annotate rgFastQC.xml @ 6:28d39af2dd06 draft

planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/fastqc commit 8328b3d01e1cb49c5dcbb6578ec42784ad6beaa8
author devteam
date Mon, 18 Jan 2016 09:33:58 -0500
parents 0b201de108b9
children 3fdc1a74d866
Ignore whitespace changes - Everywhere: Within whitespace: At end of lines:
rev   line source
6
28d39af2dd06 planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/fastqc commit 8328b3d01e1cb49c5dcbb6578ec42784ad6beaa8
devteam
parents: 3
diff changeset
1 <tool id="fastqc" name="FastQC" version="0.64">
3
0b201de108b9 Uploaded
devteam
parents: 2
diff changeset
2 <description>Read Quality reports</description>
0b201de108b9 Uploaded
devteam
parents: 2
diff changeset
3 <requirements>
6
28d39af2dd06 planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/fastqc commit 8328b3d01e1cb49c5dcbb6578ec42784ad6beaa8
devteam
parents: 3
diff changeset
4 <requirement type="package" version="0.11.4">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>
0b201de108b9 Uploaded
devteam
parents: 2
diff changeset
12 <command interpreter="python">
0b201de108b9 Uploaded
devteam
parents: 2
diff changeset
13 rgFastQC.py
2
d2cf2c0c8a11 Uploaded from GH
devteam
parents: 1
diff changeset
14 -i "$input_file"
d2cf2c0c8a11 Uploaded from GH
devteam
parents: 1
diff changeset
15 -d "$html_file.files_path"
d2cf2c0c8a11 Uploaded from GH
devteam
parents: 1
diff changeset
16 -o "$html_file"
d2cf2c0c8a11 Uploaded from GH
devteam
parents: 1
diff changeset
17 -t "$text_file"
d2cf2c0c8a11 Uploaded from GH
devteam
parents: 1
diff changeset
18 -f "$input_file.ext"
d2cf2c0c8a11 Uploaded from GH
devteam
parents: 1
diff changeset
19 -j "$input_file.name"
d2cf2c0c8a11 Uploaded from GH
devteam
parents: 1
diff changeset
20 -e "\$FASTQC_JAR_PATH/fastqc"
d2cf2c0c8a11 Uploaded from GH
devteam
parents: 1
diff changeset
21 #if $contaminants.dataset and str($contaminants) > ''
d2cf2c0c8a11 Uploaded from GH
devteam
parents: 1
diff changeset
22 -c "$contaminants"
d2cf2c0c8a11 Uploaded from GH
devteam
parents: 1
diff changeset
23 #end if
d2cf2c0c8a11 Uploaded from GH
devteam
parents: 1
diff changeset
24 #if $limits.dataset and str($limits) > ''
d2cf2c0c8a11 Uploaded from GH
devteam
parents: 1
diff changeset
25 -l "$limits"
d2cf2c0c8a11 Uploaded from GH
devteam
parents: 1
diff changeset
26 #end if
3
0b201de108b9 Uploaded
devteam
parents: 2
diff changeset
27 </command>
0b201de108b9 Uploaded
devteam
parents: 2
diff changeset
28 <inputs>
0b201de108b9 Uploaded
devteam
parents: 2
diff changeset
29 <param format="fastqsanger,fastq,bam,sam" name="input_file" type="data" label="Short read data from your current history" />
0b201de108b9 Uploaded
devteam
parents: 2
diff changeset
30 <param name="contaminants" type="data" format="tabular" optional="true" label="Contaminant list"
0b201de108b9 Uploaded
devteam
parents: 2
diff changeset
31 help="tab delimited file with 2 columns: name and sequence. For example: Illumina Small RNA RT Primer CAAGCAGAAGACGGCATACGA"/>
0b201de108b9 Uploaded
devteam
parents: 2
diff changeset
32 <param name="limits" type="data" format="txt" optional="true" label="Submodule and Limit specifing file"
0b201de108b9 Uploaded
devteam
parents: 2
diff changeset
