Mercurial > repos > devteam > fastqc
annotate rgFastQC.xml @ 7:ec73b7c83b2c draft
planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/fastqc commit 8918618a5ef7bdca55a31cd919efa593044a376e
| author | devteam |
|---|---|
| date | Wed, 02 Nov 2016 16:12:38 -0400 |
| parents | e8c90ad3cbf9 |
| children | 5b995cef2fbb |
| rev | line source |
|---|---|
|
7
ec73b7c83b2c
planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/fastqc commit 8918618a5ef7bdca55a31cd919efa593044a376e
devteam
parents:
6
diff
changeset
|
1 <tool id="fastqc" name="FastQC" version="0.67"> |
| 3 | 2 <description>Read Quality reports</description> |
| 3 <requirements> | |
|
6
e8c90ad3cbf9
planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/fastqc commit df4c0b0c6372e2984966e220fa42ecd8a3d370e8
devteam
parents:
5
diff
changeset
|
4 <requirement type="package" version="0.11.5">fastqc</requirement> |
| 3 | 5 </requirements> |
| 6 <stdio> | |
| 7 <exit_code range="1:" /> | |
| 8 <exit_code range=":-1" /> | |
| 9 <regex match="Error:" /> | |
| 10 <regex match="Exception:" /> | |
| 11 </stdio> | |
|
6
e8c90ad3cbf9
planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/fastqc commit df4c0b0c6372e2984966e220fa42ecd8a3d370e8
devteam
parents:
5
diff
changeset
|
12 <command><![CDATA[ |
|
e8c90ad3cbf9
planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/fastqc commit df4c0b0c6372e2984966e220fa42ecd8a3d370e8
devteam
parents:
5
diff
changeset
|
13 python '$__tool_directory__'/rgFastQC.py |
| 2 | 14 -i "$input_file" |
| 15 -d "$html_file.files_path" | |
| 16 -o "$html_file" | |
| 17 -t "$text_file" | |
| 18 -f "$input_file.ext" | |
| 19 -j "$input_file.name" | |
| 20 #if $contaminants.dataset and str($contaminants) > '' | |
| 21 -c "$contaminants" | |
| 22 #end if | |
| 23 #if $limits.dataset and str($limits) > '' | |
| 24 -l "$limits" | |
| 25 #end if | |
|
6
e8c90ad3cbf9
planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/fastqc commit df4c0b0c6372e2984966e220fa42ecd8a3d370e8
devteam
parents:
5
diff
changeset
|
26 ]]></command> |
| 3 | 27 <inputs> |
| 28 <param format="fastqsanger,fastq,bam,sam" name="input_file" type="data" label="Short read data from your current history" /> | |
|
6
e8c90ad3cbf9
planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/fastqc commit df4c0b0c6372e2984966e220fa42ecd8a3d370e8
devteam
parents:
5
diff
changeset
|
29 <param name="contaminants" type="data" format="tabular" optional="true" label="Contaminant list" |
| 3 | 30 help="tab delimited file with 2 columns: name and sequence. For example: Illumina Small RNA RT Primer CAAGCAGAAGACGGCATACGA"/> |
| 31 <param name="limits" type="data" format="txt" optional="true" label="Submodule and Limit specifing file" | |
| 32 help="a file that specifies which submodules are to be executed (default=all) and also specifies the thresholds for the each submodules warning parameter" /> | |
| 33 </inputs> | |
| 34 <outputs> | |
| 35 <data format="html" name="html_file" label="${tool.name} on ${on_string}: Webpage" /> | |
| 36 <data format="txt" name="text_file" label="${tool.name} on ${on_string}: RawData" /> | |
| 37 </outputs> | |
| 38 <tests> | |
| 39 <test> | |
| 40 <param name="input_file" value="1000gsample.fastq" /> | |
| 41 <param name="contaminants" value="fastqc_contaminants.txt" ftype="tabular" /> | |
| 42 <output name="html_file" file="fastqc_report.html" ftype="html" lines_diff="100"/> | |
| 43 <output name="text_file" file="fastqc_data.txt" ftype="txt" lines_diff="100"/> | |
| 44 </test> | |
| 45 <test> | |
| 46 <param name="input_file" value="1000gsample.fastq" /> | |
| 47 <param name="limits" value="fastqc_customlimits.txt" ftype="txt" /> | |
|
6
e8c90ad3cbf9
planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/fastqc commit df4c0b0c6372e2984966e220fa42ecd8a3d370e8
devteam
parents:
5
diff
changeset
|
48 <output name="html_file" file="fastqc_report2.html" ftype="html" compare="sim_size" delta="4096"/> |
|
e8c90ad3cbf9
planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/fastqc commit df4c0b0c6372e2984966e220fa42ecd8a3d370e8
devteam
parents:
5
diff
changeset
|
49 <output name="text_file" file="fastqc_data2.txt" ftype="txt" compare="sim_size"/> |
| 3 | 50 </test> |
|
7
ec73b7c83b2c
planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/fastqc commit 8918618a5ef7bdca55a31cd919efa593044a376e
devteam
parents:
6
diff
changeset
|
51 <test> |
|
ec73b7c83b2c
planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/fastqc commit 8918618a5ef7bdca55a31cd919efa593044a376e
devteam
parents:
6
diff
changeset
|
52 <param name="input_file" value="1000gsample.fastq.gz" /> |
|
ec73b7c83b2c
planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/fastqc commit 8918618a5ef7bdca55a31cd919efa593044a376e
devteam
parents:
6
diff
changeset
|
53 <param name="contaminants" value="fastqc_contaminants.txt" ftype="tabular" /> |
|
ec73b7c83b2c
planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/fastqc commit 8918618a5ef7bdca55a31cd919efa593044a376e
