Mercurial > repos > artbio > lumpy_smoove

comparison lumpy_smoove.xml @ 3:65b400409455 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_smoove commit c52939d44f8e8287ad4068949daadf616879f008"
author artbio
date Wed, 26 Aug 2020 12:24:07 -0400
parents 49a8a327cc72
children 49da975ba395
comparison
equal deleted inserted replaced
2:49a8a327cc72 3:65b400409455
1 <tool id="lumpy_smoove" name="lumpy_smoove" version="0.4.0"> 1 <tool id="lumpy_smoove" name="lumpy_smoove" version="0.5.0">
2 <description>find structural variants using the smoove workflow</description> 2 <description>find structural variants using the smoove workflow</description>
3 <macros> 3 <macros>
4 <import>macro_lumpy_smoove.xml</import> 4 <import>macro_lumpy_smoove.xml</import>
5 </macros> 5 </macros>
6 <requirements> 6 <requirements>
12 <command detect_errors="exit_code"><![CDATA[ 12 <command detect_errors="exit_code"><![CDATA[
13 @pipefail@ 13 @pipefail@
14 @set_fasta_index@ 14 @set_fasta_index@
15 ln -s $normal_bam normal.bam && 15 ln -s $normal_bam normal.bam &&
16 ln -s $tumor_bam tumor.bam && 16 ln -s $tumor_bam tumor.bam &&
17 17 samtools index -@ \${GALAXY_SLOTS:-4} normal.bam &&
18 smoove call -x --name output 18 samtools index -@ \${GALAXY_SLOTS:-4} tumor.bam &&
19
20 smoove call --name output
19 #if $set_exclusion.choices=="yes": 21 #if $set_exclusion.choices=="yes":
20 --exclude $bedmask 22 --exclude $bedmask
21 #end if 23 #end if
22 --fasta reference.fa -p \${GALAXY_SLOTS:-4} normal.bam tumor.bam && 24 --fasta reference.fa
23 gunzip output-smoove.vcf.gz 25 --processes \${GALAXY_SLOTS:-4}
24 #if $prpos=="no": 26 --genotype
25 && sed -i -E 's/;PRPOS=.+\tGT/\tGT/g' output-smoove.vcf 27 #if $prpos=="no":
26 #end if 28 --removepr
27 29 #end if
30 normal.bam tumor.bam &&
31 ls -latr &&
32 gunzip output-smoove.genotyped.vcf.gz
28 33
29 ]]></command> 34 ]]></command>
30 <inputs> 35 <inputs>
31 <expand macro="reference_source_conditional" /> 36 <expand macro="reference_source_conditional" />
32 <param format="bam" name="normal_bam" type="data" label="BAM alignments from the normal sample"/> 37 <param format="bam" name="normal_bam" type="data" label="BAM alignments from the normal sample"/>
47 <option value="yes">Yes</option> 52 <option value="yes">Yes</option>
48 </param> 53 </param>
49 </inputs> 54 </inputs>
50 55
51 <outputs> 56 <outputs>
52 <data format="vcf" name="vcf_call" label="lumpy-smoove Variant Calling" from_work_dir="./output-smoove.vcf" /> 57 <data format="vcf" name="vcf_call" label="lumpy-smoove Variant Calling" from_work_dir="./output-smoove.genotyped.vcf" />
53 </outputs> 58 </outputs>
54 59
55 <tests> 60 <tests>
56 <test> 61 <test>
57 <param name="reference_source_selector" value="history" /> 62 <param name="reference_source_selector" value="history" />
58 <param name="ref_file" value="chrI-ce11.fa"/> 63 <param name="ref_file" value="chrI-ce11.fa"/>
59 <param name="normal_bam" value="celegans_1.bam"/> 64 <param name="normal_bam" value="celegans_RG_1.bam"/>
60 <param name="tumor_bam" value="celegans_2.bam"/> 65 <param name="tumor_bam" value="celegans_RG_2.bam"/>
61 <param name="choices" value="yes"/> 66 <param name="choices" value="yes"/>
