutil.copyfile("heatmap.pdf",heatmapfn) #
251 #plt.show()
252
253 def deviationFromMeanHeatMap(name,devList, pdf, htmlresource):
254 localDevList = devList[:]
255 localDevList.insert(0, name)
256 dir_path = os.path.dirname(os.path.realpath(__file__))
257 j_fname = dir_path+ "/data/congodata_deviationfromthemean.csv"
258 #j_fname = r"data/congodata_deviationfromthemean.csv"
259 congo_df = pd.read_csv(j_fname)
260 congo_df.drop('Colour', axis=1, inplace=True)
261 congo_df.loc[congo_df.index.max() + 1] = localDevList
262 congo_df.set_index('Strain', inplace=True)
263 cg = sns.clustermap(congo_df, method='ward',cmap = "RdBu_r", col_cluster=False, yticklabels = congo_df.index.values)
264 plt.setp(cg.ax_heatmap.yaxis.get_majorticklabels(), rotation=0, fontsize=8) # get y labels printed horizontally
265 ax = cg.ax_heatmap
266 title = "Variant Antigen Profiles of $\itTrypanosoma$ $\itcongolense$ expressed as the deviation from the mean phylotypes "
267 title +="\nproportions of the sample cohort. Dendrogram reflects the relationships amongst the VSG repertoires of "
268 title +="each \nstrain. Strains were isolated from multiple African countries as described in Silva Pereira et al. (2018)."
269 title +="\nData was produced with the 'Variant Antigen Profiler' (Silva Pereira and Jackson, 2018)."
270 #ax.set_title(title,ha = "center", va = "bottom",wrap = "True")
271 ax.text(-0.2, -0.05, title, va="top", transform=ax.transAxes, wrap="True")
272 plt.savefig(htmlresource+"/dheatmap.png",bbox_inches='tight')
273 if pdf == 'PDF_Yes':
274 plt.savefig(htmlresource+"/dheatmap.pdf", bbox_inches='tight')
275 #shutil.copyfile("dheatmap.pdf",dhmapfn)
276 #plt.show()
277
278
279 def plotPCA(name, freqList, pdf, htmlresource):
280 localFreqList = freqList[:]
281 localFreqList.insert(0, name)
282 localFreqList.append(name)
283 dir_path = os.path.dirname(os.path.realpath(__file__))
284 j_fname = dir_path + "/data/congodata.csv"
285 #j_fname = r"data/congodata.csv"
286 congo_df = pd.read_csv(j_fname)
287 congo_df.loc[congo_df.index.max() + 1] = localFreqList
288 # print(congo_df.tail(2))
289 myColours = congo_df['Colour']
290 myCountries = congo_df.drop_duplicates('Colour')['Colour'].tolist()
291 # print(myCountries)
292 congo_df.drop('Colour', axis=1, inplace=True)
293 congo_df.set_index('Strain', inplace=True)
294 dataArray = congo_df.as_matrix()
295 pcaResult = PCA(dataArray)
296 # pcaResult.center(0)
297 # can't seem to find a simple way of prooducing a decent legend.
298 # going to seperate items in to different countires.
299 compoundList = []
300 for i in myCountries:
301 compoundList.append([])
302
303 i = 0
304 for item in pcaResult.Y:
305 col = myCountries.index(myColours[i])
306 compoundList[col].append(-item[0])
307 compoundList[col].append(item[1])
308 i = i + 1
309 cols = ['r', 'g', 'b', 'c', 'm', 'y', 'grey', 'k']
310
311 fig, ax = plt.subplots(figsize=(9, 6))
312 #plt.figure(num=1,figsize=(12, 6))
313 i = 0
314 for d in myCountries:
315 a = compoundList[i]
316 b = a[::2]
317 c = a[1::2]
318 ax.scatter(b, c, color=cols[i], label=myCountries[i])
319 i = i + 1
320 leg = ax.legend( bbox_to_anchor=(1.02,1.02), loc = "upper left") #move legend out of plot
321 title = "Principal Component Analysis of the Variant Antigen Profiles of $\itTrypanosoma$ $\itcongolense$. " \
322 "The plot reflects the\nrelationships amongst the VSG repertoires of each strain. Strains are color-coded " \
323 "by location of collection according\nto key. Strains were isolated from multiple African countries as described in Silva Pereira et al. (2018)."
324 title +="\nData was produced with the 'Variant Antigen Profiler' (Silva Pereira and Jackson, 2018)."
