|
0
|
1 <?xml version="1.0"?>
|
|
3
|
2 <tool id="shear_sv" name="SHEAR-SV" version="0.0.11">
|
|
0
|
3 <description>find SVs and estimate the heterogeneity levels from a BAM</description>
|
|
|
4 <requirements>
|
|
3
|
5 <requirement type="package" version="0.2.11">shear</requirement>
|
|
1
|
6 <requirement type="package" version="0.1.19">samtools</requirement>
|
|
0
|
7 <requirement type="package" version="0.6.2">bwa</requirement>
|
|
|
8 <requirement type="package" version="1.0.1">crest</requirement>
|
|
|
9 <requirement type="package" version="latest">blat_server</requirement>
|
|
|
10 <requirement type="package" version="3">cap3</requirement>
|
|
|
11 </requirements>
|
|
|
12 <!--
|
|
|
13 <version_command></version_command>
|
|
|
14 -->
|
|
|
15 <command interpreter="python">
|
|
|
16 shear_wrapper.py -j \$SHEAR_JAR_PATH/SHEAR.jar --command sv
|
|
|
17 -p $prefix ## used in gerenating ouput file names
|
|
|
18 -b $bamfile
|
|
|
19 #if $genomeSource.refGenomeSource == 'indexed':
|
|
|
20 -f $genomeSource.ref_fastas.fields.path
|
|
|
21 -i $genomeSource.bwa_indices.fields.path
|
|
|
22 -t $genomeSource.twobit_indices.fields.path
|
|
|
23 #elif $genomeSource.refGenomeSource == 'svidx':
|
|
|
24 -f $genomeSource.svidx.extra_files_path/${genomeSource.svidx.metadata.base_name}.fa
|
|
|
25 -i $genomeSource.svidx.extra_files_path/${genomeSource.svidx.metadata.base_name}.fa
|
|
|
26 -t $genomeSource.svidx.extra_files_path/${genomeSource.svidx.metadata.base_name}.2bit
|
|
|
27 #else:
|
|
|
28 -f $genomeSource.ref_fasta
|
|
|
29 #if $genomeSource.save_svidx:
|
|
|
30 -D $sv_idx.extra_files_path
|
|
|
31 #end if
|
|
|
32 #end if
|
|
|
33 #if $region and $region.__str__.strip() != '':
|
|
|
34 -r $region
|
|
|
35 #end if
|
|
|
36 $sv_only
|
|
|
37 </command>
|
|
|
38 <inputs>
|
|
|
39 <param name="bamfile" type="data" format="bam" label="BAM alignment file containing the input sequences to the assembly."/>
|
|
|
40 <param name="prefix" type="hidden" value="shear_sv" label="Prefix for all generated files"/>
|
|
|
41 <!--
|
|
|
42 <param name="prefix" type="text" value="shear_sv" label="Prefix for all generated files">
|
|
|
43 <validator type="regex" message="Prefix should start with a letter and contain only letter, digit, and '_' or '-' characters">[a-zA-Z0-9][_a-zA-Z0-9-]*</validator>
|
|
|
44 </param>
|
|
|
45 -->
|
|
|
46 <!-- reference data -->
|
|
|
47 <conditional name="genomeSource">
|
|
|
48 <param name="refGenomeSource" type="select" label="Will you select a reference genome from your history or use a cached file?">
|
|
|
49 <option value="indexed" selected="true">Use a cached reference genome</option>
|
|
|
50 <option value="history">Use fasta from the history</option>
|
|
|
51 <option value="svidx">Use SHEAR sv index from the history</option>
|
|
|
52 </param>
|
|
|
53 <when value="indexed">
|
|
|
54 <param name="ref_fastas" type="select" label="Select a reference genome fasta">
|
|
|
55 <options from_data_table="all_fasta">
|
|
|
56 <filter type="sort_by" column="2" />
|
|
|
57 <validator type="no_options" message="No reference fasta files are available" />
|
|
|
58 </options>
|
|
|
59 </param>
|
|
|
60 <param name="twobit_indices" type="select" label="Select the reference genome 2bit">
|
|
|
61 <options from_data_table="twobit">
|
|
|
62 <filter type="sort_by" column="0" />
|
|
|
63 <!--
|
|
|
64 <filter type="data_meta" ref="ref_fastas" key="dbkey" column="0" />
|
|
|
65 -->
|
|
|
66 <validator type="no_options" message="No indexes are available" />
|
|
|
67 </options>
|
|
|
68 </param>
|
|
|
69 <param name="bwa_indices" type="select" label="Select the reference genome bwa indices">
|
|
|
70 <options from_data_table="bwa_indexes">
|
|
|
71 <filter type="sort_by" column="2" />
|
|
|
72 <!--
|
|
|
73 <filter type="data_meta" ref="ref_fastas" key="dbkey" column="0" />
|
|
|
74 -->
|
|
|
75 <validator type="no_options" message="No indexes are available" />
|
|
|
76 </options>
|
|
|
77 </param>
|
|
|
78 </when>
|
|
|
79 <when value="history">
|
|
|
80 <param name="ref_fasta" type="data" format="fasta" label="Select a reference from history" />
|
|
|
81 <param name="save_svidx" type="boolean" truevalue="yes" falsevalue="no" label="Save sv generated reference indexes"/>
|
|
|
82 </when>
|
|
|
83 <when value="svidx">
|
|
|
84 <param name="svidx" type="data" format="shear.svidx" label="Select a reference from history" />
|
|
|
85 </when>
|
|
|
86 </conditional>
|
|
|
87 <param name="region" type="text" value="" optional="true" label="Region of the input alignment to analyze">
|
|
|
88 <help>"chr1" for full chromosome or "chr1:10000-15000" for a particular region, including endpoints).
