| Next changeset 1:8959eda17fca (2016-07-06) |
|
Commit message:
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/bcftools commit bbfd77c34b609b86ef3a24525dae1127d8b3d99b |
|
added:
README.md bcftools_call.xml macros.xml test-data/mpileup.1.out test-data/mpileup.2.out test-data/mpileup.vcf tool_dependencies.xml |
| b |
| diff -r 000000000000 -r a531317a3527 README.md --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/README.md Mon May 02 17:27:10 2016 -0400 |
| b |
| @@ -0,0 +1,21 @@ +# bcftools (v1.2) + +This aims to be a "faithful" rendering of the bcftool suite. I.e. options are +presented essentially as closely to the command line version as is useful. + +This may not appeal to all, if you'd like to see smaller and more dedicated +tools (e.g. "intersect", "union" and "complement" being separate tools instead +of all of them included in the "isec" tool,) please feel free to file an issue. + +## TODO: + +- Galaxy needs datatypes for bcf and vcf files, block-gzipped and uncompressed. +- Galaxy needs to automatically index those files with tabix + +## "Complete" Wrappers + +The wrappers were automatically generated in bulk. That doesn't get them 100% +of the way there (e.g. meaningful test cases), so the rest of the process is a +bit slower. + +- bcftools call |
| b |
| diff -r 000000000000 -r a531317a3527 bcftools_call.xml --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/bcftools_call.xml Mon May 02 17:27:10 2016 -0400 |
| [ |
| b'@@ -0,0 +1,159 @@\n+<?xml version=\'1.0\' encoding=\'utf-8\'?>\n+<tool name="bcftools @EXECUTABLE@" id="bcftools_@EXECUTABLE@" version="@VERSION@.0">\n+ <description>SNP/indel variant calling from VCF/BCF</description>\n+ <macros>\n+ <token name="@EXECUTABLE@">call</token>\n+ <import>macros.xml</import>\n+ </macros>\n+ <expand macro="requirements" />\n+ <expand macro="version_command" />\n+ <command detect_errors="aggressive"><![CDATA[\n+bcftools @EXECUTABLE@\n+\n+## Consensus/variant calling section\n+#if $sec_consensus_variant_calling.select_caller == "consensus":\n+ --consensus-caller\n+#else:\n+ --multiallelic-caller\n+#end if\n+\n+#if $sec_consensus_variant_calling.constraints.constrain_select == "alleles":\n+ --constrain alleles\n+#elif $sec_consensus_variant_calling.constraints.constrain_select == "trio":\n+ --constrain trio\n+ --novel-rate ${sec_consensus_variant_calling.constraints.novel_snp},${sec_consensus_variant_calling.constraints.novel_ins},${sec_consensus_variant_calling.constraints.novel_del}\n+ --pval-threshold "${sec_consensus_variant_calling.constraints.pval_threshold}"\n+#end if\n+\n+#if $sec_consensus_variant_calling.prior:\n+ --prior "${sec_consensus_variant_calling.prior}"\n+#end if\n+${sec_consensus_variant_calling.chromosome_X}\n+${sec_consensus_variant_calling.chromosome_Y}\n+\n+\n+## File format section\n+#if str($sec_default.select_output_type) != "__none__":\n+ --output-type "${sec_default.select_output_type}"\n+#end if\n+@SEC_DEF_REGIONS@\n+@SEC_DEF_SAMPLES@\n+@SEC_DEF_TARGETS@\n+\n+\n+## Input/output section\n+${sec_input_output.keep_alts}\n+#set values_sec_input_output_format_fields = \'","\'.join([str($value) for $value in $sec_input_output.format_fields_repeat])\n+#if $values_sec_input_output_format_fields:\n+ --format-fields "${values_sec_input_output_format_fields}"\n+#end if\n+\n+#if str($sec_input_output.gvcf) != "":\n+ --gvcf "${sec_input_output.gvcf}"\n+#end if\n+\n+${sec_input_output.insert_missed}\n+${sec_input_output.keep_masked_ref}\n+\n+#if str($sec_input_output.skip_variants) != "__none__":\n+ --skip-variants "${sec_input_output.skip_variants}"\n+#end if\n+\n+${sec_input_output.variants_only}\n+\n+## Primary