|
5
|
1 <tool name="CollectGcBiasMetrics" id="picard_CollectGcBiasMetrics" version="1.126.0">
|
|
|
2 <description>charts the GC bias metrics</description>
|
|
|
3 <requirements>
|
|
|
4 <requirement type="package" version="1.126.0">picard</requirement>
|
|
|
5 </requirements>
|
|
|
6
|
|
|
7 <macros>
|
|
|
8 <import>picard_macros.xml</import>
|
|
|
9 </macros>
|
|
|
10
|
|
|
11 <command>
|
|
|
12 @java_options@
|
|
|
13 ##set up input files
|
|
|
14
|
|
|
15 #set $reference_fasta_filename = "localref.fa"
|
|
|
16
|
|
|
17 #if str( $reference_source.reference_source_selector ) == "history":
|
|
|
18 ln -s "${reference_source.ref_file}" "${reference_fasta_filename}" &&
|
|
|
19 #else:
|
|
|
20 #set $reference_fasta_filename = str( $reference_source.ref_file.fields.path )
|
|
|
21 #end if
|
|
|
22
|
|
|
23 java -jar \$JAVA_JAR_PATH/picard.jar
|
|
|
24 CollectGcBiasMetrics
|
|
|
25 INPUT="${inputFile}"
|
|
|
26 OUTPUT="${outFile}"
|
|
|
27 CHART_OUTPUT="${pdfFile}"
|
|
|
28 SUMMARY_OUTPUT="${summaryFile}"
|
|
|
29 WINDOW_SIZE="${window_size}"
|
|
|
30 MINIMUM_GENOME_FRACTION="${minimum_genome_fraction}"
|
|
|
31 IS_BISULFITE_SEQUENCED="${is_bisulfite_sequenced}"
|
|
|
32 REFERENCE_SEQUENCE="${reference_fasta_filename}"
|
|
|
33 ASSUME_SORTED="${assume_sorted}"
|
|
|
34
|
|
|
35 VALIDATION_STRINGENCY="${validation_stringency}"
|
|
|
36 QUIET=true
|
|
|
37 VERBOSITY=ERROR
|
|
|
38
|
|
|
39 </command>
|
|
|
40 <inputs>
|
|
|
41 <param format="sam,bam" name="inputFile" type="data" label="Select SAM/BAM dataset or dataset collection" help="If empty, upload or import a SAM/BAM dataset."/>
|
|
|
42 <conditional name="reference_source">
|
|
|
43 <param name="reference_source_selector" type="select" label="Load reference genome from">
|
|
|
44 <option value="cached">Local cache</option>
|
|
|
45 <option value="history">History</option>
|
|
|
46 </param>
|
|
|
47 <when value="cached">
|
|
|
48 <param name="ref_file" type="select" label="Using reference genome" help="REFERENCE_SEQUENCE">
|
|
|
49 <options from_data_table="all_fasta">
|
|
|
50 </options>
|
|
|
51 <validator type="no_options" message="A built-in reference genome is not available for the build associated with the selected input file"/>
|
|
|
52 </param>
|
|
|
53 </when>
|
|
|
54 <when value="history">
|
|
|
55 <param name="ref_file" type="data" format="fasta" label="Use the folloing dataset as the reference sequence" help="REFERENCE_SEQUENCE; You can upload a FASTA sequence to the history and use it as reference" />
|
|
|
56 </when>
|
|
|
57 </conditional>
|
|
|
58 <param name="window_size" type="integer" value="100" label="The size of windows on the genome that are used to bin reads" help="WINDOW_SIZE; default=100"/>
|
|
|
59 <param name="minimum_genome_fraction" type="float" value="0.00005" label="For summary metrics, exclude GC windows that include less than this fraction of the genome" help="MINIMUM_GENOME_FRACTION; default=0.0005"/>
|
|
|
60 <param name="is_bisulfite_sequenced" type="boolean" label="Calculate the base distribution over PF (passing filtering) reads only" checked="true" truevalue="true" falsevalue="false" help="PF_READS_ONLY"/>
|
|
|
61 <param name="assume_sorted" type="boolean" label="Assume the input file is already sorted" checked="true" truevalue="true" falsevalue="false" help="ASSUME_SORTED"/>
|
|
|
62
|
|
|
63 <expand macro="VS" />
|
|
|
64
|
|
|
65 </inputs>
|
|
|
66
|
|
|
67 <outputs>
|
|
|
68 <data format="tabular" name="summaryFile" label="${tool.name} on ${on_string}: Summary stats"/>
|
|
|
69 <data format="tabular" name="outFile" label="${tool.name} on ${on_string}: Summary data"/>
|
|
|
70 <data format="pdf" name="pdfFile" label="${tool.name} on ${on_string}: Chart PDF"/>
|
|
|
71 </outputs>
|
|
|
72
|
|
|
73 <tests>
|
|
|
74 <test>
|
|
|
75 <param name="window_size" value="100" />
|
|
|
76 <param name="minimum_genome_fraction" value="0.00005" />
|
|
|
77 <param name="assume_sorted" value="true" />
|
|
|
78 <param name="is_bisulfite_sequenced" value="true" />
|
|
|
79 <param name="reference_source_selector" value="history" />
|
|
|
80 <param name="ref_file" value="picard_CollectGcBiasMetrics_ref.fa" />
|
|
|
81 <param name="inputFile" value="picard_CollectGcBiasMetrics.bam" ftype="bam" />
|
|
|
82 <output name="outFile" file="picard_CollectGcBiasMetrics_test1.tab" ftype="tabular" lines_diff="4"/>
|
|
|
83 </test>
|
|
|
84 </tests>
|
|
|
85
|
|
|
86 <stdio>
|
|
|
87 <exit_code range="1:" level="fatal"/>
|
|
|
88 </stdio>
|
|
|
89
|
|
|
90 <help>
|
|
|
91
|
|
|
92 .. class:: infomark
|
|
|
93
|
|
|
94 **Purpose**
|
|
|
95
|
|
|
96 Program to chart the nucleotide distribution per cycle in a SAM or BAM file.
|
|
|
97
|
|
|
98 @dataset_collections@
|
|
|
99
|
|
|
100 @description@
|
|
|
101
|
|
|
102 ALIGNED_READS_ONLY=Boolean If set to true, calculate the base distribution over aligned reads only. Default value:
|
|
|
103 false. Possible values: {true, false}
|
|
|
104
|
|
|
105 PF_READS_ONLY=Boolean If set to true calculate the base distribution over PF reads only. Default value: false.
|
|
|
106 This option can be set to 'null' to clear the default value. Possible values: {true,
|
|
|
107 false}
|
|
|
108
|
|
|
109 ASSUME_SORTED=Boolean
|
|
|
110 AS=Boolean If true (default), then the sort order in the header file will be ignored. Default: True
|
|
|
111
|
|
|
112 @more_info@
|
|
|
113
|
|
|
114 </help>
|
|
|
115 </tool>
|
|
|
116
|
|
|
117
|