|
|
|
89 Coordinates are 1-based.
|
|
|
90 </help>
|
|
|
91 <validator type="regex" message="format: chr1:100-200">^\w+(:\d+-\d+)?$</validator>
|
|
|
92 </param>
|
|
|
93 <param name="sv_only" type="boolean" truevalue="--sv-only" falsevalue="" checked="false" label="SV Only prediction mode."
|
|
|
94 help="Will skip SNP/INDEL prediction and only return *.sdi and *.report results for SVs."/>
|
|
|
95 </inputs>
|
|
|
96 <stdio>
|
|
|
97 <exit_code range="1:" level="fatal" description="Error" />
|
|
|
98 </stdio>
|
|
|
99 <outputs>
|
|
|
100 <data format="txt" name="report_snpindel" label="${tool.name} on ${on_string}: ${prefix}.snpindel.report" from_work_dir="shear_sv.snpindel.report">
|
|
|
101 <filter>sv_only == False</filter>
|
|
|
102 </data>
|
|
|
103 <data format="txt" name="report_sv" label="${tool.name} on ${on_string}: ${prefix}.sv.report" from_work_dir="shear_sv.sv.report"/>
|
|
|
104 <data format="txt" name="report_all" label="${tool.name} on ${on_string}: ${prefix}.all.report" from_work_dir="shear_sv.all.report">
|
|
|
105 <filter>sv_only == False</filter>
|
|
|
106 </data>
|
|
|
107 <data format="shear.sdi" name="sdi_snpindel" label="${tool.name} on ${on_string}: ${prefix}.snpindel.sdi" from_work_dir="shear_sv.snpindel.sdi">
|
|
|
108 <filter>sv_only == False</filter>
|
|
|
109 </data>
|
|
|
110 <data format="shear.sdi" name="sdi_sv" label="${tool.name} on ${on_string}: ${prefix}.sv.sdi" from_work_dir="shear_sv.sv.sdi"/>
|
|
|
111 <data format="shear.sdi" name="sdi_all" label="${tool.name} on ${on_string}: ${prefix}.all.sdi" from_work_dir="shear_sv.all.sdi">
|
|
|
112 <filter>sv_only == False</filter>
|
|
|
113 </data>
|
|
|
114 <data format="shear.svidx" name="sv_idx" label="${tool.name} on ${on_string}: ${prefix}.svidx">
|
|
|
115 <filter>genomeSource['refGenomeSource'] == 'history' and genomeSource['save_svidx'] == True</filter>
|
|
|
116 </data>
|
|
|
117 </outputs>
|
|
|
118 <tests>
|
|
|
119 <test>
|
|
|
120 <param name="prefix" value="shear_test" />
|
|
|
121 <param name="bamfile" value="simulated-data.bam" ftype="bam" />
|
|
|
122 <param name="refGenomeSource" value="history"/>
|
|
|
123 <param name="ref_fasta" value="syn.fa" ftype="fasta" />
|
|
|
124 <param name="save_svidx" value="false"/>
|
|
|
125 <param name="sv_only" value="true"/>
|
|
|
126 <output name="sdi_sv" file="shear_sv.sdi"/>
|
|
|
127 <output name="report_sv" file="shear_sv.report"/>
|
|
|
128 </test>
|
|
|
129 </tests>
|
|
|
130 <help>
|
|
|
131 SHEAR-SV will process a BAM alignment file to find SVs and estimate the
|
|
|
132 heterogeneity level of those SVs. It will output a *.report file reporing the
|
|
|
133 SVs and their heterogeneity levels, and it will output a *.sdi file that can be
|
|
|
134 used for SHEAR-Assemble to reconstruct the new genome.
|
|
2
|
135
|
|
|
136 Please cite the following article:
|
|
|
137
|
|
|
138 Landman SR, Hwang TH, Silverstein KAT, Li Y, Dehm SM, Steinbach M, and Kumar V. SHEAR: sample heterogeneity estimation and assembly by reference. BMC Genomics 2014, 15:84.
|
|
|
139
|
|
0
|
140 </help>
|
|
|
141 </tool>
|
