annotate rgPicardGCBiasMetrics.xml @ 4:ab1f60c26526 draft

Uploaded valid tools and complex repository dependency definition.
author devteam
date Fri, 21 Feb 2014 12:07:49 -0500
parents 9227b8c3093b
children
Ignore whitespace changes - Everywhere: Within whitespace: At end of lines:
rev   line source
0
1cd7f3b42609 Uploaded tool.
devteam
parents:
diff changeset
1 <tool name="SAM/BAM GC Bias Metrics" id="PicardGCBiasMetrics" version="1.56.0">
1cd7f3b42609 Uploaded tool.
devteam
parents:
diff changeset
2 <command interpreter="python">
2
9227b8c3093b Updated command line format per dev team standards.
devteam <devteam@galaxyproject.org>
parents: 0
diff changeset
3 picard_wrapper.py -i "${input_file}" -d "${html_file.files_path}" -t "${html_file}"
9227b8c3093b Updated command line format per dev team standards.
devteam <devteam@galaxyproject.org>
parents: 0
diff changeset
4 --windowsize "${windowsize}" --mingenomefrac "${mingenomefrac}" -n "${out_prefix}" --tmpdir "${__new_file_path__}"
9227b8c3093b Updated command line format per dev team standards.
devteam <devteam@galaxyproject.org>
parents: 0
diff changeset
5 -j "\$JAVA_JAR_PATH/CollectGcBiasMetrics.jar"
0
1cd7f3b42609 Uploaded tool.
devteam
parents:
diff changeset
6 #if $genomeSource.refGenomeSource == "history":
1cd7f3b42609 Uploaded tool.
devteam
parents:
diff changeset
7 --ref-file "${genomeSource.ownFile}"
1cd7f3b42609 Uploaded tool.
devteam
parents:
diff changeset
8 #else:
1cd7f3b42609 Uploaded tool.
devteam
parents:
diff changeset
9 --ref "${genomeSource.index.fields.path}"
1cd7f3b42609 Uploaded tool.
devteam
parents:
diff changeset
10 #end if
1cd7f3b42609 Uploaded tool.
devteam
parents:
diff changeset
11 </command>
1cd7f3b42609 Uploaded tool.
devteam
parents:
diff changeset
12 <requirements><requirement type="package" version="1.56.0">picard</requirement></requirements>
1cd7f3b42609 Uploaded tool.
devteam
parents:
diff changeset
13 <inputs>
1cd7f3b42609 Uploaded tool.
devteam
parents:
diff changeset
14 <param format="sam,bam" name="input_file" type="data" label="SAM/BAM dataset to generateGC bias metrics"
1cd7f3b42609 Uploaded tool.
devteam
parents:
diff changeset
15 help="If empty, upload or import a SAM/BAM dataset."/>
1cd7f3b42609 Uploaded tool.
devteam
parents:
diff changeset
16 <param name="out_prefix" value="Short Read GC Bias Metrics" type="text"
1cd7f3b42609 Uploaded tool.
devteam
parents:
diff changeset
17 label="Title for the output file" help="Use this remind you what the job was for." size="80" />
1cd7f3b42609 Uploaded tool.
devteam
parents:
diff changeset
18 <conditional name="genomeSource">
1cd7f3b42609 Uploaded tool.
devteam
parents:
diff changeset
19 <param name="refGenomeSource" type="select" label="Select Reference Genome">
1cd7f3b42609 Uploaded tool.
devteam
parents:
diff changeset
20 <option value="default" selected="true">Use the assigned data genome/build</option>
1cd7f3b42609 Uploaded tool.
devteam
parents:
diff changeset
21 <option value="indexed">Select a different built-in genome</option>
1cd7f3b42609 Uploaded tool.
devteam
parents:
diff changeset
22 <option value="history">Use a genome (fasta format) from my history</option>
1cd7f3b42609 Uploaded tool.
devteam
parents:
diff changeset
23 </param>
1cd7f3b42609 Uploaded tool.
devteam
parents:
diff changeset
24 <when value="default">
1cd7f3b42609 Uploaded tool.
devteam
parents:
diff changeset
25 <param name="index" type="select" label="Check the assigned reference genome" help="Galaxy thinks that the reads in you dataset were aligned against this reference. If this is not correct, use the 'Select a build-in reference genome' option of the 'Select Reference Genome' dropdown to select approprtiate Reference.">
1cd7f3b42609 Uploaded tool.
