annotate rgFastQC.xml @ 11:db2dc6bc8f05 draft

planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/fastqc commit 168f7aeb0f9f38de6dec873f3cbf0c30014fdd72
author iuc
date Thu, 20 Apr 2017 11:06:17 -0400
parents a00a6402d09a
children 484e86282f4b
Ignore whitespace changes - Everywhere: Within whitespace: At end of lines:
rev   line source
11
db2dc6bc8f05 planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/fastqc commit 168f7aeb0f9f38de6dec873f3cbf0c30014fdd72
iuc
parents: 10
diff changeset
1 <tool id="fastqc" name="FastQC" version="0.68">
3
0b201de108b9 Uploaded
devteam
parents: 2
diff changeset
2 <description>Read Quality reports</description>
0b201de108b9 Uploaded
devteam
parents: 2
diff changeset
3 <requirements>
8
06819360a9e2 planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/fastqc commit df4c0b0c6372e2984966e220fa42ecd8a3d370e8
devteam
parents: 7
diff changeset
4 <requirement type="package" version="0.11.5">fastqc</requirement>
3
0b201de108b9 Uploaded
devteam
parents: 2
diff changeset
5 </requirements>
0b201de108b9 Uploaded
devteam
parents: 2
diff changeset
6 <stdio>
0b201de108b9 Uploaded
devteam
parents: 2
diff changeset
7 <exit_code range="1:" />
0b201de108b9 Uploaded
devteam
parents: 2
diff changeset
8 <exit_code range=":-1" />
0b201de108b9 Uploaded
devteam
parents: 2
diff changeset
9 <regex match="Error:" />
0b201de108b9 Uploaded
devteam
parents: 2
diff changeset
10 <regex match="Exception:" />
0b201de108b9 Uploaded
devteam
parents: 2
diff changeset
11 </stdio>
8
06819360a9e2 planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/fastqc commit df4c0b0c6372e2984966e220fa42ecd8a3d370e8
devteam
parents: 7
diff changeset
12 <command><![CDATA[
10
a00a6402d09a planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/fastqc commit 2bfbb5ae6b801e43355fdc3f964a5111fe3fe3a1
iuc
parents: 9
diff changeset
13 python '${__tool_directory__}/rgFastQC.py'
a00a6402d09a planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/fastqc commit 2bfbb5ae6b801e43355fdc3f964a5111fe3fe3a1
iuc
parents: 9
diff changeset
14 -i '$input_file'
a00a6402d09a planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/fastqc commit 2bfbb5ae6b801e43355fdc3f964a5111fe3fe3a1
iuc
parents: 9
diff changeset
15 -d '${html_file.files_path}'
a00a6402d09a planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/fastqc commit 2bfbb5ae6b801e43355fdc3f964a5111fe3fe3a1
iuc
parents: 9
diff changeset
16 -o '$html_file'
a00a6402d09a planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/fastqc commit 2bfbb5ae6b801e43355fdc3f964a5111fe3fe3a1
iuc
parents: 9
diff changeset
17 -t '$text_file'
a00a6402d09a planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/fastqc commit 2bfbb5ae6b801e43355fdc3f964a5111fe3fe3a1
iuc
parents: 9
diff changeset
18 -f '${input_file.ext}'
a00a6402d09a planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/fastqc commit 2bfbb5ae6b801e43355fdc3f964a5111fe3fe3a1
iuc
parents: 9
diff changeset
19 -j '${input_file.name}'
a00a6402d09a planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/fastqc commit 2bfbb5ae6b801e43355fdc3f964a5111fe3fe3a1
iuc
parents: 9
diff changeset
20 #if $contaminants.dataset and str($contaminants) > ''
a00a6402d09a planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/fastqc commit 2bfbb5ae6b801e43355fdc3f964a5111fe3fe3a1
iuc
parents: 9
diff changeset
21 -c '$contaminants'
a00a6402d09a planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/fastqc commit 2bfbb5ae6b801e43355fdc3f964a5111fe3fe3a1
iuc
parents: 9
diff changeset
22 #end if
a00a6402d09a planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/fastqc commit 2bfbb5ae6b801e43355fdc3f964a5111fe3fe3a1
iuc
parents: 9
diff changeset
23 #if $limits.dataset and str($limits) > ''