62 <param name="bedmask" value="exclude.bed"/> 67 <param name="bedmask" value="exclude.bed"/>
63 <param name="prpos" value="no"/> 68 <param name="prpos" value="no"/>
64 <output name="vcf_call" ftype="vcf" file="result-1.vcf" lines_diff="4"/> 69 <output name="vcf_call" ftype="vcf" file="result-1.vcf" lines_diff="6"/>
65 </test> 70 </test>
66 <test> 71 <test>
67 <param name="reference_source_selector" value="history" /> 72 <param name="reference_source_selector" value="history" />
68 <param name="ref_file" value="chrI-ce11.fa"/> 73 <param name="ref_file" value="chrI-ce11.fa"/>
69 <param name="normal_bam" value="celegans_1.bam"/> 74 <param name="normal_bam" value="celegans_RG_1.bam"/>
70 <param name="tumor_bam" value="celegans_2.bam"/> 75 <param name="tumor_bam" value="celegans_RG_2.bam"/>
71 <param name="choices" value="no"/> 76 <param name="choices" value="no"/>
72 <param name="prpos" value="no"/> 77 <param name="prpos" value="no"/>
73 <output name="vcf_call" ftype="vcf" file="result-2.vcf" lines_diff="4"/> 78 <output name="vcf_call" ftype="vcf" file="result-2.vcf" lines_diff="6"/>
74 </test> 79 </test>
75 <test> 80 <test>
76 <param name="reference_source_selector" value="history" /> 81 <param name="reference_source_selector" value="history" />
77 <param name="ref_file" value="chrI-ce11.fa"/> 82 <param name="ref_file" value="chrI-ce11.fa"/>
78 <param name="normal_bam" value="celegans_2.bam"/> 83 <param name="normal_bam" value="celegans_RG_2.bam"/>
79 <param name="tumor_bam" value="celegans_1.bam"/> 84 <param name="tumor_bam" value="celegans_RG_1.bam"/>
80 <param name="choices" value="no"/> 85 <param name="choices" value="no"/>
81 <param name="prpos" value="no"/> 86 <param name="prpos" value="no"/>
82 <output name="vcf_call" ftype="vcf" file="result-3.vcf" lines_diff="4"/> 87 <output name="vcf_call" ftype="vcf" file="result-3.vcf" lines_diff="6"/>
83 </test> 88 </test>
84 <test> 89 <test>
85 <param name="reference_source_selector" value="history" /> 90 <param name="reference_source_selector" value="history" />
86 <param name="ref_file" value="chrI-ce11.fa"/> 91 <param name="ref_file" value="chrI-ce11.fa"/>
87 <param name="normal_bam" value="celegans_1.bam"/> 92 <param name="normal_bam" value="celegans_RG_1.bam"/>
88 <param name="tumor_bam" value="celegans_2.bam"/> 93 <param name="tumor_bam" value="celegans_RG_2.bam"/>
89 <param name="choices" value="no"/> 94 <param name="choices" value="no"/>
90 <param name="prpos" value="yes"/> 95 <param name="prpos" value="yes"/>
91 <output name="vcf_call" ftype="vcf" file="result-4.vcf" lines_diff="4"/> 96 <output name="vcf_call" ftype="vcf" file="result-4.vcf" lines_diff="6"/>
92 </test> 97 </test>
93 98
94 </tests> 99 </tests>
95 100
96 <help> 101 <help>
97
98 **smoove** simplifies and speeds calling and genotyping SVs for short reads. It also improves 102 **smoove** simplifies and speeds calling and genotyping SVs for short reads. It also improves
99 specificity by removing many spurious alignment signals that are indicative of low-level 103 specificity by removing many spurious alignment signals that are indicative of low-level
100 noise and often contribute to spurious calls. 104 noise and often contribute to spurious calls.