devteam
parents:
diff changeset
26 <options from_data_table="all_fasta">
4
ab1f60c26526 Uploaded valid tools and complex repository dependency definition.
devteam
parents: 2
diff changeset
27 <filter type="data_meta" ref="input_file" key="dbkey" column="1" multiple="True" separator=","/>
0
1cd7f3b42609 Uploaded tool.
devteam
parents:
diff changeset
28 <validator type="no_options" message="No reference build available for the selected input data" />
1cd7f3b42609 Uploaded tool.
devteam
parents:
diff changeset
29 </options>
1cd7f3b42609 Uploaded tool.
devteam
parents:
diff changeset
30 </param>
1cd7f3b42609 Uploaded tool.
devteam
parents:
diff changeset
31 </when>
1cd7f3b42609 Uploaded tool.
devteam
parents:
diff changeset
32 <when value="indexed">
1cd7f3b42609 Uploaded tool.
devteam
parents:
diff changeset
33 <param name="index" type="select" label="Select a built-in reference genome" help="This list contains genomes cached at this Galaxy instance. If your genome of interest is not present here request it by using 'Help' link at the top of Galaxy interface or use the 'Use a genome (fasta format) from my history' option of the 'Select Reference Genome' dropdown.">
1cd7f3b42609 Uploaded tool.
devteam
parents:
diff changeset
34 <options from_data_table="all_fasta"/>
1cd7f3b42609 Uploaded tool.
devteam
parents:
diff changeset
35 </param>
1cd7f3b42609 Uploaded tool.
devteam
parents:
diff changeset
36 </when>
1cd7f3b42609 Uploaded tool.
devteam
parents:
diff changeset
37 <when value="history">
1cd7f3b42609 Uploaded tool.
devteam
parents:
diff changeset
38 <param name="ownFile" type="data" format="fasta" metadata_name="dbkey" label="Select a reference genome from history" help="This option works best for relatively small genomes. If you are working with large human-sized genomes, send request to Galaxy team for adding your reference to this Galaxy instance by using 'Help' link at the top of Galaxy interface."/>
1cd7f3b42609 Uploaded tool.
devteam
parents:
diff changeset
39 </when>
1cd7f3b42609 Uploaded tool.
devteam
parents:
diff changeset
40 </conditional>
1cd7f3b42609 Uploaded tool.
devteam
parents:
diff changeset
41 <param name="windowsize" type="integer" label="GC minimum window size" value="100"
1cd7f3b42609 Uploaded tool.
devteam
parents:
diff changeset
42 help="The size of windows on the genome that are used to bin reads. Default value: 100."/>
1cd7f3b42609 Uploaded tool.
devteam
parents:
diff changeset
43 <param name="mingenomefrac" value="0.00001" type="float" label="Minimum Genome Fraction"
1cd7f3b42609 Uploaded tool.
devteam
parents:
diff changeset
44 help="For summary metrics, exclude GC windows that include less than this fraction of the genome. Default value: 1.0E-5." />
1cd7f3b42609 Uploaded tool.
devteam
parents:
diff changeset
45 <!--
1cd7f3b42609 Uploaded tool.
devteam
parents:
diff changeset
46
1cd7f3b42609 Uploaded tool.
devteam
parents:
diff changeset
47 Users can be enabled to set Java heap size by uncommenting this option and adding '-x "$maxheap"' to the <command> tag.
1cd7f3b42609 Uploaded tool.
devteam
parents:
diff changeset
48 If commented out the heapsize defaults to the value specified within picard_wrapper.py
1cd7f3b42609 Uploaded tool.
devteam
parents:
diff changeset
49
1cd7f3b42609 Uploaded tool.
devteam
parents:
diff changeset
50 <param name="maxheap" type="select" help="If in doubt, choose 8G and read Picard documentation please"
1cd7f3b42609 Uploaded tool.
devteam
parents:
diff changeset
51 label="Java heap size">
1cd7f3b42609 Uploaded tool.
devteam
parents:
diff changeset
52 <option value="1G">1GB: very small data</option>
1cd7f3b42609 Uploaded tool.
devteam
parents:
diff changeset
53 <option value="2G" selected="true">2GB</option>
1cd7f3b42609 Uploaded tool.
devteam
parents:
diff changeset
54 <option value="4G">4GB for larger datasets </option>
1cd7f3b42609 Uploaded tool.