a00a6402d09a planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/fastqc commit 2bfbb5ae6b801e43355fdc3f964a5111fe3fe3a1
iuc
parents: 9
diff changeset
24 -l '$limits'
a00a6402d09a planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/fastqc commit 2bfbb5ae6b801e43355fdc3f964a5111fe3fe3a1
iuc
parents: 9
diff changeset
25 #end if
8
06819360a9e2 planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/fastqc commit df4c0b0c6372e2984966e220fa42ecd8a3d370e8
devteam
parents: 7
diff changeset
26 ]]></command>
3
0b201de108b9 Uploaded
devteam
parents: 2
diff changeset
27 <inputs>
10
a00a6402d09a planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/fastqc commit 2bfbb5ae6b801e43355fdc3f964a5111fe3fe3a1
iuc
parents: 9
diff changeset
28 <param format="fastq,fastq.gz,fastq.bz2,bam,sam" name="input_file" type="data" label="Short read data from your current history" />
8
06819360a9e2 planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/fastqc commit df4c0b0c6372e2984966e220fa42ecd8a3d370e8
devteam
parents: 7
diff changeset
29 <param name="contaminants" type="data" format="tabular" optional="true" label="Contaminant list"
10
a00a6402d09a planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/fastqc commit 2bfbb5ae6b801e43355fdc3f964a5111fe3fe3a1
iuc
parents: 9
diff changeset
30 help="tab delimited file with 2 columns: name and sequence. For example: Illumina Small RNA RT Primer CAAGCAGAAGACGGCATACGA" />
3
0b201de108b9 Uploaded
devteam
parents: 2
diff changeset
31 <param name="limits" type="data" format="txt" optional="true" label="Submodule and Limit specifing file"
10
a00a6402d09a planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/fastqc commit 2bfbb5ae6b801e43355fdc3f964a5111fe3fe3a1
iuc
parents: 9
diff changeset
32 help="a file that specifies which submodules are to be executed (default=all) and also specifies the thresholds for the each submodules warning parameter" />
3
0b201de108b9 Uploaded
devteam
parents: 2
diff changeset
33 </inputs>
0b201de108b9 Uploaded
devteam
parents: 2
diff changeset
34 <outputs>
0b201de108b9 Uploaded
devteam
parents: 2
diff changeset
35 <data format="html" name="html_file" label="${tool.name} on ${on_string}: Webpage" />
0b201de108b9 Uploaded
devteam
parents: 2
diff changeset
36 <data format="txt" name="text_file" label="${tool.name} on ${on_string}: RawData" />
0b201de108b9 Uploaded
devteam
parents: 2
diff changeset
37 </outputs>
0b201de108b9 Uploaded
devteam
parents: 2
diff changeset
38 <tests>
0b201de108b9 Uploaded
devteam
parents: 2
diff changeset
39 <test>
0b201de108b9 Uploaded
devteam
parents: 2
diff changeset
40 <param name="input_file" value="1000gsample.fastq" />
0b201de108b9 Uploaded
devteam
parents: 2
diff changeset
41 <param name="contaminants" value="fastqc_contaminants.txt" ftype="tabular" />
0b201de108b9 Uploaded
devteam
parents: 2
diff changeset
42 <output name="html_file" file="fastqc_report.html" ftype="html" lines_diff="100"/>
0b201de108b9 Uploaded
devteam
parents: 2
diff changeset
43 <output name="text_file" file="fastqc_data.txt" ftype="txt" lines_diff="100"/>
0b201de108b9 Uploaded
devteam
parents: 2
diff changeset
44 </test>
0b201de108b9 Uploaded
devteam
parents: 2
diff changeset
45 <test>
0b201de108b9 Uploaded
devteam
parents: 2
diff changeset
46 <param name="input_file" value="1000gsample.fastq" />
0b201de108b9 Uploaded
devteam
parents: 2
diff changeset
47 <param name="limits" value="fastqc_customlimits.txt" ftype="txt" />
8
06819360a9e2 planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/fastqc commit df4c0b0c6372e2984966e220fa42ecd8a3d370e8
devteam
parents: 7
diff changeset
48 <output name="html_file" file="fastqc_report2.html" ftype="html" compare="sim_size" delta="4096"/>