325 #plt.title(title, ha = "center", va = "bottom",wrap = "True")
326 tx = ax.text(-0.1, -0.07, title, va="top", transform=ax.transAxes, wrap="True")
327 #fig.add_axes([0,0.05,1.05,1.05])
328 #fig.tight_layout(rect=[0, 0.03, 1, 0.95])
329 fig.subplots_adjust(bottom = 0.3)
330
331 fig.savefig(htmlresource+"/vapPCA.png", bbox_extra_artists=(leg,tx), bbox_inches='tight')
332 #fig.savefig(htmlresource+"/vapPCA.png", bbox_extra_artists=(leg,))
333 if pdf == 'PDF_Yes':
334 fig.savefig(htmlresource+"/vapPCA.pdf",bbox_extra_artists=(leg,tx), bbox_inches='tight')
335 #shutil.copyfile("vapPCA.pdf",PCAfn) # my $namechange = "mv ".$input."_k65/contigs.fa ".$input.".fa";
336 #plt.show()
337
338 def createHTML(name,htmlfn,freqList,devList):
339 #assumes imgs are heatmap.png, dheatmap.png, vapPCA.png and already in htmlresource
340 htmlString = r"<html><title>T.congolense VAP</title><body><div style='text-align:center'><h2><i>Trypanosoma congolense</i> Variant Antigen Profile</h2><h3>"
341 htmlString += name
342 htmlString += r"<br/>Genomic Analysis</h3>"
343 htmlString += "<p style = 'margin-left:23%; margin-right:23%'>Table Legend: Variant Antigen Profiles of <i>Trypanosoma congolense</i> estimated as the phylotype proportion and as the deviation from the mean across the sample cohort.<br>" \
344 "Data was produced with the 'Variant Antigen Profiler' (Silva Pereira and Jackson, 2018).</p>"
345 htmlString += r"<style> table, th, tr, td {border: 1px solid black; border-collapse: collapse;}</style>"
346
347 htmlString += r"<table style='width:50%;margin-left:25%;text-align:center'><tr><th>Phylotype</th><th>Relative Frequency</th><th>Deviation from Mean</th></tr>"
348 tabString = ""
349 # flush out table with correct values
350 for i in range(0, 15):
351 f= format(freqList[i],'.4f')
352 d= format(devList[i],'.4f')
353 tabString += "<tr><td>phy" + str(i + 1) + "</td><td>" + f + "</td><td>" + d + "</td></tr>"
354 #tabString += "<tr><td>phy" + str(i + 1) + "</td><td>" + str(freqList[i]) + "</td><td>" + str(devList[i]) + "</td></tr>"
355 htmlString += tabString + "</table><br><br><br><br><br>"
356
357 htmlString += r"<h3>The Variation Heat Map and Dendrogram</h3><p>The absolute phylotype variation in the sample compared to model dataset.</p>"
358 imgString = r"<img src = 'heatmap.png' alt='Variation Heatmap' style='max-width:100%'><br><br>"
359 htmlString += imgString
360
361 htmlString += r"<br><br><br><br><h3>The Deviation Heat Map and Dendrogram</h3><p>The phylotype variation expressed as the deviation from your sample mean compared to the model dataset</p>"
362 imgString = r"<img src = 'dheatmap.png' alt='Deviation Heatmap' style='max-width:100%'><br><br>"
363 htmlString += imgString
364
365 htmlString += r"<br><br><br><br><h3>The Variation PCA plot</h3><p>PCA analysis corresponding to absolute variation. Colour coded according to location</p>"
366 imgString = r"<img src = 'vapPCA.png' alt='PCA Analysis' style='max-width:100%'><br><br>"
367 htmlString += imgString + r"</div></body></html>"
368
369 with open(htmlfn, "w") as htmlfile:
370 htmlfile.write(htmlString)
371
372
373 def assemble(args,dict):
374 #argdict = {'name': 2, 'pdfexport': 3, 'kmers': 4, 'inslen': 5, 'covcut': 6, 'forward': 7, 'reverse': 8, 'html_file': 9,'html_resource': 10}
375 assembleWithVelvet(args[dict['name']],args[dict['kmers']], args[dict['inslen']],args[dict['covcut']], args[dict['forward']],args[dict['reverse']])
376 contigTranslation(args[dict['name']])
377 myCountList = HMMerMotifSearch(args[dict['name']])
378 myFreqList = relativeFrequencyTable(myCountList, args[dict['name']],args[dict['html_resource']]) # saves out inputname_relative_frequncy.csv
379 # myFreqList = [0.111670020120724, 0.103621730382294, 0.0784708249496982, 0.0110663983903421,
380 # 0.0543259557344064, 0.0563380281690141, 0.0734406438631791, 0.0160965794768612,
381 # 0.0110663983903421, 0.028169014084507, 0.126760563380282, 0.0583501006036217, 0.062374245472837,
382 # 0.0372233400402414, 0.17102615694165]
383
384
385 myDevList = getDeviationFromMean(myFreqList, args[dict['name']], args[dict['html_resource']]) # saves out inputname_deviation_from_mean.csv
