Mercurial > repos > devteam > cd_hit_dup
comparison cd_hit_dup.xml @ 0:2e150ed1b76e draft
Uploaded
author | devteam |
---|---|
date | Wed, 29 Apr 2015 12:06:47 -0400 |
parents | |
children | 0fb894bd8eba |
comparison
equal
deleted
inserted
replaced
-1:000000000000 | 0:2e150ed1b76e |
---|---|
1 <tool id="cd_hit_dup" name="cd-hit-dup" version="0.0.1"> | |
2 <requirements> | |
3 <requirement type="package" version="0.5-2012-03-07-fix-dan-gh-0.0.1">cd-hit-auxtools</requirement> | |
4 </requirements> | |
5 <stdio> | |
6 <exit_code range="1:" /> | |
7 <exit_code range=":-1" /> | |
8 </stdio> | |
9 | |
10 <command><![CDATA[ | |
11 cd-hit-dup | |
12 -i "${ fastq_input.fastq_input1 }" | |
13 #if str( $fastq_input.fastq_input_selector ) == "paired": | |
14 -i2 "${ fastq_input.fastq_input2 }" | |
15 #elif str( $fastq_input.filter_chimeras.filter_chimeras_selector ) == "true": | |
16 -f "true" | |
17 -s "${ fastq_input.filter_chimeras.min_chimeric_length }" | |
18 -a "${ fastq_input.filter_chimeras.abundance_cutoff }" | |
19 -b "${ fastq_input.filter_chimeras.abundance_ratio }" | |
20 -p "${ fastq_input.filter_chimeras.dissimilarity_control }" | |
21 #end if | |
22 -u "${ prefix_length }" | |
23 -m "${ match_length }" | |
24 #if str( $mismatches_allowed ) != "": | |
25 #if float( str( $mismatches_allowed ) ) == int( float( str( $mismatches_allowed ) ) ): | |
26 -e "${ int( float( str( $mismatches_allowed ) ) ) }" | |
27 #else: | |
28 -e "${ mismatches_allowed }" | |
29 #end if | |
30 #end if | |
31 -d "${ description_length }" | |
32 -o "output" | |
33 ]]> | |
34 </command> | |
35 <inputs> | |
36 <conditional name="fastq_input"> | |
37 <param name="fastq_input_selector" type="select" label="Single or Paired-end reads" help="For joined Paired-end reads choose Single."> | |
38 <option value="paired">Paired</option> | |
39 <option value="single" selected="True">Single</option> | |
40 </param> | |
41 <when value="paired"> | |
42 <param name="fastq_input1" type="data" format="fastqsanger,fasta" label="Select first set of reads" help="Specify dataset with forward reads"/> | |
43 <param name="fastq_input2" type="data" format="fastqsanger,fasta" label="Select second set of reads" help="Specify dataset with reverse reads"/> | |
44 </when> | |
45 <when value="single"> | |
46 <param name="fastq_input1" type="data" format="fastqsanger,fasta" label="Select read dataset" help="Specify dataset with single reads"/> | |
47 <conditional name="filter_chimeras"> | |
48 <param name="filter_chimeras_selector" type="select" label="Filter out chimeric clusters"> | |
49 <option value="true">Yes</option> | |
50 <option value="false" selected="True">No</option> | |
51 </param> | |
52 <when value="true"> | |
53 <param name="min_chimeric_length" type="integer" value="30" min="20" label="Minimum length of common sequence shared between a chimeric read and each of its parents" help="-s"/> | |
54 <param name="abundance_cutoff" type="integer" value="1" min="1" label="Abundance cutoff" help="-a; Tool Author recommend default of 2, but this would require the chimera itself to need 2 copies"/> | |
55 <param name="abundance_ratio" type="integer" value="1" min="1" label="Abundance ratio between a parent read and a chimeric read" help="-b"/> | |
56 <param name="dissimilarity_control" type="integer" value="1" min="1" label="Dissimilarity control for chimeric filtering" help="-p"/> | |
57 </when> | |
58 <when value="false"> | |
59 <!-- do nothing here --> | |
60 </when> | |
61 </conditional> | |
62 </when> | |
63 </conditional> | |
64 <param name="prefix_length" type="integer" value="0" min="0" label="Length of prefix to be used in the analysis" help="-u"/> | |
65 <param name="match_length" type="boolean" truevalue="true" falsevalue="false" checked="true" label="Match length" help="-m; specifies whether the lengths of two reads should be exactly the same to be considered as duplicates. "/> | |
66 <param name="mismatches_allowed" type="float" optional="True" value="" min="0" label="Maximum number/percent of mismatches allowed" help="-e"/> | |
67 <param name="description_length" type="integer" value="0" min="0" label="Description length" help="-d; 0 means truncate at the first whitespace character"/> | |
68 </inputs> | |
69 <outputs> | |
70 <data format="fastqsanger" format_source="fastq_input1" name="output_reads" label="${tool.name} on ${on_string} (filtered reads)" from_work_dir="output"/> | |
71 <data format="tabular" name="output_duplicate_clusters" label="${tool.name} on ${on_string} (duplicate clusters)" from_work_dir="output.clstr"/> | |