06819360a9e2 planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/fastqc commit df4c0b0c6372e2984966e220fa42ecd8a3d370e8
devteam
parents: 7
diff changeset
49 <output name="text_file" file="fastqc_data2.txt" ftype="txt" compare="sim_size"/>
3
0b201de108b9 Uploaded
devteam
parents: 2
diff changeset
50 </test>
9
3a458e268066 planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/fastqc commit 8918618a5ef7bdca55a31cd919efa593044a376e
devteam
parents: 8
diff changeset
51 <test>
10
a00a6402d09a planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/fastqc commit 2bfbb5ae6b801e43355fdc3f964a5111fe3fe3a1
iuc
parents: 9
diff changeset
52 <param name="input_file" value="1000gsample.fastq.gz" ftype="fastq.gz" />
a00a6402d09a planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/fastqc commit 2bfbb5ae6b801e43355fdc3f964a5111fe3fe3a1
iuc
parents: 9
diff changeset
53 <param name="contaminants" value="fastqc_contaminants.txt" ftype="tabular" />
a00a6402d09a planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/fastqc commit 2bfbb5ae6b801e43355fdc3f964a5111fe3fe3a1
iuc
parents: 9
diff changeset
54 <output name="html_file" file="fastqc_report.html" ftype="html" lines_diff="100"/>
a00a6402d09a planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/fastqc commit 2bfbb5ae6b801e43355fdc3f964a5111fe3fe3a1
iuc
parents: 9
diff changeset
55 <output name="text_file" file="fastqc_data.txt" ftype="txt" lines_diff="100"/>
a00a6402d09a planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/fastqc commit 2bfbb5ae6b801e43355fdc3f964a5111fe3fe3a1
iuc
parents: 9
diff changeset
56 </test>
a00a6402d09a planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/fastqc commit 2bfbb5ae6b801e43355fdc3f964a5111fe3fe3a1
iuc
parents: 9
diff changeset
57 <test>
a00a6402d09a planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/fastqc commit 2bfbb5ae6b801e43355fdc3f964a5111fe3fe3a1
iuc
parents: 9
diff changeset
58 <param name="input_file" value="1000gsample.fastq.bz2" ftype="fastq.bz2" />
9
3a458e268066 planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/fastqc commit 8918618a5ef7bdca55a31cd919efa593044a376e
devteam
parents: 8
diff changeset
59 <param name="contaminants" value="fastqc_contaminants.txt" ftype="tabular" />
3a458e268066 planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/fastqc commit 8918618a5ef7bdca55a31cd919efa593044a376e
devteam
parents: 8
diff changeset
60 <output name="html_file" file="fastqc_report.html" ftype="html" lines_diff="100"/>
3a458e268066 planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/fastqc commit 8918618a5ef7bdca55a31cd919efa593044a376e
devteam
parents: 8
diff changeset
61 <output name="text_file" file="fastqc_data.txt" ftype="txt" lines_diff="100"/>
3a458e268066 planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/fastqc commit 8918618a5ef7bdca55a31cd919efa593044a376e
devteam
parents: 8
diff changeset
62 </test>
3
0b201de108b9 Uploaded
devteam
parents: 2
diff changeset
63 </tests>
0b201de108b9 Uploaded
devteam
parents: 2
diff changeset
64 <help>
0
e28c965eeed4 Imported from capsule None
devteam
parents:
diff changeset
65 .. class:: infomark
e28c965eeed4 Imported from capsule None
devteam
parents:
diff changeset
66
e28c965eeed4 Imported from capsule None
devteam
parents:
diff changeset
67 **Purpose**
e28c965eeed4 Imported from capsule None
devteam
parents:
diff changeset
68
e28c965eeed4 Imported from capsule None
devteam
parents:
diff changeset
69 FastQC aims to provide a simple way to do some quality control checks on raw
8
06819360a9e2 planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/fastqc commit df4c0b0c6372e2984966e220fa42ecd8a3d370e8
devteam
parents: 7
diff changeset
70 sequence data coming from high throughput sequencing pipelines.