33 help="a file that specifies which submodules are to be executed (default=all) and also specifies the thresholds for the each submodules warning parameter" />
0b201de108b9 Uploaded
devteam
parents: 2
diff changeset
34 </inputs>
0b201de108b9 Uploaded
devteam
parents: 2
diff changeset
35 <outputs>
0b201de108b9 Uploaded
devteam
parents: 2
diff changeset
36 <data format="html" name="html_file" label="${tool.name} on ${on_string}: Webpage" />
0b201de108b9 Uploaded
devteam
parents: 2
diff changeset
37 <data format="txt" name="text_file" label="${tool.name} on ${on_string}: RawData" />
0b201de108b9 Uploaded
devteam
parents: 2
diff changeset
38 </outputs>
0b201de108b9 Uploaded
devteam
parents: 2
diff changeset
39 <tests>
0b201de108b9 Uploaded
devteam
parents: 2
diff changeset
40 <test>
0b201de108b9 Uploaded
devteam
parents: 2
diff changeset
41 <param name="input_file" value="1000gsample.fastq" />
0b201de108b9 Uploaded
devteam
parents: 2
diff changeset
42 <param name="contaminants" value="fastqc_contaminants.txt" ftype="tabular" />
0b201de108b9 Uploaded
devteam
parents: 2
diff changeset
43 <output name="html_file" file="fastqc_report.html" ftype="html" lines_diff="100"/>
0b201de108b9 Uploaded
devteam
parents: 2
diff changeset
44 <output name="text_file" file="fastqc_data.txt" ftype="txt" lines_diff="100"/>
0b201de108b9 Uploaded
devteam
parents: 2
diff changeset
45 </test>
0b201de108b9 Uploaded
devteam
parents: 2
diff changeset
46 <test>
0b201de108b9 Uploaded
devteam
parents: 2
diff changeset
47 <param name="input_file" value="1000gsample.fastq" />
0b201de108b9 Uploaded
devteam
parents: 2
diff changeset
48 <param name="limits" value="fastqc_customlimits.txt" ftype="txt" />
0b201de108b9 Uploaded
devteam
parents: 2
diff changeset
49 <output name="html_file" file="fastqc_report2.html" ftype="html" lines_diff="100"/>
0b201de108b9 Uploaded
devteam
parents: 2
diff changeset
50 <output name="text_file" file="fastqc_data2.txt" ftype="txt" lines_diff="100"/>
0b201de108b9 Uploaded
devteam
parents: 2
diff changeset
51 </test>
0b201de108b9 Uploaded
devteam
parents: 2
diff changeset
52 </tests>
0b201de108b9 Uploaded
devteam
parents: 2
diff changeset
53 <help>
0
e28c965eeed4 Imported from capsule None
devteam
parents:
diff changeset
54
e28c965eeed4 Imported from capsule None
devteam
parents:
diff changeset
55 .. class:: infomark
e28c965eeed4 Imported from capsule None
devteam
parents:
diff changeset
56
e28c965eeed4 Imported from capsule None
devteam
parents:
diff changeset
57 **Purpose**
e28c965eeed4 Imported from capsule None
devteam
parents:
diff changeset
58
e28c965eeed4 Imported from capsule None
devteam
parents:
diff changeset
59 FastQC aims to provide a simple way to do some quality control checks on raw
e28c965eeed4 Imported from capsule None
devteam
parents:
diff changeset
60 sequence data coming from high throughput sequencing pipelines.
e28c965eeed4 Imported from capsule None
devteam
parents:
diff changeset
61 It provides a modular set of analyses which you can use to give a quick
e28c965eeed4 Imported from capsule None
devteam
parents:
diff changeset
62 impression of whether your data has any problems of
e28c965eeed4 Imported from capsule None
devteam
parents:
diff changeset
63 which you should be aware before doing any further analysis.