devteam
parents:
diff changeset
55 <option value="8G" >8GB use if 4GB fails</option>
1cd7f3b42609 Uploaded tool.
devteam
parents:
diff changeset
56 <option value="16G">16GB - try this if 8GB fails</option>
1cd7f3b42609 Uploaded tool.
devteam
parents:
diff changeset
57 </param>
1cd7f3b42609 Uploaded tool.
devteam
parents:
diff changeset
58
1cd7f3b42609 Uploaded tool.
devteam
parents:
diff changeset
59 -->
1cd7f3b42609 Uploaded tool.
devteam
parents:
diff changeset
60
1cd7f3b42609 Uploaded tool.
devteam
parents:
diff changeset
61 </inputs>
1cd7f3b42609 Uploaded tool.
devteam
parents:
diff changeset
62 <outputs>
1cd7f3b42609 Uploaded tool.
devteam
parents:
diff changeset
63 <data format="html" name="html_file" label="${out_prefix}.html"/>
1cd7f3b42609 Uploaded tool.
devteam
parents:
diff changeset
64 </outputs>
1cd7f3b42609 Uploaded tool.
devteam
parents:
diff changeset
65 <tests>
1cd7f3b42609 Uploaded tool.
devteam
parents:
diff changeset
66 <test>
1cd7f3b42609 Uploaded tool.
devteam
parents:
diff changeset
67 <!-- Uncomment this if maxheap is enabled above
1cd7f3b42609 Uploaded tool.
devteam
parents:
diff changeset
68 <param name="maxheap" value="8G" />
1cd7f3b42609 Uploaded tool.
devteam
parents:
diff changeset
69 -->
1cd7f3b42609 Uploaded tool.
devteam
parents:
diff changeset
70 <param name="out_prefix" value="CollectGCBias" />
1cd7f3b42609 Uploaded tool.
devteam
parents:
diff changeset
71 <param name="windowsize" value="100" />
1cd7f3b42609 Uploaded tool.
devteam
parents:
diff changeset
72 <param name="mingenomefrac" value="0.00001" />
1cd7f3b42609 Uploaded tool.
devteam
parents:
diff changeset
73 <param name="refGenomeSource" value="history" />
1cd7f3b42609 Uploaded tool.
devteam
parents:
diff changeset
74 <param name="ownFile" value="picard_input_hg18.trimmed.fasta" dbkey="hg18" />
1cd7f3b42609 Uploaded tool.
devteam
parents:
diff changeset
75 <param name="input_file" value="picard_input_summary_alignment_stats.sam" ftype="sam" dbkey="hg18"/>
1cd7f3b42609 Uploaded tool.
devteam
parents:
diff changeset
76 <output name="html_file" file="picard_output_GcBias_uploaded_hg18_summary_alignment_stats.html" ftype="html" lines_diff="50"/>
1cd7f3b42609 Uploaded tool.
devteam
parents:
diff changeset
77 </test>
1cd7f3b42609 Uploaded tool.
devteam
parents:
diff changeset
78 </tests>
1cd7f3b42609 Uploaded tool.
devteam
parents:
diff changeset
79 <help>
1cd7f3b42609 Uploaded tool.
devteam
parents:
diff changeset
80
1cd7f3b42609 Uploaded tool.
devteam
parents:
diff changeset
81
1cd7f3b42609 Uploaded tool.
devteam
parents:
diff changeset
82 .. class:: infomark
1cd7f3b42609 Uploaded tool.
devteam
parents:
diff changeset
83
1cd7f3b42609 Uploaded tool.
devteam
parents:
diff changeset
84 **Summary**
1cd7f3b42609 Uploaded tool.
devteam
parents:
diff changeset
85
1cd7f3b42609 Uploaded tool.
devteam
parents:
diff changeset
86 This Galaxy tool uses Picard to report detailed metrics about reads that fall within windows of a certain GC bin on the reference genome.