0
e28c965eeed4 Imported from capsule None
devteam
parents:
diff changeset
71 It provides a modular set of analyses which you can use to give a quick
8
06819360a9e2 planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/fastqc commit df4c0b0c6372e2984966e220fa42ecd8a3d370e8
devteam
parents: 7
diff changeset
72 impression of whether your data has any problems of
0
e28c965eeed4 Imported from capsule None
devteam
parents:
diff changeset
73 which you should be aware before doing any further analysis.
e28c965eeed4 Imported from capsule None
devteam
parents:
diff changeset
74
e28c965eeed4 Imported from capsule None
devteam
parents:
diff changeset
75 The main functions of FastQC are:
e28c965eeed4 Imported from capsule None
devteam
parents:
diff changeset
76
10
a00a6402d09a planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/fastqc commit 2bfbb5ae6b801e43355fdc3f964a5111fe3fe3a1
iuc
parents: 9
diff changeset
77 - Import of data from BAM, SAM or FastQ/FastQ.gz files (any variant),
0
e28c965eeed4 Imported from capsule None
devteam
parents:
diff changeset
78 - Providing a quick overview to tell you in which areas there may be problems
e28c965eeed4 Imported from capsule None
devteam
parents:
diff changeset
79 - Summary graphs and tables to quickly assess your data
e28c965eeed4 Imported from capsule None
devteam
parents:
diff changeset
80 - Export of results to an HTML based permanent report
e28c965eeed4 Imported from capsule None
devteam
parents:
diff changeset
81 - Offline operation to allow automated generation of reports without running the interactive application
e28c965eeed4 Imported from capsule None
devteam
parents:
diff changeset
82
e28c965eeed4 Imported from capsule None
devteam
parents:
diff changeset
83 -----
e28c965eeed4 Imported from capsule None
devteam
parents:
diff changeset
84
e28c965eeed4 Imported from capsule None
devteam
parents:
diff changeset
85 .. class:: infomark
e28c965eeed4 Imported from capsule None
devteam
parents:
diff changeset
86
e28c965eeed4 Imported from capsule None
devteam
parents:
diff changeset
87 **FastQC**
e28c965eeed4 Imported from capsule None
devteam
parents:
diff changeset
88
e28c965eeed4 Imported from capsule None
devteam
parents:
diff changeset
89 This is a Galaxy wrapper. It merely exposes the external package FastQC_ which is documented at FastQC_
e28c965eeed4 Imported from capsule None
devteam
parents:
diff changeset
90 Kindly acknowledge it as well as this tool if you use it.
e28c965eeed4 Imported from capsule None
devteam
parents:
diff changeset
91 FastQC incorporates the Picard-tools_ libraries for sam/bam processing.
e28c965eeed4 Imported from capsule None
devteam
parents:
diff changeset
92
e28c965eeed4 Imported from capsule None
devteam
parents:
diff changeset
93 The contaminants file parameter was borrowed from the independently developed
e28c965eeed4 Imported from capsule None
devteam
parents:
diff changeset
94 fastqcwrapper contributed to the Galaxy Community Tool Shed by J. Johnson.
1
8fae48caaf06 Uploaded form GH
devteam
parents: 0
diff changeset
95 Adaption to version 0.11.2 by T. McGowan.
0
e28c965eeed4 Imported from capsule None
devteam
parents:
diff changeset
96
e28c965eeed4 Imported from capsule None
devteam
parents:
diff changeset
97 -----
e28c965eeed4 Imported from capsule None
devteam
parents:
diff changeset
98
e28c965eeed4 Imported from capsule None
devteam
parents:
diff changeset
99 .. class:: infomark
e28c965eeed4 Imported from capsule None
devteam
parents:
diff changeset
100
e28c965eeed4 Imported from capsule None
devteam
parents:
diff changeset
101 **Inputs and outputs**
e28c965eeed4 Imported from capsule None
devteam
parents:
diff changeset
102
8
06819360a9e2 planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/fastqc commit df4c0b0c6372e2984966e220fa42ecd8a3d370e8
devteam
parents: 7
diff changeset
103 FastQC_ is the best place to look for documentation - it's very good.
0
e28c965eeed4 Imported from capsule None
devteam
parents:
diff changeset
104 A summary follows below for those in a tearing hurry.
e28c965eeed4 Imported from capsule None
devteam
parents:
diff changeset
105
9
3a458e268066 planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/fastqc commit 8918618a5ef7bdca55a31cd919efa593044a376e
devteam
parents: 8
diff changeset
106 This wrapper will accept a Galaxy fastq, fastq.gz, sam or bam as the input read file to check.
0
e28c965eeed4 Imported from capsule None
devteam
parents:
diff changeset
107 It will also take an optional file containing a list of contaminants information, in the form of
1
8fae48caaf06 Uploaded form GH
devteam
parents: 0
diff changeset
108 a tab-delimited file with 2 columns, name and sequence. As another option the tool takes a custom
8fae48caaf06 Uploaded form GH
devteam
parents: 0
diff changeset
109 limits.txt file that allows setting the warning thresholds for the different modules and also specifies
8fae48caaf06 Uploaded form GH
devteam
parents: 0
diff changeset
110 which modules to include in the output.
