Mercurial > repos > portiahollyoak > temp
comparison temp_absences.xml @ 21:9672fe07a232 draft default tip
planemo upload for repository https://github.com/portiahollyoak/Tools commit 0fea84d05f8976b8360a8b4943ecb01b87e3ade0-dirty
author | mvdbeek |
---|---|
date | Mon, 05 Dec 2016 09:58:47 -0500 |
parents | |
children |
comparison
equal
deleted
inserted
replaced
20:6e02b9179a24 | 21:9672fe07a232 |
---|---|
1 <tool id ="TEMP_absences" name="TEMP Excision" version="0.3.0"> | |
2 <description>finds TEs that have excised relative to the reference</description> | |
3 <requirements> | |
4 <requirement type="package" version="1.6.924=pl5.22.0_0">perl-bioperl</requirement> | |
5 <requirement type="package" version="0.7.13">bwa</requirement> | |
6 <requirement type="package" version="2.25.0">bedtools</requirement> | |
7 <requirement type="package" version="324">ucsc-twobittofa</requirement> | |
8 <requirement type="package" version="1.3.1">samtools</requirement> | |
9 </requirements> | |
10 <stdio> | |
11 <exit_code range="1:" /> | |
12 </stdio> | |
13 <command><![CDATA[ | |
14 ln -f -s "$alignment.metadata.bam_index" alignment.sorted.bam.bai && | |
15 ln -f -s "$alignment" alignment.sorted.bam && | |
16 bash $__tool_directory__/scripts/TEMP_Absence.sh | |
17 -x "$minimum_score_difference" | |
18 -i alignment.sorted.bam | |
19 -s $__tool_directory__/scripts | |
20 -r "$te_locations" | |
21 -t "$reference2bit" | |
22 -f "$median_insertsize" | |
23 -c \${GALAXY_SLOTS:-2} && | |
24 mv alignment.absence.refined.bp.summary $absence_summary | |
25 ]]></command> | |
26 <inputs> | |
27 <param format="bam" name="alignment" type="data" label="Alignment bam file"/> | |
28 <param format="twobit" name="reference2bit" type="data" label="Reference twobit file"/> | |
29 <param format="bed" name="te_locations" type="data" label="TE Annotations bed file"/> | |
30 <param name="median_insertsize" value="" type="integer" label="Median Insert Length"/> | |
31 <param name="minimum_score_difference" type="integer" min="10" max="37" value="30" label="Minimum difference between mapping scores"/> | |
32 </inputs> | |
33 <outputs> | |
34 <data format="bed" name="absence_summary" label="${alignment.element_identifier} Absences" /> | |
35 </outputs> | |
36 <tests> | |
37 <test> | |
38 <param name="alignment" value="test_chromosome.sorted.bam" ftype="bam"/> | |
39 <param name="reference2bit" value="dm3_chr2L.2bit" ftype="twobit"/> | |
40 <param name="te_locations" value="test_TE_annotation.bed" ftype="bed"/> | |
41 <param name="median_insertsize" value="500" ftype="integer"/> | |
42 <output name="absence_summary" file="test_absence_out.bed" ftype="bed"/> | |
43 </test> | |
44 </tests> | |
45 <help> <![CDATA[ | |
46 | |
47 | |
48 TEMP | |
49 ------------- | |
50 TEMP is a software package for detecting transposable elements (TEs) insertions and absences from pooled high-throughput sequencing data | |
51 | |
52 Current version v1.04 | |
53 | |
54 Author: Jiali Zhuang (jiali.zhuang@umassmed.edu) and Jie Wang (jie.wangj@umassmed.edu) Weng Lab, University of Massachusetts Medical School, Worcester, MA, USA | |
55 | |
56 *Input files/variables* | |
57 ------------------------- | |
58 * Alignment file in BAM format | |
59 * Reference genome used in aligning, in fasta or twobit format. | |
60 * Transposable Elements' Consensus Sequences in fasta format. | |
61 * Annotations of TEs in reference genome in bed format. | |
62 * TE Identifiers and Families (optional) - A file containing in the first column the TE names/identifiers from the consensus sequences file, and in the second column, their respective TE family names as in the TE annotations file. When supplied, if a detected insertion overlaps with an annotated TE of the same family, the detected insertion will be excluded from the results. | |
63 * Median Insert Length | |
64 * Number of Mismatches allowed (default 3) | |
65 * Minimum difference between mapping scores. The minimum difference in scores between the optimal and suboptimal alignments to consider a read uniquely mapped. | |
66 | |
67 *Output files* | |
68 ----------------- | |
69 * **In the Insertions output file there are 14 columns:** | |
70 * Column 1: The chromosome where the detected insertion happens. | |
71 * Column 2: The coordinate of the start position of the detected insertion. | |
72 * Column 3: The coordinate of the end position of the detected insertion. | |
73 * Column 4: The TE family that the detected insertion belongs to. | |
74 * Column 5: The direction of the insertion. “Plus” means that the TE is integrated with the plus strand of the genome while “minus” means the TE is integrated with the minus strand. | |
75 * Column 6: The class of the insertion. “1p1” means that the detected insertion is supported by reads at both sides. “2p” means the detected insertion is supported by more than 1 read at only 1 side. “Singleton” means the detected insertion is supported by only 1 read at 1 side. | |
76 * Column 7: The total number of read pairs that support the detected insertion. | |
77 * Column 8: The estimated population frequency of the detected insertion. | |
78 * Columns 9 & 10: The coordinate of a junction and the number of the reads supporting it. If the junction is not found column 9 will be the arithmetic mean of the start and end coordinates and column 10 will have the value 0. | |
79 * Columns 11 & 12: Same as Columns 9 & 10 except for the junction on the other strand. | |
80 * Column 13: The number of reads supporting the detected insertion at the 5’ end of the TE (not including junction spanning reads). | |
81 * Column 13: The number of reads supporting the detected insertion at the 3’ end of the TE (not including junction spanning reads). | |
82 | |
83 | |
84 ----- | |
85 | |
86 | |
87 * **In the Absences output file there are 14 columns:** | |
88 * Column 1: The chromosome where the detected absence happens. | |
89 * Column 2: The coordinate of the start position of the detected absence. | |
90 * Column 3: The coordinate of the end position of the detected absence. | |
91 * Column 4: The TE family that the detected insertion belongs to. | |
92 * Column 5: Junctions at 5’ of the excised TE. The two numbers are the coordinates of the junctions on the two strands. | |
93 * Column 6: Junctions at 3’ of the excised TE. The two numbers are the coordinates of the junctions on the two strands. | |
94 * Column 7: The number of reads supporting the absence. | |
95 * Column 8: The number of reads supporting the reference (no absence). | |
96 * Column 9: Estimated population frequency of the detected absence event. | |
97 | |
98 | |
99 ]]> </help> | |
100 <citations> | |
101 <citation type="doi">10.1093/nar/gku323</citation> | |
102 </citations> | |
103 </tool> |