Mercurial > repos > drosofff > lumpy

comparison lumpy.xml @ 8:bed99920f656 draft

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/master/tools/lumpy commit 8375ddf784506b68d28bc9e6224648fafa796d9f
author drosofff
date Sat, 10 Dec 2016 20:27:28 -0500
parents e8faf45e6430
children ee2ee0b9de52
comparison
equal deleted inserted replaced
7:e8faf45e6430 8:bed99920f656
6 <requirement type="package" version="1.11.2">numpy</requirement> 6 <requirement type="package" version="1.11.2">numpy</requirement>
7 </requirements> 7 </requirements>
8 <stdio> 8 <stdio>
9 <exit_code range="1:" level="fatal" description="Tool exception" /> 9 <exit_code range="1:" level="fatal" description="Tool exception" />
10 </stdio> 10 </stdio>
11 <version_command>lumpy --version</version_command>
12 <command detect_errors="exit_code"><![CDATA[ 11 <command detect_errors="exit_code"><![CDATA[
13 #if $analysis_type.analysis_type_list == "one_sample": 12 #if $analysis_type.analysis_type_list == "one_sample":
14 ln -f -s '$analysis_type.input_file' input.bam && 13 ln -f -s '$analysis_type.input_file' input.bam &&
15 #else: 14 #else:
16 ln -f -s '$analysis_type.input_file' input.A.bam && 15 ln -f -s '$analysis_type.input_file' input.A.bam &&
22 #if $seq_method.seq_method_list == "paired-end": 21 #if $seq_method.seq_method_list == "paired-end":
23 samtools view -b -F 1294 input.bam > "input.discordants.unsorted.bam" && 22 samtools view -b -F 1294 input.bam > "input.discordants.unsorted.bam" &&
24 samtools view -h input.bam | python $__tool_directory__/extractSplitReads_BwaMem.py -i stdin | samtools view -Sb - > "input.splitters.unsorted.bam" && 23 samtools view -h input.bam | python $__tool_directory__/extractSplitReads_BwaMem.py -i stdin | samtools view -Sb - > "input.splitters.unsorted.bam" &&
25 samtools sort input.discordants.unsorted.bam > input.discordants.bam && 24 samtools sort input.discordants.unsorted.bam > input.discordants.bam &&
26 samtools sort input.splitters.unsorted.bam > input.splitters.bam && 25 samtools sort input.splitters.unsorted.bam > input.splitters.bam &&
27 samtools view -r readgroup input.bam 26 samtools view input.bam
28 |tail -n +1 27 |tail -n +1
29 |python $__tool_directory__/pairend_distro.py -r 101 -X 4 -N $seq_method.additional_params.samplingValue -o input.lib.histo > meandev.txt && 28 |python $__tool_directory__/pairend_distro.py -r $readLength -X 4 -N $seq_method.additional_params.samplingValue -o input.lib.histo > meandev.txt &&
30 mean=\$(cat meandev.txt | sed s/mean:// | sed -r s/stdev:.+//) && 29 mean=\$(cat meandev.txt | sed s/mean:// | sed -r s/stdev:.+//) &&
31 stdev=\$(cat meandev.txt | sed -r s/mean:.+stdev://) && 30 stdev=\$(cat meandev.txt | sed -r s/mean:.+stdev://) &&
32 lumpy -mw $seq_method.additional_params.mw -tt $seq_method.additional_params.tt 31 lumpy -mw $seq_method.additional_params.mw -tt $seq_method.additional_params.tt
33 #if $output_format == "BEDPE": 32 #if $output_format == "BEDPE":
34 -b 33 -b
35 #end if 34 #end if
36 -pe id:input.bam,bam_file:input.discordants.bam,histo_file:input.lib.histo,mean:"\$mean",stdev:"\$stdev",read_length:$analysis_type.readLength,min_non_overlap:$seq_method.additional_params.min_non_overlap,discordant_z:$seq_method.additional_params.discordant_z,back_distance:$seq_method.additional_params.back_distance,weight:$seq_method.additional_params.weight,min_mapping_threshold:$seq_method.additional_params.min_mapping_threshold 35 -pe id:input.bam,bam_file:input.discordants.bam,histo_file:input.lib.histo,mean:"\$mean",stdev:"\$stdev",read_length:$analysis_type.readLength,min_non_overlap:$seq_method.additional_params.min_non_overlap,discordant_z:$seq_method.additional_params.discordant_z,back_distance:$seq_method.additional_params.back_distance,weight:$seq_method.additional_params.weight,min_mapping_threshold:$seq_method.additional_params.min_mapping_threshold