101 105
102 There is a blog-post describing smoove in more detail 106 There is a blog-post describing smoove in more detail
103 here: https://brentp.github.io/post/smoove/ 107 here: https://brentp.github.io/post/smoove/
104 108
105 Currently, this Galaxy tool only wraps smoove for 2 samples (bam normal and tumor inputs), 109 Currently, this Galaxy tool only wraps smoove for 2 samples (bam normal and tumor inputs),
106 which translates in the command line:: 110 which translates in the command line::
107 111
108 <![CDATA[smoove call -x --name my-cohort --exclude $bed --fasta $fasta -p $threads /path/to/*.bam]]> 112 <![CDATA[smoove call --name my-cohort --exclude $bed --fasta $fasta -p $threads --genotype [--removepr] /path/to/*.bam]]>
109 113
110 Note that the --genotype option which allows to stream smoove to svtyper is not implemented
111 due to an error returned by svtyper in the smoove conda environment
112 114
113 the --exclude $bed is highly recommended as it can be used to ignore reads that overlap 115 the --exclude $bed is highly recommended as it can be used to ignore reads that overlap
114 problematic regions. 116 problematic regions.
115 117
116 A good set of regions for GRCh37 is https://github.com/hall-lab/speedseq/blob/master/annotations/ceph18.b37.lumpy.exclude.2014-01-15.bed 118 A good set of regions for GRCh37 can be found here_
117 119
118 And for hg38 https://github.com/hall-lab/speedseq/blob/master/annotations/exclude.cnvnator_100bp.GRCh38.20170403.bed 120 .. _here: https://github.com/hall-lab/speedseq/blob/master/annotations/ceph18.b37.lumpy.exclude.2014-01-15.bed
121
122
123 And a good set for GRCh38 can be found there_
124
125 .. _there: https://github.com/hall-lab/speedseq/blob/master/annotations/exclude.cnvnator_100bp.GRCh38.20170403.bed
126
119 127
120 smoove will:: 128 smoove will::
121 129
122 1. parallelize calls to lumpy_filter to extract split and discordant reads required by lumpy 130 1. parallelize calls to lumpy_filter to extract split and discordant reads required by lumpy
123 131
128 136
129 3. calculate per-sample metrics for mean, standard deviation, and distribution of insert 137 3. calculate per-sample metrics for mean, standard deviation, and distribution of insert
130 size as required by lumpy. 138 size as required by lumpy.
131 139
132 4. stream output of lumpy directly into multiple svtyper processes for parallel-by-region 140 4. stream output of lumpy directly into multiple svtyper processes for parallel-by-region
133 genotyping while lumpy is still running. This option in not currently implemented in Galaxy 141 genotyping while lumpy is still running.
134 142
135 5. sort, compress, and index final VCF. 143 5. sort, compress, and index final VCF (but this galaxy wrapper is uncompression the gzip_vcf output)
136 144
137 **Input(s)** 145 **Input(s)**
138 146
139 147 * BAM files: One Bam for normal sample and one Bam for tumor sample. Only BAM alignments produced by BWA-mem have been tested with this tool
140 *BAM files*: One Bam for normal sample and one Bam for tumor sample. 148
141 Only BAM alignments produced by BWA-mem have been tested with this tool 149 .. class:: warningmark
142 150
143 *A bed file* describing the regions to exclude from the analysis 151 It is mandatory for proper run of svtyper that **BAM files contain read group information**,
152 ie the @RG tag is present and filled in each BAM
144 153
145 154
146 *Additional options*: refer to smoove GitHub repository_ and the lumpy publication (doi 10.1186/gb-2014-15-6-r84) 155 * A bed file describing the regions to exclude from the analysis
156 * Additional options*: refer to smoove GitHub repository_ and the lumpy publication (doi 10.1186/gb-2014-15-6-r84)
147 157
148 .. _repository: https://github.com/brentp/smoove 158 .. _repository: https://github.com/brentp/smoove
149 159
150 160
151 Options:: 161 Options::