Mercurial > repos > devteam > fastqc

comparison rgFastQC.xml @ 18:3e1cdf5406db draft

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/fastqc commit 8a5d4f0470a7778a87d01dc84578f94a30ab7f43
author iuc
date Mon, 05 Nov 2018 12:08:29 -0500
parents c15237684a01
children 9da02be9c6cc
comparison
equal deleted inserted replaced
17:c15237684a01 18:3e1cdf5406db
1 <tool id="fastqc" name="FastQC" version="0.72"> 1 <tool id="fastqc" name="FastQC" version="0.72">
2 <description>Read Quality reports</description> 2 <description>Read Quality reports</description>
3 <requirements> 3 <requirements>
4 <requirement type="package" version="0.11.7">fastqc</requirement> 4 <requirement type="package" version="0.11.8">fastqc</requirement>
5 </requirements> 5 </requirements>
6 <command detect_errors="exit_code"><![CDATA[ 6 <stdio>
7 <exit_code range="1:" level="fatal" description="FastQC returned non zero exit code" />
8 <exit_code range=":-1" level="fatal" description="FastQC returned non zero exit code" />
9 <regex match="There is insufficient memory for the Java Runtime Environment"
10 source="stdout"
11 level="fatal_oom"
12 description="Out of memory error occurred" />
13 </stdio>
14 <command><![CDATA[
7 #import re 15 #import re
8 #set input_name = re.sub('[^\w\-\s]', '_', str($input_file.element_identifier)) 16 #set input_name = re.sub('[^\w\-\s]', '_', str($input_file.element_identifier))
9 17
10 #if $input_file.ext.endswith('.gz'): 18 #if $input_file.ext.endswith('.gz'):
11 #set input_file_sl = $input_name + '.gz' 19 #set input_file_sl = $input_name + '.gz'
25 33
26 ln -s '${input_file}' '${input_file_sl}' && 34 ln -s '${input_file}' '${input_file_sl}' &&
27 mkdir -p '${html_file.files_path}' && 35 mkdir -p '${html_file.files_path}' &&
28 fastqc 36 fastqc
29 --outdir '${html_file.files_path}' 37 --outdir '${html_file.files_path}'
30
31 #if $contaminants.dataset and str($contaminants) > '' 38 #if $contaminants.dataset and str($contaminants) > ''
32 --contaminants '${contaminants}' 39 --contaminants '${contaminants}'
33 #end if 40 #end if
34 41
42 #if $adapters.dataset and str($adapters) > ''
43 --adapters '${adapters}'
44 #end if
45
35 #if $limits.dataset and str($limits) > '' 46 #if $limits.dataset and str($limits) > ''
36 --limits '${limits}' 47 --limits '${limits}'
37 #end if 48 #end if
38 49
39 --quiet 50 --quiet
40 --extract 51 --extract
52 #if $min_length:
53 --min_length $min_length
54 #end if
55 $nogroup
56 --kmers $kmers
41 -f '${format}' 57 -f '${format}'
42 '${input_file_sl}' 58 '${input_file_sl}'
43 59
44 && cp '${html_file.files_path}'/*/fastqc_data.txt output.txt 60 && cp '${html_file.files_path}'/*/fastqc_data.txt output.txt
45 && cp '${html_file.files_path}'/*\.html output.html 61 && cp '${html_file.files_path}'/*\.html output.html
48 <inputs> 64 <inputs>
49 <param format="fastq,fastq.gz,fastq.bz2,bam,sam" name="input_file" type="data" 65 <param format="fastq,fastq.gz,fastq.bz2,bam,sam" name="input_file" type="data"
50 label="Short read data from your current history" /> 66 label="Short read data from your current history" />
51 <param name="contaminants" type="data" format="tabular" optional="true" label="Contaminant list" 67 <param name="contaminants" type="data" format="tabular" optional="true" label="Contaminant list"
52 help="tab delimited file with 2 columns: name and sequence. For example: Illumina Small RNA RT Primer CAAGCAGAAGACGGCATACGA" /> 68 help="tab delimited file with 2 columns: name and sequence. For example: Illumina Small RNA RT Primer CAAGCAGAAGACGGCATACGA" />
69 <param argument="--adapters" type="data" format="tabular" optional="true" label="Adapter list"
70 help="list of adapters adapter sequences which will be explicity searched against the library. tab delimited file with 2 columns: name and sequence." />
53 <param name="limits" type="data" format="txt" optional="true" label="Submodule and Limit specifing file" 71 <param name="limits" type="data" format="txt" optional="true" label="Submodule and Limit specifing file"