0
e28c965eeed4 Imported from capsule None
devteam
parents:
diff changeset
111
1
8fae48caaf06 Uploaded form GH
devteam
parents: 0
diff changeset
112 The tool produces a basic text and a HTML output file that contain all of the results, including the following:
0
e28c965eeed4 Imported from capsule None
devteam
parents:
diff changeset
113
e28c965eeed4 Imported from capsule None
devteam
parents:
diff changeset
114 - Basic Statistics
e28c965eeed4 Imported from capsule None
devteam
parents:
diff changeset
115 - Per base sequence quality
e28c965eeed4 Imported from capsule None
devteam
parents:
diff changeset
116 - Per sequence quality scores
e28c965eeed4 Imported from capsule None
devteam
parents:
diff changeset
117 - Per base sequence content
e28c965eeed4 Imported from capsule None
devteam
parents:
diff changeset
118 - Per base GC content
e28c965eeed4 Imported from capsule None
devteam
parents:
diff changeset
119 - Per sequence GC content
e28c965eeed4 Imported from capsule None
devteam
parents:
diff changeset
120 - Per base N content
e28c965eeed4 Imported from capsule None
devteam
parents:
diff changeset
121 - Sequence Length Distribution
e28c965eeed4 Imported from capsule None
devteam
parents:
diff changeset
122 - Sequence Duplication Levels
e28c965eeed4 Imported from capsule None
devteam
parents:
diff changeset
123 - Overrepresented sequences
e28c965eeed4 Imported from capsule None
devteam
parents:
diff changeset
124 - Kmer Content
e28c965eeed4 Imported from capsule None
devteam
parents:
diff changeset
125
e28c965eeed4 Imported from capsule None
devteam
parents:
diff changeset
126 All except Basic Statistics and Overrepresented sequences are plots.
11
db2dc6bc8f05 planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/fastqc commit 168f7aeb0f9f38de6dec873f3cbf0c30014fdd72
iuc
parents: 10
diff changeset
127 .. _FastQC: http://www.bioinformatics.babraham.ac.uk/projects/fastqc/
0
e28c965eeed4 Imported from capsule None
devteam
parents:
diff changeset
128 .. _Picard-tools: http://picard.sourceforge.net/index.shtml
2
d2cf2c0c8a11 Uploaded from GH
devteam
parents: 1
diff changeset
129 </help>
d2cf2c0c8a11 Uploaded from GH
devteam
parents: 1
diff changeset
130 <citations>
d2cf2c0c8a11 Uploaded from GH
devteam
parents: 1
diff changeset
131 <citation type="bibtex">
10
a00a6402d09a planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/fastqc commit 2bfbb5ae6b801e43355fdc3f964a5111fe3fe3a1
iuc
parents: 9
diff changeset
132 @unpublished{andrews_s,
2
d2cf2c0c8a11 Uploaded from GH
devteam
parents: 1
diff changeset
133 author = {Andrews, S.},
d2cf2c0c8a11 Uploaded from GH
devteam
parents: 1
diff changeset
134 keywords = {bioinformatics, ngs, qc},
d2cf2c0c8a11 Uploaded from GH
devteam
parents: 1
diff changeset
135 priority = {2},
d2cf2c0c8a11 Uploaded from GH
devteam
parents: 1
diff changeset
136 title = {{FastQC A Quality Control tool for High Throughput Sequence Data}},
d2cf2c0c8a11 Uploaded from GH
devteam
parents: 1
diff changeset
137 url = {http://www.bioinformatics.babraham.ac.uk/projects/fastqc/}
d2cf2c0c8a11 Uploaded from GH
devteam
parents: 1
diff changeset
138 }
d2cf2c0c8a11 Uploaded from GH
devteam
parents: 1
diff changeset
139 </citation>
d2cf2c0c8a11 Uploaded from GH
devteam
parents: 1
diff changeset
140 </citations>
0
e28c965eeed4 Imported from capsule None
devteam
parents:
diff changeset
141 </tool>