37 -sr id:input.bam,bam_file:input.splitters.bam,back_distance:$seq_method.additional_params.back_distance,weight:$seq_method.additional_params.weight,min_mapping_threshold:$seq_method.additional_params.min_mapping_threshold > output.vcf && 36 -sr id:input.bam,bam_file:input.splitters.bam,back_distance:$seq_method.additional_params.back_distance,weight:$seq_method.additional_params.weight,min_mapping_threshold:$seq_method.additional_params.min_mapping_threshold > output.vcf &&
38 mv input.discordants.bam $discordants && 37 mv input.discordants.bam $discordants &&
39 mv input.splitters.bam $splits && 38 mv input.splitters.bam $splits &&
40 mv input.lib.histo $histogram && 39 mv input.lib.histo $histogram &&
41 mv output.vcf $vcf_call && 40 mv output.vcf $vcf_call &&
49 #end if 48 #end if
50 -sr id:input.bam,bam_file:input.splitters.unsorted.bam,back_distance:$seq_method.additional_params.back_distance,weight:$seq_method.additional_params.weight,min_mapping_threshold:$seq_method.additional_params.min_mapping_threshold > output.vcf && 49 -sr id:input.bam,bam_file:input.splitters.unsorted.bam,back_distance:$seq_method.additional_params.back_distance,weight:$seq_method.additional_params.weight,min_mapping_threshold:$seq_method.additional_params.min_mapping_threshold > output.vcf &&
51 mv input.splitters.unsorted.bam $splits && 50 mv input.splitters.unsorted.bam $splits &&
52 mv output.vcf $vcf_call 51 mv output.vcf $vcf_call
53 #end if 52 #end if
54 53
55 #else: 54 #else:
56 55
57 #if $seq_method.seq_method_list == "paired-end": 56 #if $seq_method.seq_method_list == "paired-end":
58 samtools view -b -F 1294 input.A.bam > "input.A.discordants.unsorted.bam" && 57 samtools view -b -F 1294 input.A.bam > "input.A.discordants.unsorted.bam" &&
59 samtools view -b -F 1294 input.B.bam > "input.B.discordants.unsorted.bam" && 58 samtools view -b -F 1294 input.B.bam > "input.B.discordants.unsorted.bam" &&
61 samtools view -h input.B.bam | python $__tool_directory__/extractSplitReads_BwaMem.py -i stdin | samtools view -Sb - > "input.B.splitters.unsorted.bam" && 60 samtools view -h input.B.bam | python $__tool_directory__/extractSplitReads_BwaMem.py -i stdin | samtools view -Sb - > "input.B.splitters.unsorted.bam" &&
62 samtools sort input.A.discordants.unsorted.bam > input.A.discordants.bam && 61 samtools sort input.A.discordants.unsorted.bam > input.A.discordants.bam &&
63 samtools sort input.B.discordants.unsorted.bam > input.B.discordants.bam && 62 samtools sort input.B.discordants.unsorted.bam > input.B.discordants.bam &&
64 samtools sort input.A.splitters.unsorted.bam > input.A.splitters.bam && 63 samtools sort input.A.splitters.unsorted.bam > input.A.splitters.bam &&
65 samtools sort input.B.splitters.unsorted.bam > input.B.splitters.bam && 64 samtools sort input.B.splitters.unsorted.bam > input.B.splitters.bam &&
66 samtools view -r readgroup input.A.bam 65 samtools view input.A.bam
67 |tail -n +1 66 |tail -n +1
68 |python $__tool_directory__/pairend_distro.py -r 101 -X 4 -N $seq_method.additional_params.samplingValue -o input.A.lib.histo > meandevA.txt && 67 |python $__tool_directory__/pairend_distro.py -r $readLength -X 4 -N $seq_method.additional_params.samplingValue -o input.A.lib.histo > meandevA.txt &&
69 samtools view -r readgroup input.B.bam 68 samtools view input.B.bam
70 |tail -n +1 69 |tail -n +1
71 |python $__tool_directory__/pairend_distro.py -r 101 -X 4 -N $seq_method.additional_params.samplingValue -o input.B.lib.histo > meandevB.txt && 70 |python $__tool_directory__/pairend_distro.py -r $readLengthB -X 4 -N $seq_method.additional_params.samplingValue -o input.B.lib.histo > meandevB.txt &&
72 meanA=\$(cat meandevA.txt | sed s/mean:// | sed -r s/stdev:.+//) && 71 meanA=\$(cat meandevA.txt | sed s/mean:// | sed -r s/stdev:.+//) &&