Input/Outputs\n+\n+$input_file\n+>\n+$output_file\n+]]>\n+</command>\n+ <inputs>\n+ <param name="input_file" label="VCF/BCF Data" type="data" format="vcf,bcf,vcf_bgz,bcf_bgz" />\n+ <section name="sec_consensus_variant_calling" expanded="true" title="Consensus/variant calling Options">\n+ <param name="select_caller" label="Calling Method" type="select">\n+ <option value="consensus">the original calling method (-c, --consensus-caller)</option>\n+ <option value="multiallelic">alternative model for multiallelic and rare-variant calling (-m, --multiallelic-caller)</option>\n+ </param>\n+ <conditional name="constraints" label="Constraints">\n+ <param name="constrain_select" label="Constraints" type="select" argument="-C">\n+ <option value="__none__" selected="True">No constraints</option>\n+ <option value="alleles">call genotypes given alleles (alleles)</option>\n+ <option value="trio">call genotypes given the father-mother-child constraint (trio)</option>\n+ </param>\n+ <when value="__none__" />\n+ <when value="alleles" />\n+ <when value="trio">\n+ <param name="novel_snp" label="Novel Rate: SNPs" type="float" default="1e-8" optional="True" help="mutation rate of SNPs" argument="--novel-rate"/>\n+ <param name="novel_ins" label="Novel Rate: Insertions" type="float" default="1e-9" optional="True" help="mutation rate of insertions according to their length" argument="--novel-rate" />\n+ <param name="novel_del" label="Novel Rate: Deletions" type="float" default="1e-9" optional="True" help="mutation rate of deletions according to their length" argument="--novel-rate" />\n+ <param name="pval_threshold" label="Pval Threshold" type="float" default="0.5" optional="True" help="variant if P(ref|D)<FLOAT with -c" argument="--p'..b'e="" help="haploid output for males and skips females (requires PED file with -s)" argument="--chromosome-Y"/>\n+ </section>\n+ <section name="sec_default" expanded="true" title="Default Options">\n+ <expand macro="macro_select_output_type" />\n+ <expand macro="macro_regions" />\n+ <expand macro="macro_samples" />\n+ <expand macro="macro_targets" />\n+ </section>\n+ <section name="sec_input_output" expanded="true" title="Input/output Options">\n+ <param name="keep_alts" label="Keep Alts" type="boolean" truevalue="--keep-alts" falsevalue="" help="keep all possible alternate alleles at variant sites" argument="--keep-alts"/>\n+ <repeat name="format_fields_repeat" title="Format Fields">\n+ <param name="format_fields" type="text" label="Format Fields" help="output format fields: e.g. GQ, GP (lowercase allowed)" argument="--format-fields" />\n+ </repeat>\n+ <param name="gvcf" label="Gvcf" type="integer" optional="True" help="output gVCF blocks of homozygous REF calls. The parameter is the minimum per-sample depth required to include a site in the non-variant block." argument="--gvcf"/>\n+ <param name="insert_missed" label="Insert Missed" type="boolean" truevalue="--insert-missed" falsevalue="" help="output also sites missed by mpileup but present in -T" argument="--insert-missed"/>\n+ <param name="keep_masked_ref" label="Keep Masked Ref" type="boolean" truevalue="--keep-masked-ref" falsevalue="" help="keep sites with masked reference allele (REF=N)" argument="--keep-masked-ref"/>\n+ <param name="skip_variants" label="Skip Variants" type="select" help="Skip indels/SNP sites" argument="--skip-variants">\n+ <option value="__none__" selected="True">Don\'t skip any</option>\n+ <option value="indels">Skip indels</option>\n+ <option value="snps">Skip snps</option>\n+ </param>\n+ <param name="variants_only" label="Variants Only" type="boolean" truevalue="--variants-only" falsevalue="" help="output variant sites only" argument="--variants-only"/>\n+ </section>\n+ </inputs>\n+ <outputs>\n+ <data name="output_file" format="vcf">\n+ <change_format>\n+ <when input="sec_file_format|select_output_type" value="b" format="bcf_bgz" />\n+ <when input="sec_file_format|select_output_type" value="u" format="bcf" />\n+ <when input="sec_file_format|select_output_type" value="z" format="vcf_bgz" />\n+ <when input="sec_file_format|select_output_type" value="v" format="vcf" />\n+ </change_format>\n+ </data>\n+ </outputs>\n+ <tests>\n+ <test>\n+ <param name="input_file" value="mpileup.vcf" />\n+ <param name="sec_consensus_variant_calling|select_caller" value="multiallelic" />\n+ <param name="sec_input_output|variants_only" value="--variants-only" />\n+ <param name="sec_file_format|select_output_type" value="v" />\n+ <output name="output_file" file="mpileup.1.out" lines_diff="2" ftype="vcf" />\n+ </test>\n+ <test>\n+ <param name="input_file" value="mpileup.vcf" />\n+ <param name="sec_consensus_variant_calling|select_caller" value="multiallelic" />\n+ <param name="sec_input_output|variants_only" value="--variants-only" />\n+ <param name="sec_input_output|gvcf" value="0" />\n+ <param name="sec_file_format|select_output_type" value="v" />\n+ <output name="output_file" file="mpileup.2.out" lines_diff="2" ftype="vcf" />\n+ </test>\n+ </tests>\n+ <help>\n+ <![CDATA[\n+ **bcftools call**\n+\n+ SNP/indel variant calling from VCF/BCF. To be used in conjunction with\n+ samtools mpileup. This command replaces the former "bcftools view"\n+ caller. Some of the original functionality has been temporarily lost in\n+ the process of transition to htslib, but will be added back on popular\n+ demand. The original calling model can be invoked with the -c\n+ option.\n+ ]]>\n+ </help>\n+ <expand macro="citations" />\n+</tool>\n' |
| b |
| diff -r 000000000000 -r a531317a3527 macros.xml --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/macros.xml Mon May 02 17:27:10 2016 -0400 |
| [ |
| @@ -0,0 +1,74 @@ +<?xml version='1.0' encoding='utf-8'?> +<macros> + <token name="@VERSION@">1.2</token> + <xml name="requirements"> + <requirements> + <!-- This requirement handles also bcftools from BioConda channel => https://github.com/bioconda/bioconda-recipes/tree/60d2ea750430dbe0191f6f8d5639f90fc1223bd9/recipes/bcftools/1.2 --> + <requirement type="package" version="1.2">bcftools</requirement> + </requirements> + </xml> + <xml name="version_command"> + <version_command><![CDATA[bcftools 2>&1 | grep 'Version:']]></version_command> + </xml> + <xml name="citations"> + <citations> + <citation type="doi">10.1093/bioinformatics/btp352</citation> + <yield /> + </citations> + </xml> + <xml name="macro_exclude"> + <param name="exclude" label="Exclude" help="exclude sites for which the expression is true (see man page for details)" /> + </xml> + <xml name="macro_collapse"> + <param name="collapse" label="Collapse" type="select" optional="True" help="Controls how to treat records with duplicate positions and defines compatible records across multiple input files"> + <option value="snps">snps</option> + <option value="indels">indels</option> + <option value="both">both</option> + <option value="all">all</option> + <option value="some">some</option> + <option value="none" selected="True">None</option> + </param> + </xml> + <xml name="macro_apply_filters_repeat"> + <repeat name="apply_filters_repeat" title="Apply Filters"> + <param name="apply_filters" label="Apply Filters" help="require at least one of the listed FILTER strings (e.g. "PASS,.")" /> + </repeat> + </xml> + + <token name="@SEC_DEF_REGIONS@"> +#if $sec_default.regions_file: + --regions-file "${sec_default.regions_file}" +#end if + </token> + <token name="@SEC_DEF_TARGETS@"> +#if $sec_default.targets_file: + --targets-file "${sec_default.targets_file}" +#end if + </token> + <token name="@SEC_DEF_SAMPLES@"> +#if $sec_default.samples_file: + --samples-file "${sec_default.samples_file}" +#end if + </token> + + <xml name="macro_samples"> + <param name="samples_file" label="Samples File" type="data" format="data" optional="True" help="file of samples to include" /> + <param name="invert_samples_file" label="Invert Samples" type="boolean" truevalue="^" falsevalue="" help="inverts the query/filtering applied by the sample file selection" /> + </xml> + <xml name="macro_targets"> + <param name="targets_file" label="Targets File" type="data" format="data" optional="True" help="similar to -R but streams rather than index-jumps" /> + <param name="invert_targets_file" label="Invert Targets" type="boolean" truevalue="^" falsevalue="" help="inverts the query/filtering applied by the target file selection" /> + </xml> + <xml name="macro_regions"> + <param name="regions_file" label="Regions File" type="data" format="data" optional="True" help="restrict to regions listed in a file" /> + <param name="invert_regions_file" label="Invert Regions" type="boolean" truevalue="^" falsevalue="" help="inverts the query/filtering applied by region file selection" /> + </xml> + <xml name="macro_select_output_type"> + <param name="select_output_type" type="select"> + <option value="v" selected="True">uncompressed VCF</option> + <option value="z">compressed VCF</option> + <option value="u">uncompressed BCF</option> + <option value="b">compressed BCF</option> + </param> + </xml> +</macros> |
| b |
| diff -r 000000000000 -r a531317a3527 test-data/mpileup.1.out --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/test-data/mpileup.1.out Mon May 02 17:27:10 2016 -0400 |
| b |
| @@ -0,0 +1,40 @@ +##fileformat=VCFv4.2 +##FILTER=<ID=PASS,Description="All filters passed"> +##samtoolsVersion=1.1-19-g6b249e2+htslib-1.1-74-g845c515 +##samtoolsCommand=samtools mpileup -uvDV -b xxx//mpileup.bam.list -f xxx//mpileup.ref.fa.gz +##reference=file://xxx//mpileup.ref.fa.gz +##contig=<ID=17,length=81195210> +##ALT=<ID=X,Description="Represents allele(s) other than observed."> +##INFO=<ID=INDEL,Number=0,Type=Flag,Description="Indicates that the variant is an INDEL."> +##INFO=<ID=IDV,Number=1,Type=Integer,Description="Maximum number of reads supporting an indel"> +##INFO=<ID=IMF,Number=1,Type=Float,Description="Maximum fraction of reads supporting an indel"> +##INFO=<ID=DP,Number=1,Type=Integer,Description="Raw read depth"> +##INFO=<ID=VDB,Number=1,Type=Float,Description="Variant Distance Bias for filtering splice-site artefacts in RNA-seq data (bigger is better)",Version="3"> +##INFO=<ID=RPB,Number=1,Type=Float,Description="Mann-Whitney U test of Read Position Bias (bigger is better)"> +##INFO=<ID=MQB,Number=1,Type=Float,Description="Mann-Whitney U test of Mapping Quality Bias (bigger is better)"> +##INFO=<ID=BQB,Number=1,Type=Float,Description="Mann-Whitney U test of Base Quality Bias (bigger is better)"> +##INFO=<ID=MQSB,Number=1,Type=Float,Description="Mann-Whitney U test of Mapping Quality vs Strand Bias (bigger is better)"> +##INFO=<ID=SGB,Number=1,Type=Float,Description="Segregation based metric."