1cd7f3b42609 Uploaded tool.
devteam
parents:
diff changeset
87
1cd7f3b42609 Uploaded tool.
devteam
parents:
diff changeset
88 **Picard documentation**
1cd7f3b42609 Uploaded tool.
devteam
parents:
diff changeset
89
1cd7f3b42609 Uploaded tool.
devteam
parents:
diff changeset
90 This is a Galaxy wrapper for CollectGcBiasMetrics, a part of the external package Picard-tools_.
1cd7f3b42609 Uploaded tool.
devteam
parents:
diff changeset
91
1cd7f3b42609 Uploaded tool.
devteam
parents:
diff changeset
92 .. _Picard-tools: http://www.google.com/search?q=picard+samtools
1cd7f3b42609 Uploaded tool.
devteam
parents:
diff changeset
93
1cd7f3b42609 Uploaded tool.
devteam
parents:
diff changeset
94 -----
1cd7f3b42609 Uploaded tool.
devteam
parents:
diff changeset
95
1cd7f3b42609 Uploaded tool.
devteam
parents:
diff changeset
96 .. class:: infomark
1cd7f3b42609 Uploaded tool.
devteam
parents:
diff changeset
97
1cd7f3b42609 Uploaded tool.
devteam
parents:
diff changeset
98 **Syntax**
1cd7f3b42609 Uploaded tool.
devteam
parents:
diff changeset
99
1cd7f3b42609 Uploaded tool.
devteam
parents:
diff changeset
100 - **Input** - SAM/BAM format aligned short read data in your current history
1cd7f3b42609 Uploaded tool.
devteam
parents:
diff changeset
101 - **Title** - the title to use for all output files from this job - use it for high level metadata
1cd7f3b42609 Uploaded tool.
devteam
parents:
diff changeset
102 - **Reference Genome** - Galaxy (and Picard) needs to know which genomic reference was used to generate alignemnts within the input SAM/BAM dataset. Here you have three choices:
1cd7f3b42609 Uploaded tool.
devteam
parents:
diff changeset
103
1cd7f3b42609 Uploaded tool.
devteam
parents:
diff changeset
104 - *Assigned data genome/build* - a genome specified for this dataset. If you your SAM/BAM dataset has an assigned reference genome it will be displayed below this dropdown. If it does not -> use one of the following two options.
1cd7f3b42609 Uploaded tool.
devteam
parents:
diff changeset
105 - *Select a different built-in genome* - this option will list all reference genomes presently cached at this instance of Galaxy.
1cd7f3b42609 Uploaded tool.
devteam
parents:
diff changeset
106 - *Select a reference genome from history* - alternatively you can upload your own version of reference genome into your history and use it with this option. This is however not advisable with large human-sized genomes. If your genome is large contact Galaxy team using "Help" link at the top of the interface and provide exact details on where we can download sequences you would like to use as the refenece. We will then install them as a part of locally cached genomic references.
1cd7f3b42609 Uploaded tool.
devteam
parents:
diff changeset
107
1cd7f3b42609 Uploaded tool.
devteam
parents:
diff changeset
108 - **Window Size** see Picard documentation http://picard.sourceforge.net/command-line-overview.shtml#CollectGCBiasMetrics
1cd7f3b42609 Uploaded tool.
devteam
parents:
diff changeset
109 - **Minimum Genome Fraction** See Picard documentation at http://picard.sourceforge.net/command-line-overview.shtml#CollectGCBiasMetrics
1cd7f3b42609 Uploaded tool.
devteam
parents:
diff changeset
110
1cd7f3b42609 Uploaded tool.
devteam
parents:
diff changeset
111 -----
1cd7f3b42609 Uploaded tool.
devteam
parents:
diff changeset
112
1cd7f3b42609 Uploaded tool.
devteam
parents:
diff changeset
113 .. class:: infomark
1cd7f3b42609 Uploaded tool.
devteam
parents:
diff changeset
114
1cd7f3b42609 Uploaded tool.
devteam
parents:
diff changeset
115 **Inputs, outputs, and parameters**
1cd7f3b42609 Uploaded tool.
devteam
parents:
diff changeset
116
1cd7f3b42609 Uploaded tool.
devteam
parents:
diff changeset
117 The Picard documentation (reformatted for Galaxy) says:
1cd7f3b42609 Uploaded tool.
devteam
parents:
diff changeset
118
1cd7f3b42609 Uploaded tool.
devteam
parents:
diff changeset
119 .. csv-table::
1cd7f3b42609 Uploaded tool.
devteam
parents:
diff changeset
120 :header-rows: 1
1cd7f3b42609 Uploaded tool.
devteam
parents:
diff changeset
121
1cd7f3b42609 Uploaded tool.
devteam
parents:
diff changeset
122 Option,Description
1cd7f3b42609 Uploaded tool.
devteam
parents:
diff changeset
123 "REFERENCE_SEQUENCE=File","The reference sequence fasta file. Required."