54 help="a file that specifies which submodules are to be executed (default=all) and also specifies the thresholds for the each submodules warning parameter" /> 72 help="a file that specifies which submodules are to be executed (default=all) and also specifies the thresholds for the each submodules warning parameter" />
73 <param argument="--nogroup" type="boolean" truevalue="--nogroup" falsevalue="" checked="False"
74 label="Disable grouping of bases for reads >50bp" help="Using this option will cause fastqc to crash and burn if you use it on really long reads, and your plots may end up a ridiculous size. You have been warned!"/>
75 <param argument="--min_length" type="integer" value="" optional="true"
76 label="Lower limit on the length of the sequence to be shown in the report"
77 help=" As long as you set this to a value greater or equal to your longest read length then this will be the sequence length used to create your read groups. This can be useful for making directly comaparable statistics from datasets with somewhat variable read lengths."/>
78 <param argument="--kmers" type="integer" value="7" min="2" max="10"
79 label="length of Kmer to look for" help="note: the Kmer test is disabled and needs to be enabled using a custom Submodule and limits file"/>
55 </inputs> 80 </inputs>
56 <outputs> 81 <outputs>
57 <data format="html" name="html_file" from_work_dir="output.html" label="${tool.name} on ${on_string}: Webpage" /> 82 <data format="html" name="html_file" from_work_dir="output.html" label="${tool.name} on ${on_string}: Webpage" />
58 <data format="txt" name="text_file" from_work_dir="output.txt" label="${tool.name} on ${on_string}: RawData" /> 83 <data format="txt" name="text_file" from_work_dir="output.txt" label="${tool.name} on ${on_string}: RawData" />
59 </outputs> 84 </outputs>
60 <tests> 85 <tests>
61 <test> 86 <test>
62 <param name="input_file" value="1000gsample.fastq" /> 87 <param name="input_file" value="1000trimmed.fastq" />
88 <output name="html_file" file="fastqc_report.html" ftype="html" compare="sim_size" delta="5000"/>
89 <output name="text_file" file="fastqc_data.txt" ftype="txt"/>
90 </test>
91 <test>
92 <param name="input_file" value="1000trimmed.fastq" />
63 <param name="contaminants" value="fastqc_contaminants.txt" ftype="tabular" /> 93 <param name="contaminants" value="fastqc_contaminants.txt" ftype="tabular" />
64 <output name="html_file" file="fastqc_report.html" ftype="html" lines_diff="100"/> 94 <output name="html_file" file="fastqc_report_contaminants.html" ftype="html" compare="sim_size" delta="5000"/>
65 <output name="text_file" file="fastqc_data.txt" ftype="txt" lines_diff="4"/> 95 <output name="text_file" file="fastqc_data_contaminants.txt" ftype="txt"/>
66 </test> 96 </test>
67 <test> 97 <test>
68 <param name="input_file" value="1000gsample.fastq" /> 98 <param name="input_file" value="1000trimmed.fastq" />
99 <param name="adapters" value="fastqc_adapters.txt" ftype="tabular" />
100 <output name="html_file" file="fastqc_report_adapters.html" ftype="html" compare="sim_size" delta="5000"/>
101 <output name="text_file" file="fastqc_data_adapters.txt" ftype="txt"/>
102 </test>
103 <test>
104 <param name="input_file" value="1000trimmed.fastq" />
69 <param name="limits" value="fastqc_customlimits.txt" ftype="txt" /> 105 <param name="limits" value="fastqc_customlimits.txt" ftype="txt" />
70 <output name="html_file" file="fastqc_report2.html" ftype="html" compare="sim_size" delta="4096"/> 106 <output name="html_file" file="fastqc_report_customlimits.html" ftype="html" compare="sim_size" delta="5000"/>
71 <output name="text_file" file="fastqc_data2.txt" ftype="txt" lines_diff="4"/> 107 <output name="text_file" file="fastqc_data_customlimits.txt" ftype="txt"/>
72 </test> 108 </test>
73 <test> 109 <test>
74 <param name="input_file" value="1000gsample.fastq.gz" ftype="fastq.gz" /> 110 <param name="input_file" value="1000trimmed.fastq" ftype="fastq" />