> +##INFO=<ID=MQ0F,Number=1,Type=Float,Description="Fraction of MQ0 reads (smaller is better)"> +##FORMAT=<ID=PL,Number=G,Type=Integer,Description="List of Phred-scaled genotype likelihoods"> +##FORMAT=<ID=DP,Number=1,Type=Integer,Description="Number of high-quality bases"> +##FORMAT=<ID=DV,Number=1,Type=Integer,Description="Number of high-quality non-reference bases"> +##FORMAT=<ID=GT,Number=1,Type=String,Description="Genotype"> +##INFO=<ID=ICB,Number=1,Type=Float,Description="Inbreeding Coefficient Binomial test (bigger is better)"> +##INFO=<ID=HOB,Number=1,Type=Float,Description="Bias in the number of HOMs number (smaller is better)"> +##INFO=<ID=AC,Number=A,Type=Integer,Description="Allele count in genotypes for each ALT allele, in the same order as listed"> +##INFO=<ID=AN,Number=1,Type=Integer,Description="Total number of alleles in called genotypes"> +##INFO=<ID=DP4,Number=4,Type=Integer,Description="Number of high-quality ref-forward , ref-reverse, alt-forward and alt-reverse bases"> +##INFO=<ID=MQ,Number=1,Type=Integer,Description="Average mapping quality"> +#CHROM POS ID REF ALT QUAL FILTER INFO FORMAT HG00100 HG00101 HG00102 +17 302 . T TA 488 . INDEL;IDV=7;IMF=1;DP=25;VDB=0.27613;SGB=-4.22417;MQSB=0.0443614;MQ0F=0;ICB=0.8;HOB=0.222222;AC=4;AN=6;DP4=2,4,8,11;MQ=49 GT:PL:DP:DV 0/1:167,0,96:11:6 0/1:157,0,9:7:6 1/1:201,21,0:7:7 +17 828 . T C 409 . DP=25;VDB=0.842082;SGB=-4.20907;RPB=0.950652;MQB=1;MQSB=1;BQB=0.929717;MQ0F=0;ICB=0.8;HOB=0.222222;AC=4;AN=6;DP4=2,4,8,11;MQ=60 GT:PL:DP:DV 0/1:211,0,35:12:10 0/1:116,0,91:9:5 1/1:120,12,0:4:4 +17 834 . G A 364 . DP=25;VDB=0.788006;SGB=-4.01214;RPB=0.999233;MQB=1;MQSB=1;BQB=0.821668;MQ0F=0;ICB=0.8;HOB=0.222222;AC=4;AN=6;DP4=2,3,7,10;MQ=60 GT:PL:DP:DV 0/1:185,0,46:11:9 0/1:128,0,59:8:5 1/1:89,9,0:3:3 +17 1665 . T C 3.10665 . DP=20;VDB=0.1;SGB=0.346553;RPB=0.222222;MQB=0.611111;MQSB=0.988166;BQB=0.944444;MQ0F=0;ICB=0.128205;HOB=0.0555556;AC=1;AN=6;DP4=7,11,1,1;MQ=55 GT:PL:DP:DV 0/0:0,21,185:7:0 0/0:0,27,222:9:0 0/1:35,0,51:4:2 +17 1869 . A T 138 . DP=24;VDB=0.928022;SGB=-11.9537;RPB=0.984127;MQB=0.96464;MQSB=0.931547;BQB=0.359155;MQ0F=0;ICB=0.8;HOB=0.222222;AC=4;AN=6;DP4=6,9,5,4;MQ=58 GT:PL:DP:DV 0/1:115,0,224:18:7 0/1:16,0,104:5:1 1/1:42,3,0:1:1 +17 2041 . G A 447 . DP=31;VDB=0.816435;SGB=-4.18892;RPB=0.88473;MQB=0.972375;MQSB=0.968257;BQB=0.311275;MQ0F=0;ICB=0.8;HOB=0.222222;AC=4;AN=6;DP4=6,5,12,7;MQ=58 GT:PL:DP:DV 0/1:229,0,212:21:11 0/1:32,0,24:2:1 1/1:223,21,0:7:7 +17 2220 . G A 303 . DP=21;VDB=0.532753;SGB=-3.51597;RPB=0.964198;MQB=0.898397;MQSB=0.875769;BQB=0.0354359;MQ0F=0;ICB=0.8;HOB=0.222222;AC=4;AN=6;DP4=6,2,1,11;MQ=58 GT:PL:DP:DV 0/1:139,0,130:12:6 0/1:69,0,46:4:2 1/1:131,12,0:4:4 +17 2564 . A G 233 . DP=15;VDB=0.690812;SGB=-3.20711;RPB=0.197899;MQB=1;MQSB=1;BQB=0.965069;MQ0F=0;ICB=0.8;HOB=0.222222;AC=4;AN=6;DP4=1,4,4,5;MQ=60 GT:PL:DP:DV 0/1:88,0,78:6:3 0/1:57,0,56:4:2 1/1:124,12,0:4:4 +17 3104 . C T 24.2837 . DP=25;VDB=0.8;SGB=0.346553;RPB=0.717391;MQB=0.956522;MQSB=0.962269;BQB=0.978261;MQ0F=0;ICB=0.128205;HOB=0.0555556;AC=1;AN=6;DP4=8,15,2,0;MQ=58 GT:PL:DP:DV 0/0:0,48,255:16:0 0/0:0,12,144:4:0 0/1:59,0,93:5:2 +17 3587 . G A 358 . DP=29;VDB=0.902044;SGB=-3.91326;RPB=0.800999;MQB=1;MQSB=1;BQB=0.156944;MQ0F=0;ICB=0.8;HOB=0.222222;AC=4;AN=6;DP4=4,7,10,6;MQ=60 GT:PL:DP:DV 0/1:161,0,184:14:7 0/1:22,0,118:5:1 1/1:212,24,0:8:8 +17 3936 . A G 469 . DP=37;VDB=0.0574114;SGB=-4.60123;RPB=0.741697;MQB=0.812605;MQSB=0.143788;BQB=0.883831;MQ0F=0;ICB=0.8;HOB=0.222222;AC=4;AN=6;DP4=5,6,6,17;MQ=56 GT:PL:DP:DV 0/1:233,0,206:20:11 0/1:77,0,58:6:4 1/1:196,24,0:8:8 |
| b |
| diff -r 000000000000 -r a531317a3527 test-data/mpileup.2.out --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/test-data/mpileup.2.out Mon May 02 17:27:10 2016 -0400 |
| b |