1cd7f3b42609 Uploaded tool.
devteam
parents:
diff changeset
124 "INPUT=File","The BAM or SAM file containing aligned reads. Required."
1cd7f3b42609 Uploaded tool.
devteam
parents:
diff changeset
125 "OUTPUT=File","The text file to write the metrics table to. Required."
1cd7f3b42609 Uploaded tool.
devteam
parents:
diff changeset
126 "CHART_OUTPUT=File","The PDF file to render the chart to. Required."
1cd7f3b42609 Uploaded tool.
devteam
parents:
diff changeset
127 "SUMMARY_OUTPUT=File","The text file to write summary metrics to. Default value: null."
1cd7f3b42609 Uploaded tool.
devteam
parents:
diff changeset
128 "WINDOW_SIZE=Integer","The size of windows on the genome that are used to bin reads. Default value: 100."
1cd7f3b42609 Uploaded tool.
devteam
parents:
diff changeset
129 "MINIMUM_GENOME_FRACTION=Double","For summary metrics, exclude GC windows that include less than this fraction of the genome. Default value: 1.0E-5."
1cd7f3b42609 Uploaded tool.
devteam
parents:
diff changeset
130 "CREATE_MD5_FILE=Boolean","Whether to create an MD5 digest for any BAM files created. Default value: false."
1cd7f3b42609 Uploaded tool.
devteam
parents:
diff changeset
131
1cd7f3b42609 Uploaded tool.
devteam
parents:
diff changeset
132 The output produced by the tool has the following columns::
1cd7f3b42609 Uploaded tool.
devteam
parents:
diff changeset
133
1cd7f3b42609 Uploaded tool.
devteam
parents:
diff changeset
134 1. GC: The G+C content of the reference sequence represented by this bin. Values are from 0% to 100%
1cd7f3b42609 Uploaded tool.
devteam
parents:
diff changeset
135 2. WINDOWS: The number of windows on the reference genome that have this G+C content.
1cd7f3b42609 Uploaded tool.
devteam
parents:
diff changeset
136 3. READ_STARTS: The number of reads who's start position is at the start of a window of this GC.
1cd7f3b42609 Uploaded tool.
devteam
parents:
diff changeset
137 4. MEAN_BASE_QUALITY: The mean quality (determined via the error rate) of all bases of all reads that are assigned to windows of this GC.
1cd7f3b42609 Uploaded tool.
devteam
parents:
diff changeset
138 5. NORMALIZED_COVERAGE: The ration of "coverage" in this GC bin vs. the mean coverage of all GC bins. A number of 1 represents mean coverage, a number less than one represents lower than mean coverage (e.g. 0.5 means half as much coverage as average) while a number greater than one represents higher than mean coverage (e.g. 3.1 means this GC bin has 3.1 times more reads per window than average).
1cd7f3b42609 Uploaded tool.
devteam
parents:
diff changeset
139 6. ERROR_BAR_WIDTH: The radius of error bars in this bin based on the number of observations made. For example if the normalized coverage is 0.75 and the error bar width is 0.1 then the error bars would be drawn from 0.65 to 0.85.
1cd7f3b42609 Uploaded tool.
devteam
parents:
diff changeset
140
1cd7f3b42609 Uploaded tool.
devteam
parents:
diff changeset
141 .. class:: warningmark
1cd7f3b42609 Uploaded tool.
devteam
parents:
diff changeset
142
1cd7f3b42609 Uploaded tool.
devteam
parents:
diff changeset
143 **Warning on SAM/BAM quality**
1cd7f3b42609 Uploaded tool.
devteam
parents:
diff changeset
144
1cd7f3b42609 Uploaded tool.
devteam
parents:
diff changeset
145 Many SAM/BAM files produced externally and uploaded to Galaxy do not fully conform to SAM/BAM specifications. Galaxy deals with this by using the **LENIENT**
1cd7f3b42609 Uploaded tool.
devteam
parents:
diff changeset
146 flag when it runs Picard, which allows reads to be discarded if they're empty or don't map. This appears
1cd7f3b42609 Uploaded tool.
devteam
parents:
diff changeset
147 to be the only way to deal with SAM/BAM that cannot be parsed.
1cd7f3b42609 Uploaded tool.
devteam
parents:
diff changeset
148
1cd7f3b42609 Uploaded tool.
devteam
parents:
diff changeset
149 </help>
1cd7f3b42609 Uploaded tool.
devteam
parents:
diff changeset
150 </tool>