75 <param name="contaminants" value="fastqc_contaminants.txt" ftype="tabular" /> 111 <param name="kmers" value="3" />
76 <output name="html_file" file="fastqc_report.html" ftype="html" lines_diff="100"/> 112 <param name="limits" value="fastqc_customlimits.txt" ftype="txt" />
77 <output name="text_file" file="fastqc_data.txt" ftype="txt" lines_diff="4"/> 113 <output name="html_file" file="fastqc_report_kmer.html" ftype="html" compare="sim_size" delta="5000"/>
78 </test> 114 <output name="text_file" file="fastqc_data_kmer.txt" ftype="txt"/>
79 <test> 115 <assert_command>
80 <param name="input_file" value="1000gsample.fastq.bz2" ftype="fastq.bz2" /> 116 <has_text text="--kmers 3"/>
81 <param name="contaminants" value="fastqc_contaminants.txt" ftype="tabular" /> 117 </assert_command>
82 <output name="html_file" file="fastqc_report.html" ftype="html" lines_diff="100"/> 118 </test>
83 <output name="text_file" file="fastqc_data.txt" ftype="txt" lines_diff="4"/> 119 <test>
120 <param name="input_file" value="1000trimmed.fastq" />
121 <param name="min_length" value="108" />
122 <output name="html_file" file="fastqc_report_min_length.html" ftype="html" compare="sim_size" delta="5000"/>
123 <output name="text_file" file="fastqc_data_min_length.txt" ftype="txt"/>
124 </test>
125 <test>
126 <param name="input_file" value="1000trimmed.fastq" ftype="fastq" />
127 <param name="nogroup" value="--nogroup" />
128 <output name="html_file" file="fastqc_report_nogroup.html" ftype="html" compare="sim_size" delta="5000"/>
129 <output name="text_file" file="fastqc_data_nogroup.txt" ftype="txt"/>
130 <assert_command>
131 <has_text text="--nogroup"/>
132 </assert_command>
84 </test> 133 </test>
85 <test> 134 <test>
86 <param name="input_file" value="hisat_output_1.bam" ftype="bam" /> 135 <param name="input_file" value="hisat_output_1.bam" ftype="bam" />
87 <output name="html_file" file="fastqc_report_hisat.html" ftype="html" lines_diff="100"/> 136 <output name="html_file" file="fastqc_report_hisat.html" ftype="html" compare="sim_size" delta="5000"/>
88 <output name="text_file" file="fastqc_data_hisat.txt" ftype="txt" lines_diff="4"/> 137 <output name="text_file" file="fastqc_data_hisat.txt" ftype="txt"/>
89 </test> 138 </test>
90 </tests> 139 </tests>
91 <help> 140 <help><![CDATA[
92 .. class:: infomark 141 .. class:: infomark
93 142
94 **Purpose** 143 **Purpose**
95 144
96 FastQC aims to provide a simple way to do some quality control checks on raw 145 FastQC aims to provide a simple way to do some quality control checks on raw
97 sequence data coming from high throughput sequencing pipelines. 146 sequence data coming from high throughput sequencing pipelines.
98 It provides a modular set of analyses which you can use to give a quick 147 It provides a set of analyses which you can use to get a quick
99 impression of whether your data has any problems of 148 impression of whether your data has any problems of
100 which you should be aware before doing any further analysis. 149 which you should be aware before doing any further analysis.
101 150
102 The main functions of FastQC are: 151 The main functions of FastQC are:
103 152
151 - Kmer Content 200 - Kmer Content
152 201
153 All except Basic Statistics and Overrepresented sequences are plots. 202 All except Basic Statistics and Overrepresented sequences are plots.
154 .. _FastQC: http://www.bioinformatics.babraham.ac.uk/projects/fastqc/ 203 .. _FastQC: http://www.bioinformatics.babraham.ac.uk/projects/fastqc/
155 .. _Picard-tools: https://broadinstitute.github.io/picard/ 204 .. _Picard-tools: https://broadinstitute.github.io/picard/
156 </help> 205 ]]></help>
157 <citations> 206 <citations>
158 <citation type="bibtex"> 207 <citation type="bibtex">
159 @unpublished{andrews_s, 208 @unpublished{andrews_s,
160 author = {Andrews, S.}, 209 author = {Andrews, S.},
161 keywords = {bioinformatics, ngs, qc}, 210 keywords = {bioinformatics, ngs, qc},