| @@ -0,0 +1,53 @@ +##fileformat=VCFv4.2 +##FILTER=<ID=PASS,Description="All filters passed"> +##samtoolsVersion=1.1-19-g6b249e2+htslib-1.1-74-g845c515 +##samtoolsCommand=samtools mpileup -uvDV -b xxx//mpileup.bam.list -f xxx//mpileup.ref.fa.gz +##reference=file://xxx//mpileup.ref.fa.gz +##contig=<ID=17,length=81195210> +##ALT=<ID=X,Description="Represents allele(s) other than observed."> +##INFO=<ID=INDEL,Number=0,Type=Flag,Description="Indicates that the variant is an INDEL."> +##INFO=<ID=IDV,Number=1,Type=Integer,Description="Maximum number of reads supporting an indel"> +##INFO=<ID=IMF,Number=1,Type=Float,Description="Maximum fraction of reads supporting an indel"> +##INFO=<ID=DP,Number=1,Type=Integer,Description="Raw read depth"> +##INFO=<ID=VDB,Number=1,Type=Float,Description="Variant Distance Bias for filtering splice-site artefacts in RNA-seq data (bigger is better)",Version="3"> +##INFO=<ID=RPB,Number=1,Type=Float,Description="Mann-Whitney U test of Read Position Bias (bigger is better)"> +##INFO=<ID=MQB,Number=1,Type=Float,Description="Mann-Whitney U test of Mapping Quality Bias (bigger is better)"> +##INFO=<ID=BQB,Number=1,Type=Float,Description="Mann-Whitney U test of Base Quality Bias (bigger is better)"> +##INFO=<ID=MQSB,Number=1,Type=Float,Description="Mann-Whitney U test of Mapping Quality vs Strand Bias (bigger is better)"> +##INFO=<ID=SGB,Number=1,Type=Float,Description="Segregation based metric."> +##INFO=<ID=MQ0F,Number=1,Type=Float,Description="Fraction of MQ0 reads (smaller is better)"> +##FORMAT=<ID=PL,Number=G,Type=Integer,Description="List of Phred-scaled genotype likelihoods"> +##FORMAT=<ID=DP,Number=1,Type=Integer,Description="Number of high-quality bases"> +##FORMAT=<ID=DV,Number=1,Type=Integer,Description="Number of high-quality non-reference bases"> +##FORMAT=<ID=GT,Number=1,Type=String,Description="Genotype"> +##INFO=<ID=ICB,Number=1,Type=Float,Description="Inbreeding Coefficient Binomial test (bigger is better)"> +##INFO=<ID=HOB,Number=1,Type=Float,Description="Bias in the number of HOMs number (smaller is better)"> +##INFO=<ID=AC,Number=A,Type=Integer,Description="Allele count in genotypes for each ALT allele, in the same order as listed"> +##INFO=<ID=AN,Number=1,Type=Integer,Description="Total number of alleles in called genotypes"> +##INFO=<ID=DP4,Number=4,Type=Integer,Description="Number of high-quality ref-forward , ref-reverse, alt-forward and alt-reverse bases"> +##INFO=<ID=MQ,Number=1,Type=Integer,Description="Average mapping quality"> +##INFO=<ID=END,Number=1,Type=Integer,Description="End position of the variant described in this record"> +#CHROM POS ID REF ALT QUAL FILTER INFO FORMAT HG00100 HG00101 HG00102 +17 1 . A . . . END=301 GT 0/0 0/0 0/0 +17 302 . T TA 488 . INDEL;IDV=7;IMF=1;DP=25;VDB=0.27613;SGB=-4.22417;MQSB=0.0443614;MQ0F=0;ICB=0.8;HOB=0.222222;AC=4;AN=6;DP4=2,4,8,11;MQ=49 GT:PL:DP:DV 0/1:167,0,96:11:6 0/1:157,0,9:7:6 1/1:201,21,0:7:7 +17 303 . G . . . END=827 GT 0/0 0/0 0/0 +17 828 . T C 409 . DP=25;VDB=0.842082;SGB=-4.20907;RPB=0.950652;MQB=1;MQSB=1;BQB=0.929717;MQ0F=0;ICB=0.8;HOB=0.222222;AC=4;AN=6;DP4=2,4,8,11;MQ=60 GT:PL:DP:DV 0/1:211,0,35:12:10 0/1:116,0,91:9:5 1/1:120,12,0:4:4 +17 829 . T . . . END=833 GT 0/0 0/0 0/0 +17 834 . G A 364 . DP=25;VDB=0.788006;SGB=-4.01214;RPB=0.999233;MQB=1;MQSB=1;BQB=0.821668;MQ0F=0;ICB=0.8;HOB=0.222222;AC=4;AN=6;DP4=2,3,7,10;MQ=60 GT:PL:DP:DV 0/1:185,0,46:11:9 0/1:128,0,59:8:5 1/1:89,9,0:3:3 +17 835 . T . . . END=1664 GT 0/0 0/0 0/0 +17 1665 . T C 3.10665 . DP=20;VDB=0.1;SGB=0.346553;RPB=0.222222;MQB=0.611111;MQSB=0.988166;BQB=0.944444;MQ0F=0;ICB=0.128205;HOB=0.0555556;AC=1;AN=6;DP4=7,11,1,1;MQ=55 GT:PL:DP:DV 0/0:0,21,185:7:0 0/0:0,27,222:9:0 0/1:35,0,51:4:2 +17 1666 . G . . . END=1868 GT 0/0 0/0 0/0 +17 1869 . A T 138 . DP=24;VDB=0.928022;SGB=-11.9537;RPB=0.984127;MQB=0.96464;MQSB=0.931547;BQB=0.359155;MQ0F=0;ICB=0.8;HOB=0.222222;AC=4;AN=6;DP4=6,9,5,4;MQ=58 GT:PL:DP:DV 0/1:115,0,224:18:7 0/1:16,0,104:5:1 1/1:42,3,0:1:1 +17 1870 . C . . . END=2040 GT 0/0 0/0 0/0 +17 2041 . G A 447 . DP=31;VDB=0.816435;SGB=-4.18892;RPB=0.88473;MQB=0.972375;MQSB=0.968257;BQB=0.311275;MQ0F=0;ICB=0.8;HOB=0.222222;AC=4;AN=6;DP4=6,5,12,7;MQ=58 GT:PL:DP:DV 0/1:229,0,212:21:11 0/1:32,0,24:2:1 1/1:223,21,0:7:7 +17 2042 . G . . . END=2219 GT 0/0 0/0 0/0 +17 2220 . G A 303 . DP=21;VDB=0.532753;SGB=-3.51597;RPB=0.964198;MQB=0.898397;MQSB=0.875769;BQB=0.0354359;MQ0F=0;ICB=0.8;HOB=0.222222;AC=4;AN=6;DP4=6,2,1,11;MQ=58 GT:PL:DP:DV 0/1:139,0,130:12:6 0/1:69,0,46:4:2 1/1:131,12,0:4:4 +17 2221 . G . . . END=2563 GT 0/0 0/0 0/0 +17 2564 . A G 233 . DP=15;VDB=0.690812;SGB=-3.20711;RPB=0.197899;MQB=1;MQSB=1;BQB=0.965069;MQ0F=0;ICB=0.8;HOB=0.222222;AC=4;AN=6;DP4=1,4,4,5;MQ=60 GT:PL:DP:DV 0/1:88,0,78:6:3 0/1:57,0,56:4:2 1/1:124,12,0:4:4 +17 2565 . A . . . END=3103 GT 0/0 0/0 0/0 +17 3104 . C T 24.2837 . DP=25;VDB=0.8;SGB=0.346553;RPB=0.717391;MQB=0.956522;MQSB=0.962269;BQB=0.978261;MQ0F=0;ICB=0.128205;HOB=0.0555556;AC=1;AN=6;DP4=8,15,2,0;MQ=58 GT:PL:DP:DV 0/0:0,48,255:16:0 0/0:0,12,144:4:0 0/1:59,0,93:5:2 +17 3105 . T . . . END=3586 GT 0/0 0/0 0/0 +17 3587 . G A 358 . DP=29;VDB=0.902044;SGB=-3.91326;RPB=0.800999;MQB=1;MQSB=1;BQB=0.156944;MQ0F=0;ICB=0.8;HOB=0.222222;AC=4;AN=6;DP4=4,7,10,6;MQ=60 GT:PL:DP:DV 0/1:161,0,184:14:7 0/1:22,0,118:5:1 1/1:212,24,0:8:8 +17 3588 . A . . . END=3935 GT 0/0 0/0 0/0 +17 3936 . A G 469 . DP=37;VDB=0.0574114;SGB=-4.60123;RPB=0.741697;MQB=0.812605;MQSB=0.143788;BQB=0.883831;MQ0F=0;ICB=0.8;HOB=0.222222;AC=4;AN=6;DP4=5,6,6,17;MQ=56 GT:PL:DP:DV 0/1:233,0,206:20:11 0/1:77,0,58:6:4 1/1:196,24,0:8:8 +17 3937 . C . . . END=4101 GT 0/0 0/0 0/0 |
| b |
| diff -r 000000000000 -r a531317a3527 test-data/mpileup.vcf --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/test-data/mpileup.vcf Mon May 02 17:27:10 2016 -0400 |
| b |
| b'@@ -0,0 +1,4127 @@\n+##fileformat=VCFv4.2\n+##FILTER=<ID=PASS,Description="All filters passed">\n+##samtoolsVersion=1.1-19-g6b249e2+htslib-1.1-74-g845c515\n+##samtoolsCommand=samtools mpileup -uvDV -b xxx//mpileup.bam.list -f xxx//mpileup.ref.fa.gz\n+##reference=file://xxx//mpileup.ref.fa.gz\n+##contig=<ID=17,length=81195210>\n+##ALT=<ID=X,Description="Represents allele(s) other than observed.">\n+##INFO=<ID=INDEL,Number=0,Type=Flag,Description="Indicates that the variant is an INDEL.">\n+##INFO=<ID=IDV,Number=1,Type=Integer,Description="Maximum number of reads supporting an indel">\n+##INFO=<ID=IMF,Number=1,Type=Float,Description="Maximum fraction of reads supporting an indel">\n+##INFO=<ID=DP,Number=1,Type=Integer,Description="Raw read depth">\n+##INFO=<ID=VDB,Number=1,Type=Float,Description="Variant Distance Bias for filtering splice-site artefacts in RNA-seq data (bigger is better)",Version="3">\n+##INFO=<ID=RPB,Number=1,Type=Float,Description="Mann-Whitney U test of Read Position Bias (bigger is better)">\n+##INFO=<ID=MQB,Number=1,Type=Float,Description="Mann-Whitney U test of Mapping Quality Bias (bigger is better)">\n+##INFO=<ID=BQB,Number=1,Type=Float,Description="Mann-Whitney U test of Base Quality Bias (bigger is better)">\n+##INFO=<ID=MQSB,Number=1,Type=Float,Description="Mann-Whitney U test of Mapping Quality vs Strand Bias (bigger is better)">\n+##INFO=<ID=SGB,Number=1,Type=Float,Description="Segregation based metric.">\n+##INFO=<ID=MQ0F,Number=1,Type=Float,Description="Fraction of MQ0 reads (smaller is better)">\n+##INFO=<ID=I16,Number=16,Type=Float,Description="Auxiliary tag used for calling, see description of bcf_callret1_t in bam2bcf.h">\n+##INFO=<ID=QS,Number=R,Type=Float,Description="Auxiliary tag used for calling">\n+##FORMAT=<ID=PL,Number=G,Type=Integer,Description="List of Phred-scaled genotype likelihoods">\n+##FORMAT=<ID=DP,Number=1,Type=Integer,Description="Number of high-quality bases">\n+##FORMAT=<ID=DV,Number=1,Type=Integer,Description="Number of high-quality non-reference bases">\n+#CHROM\tPOS\tID\tREF\tALT\tQUAL\tFILTER\tINFO\tFORMAT\tHG00100\tHG00101\tHG00102\n+17\t1\t.