e28c965eeed4 Imported from capsule None
devteam
parents:
diff changeset
64
e28c965eeed4 Imported from capsule None
devteam
parents:
diff changeset
65 The main functions of FastQC are:
e28c965eeed4 Imported from capsule None
devteam
parents:
diff changeset
66
e28c965eeed4 Imported from capsule None
devteam
parents:
diff changeset
67 - Import of data from BAM, SAM or FastQ files (any variant)
e28c965eeed4 Imported from capsule None
devteam
parents:
diff changeset
68 - Providing a quick overview to tell you in which areas there may be problems
e28c965eeed4 Imported from capsule None
devteam
parents:
diff changeset
69 - Summary graphs and tables to quickly assess your data
e28c965eeed4 Imported from capsule None
devteam
parents:
diff changeset
70 - Export of results to an HTML based permanent report
e28c965eeed4 Imported from capsule None
devteam
parents:
diff changeset
71 - Offline operation to allow automated generation of reports without running the interactive application
e28c965eeed4 Imported from capsule None
devteam
parents:
diff changeset
72
e28c965eeed4 Imported from capsule None
devteam
parents:
diff changeset
73
e28c965eeed4 Imported from capsule None
devteam
parents:
diff changeset
74 -----
e28c965eeed4 Imported from capsule None
devteam
parents:
diff changeset
75
e28c965eeed4 Imported from capsule None
devteam
parents:
diff changeset
76
e28c965eeed4 Imported from capsule None
devteam
parents:
diff changeset
77 .. class:: infomark
e28c965eeed4 Imported from capsule None
devteam
parents:
diff changeset
78
e28c965eeed4 Imported from capsule None
devteam
parents:
diff changeset
79 **FastQC**
e28c965eeed4 Imported from capsule None
devteam
parents:
diff changeset
80
e28c965eeed4 Imported from capsule None
devteam
parents:
diff changeset
81 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
82 Kindly acknowledge it as well as this tool if you use it.
e28c965eeed4 Imported from capsule None
devteam
parents:
diff changeset
83 FastQC incorporates the Picard-tools_ libraries for sam/bam processing.
e28c965eeed4 Imported from capsule None
devteam
parents:
diff changeset
84
e28c965eeed4 Imported from capsule None
devteam
parents:
diff changeset
85 The contaminants file parameter was borrowed from the independently developed
e28c965eeed4 Imported from capsule None
devteam
parents:
diff changeset
86 fastqcwrapper contributed to the Galaxy Community Tool Shed by J. Johnson.
1
8fae48caaf06 Uploaded form GH
devteam
parents: 0
diff changeset
87 Adaption to version 0.11.2 by T. McGowan.
0
e28c965eeed4 Imported from capsule None
devteam
parents:
diff changeset
88
e28c965eeed4 Imported from capsule None
devteam
parents:
diff changeset
89 -----
e28c965eeed4 Imported from capsule None
devteam
parents:
diff changeset
90
e28c965eeed4 Imported from capsule None
devteam
parents:
diff changeset
91 .. class:: infomark
e28c965eeed4 Imported from capsule None
devteam
parents:
diff changeset
92
e28c965eeed4 Imported from capsule None
devteam
parents:
diff changeset
93 **Inputs and outputs**
e28c965eeed4 Imported from capsule None
devteam
parents:
diff changeset
94
e28c965eeed4 Imported from capsule None
devteam
parents:
diff changeset
95 FastQC_ is the best place to look for documentation - it's very good.
e28c965eeed4 Imported from capsule None
devteam
parents:
diff changeset
96 A summary follows below for those in a tearing hurry.
e28c965eeed4 Imported from capsule None
devteam
parents:
diff changeset
97
e28c965eeed4 Imported from capsule None
devteam
parents:
diff changeset
98 This wrapper will accept a Galaxy fastq, sam or bam as the input read file to check.
e28c965eeed4 Imported from capsule None
devteam
parents:
diff changeset
99 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
100 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
101 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
102 which modules to include in the output.