386 relativeFrequencyHeatMap(args[dict['name']], myFreqList,args[dict['pdfexport']], args[dict['html_resource']])
387 deviationFromMeanHeatMap(args[dict['name']], myDevList,args[dict['pdfexport']], args[dict['html_resource']])
388 plotPCA(args[dict['name']], myFreqList,args[dict['pdfexport']], args[dict['html_resource']])
389 createHTML(args[dict['name']], args[dict['html_file']], myFreqList, myDevList) # assumes imgs are heatmap.png, dheatmap.png, vapPCA.png and already in htmlresource
390
391 def contigs(args,dict):
392 #argdict = {'name': 2, 'pdfexport': 3, 'contigs': 4, 'html_file': 5, 'html_resource': 6}
393
394 shutil.copyfile(args[dict['contigs']], args[dict['name']]+".fa")
395
396
397
398 contigTranslation(args[dict['name']])
399 myCountList = HMMerMotifSearch(args[dict['name']])
400 myFreqList = relativeFrequencyTable(myCountList, args[dict['name']],
401 args[dict['html_resource']]) # saves out inputname_relative_frequncy.csv
402 # myFreqList = [0.111670020120724, 0.103621730382294, 0.0784708249496982, 0.0110663983903421,
403 # 0.0543259557344064, 0.0563380281690141, 0.0734406438631791, 0.0160965794768612,
404 # 0.0110663983903421, 0.028169014084507, 0.126760563380282, 0.0583501006036217, 0.062374245472837,
405 # 0.0372233400402414, 0.17102615694165]
406
407
408 myDevList = getDeviationFromMean(myFreqList, args[dict['name']],
409 args[dict['html_resource']]) # saves out inputname_deviation_from_mean.csv
410 relativeFrequencyHeatMap(args[dict['name']], myFreqList, args[dict['pdfexport']], args[dict['html_resource']])
411 deviationFromMeanHeatMap(args[dict['name']], myDevList, args[dict['pdfexport']], args[dict['html_resource']])
412 plotPCA(args[dict['name']], myFreqList, args[dict['pdfexport']], args[dict['html_resource']])
413 createHTML(args[dict['name']], args[dict['html_file']], myFreqList,
414 myDevList) # assumes imgs are heatmap.png, dheatmap.png, vapPCA.png and already in htmlresource
415
416
417 def genomicProcess(inputname, exportpdf, forwardFN, reverseFN, htmlfile, htmlresource):
418 assembleWithVelvet(inputname,forwardFN,reverseFN)
419 contigTranslation(inputname)
420 myCountList = HMMerMotifSearch(inputname)
421 myFreqList = relativeFrequencyTable(myCountList, inputname, htmlresource) # saves out inputname_relative_frequncy.csv
422 #myFreqList = [0.111670020120724, 0.103621730382294, 0.0784708249496982, 0.0110663983903421,
423 # 0.0543259557344064, 0.0563380281690141, 0.0734406438631791, 0.0160965794768612,
424 # 0.0110663983903421, 0.028169014084507, 0.126760563380282, 0.0583501006036217, 0.062374245472837,
425 # 0.0372233400402414, 0.17102615694165]
426
427
428 myDevList = getDeviationFromMean(myFreqList, inputname,htmlresource) # saves out inputname_deviation_from_mean.csv
429
430 relativeFrequencyHeatMap(inputname, myFreqList, exportpdf, htmlresource)
431 deviationFromMeanHeatMap(inputname, myDevList, exportpdf, htmlresource)
432 plotPCA(inputname, myFreqList, exportpdf, htmlresource)
433 createHTML(inputname, htmlfile, myFreqList,myDevList) # assumes imgs are heatmap.png, dheatmap.png, vapPCA.png and already in htmlresource
434 return
435
436
437
438 if __name__ == "__main__":
439 #contigTranslation('Tcongo')
440 #contigTranslation('Test')
441 #newHMMerMotifSearch('Test')
442 #HMMerMotifSearch('Tcongo')
443 #sys.exit()
444
445
446 myFreqList = [0.111670020120724, 0.103621730382294, 0.0784708249496982, 0.0110663983903421,
447 0.0543259557344064, 0.0563380281690141, 0.0734406438631791, 0.0160965794768612,
448 0.0110663983903421, 0.028169014084507, 0.126760563380282, 0.0583501006036217, 0.062374245472837,
449 0.0372233400402414, 0.17102615694165]
450 myDevList = [0.000790026,0.0073109,-0.001151769,-0.004502933,-0.013687421,-0.016159773,0.021689891,
451 0.007863809,-0.003133585,-0.001111709,-0.01313879,0.0036997,-0.00935284,0.005640693,0.015243802]
452
453 relativeFrequencyHeatMap('test', myFreqList, "PDF_Yes","results")
454 deviationFromMeanHeatMap('test', myDevList, "PDF_Yes","results")
455 plotPCA('test',myFreqList,"PDF_Yes","results")
456
457 createHTML('test',"results/test.html", myFreqList, myDevList)
458 #contigTranslation("Test")
459 #myCountList = HMMerMotifSearch("Test")
460
461
462 sys.exit()