Mercurial > repos > iuc > nugen_nudup
comparison nugen_nudup.xml @ 0:0ad51e73587e draft
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/nugen_nudup commit 9f2d2e8d94050274a4eaae7fa1e48887fed657d4
author | iuc |
---|---|
date | Fri, 02 Dec 2016 18:03:47 -0500 |
parents | |
children | 24693e595caf |
comparison
equal
deleted
inserted
replaced
-1:000000000000 | 0:0ad51e73587e |
---|---|
1 <tool id="nugen_nudup" name="NuDUP" version="2.2_post2016104"> | |
2 <description>mark/remove PCR duplicates based on molecular tags</description> | |
3 <requirements> | |
4 <requirement type="package" version="2.2_post2016104">nudup</requirement> | |
5 </requirements> | |
6 <stdio> | |
7 <exit_code range="1:" /> | |
8 </stdio> | |
9 <version_command>nudup.py --version</version_command> | |
10 <command><![CDATA[ | |
11 ln -f -s '$input' 'input.bam' && | |
12 ln -f -s '$input.metadata.bam_index' 'input.bai' && | |
13 nudup.py $paired_end | |
14 -f '$umi_fastq' | |
15 --start $start | |
16 --length $length | |
17 'input.bam' | |
18 ]]> | |
19 </command> | |
20 <inputs> | |
21 <param type="data" name="input" label="Input SAM/BAM file" | |
22 format="sam,bam" help="Input SAM/BAM containing only unique | |
23 alignments" /> | |
24 <param type="data" name="umi_fastq" label="Fastq file containing | |
25 molecular tag sequence" format="fastq,fastqsanger" help="FASTQ | |
26 file containing the molecular tag sequence for each read name in | |
27 the corresponding SAM/BAM file" /> | |
28 <param type="boolean" argument="--paired-end" | |
29 label="Paired-end deduping" name="paired_end" | |
30 truevalue="--paired-end" falsevalue="" | |
31 checked="false" | |
32 help="use paired end deduping with template. SAM/BAM alignment | |
33 must contain paired end reads. Degenerate read pairs | |
34 (alignments for one read of pair) will be discarded." /> | |
35 <param type="integer" argument="--start" label="Tag sequence start | |
36 position from 3' end" value="6" help="position in index read where | |
37 molecular tag sequence begins. This should be a 1-based value that | |
38 counts in from the 3' END of the read." /> | |
39 <param type="integer" argument="--length" label="Tag sequence length" | |
40 value="6" help="length of molecular tag sequence" /> | |
41 </inputs> | |
42 <outputs> | |
43 <data format="bam" name="markdup" from_work_dir="prefix.sorted.markdup.bam" /> | |
44 <data format="bam" name="dedup" from_work_dir="prefix.sorted.dedup.bam" /> | |
45 <data format="txt" name="log" from_work_dir="prefix_dup_log.txt" /> | |
46 </outputs> | |
47 <tests> | |
48 <test> | |
49 <param name="input" value="nudup_test_1.bam" ftype="bam" /> | |
50 <param name="umi_fastq" value="nudup_umis.fastq" ftype="fastqsanger" /> | |
51 <param name="start" value="8" /> | |
52 <param name="length" value="8" /> | |
53 <output name="markdup" file="nudup_markdup_1.bam" ftype="bam" /> | |
54 <output name="dedup" file="nudup_dedup_1.bam" ftype="bam" /> | |
55 <output name="log" file="nudup_log_1.txt" ftype="txt" /> | |
56 </test> | |
57 </tests> | |
58 <help><![CDATA[ | |
59 Marks/removes PCR introduced duplicate molecules based on the molecular tagging | |
60 technology used in NuGEN products. | |
61 | |
62 For SINGLE END reads, duplicates are marked if they fulfill the following | |
63 criteria: a) start at the same genomic coordinate b) have the same strand | |
64 orientation c) have the same molecular tag sequence. The read with the | |
65 highest mapping quality is kept as the non-duplicate read. | |
66 | |
67 For PAIRED END reads, duplicates are marked if they fulfill the following | |
68 criteria: a) start at the same genomic coordinate b) have the same template | |
69 length c) have the same molecular tag sequence. The read pair with the highest | |
70 mapping quality is kept as the non-duplicate read. | |
71 | |
72 Author: Anand Patel | |
73 | |
74 Contact: NuGEN Technologies Inc., techserv@nugen.com | |
75 | |
76 :: | |
77 | |
78 Input: | |
79 IN.sam|IN.bam input sorted/unsorted SAM/BAM containing only unique | |
80 alignments (sorted required for case 2 detailed above) | |
81 | |
82 Options: | |
83 -2, --paired-end use paired end deduping with template. SAM/BAM | |
84 alignment must contain paired end reads. Degenerate | |
85 read pairs (alignments for one read of pair) will be | |
86 discarded. | |
87 -f INDEX.fq|READ.fq FASTQ file containing the molecular tag sequence for | |
88 each read name in the corresponding SAM/BAM file | |
89 (required only for CASE 1 detailed above) | |
90 -o OUT_PREFIX, --out OUT_PREFIX | |
91 prefix of output file paths for sorted BAMs (default | |
92 will create prefix.sorted.markdup.bam, | |
93 prefix.sorted.dedup.bam, prefix_dup_log.txt) | |
94 -s START, --start START | |
95 position in index read where molecular tag sequence | |
96 begins. This should be a 1-based value that counts in | |
97 from the 3' END of the read. (default = 6) | |
98 -l LENGTH, --length LENGTH | |
99 length of molecular tag sequence (default = 6) | |
100 -v, --version show program's version number and exit | |
101 -h, --help show this help message and exit | |
102 ]]></help> | |
103 <citations> | |
104 <citation type="bibtex">@misc{Patel2016, | |
105 author = {Patel, Anand}, | |
106 title = {NuDUP}, | |
107 year = {2016}, | |
108 publisher = {GitHub}, | |
109 journal = {GitHub repository}, | |
110 howpublished = {\url{https://github.com/nugentechnologies/nudup}}, | |
111 commit = {740d9fe439dd8917605a56483a8796b377eb24c6} | |
112 } | |
113 </citation> | |
114 </citations> | |
115 </tool> |