72 <data format="tabular" name="output_chimeric_clusters" label="${tool.name} on ${on_string} (chimeric clusters)" from_work_dir="output2.clstr"> | |
73 <filter>str( fastq_input['filter_chimeras']['filter_chimeras_selector'] ) == "true"</filter> | |
74 </data> | |
75 </outputs> | |
76 <tests> | |
77 <test> | |
78 <param name="fastq_input|fastq_input_selector" value="single" /> | |
79 <param name="fastq_input|fastq_input1" ftype="fastqsanger" value="cd-hit-dup_in.fastqsanger"/> | |
80 <output name="output_reads" ftype="fastqsanger" file="cd-hit-dup_out.fastqsanger" /> | |
81 <output name="output_duplicate_clusters" ftype="tabular" file="cd-hit-dup_out.dup_clusters.tabular" /> | |
82 </test> | |
83 <test> | |
84 <param name="fastq_input|fastq_input_selector" value="single" /> | |
85 <param name="fastq_input|fastq_input1" ftype="fastqsanger" value="cd-hit-dup_in.fastqsanger"/> | |
86 <param name="fastq_input|filter_chimeras|filter_chimeras_selector" value="true"/> | |
87 <output name="output_reads" ftype="fastqsanger" file="cd-hit-dup_out_chimera.fastqsanger" /> | |
88 <output name="output_duplicate_clusters" ftype="tabular" file="cd-hit-dup_out_chimera.dup_clusters.tabular" /> | |
89 <output name="output_chimeric_clusters" ftype="tabular" file="cd-hit-dup_out_chimera.chimeric_clusters.tabular" /> | |
90 </test> | |
91 </tests> | |
92 <help> | |
93 <![CDATA[ | |
94 **What it does** | |
95 | |
96 cd-hit-dup is a simple tool for removing duplicates from sequencing reads, with optional step to detect and remove chimeric reads. A number of options are provided to tune how the duplicates are removed. | |
97 | |
98 | |
99 **Options** | |
100 | |
101 +--------+-------------------------------------------------------------------------------------------------------------------+ | |
102 | Option | Description | | |
103 +========+===================================================================================================================+ | |
104 |-i | Input file | | |
105 +--------+-------------------------------------------------------------------------------------------------------------------+ | |
106 |-i2 | Second input file | | |
107 +--------+-------------------------------------------------------------------------------------------------------------------+ | |
108 |-o | Output file | | |
109 +--------+-------------------------------------------------------------------------------------------------------------------+ | |
110 |-d | Description length (default 0, truncate at the first whitespace character) | | |
111 +--------+-------------------------------------------------------------------------------------------------------------------+ | |
112 |-u | Length of prefix to be used in the analysis (default 0, for full/maximum length) | | |
113 +--------+-------------------------------------------------------------------------------------------------------------------+ | |
114 |-m | Match length (true/false, default true) | | |
115 +--------+-------------------------------------------------------------------------------------------------------------------+ | |
116 |-e | Maximum number/percent of mismatches allowed | | |
117 +--------+-------------------------------------------------------------------------------------------------------------------+ | |
118 |-f | Filter out chimeric clusters (true/false, default false) | | |
119 +--------+-------------------------------------------------------------------------------------------------------------------+ | |
120 |-s | Minimum length of common sequence shared between a chimeric read and each of its parents (default 30, minimum 20) | | |
121 +--------+-------------------------------------------------------------------------------------------------------------------+ | |
122 |-a | Abundance cutoff (default 1 without chimeric filtering, 2 with chimeric filtering) | | |
123 +--------+-------------------------------------------------------------------------------------------------------------------+ | |
124 |-b | Abundance ratio between a parent read and a chimeric read (default 1) | | |
125 +--------+-------------------------------------------------------------------------------------------------------------------+ | |
126 |-p | Dissimilarity control for chimeric filtering (default 1) | | |
127 +--------+-------------------------------------------------------------------------------------------------------------------+ | |
128 | |
129 | |
130 ]]> | |
131 </help> | |
132 <citations> | |
133 <citation type="doi">10.1093/bioinformatics/bts565</citation> | |
134 </citations> | |
135 </tool> |