73 meanB=\$(cat meandevB.txt | sed s/mean:// | sed -r s/stdev:.+//) && 72 meanB=\$(cat meandevB.txt | sed s/mean:// | sed -r s/stdev:.+//) &&
74 stdevA=\$(cat meandevA.txt | sed -r s/mean:.+stdev://) && 73 stdevA=\$(cat meandevA.txt | sed -r s/mean:.+stdev://) &&
75 stdevB=\$(cat meandevB.txt | sed -r s/mean:.+stdev://) && 74 stdevB=\$(cat meandevB.txt | sed -r s/mean:.+stdev://) &&
76 lumpy -mw $seq_method.additional_params.mw -tt $seq_method.additional_params.tt 75 <<<<<<< HEAD
77 #if $output_format == "BEDPE": 76 lumpy -mw $seq_method.additional_params.mw -tt $seq_method.additional_params.tt
78 -b 77 #if $output_format == "BEDPE":
79 #end if 78 -b
80 -pe id:inputA.bam,bam_file:input.A.discordants.bam,histo_file:input.A.lib.histo,mean:"\$meanA",stdev:"\$stdevA",read_length:$analysis_type.readLength,min_non_overlap:$seq_method.additional_params.min_non_overlap,discordant_z:$seq_method.additional_params.discordant_z,back_distance:$seq_method.additional_params.back_distance,weight:$seq_method.additional_params.weight,min_mapping_threshold:$seq_method.additional_params.min_mapping_threshold 79 #end if
81 -pe id:inputB.bam,bam_file:input.B.discordants.bam,histo_file:input.B.lib.histo,mean:"\$meanB",stdev:"\$stdevA",read_length:$analysis_type.readLengthB,min_non_overlap:$seq_method.additional_params.min_non_overlap,discordant_z:$seq_method.additional_params.discordant_z,back_distance:$seq_method.additional_params.back_distance,weight:$seq_method.additional_params.weight,min_mapping_threshold:$seq_method.additional_params.min_mapping_threshold 80 -pe id:inputA.bam,bam_file:input.A.discordants.bam,histo_file:input.A.lib.histo,mean:"\$meanA",stdev:"\$stdevA",read_length:$analysis_type.readLength,min_non_overlap:$seq_method.additional_params.min_non_overlap,discordant_z:$seq_method.additional_params.discordant_z,back_distance:$seq_method.additional_params.back_distance,weight:$seq_method.additional_params.weight,min_mapping_threshold:$seq_method.additional_params.min_mapping_threshold
81 -pe id:inputB.bam,bam_file:input.B.discordants.bam,histo_file:input.B.lib.histo,mean:"\$meanB",stdev:"\$stdevA",read_length:$analysis_type.readLengthB,min_non_overlap:$seq_method.additional_params.min_non_overlap,discordant_z:$seq_method.additional_params.discordant_z,back_distance:$seq_method.additional_params.back_distance,weight:$seq_method.additional_params.weight,min_mapping_threshold:$seq_method.additional_params.min_mapping_threshold
82 -sr id:inputA.bam,bam_file:input.A.splitters.bam,back_distance:$seq_method.additional_params.back_distance,weight:$seq_method.additional_params.weight,min_mapping_threshold:$seq_method.additional_params.min_mapping_threshold 82 -sr id:inputA.bam,bam_file:input.A.splitters.bam,back_distance:$seq_method.additional_params.back_distance,weight:$seq_method.additional_params.weight,min_mapping_threshold:$seq_method.additional_params.min_mapping_threshold
83 -sr id:inputB.bam,bam_file:input.B.splitters.bam,back_distance:$seq_method.additional_params.back_distance,weight:$seq_method.additional_params.weight,min_mapping_threshold:$seq_method.additional_params.min_mapping_threshold > output.vcf && 83 -sr id:inputB.bam,bam_file:input.B.splitters.bam,back_distance:$seq_method.additional_params.back_distance,weight:$seq_method.additional_params.weight,min_mapping_threshold:$seq_method.additional_params.min_mapping_threshold > output.vcf &&
84 mv input.A.discordants.bam $discordants && 84 mv input.A.discordants.bam $discordants &&
85 mv input.B.discordants.bam $discordantsB && 85 mv input.B.discordants.bam $discordantsB &&
86 mv input.A.splitters.bam $splits && 86 mv input.A.splitters.bam $splits &&
102 mv input.A.splitters.unsorted.bam $splits && 102 mv input.A.splitters.unsorted.bam $splits &&
103 mv input.B.splitters.unsorted.bam $splitsB && 103 mv input.B.splitters.unsorted.bam $splitsB &&