devteam
parents:
6
diff
changeset
|
54 <output name="html_file" file="fastqc_report.html" ftype="html" lines_diff="100"/> |
|
ec73b7c83b2c
planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/fastqc commit 8918618a5ef7bdca55a31cd919efa593044a376e
devteam
parents:
6
diff
changeset
|
55 <output name="text_file" file="fastqc_data.txt" ftype="txt" lines_diff="100"/> |
|
ec73b7c83b2c
planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/fastqc commit 8918618a5ef7bdca55a31cd919efa593044a376e
devteam
parents:
6
diff
changeset
|
56 </test> |
| 3 | 57 </tests> |
| 58 <help> | |
| 0 | 59 |
| 60 .. class:: infomark | |
| 61 | |
| 62 **Purpose** | |
| 63 | |
| 64 FastQC aims to provide a simple way to do some quality control checks on raw | |
|
6
e8c90ad3cbf9
planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/fastqc commit df4c0b0c6372e2984966e220fa42ecd8a3d370e8
devteam
parents:
5
diff
changeset
|
65 sequence data coming from high throughput sequencing pipelines. |
| 0 | 66 It provides a modular set of analyses which you can use to give a quick |
|
6
e8c90ad3cbf9
planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/fastqc commit df4c0b0c6372e2984966e220fa42ecd8a3d370e8
devteam
parents:
5
diff
changeset
|
67 impression of whether your data has any problems of |
| 0 | 68 which you should be aware before doing any further analysis. |
| 69 | |
| 70 The main functions of FastQC are: | |
| 71 | |
|
7
ec73b7c83b2c
planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/fastqc commit 8918618a5ef7bdca55a31cd919efa593044a376e
devteam
parents:
6
diff
changeset
|
72 - Import of data from BAM, SAM or FastQ/FastQ.gz files (any variant), |
| 0 | 73 - Providing a quick overview to tell you in which areas there may be problems |
| 74 - Summary graphs and tables to quickly assess your data | |
| 75 - Export of results to an HTML based permanent report | |
| 76 - Offline operation to allow automated generation of reports without running the interactive application | |
| 77 | |
| 78 | |
| 79 ----- | |
| 80 | |
| 81 | |
| 82 .. class:: infomark | |
| 83 | |
| 84 **FastQC** | |
| 85 | |
| 86 This is a Galaxy wrapper. It merely exposes the external package FastQC_ which is documented at FastQC_ | |
| 87 Kindly acknowledge it as well as this tool if you use it. | |
| 88 FastQC incorporates the Picard-tools_ libraries for sam/bam processing. | |
| 89 | |
| 90 The contaminants file parameter was borrowed from the independently developed | |
| 91 fastqcwrapper contributed to the Galaxy Community Tool Shed by J. Johnson. | |
| 1 | 92 Adaption to version 0.11.2 by T. McGowan. |
| 0 | 93 |
| 94 ----- | |
| 95 | |
| 96 .. class:: infomark | |
| 97 | |
| 98 **Inputs and outputs** | |
| 99 | |
|
6
e8c90ad3cbf9
planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/fastqc commit df4c0b0c6372e2984966e220fa42ecd8a3d370e8
devteam
parents:
5
diff
changeset
|
100 FastQC_ is the best place to look for documentation - it's very good. |
| 0 | 101 A summary follows below for those in a tearing hurry. |
| 102 | |
|
7
ec73b7c83b2c
planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/fastqc commit 8918618a5ef7bdca55a31cd919efa593044a376e
devteam
parents:
6
diff
changeset
|
103 This wrapper will accept a Galaxy fastq, fastq.gz, sam or bam as the input read file to check. |
| 0 | 104 It will also take an optional file containing a list of contaminants information, in the form of |
| 1 | 105 a tab-delimited file with 2 columns, name and sequence. As another option the tool takes a custom |
| 106 limits.txt file that allows setting the warning thresholds for the different modules and also specifies | |
| 107 which modules to include in the output. | |
| 0 | 108 |
| 1 | 109 The tool produces a basic text and a HTML output file that contain all of the results, including the following: |
| 0 | 110 |
| 111 - Basic Statistics | |
| 112 - Per base sequence quality | |
| 113 - Per sequence quality scores | |
| 114 - Per base sequence content | |
| 115 - Per base GC content | |
| 116 - Per sequence GC content | |
| 117 - Per base N content | |
| 118 - Sequence Length Distribution | |
| 119 - Sequence Duplication Levels | |
| 120 - Overrepresented sequences | |
| 121 - Kmer Content | |
| 122 | |
| 123 All except Basic Statistics and Overrepresented sequences are plots. | |
| 124 .. _FastQC: http://www.bioinformatics.bbsrc.ac.uk/projects/fastqc/ | |
| 125 .. _Picard-tools: http://picard.sourceforge.net/index.shtml | |
| 126 | |
| 2 | 127 </help> |
| 128 <citations> | |
| 129 <citation type="bibtex"> | |
| 130 @ARTICLE{andrews_s, | |
| 131 author = {Andrews, S.}, | |
| 132 keywords = {bioinformatics, ngs, qc}, | |
| 133 priority = {2}, | |
| 134 title = {{FastQC A Quality Control tool for High Throughput Sequence Data}}, | |
| 135 url = {http://www.bioinformatics.babraham.ac.uk/projects/fastqc/} | |
| 136 } | |
| 137 </citation> | |
| 138 </citations> | |
| 0 | 139 </tool> |