0
e28c965eeed4 Imported from capsule None
devteam
parents:
diff changeset
103
1
8fae48caaf06 Uploaded form GH
devteam
parents: 0
diff changeset
104 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
105
e28c965eeed4 Imported from capsule None
devteam
parents:
diff changeset
106 - Basic Statistics
e28c965eeed4 Imported from capsule None
devteam
parents:
diff changeset
107 - Per base sequence quality
e28c965eeed4 Imported from capsule None
devteam
parents:
diff changeset
108 - Per sequence quality scores
e28c965eeed4 Imported from capsule None
devteam
parents:
diff changeset
109 - Per base sequence content
e28c965eeed4 Imported from capsule None
devteam
parents:
diff changeset
110 - Per base GC content
e28c965eeed4 Imported from capsule None
devteam
parents:
diff changeset
111 - Per sequence GC content
e28c965eeed4 Imported from capsule None
devteam
parents:
diff changeset
112 - Per base N content
e28c965eeed4 Imported from capsule None
devteam
parents:
diff changeset
113 - Sequence Length Distribution
e28c965eeed4 Imported from capsule None
devteam
parents:
diff changeset
114 - Sequence Duplication Levels
e28c965eeed4 Imported from capsule None
devteam
parents:
diff changeset
115 - Overrepresented sequences
e28c965eeed4 Imported from capsule None
devteam
parents:
diff changeset
116 - Kmer Content
e28c965eeed4 Imported from capsule None
devteam
parents:
diff changeset
117
e28c965eeed4 Imported from capsule None
devteam
parents:
diff changeset
118 All except Basic Statistics and Overrepresented sequences are plots.
e28c965eeed4 Imported from capsule None
devteam
parents:
diff changeset
119 .. _FastQC: http://www.bioinformatics.bbsrc.ac.uk/projects/fastqc/
e28c965eeed4 Imported from capsule None
devteam
parents:
diff changeset
120 .. _Picard-tools: http://picard.sourceforge.net/index.shtml
e28c965eeed4 Imported from capsule None
devteam
parents:
diff changeset
121
2
d2cf2c0c8a11 Uploaded from GH
devteam
parents: 1
diff changeset
122 </help>
d2cf2c0c8a11 Uploaded from GH
devteam
parents: 1
diff changeset
123 <citations>
d2cf2c0c8a11 Uploaded from GH
devteam
parents: 1
diff changeset
124 <citation type="bibtex">
d2cf2c0c8a11 Uploaded from GH
devteam
parents: 1
diff changeset
125 @ARTICLE{andrews_s,
d2cf2c0c8a11 Uploaded from GH
devteam
parents: 1
diff changeset
126 author = {Andrews, S.},
d2cf2c0c8a11 Uploaded from GH
devteam
parents: 1
diff changeset
127 keywords = {bioinformatics, ngs, qc},
d2cf2c0c8a11 Uploaded from GH
devteam
parents: 1
diff changeset
128 priority = {2},
d2cf2c0c8a11 Uploaded from GH
devteam
parents: 1
diff changeset
129 title = {{FastQC A Quality Control tool for High Throughput Sequence Data}},
d2cf2c0c8a11 Uploaded from GH
devteam
parents: 1
diff changeset
130 url = {http://www.bioinformatics.babraham.ac.uk/projects/fastqc/}
d2cf2c0c8a11 Uploaded from GH
devteam
parents: 1
diff changeset
131 }
d2cf2c0c8a11 Uploaded from GH
devteam
parents: 1
diff changeset
132 </citation>
d2cf2c0c8a11 Uploaded from GH
devteam
parents: 1
diff changeset
133 </citations>
0
e28c965eeed4 Imported from capsule None
devteam
parents:
diff changeset
134 </tool>