104 mv output.vcf $vcf_call 104 mv output.vcf $vcf_call
105 #end if 105 #end if
106 106
107 107
108 #end if 108 #end if
109 109
110 ]]></command> 110 ]]></command>
111 <!-- basic error handling --> 111 <!-- basic error handling -->
112 <inputs> 112 <inputs>
150 <param name="back_distance" value="10" type="integer" label="back_distance" help="e.g. 10" /> 150 <param name="back_distance" value="10" type="integer" label="back_distance" help="e.g. 10" />
151 <param name="weight" value="1" type="integer" label="weight" help="e.g. 1" /> 151 <param name="weight" value="1" type="integer" label="weight" help="e.g. 1" />
152 <param name="min_mapping_threshold" value="20" type="integer" label="min_mapping_threshold" help="e.g. 20" /> 152 <param name="min_mapping_threshold" value="20" type="integer" label="min_mapping_threshold" help="e.g. 20" />
153 </section> 153 </section>
154 </when> 154 </when>
155 155
156 </conditional> 156 </conditional>
157 <param help="get variant calling in vcf or BEDPE format" label="variant calling format" name="output_format" type="select"> 157 <param help="get variant calling in vcf or BEDPE format" label="variant calling format" name="output_format" type="select">
158 <option selected="True" value="vcf">vcf</option> 158 <option selected="True" value="vcf">vcf</option>
159 <option value="BEDPE">BEDPE</option> 159 <option value="BEDPE">BEDPE</option>
160 </param> 160 </param>
199 <output name="vcf_call" file="output.vcf" ftype="vcf"/> 199 <output name="vcf_call" file="output.vcf" ftype="vcf"/>
200 </test> 200 </test>
201 </tests> 201 </tests>
202 202
203 <help> 203 <help>
204 204
205 **Input(s)** 205 **Input(s)**
206 206
207 *One sample* : lumpy search structural variations inside a single sequencing dataset 207 *One sample* : lumpy search structural variations inside a single sequencing dataset
208 208
209 *Two samples*: lumpy search structural variations inside and across two sequencing datasets from two samples 209 *Two samples*: lumpy search structural variations inside and across two sequencing datasets from two samples
219 *Single-read sequencing*: Only one end of library fragment has been sequenced, resulting in a single sequencing dataset. Under these conditions, evidences of structural variation are obtained only from splited read alignments 219 *Single-read sequencing*: Only one end of library fragment has been sequenced, resulting in a single sequencing dataset. Under these conditions, evidences of structural variation are obtained only from splited read alignments
220 220
221 *Read length*: The length of the sequencing reads in the library. This information is required only for paired-end sequencing data 221 *Read length*: The length of the sequencing reads in the library. This information is required only for paired-end sequencing data
222 222
223 *Additional options*: refer to lumpy-sv_ documentation and the publication (doi 10.1186/gb-2014-15-6-r84) 223 *Additional options*: refer to lumpy-sv_ documentation and the publication (doi 10.1186/gb-2014-15-6-r84)
224 224
225 **lumpy-sv manual** 225 **lumpy-sv manual**
226 226
227 Read the lumpy-sv_ documentation for details on using lumpy. 227 Read the lumpy-sv_ documentation for details on using lumpy.
228 228
229 .. _lumpy-sv: https://github.com/arq5x/lumpy-sv 229 .. _lumpy-sv: https://github.com/arq5x/lumpy-sv
269 weight:<sample weight>, 269 weight:<sample weight>,
270 read_group:<string> 270 read_group:<string>
271 271
272 -bedpe bedpe_file:<bedpe file>, 272 -bedpe bedpe_file:<bedpe file>,
273 id:<sample name>, 273 id:<sample name>,
274 weight:<sample weight> 274 weight:<sample weight>
275 ]]> 275 ]]>
276 </help> 276 </help>
277 277
278 <citations> 278 <citations>
279 <citation type="doi">10.1186/gb-2014-15-6-r84</citation> 279 <citation type="doi">10.1186/gb-2014-15-6-r84</citation>
280 </citations> 280 </citations>