\tA\t<X>\t0\t.\tDP=11;I16=11,0,0,0,452,18594,0,0,319,9251,0,0,223,4959,0,0;QS=3,0;MQ0F=0\tPL:DP:DV\t0,15,100:5:0\t0,9,72:3:0\t0,9,72:3:0\n+17\t2\t.\tA\t<X>\t0\t.\tDP=11;I16=11,0,0,0,439,17587,0,0,319,9251,0,0,226,5030,0,0;QS=3,0;MQ0F=0\tPL:DP:DV\t0,15,100:5:0\t0,9,72:3:0\t0,9,72:3:0\n+17\t3\t.\tG\t<X>\t0\t.\tDP=11;I16=11,0,0,0,431,16971,0,0,319,9251,0,0,229,5111,0,0;QS=3,0;MQ0F=0\tPL:DP:DV\t0,15,100:5:0\t0,9,72:3:0\t0,9,72:3:0\n+17\t4\t.\tC\t<X>\t0\t.\tDP=11;I16=11,0,0,0,423,16417,0,0,319,9251,0,0,232,5202,0,0;QS=3,0;MQ0F=0\tPL:DP:DV\t0,15,100:5:0\t0,9,72:3:0\t0,9,71:3:0\n+17\t5\t.\tT\t<X>\t0\t.\tDP=11;I16=11,0,0,0,450,18520,0,0,319,9251,0,0,234,5252,0,0;QS=3,0;MQ0F=0\tPL:DP:DV\t0,15,100:5:0\t0,9,72:3:0\t0,9,72:3:0\n+17\t6\t.\tT\t<X>\t0\t.\tDP=11;I16=11,0,0,0,403,14847,0,0,319,9251,0,0,236,5310,0,0;QS=3,0;MQ0F=0\tPL:DP:DV\t0,15,100:5:0\t0,9,72:3:0\t0,9,72:3:0\n+17\t7\t.\tC\t<X>\t0\t.\tDP=11;I16=11,0,0,0,446,18114,0,0,319,9251,0,0,237,5327,0,0;QS=3,0;MQ0F=0\tPL:DP:DV\t0,15,100:5:0\t0,9,72:3:0\t0,9,72:3:0\n+17\t8\t.\tT\t<X>\t0\t.\tDP=11;I16=11,0,0,0,465,19677,0,0,319,9251,0,0,238,5354,0,0;QS=3,0;MQ0F=0\tPL:DP:DV\t0,15,100:5:0\t0,9,72:3:0\t0,9,72:3:0\n+17\t9\t.\tC\t<X>\t0\t.\tDP=11;I16=11,0,0,0,447,18205,0,0,319,9251,0,0,239,5391,0,0;QS=3,0;MQ0F=0\tPL:DP:DV\t0,15,100:5:0\t0,9,72:3:0\t0,9,72:3:0\n+17\t10\t.\tA\t<X>\t0\t.\tDP=11;I16=11,0,0,0,426,16756,0,0,319,9251,0,0,240,5438,0,0;QS=3,0;MQ0F=0\tPL:DP:DV\t0,15,100:5:0\t0,9,72:3:0\t0,9,69:3:0\n+17\t11\t.\tC\t<X>\t0\t.\tDP=11;I16=11,0,0,0,413,15603,0,0,319,9251,0,0,241,5495,0,0;QS=3,0;MQ0F=0\tPL:DP:DV\t0,15,100:5:0\t0,9,72:3:0\t0,9,72:3:0\n+17\t12\t.\tC\t<X>\t0\t.\tDP=11;I16=11,0,0,0,438,17506,0,0,319,9251,0,0,242,5562,0,0;QS=3,0;MQ0F=0\tPL:DP:DV\t0,15,100:5:0\t0,9,72:3:0\t0,9,72:3:0\n+17\t13\t.\tC\t<X>\t0\t.\tDP=11;I16=11,0,0,0,437,17463,0,0,319,9251,0,0,243,5639,0,0;QS=3,0;MQ0F=0\tPL:DP:DV\t0,15,100:5:0\t0,9,72:3:0\t0,9,72:3:0\n+17\t14\t.\tT\t<X>\t0\t.\tDP=11;I16=11,0,0,0,453,18715,0,0,319,9251,0,0,242,5628,0,0;QS=3,0;MQ0F=0\tPL:DP:DV\t0,15,100:5:0\t0,9,72:3:0\t0,9,72:3:0\n+17\t15\t.\tG\t'..b':DV\t0,15,142:5:0\t0,0,0:0:0\t0,0,0:0:0\n+17\t4072\t.\tG\t<X>\t0\t.\tDP=5;I16=2,2,0,0,138,4974,0,0,194,9938,0,0,55,987,0,0;QS=1,0;MQSB=0;MQ0F=0\tPL:DP:DV\t0,12,122:4:0\t0,0,0:0:0\t0,0,0:0:0\n+17\t4073\t.\tG\t<X>\t0\t.\tDP=5;I16=3,2,0,0,156,5082,0,0,254,13538,0,0,60,994,0,0;QS=1,0;MQSB=0.333333;MQ0F=0\tPL:DP:DV\t0,15,136:5:0\t0,0,0:0:0\t0,0,0:0:0\n+17\t4074\t.\tC\t<X>\t0\t.\tDP=5;I16=3,2,0,0,160,5602,0,0,254,13538,0,0,56,928,0,0;QS=1,0;MQSB=0.333333;MQ0F=0\tPL:DP:DV\t0,15,142:5:0\t0,0,0:0:0\t0,0,0:0:0\n+17\t4075\t.\tT\t<X>\t0\t.\tDP=5;I16=3,2,0,0,187,7069,0,0,254,13538,0,0,52,870,0,0;QS=1,0;MQSB=0.333333;MQ0F=0\tPL:DP:DV\t0,15,155:5:0\t0,0,0:0:0\t0,0,0:0:0\n+17\t4076\t.\tG\t<X>\t0\t.\tDP=5;I16=3,2,0,0,174,6298,0,0,254,13538,0,0,48,820,0,0;QS=1,0;MQSB=0.333333;MQ0F=0\tPL:DP:DV\t0,15,149:5:0\t0,0,0:0:0\t0,0,0:0:0\n+17\t4077\t.\tA\t<X>\t0\t.\tDP=4;I16=3,1,0,0,138,4810,0,0,194,9938,0,0,44,728,0,0;QS=1,0;MQSB=1;MQ0F=0\tPL:DP:DV\t0,12,121:4:0\t0,0,0:0:0\t0,0,0:0:0\n+17\t4078\t.\tT\t<X>\t0\t.\tDP=4;I16=3,1,0,0,143,5173,0,0,194,9938,0,0,40,644,0,0;QS=1,0;MQSB=1;MQ0F=0\tPL:DP:DV\t0,12,124:4:0\t0,0,0:0:0\t0,0,0:0:0\n+17\t4079\t.\tA\t<X>\t0\t.\tDP=4;I16=3,1,0,0,121,3847,0,0,194,9938,0,0,36,568,0,0;QS=1,0;MQSB=1;MQ0F=0\tPL:DP:DV\t0,12,107:4:0\t0,0,0:0:0\t0,0,0:0:0\n+17\t4080\t.\tT\t<X>\t0\t.\tDP=4;I16=3,0,0,0,106,3778,0,0,134,6338,0,0,25,451,0,0;QS=1,0;MQ0F=0\tPL:DP:DV\t0,9,87:3:0\t0,0,0:0:0\t0,0,0:0:0\n+17\t4081\t.\tT\t<X>\t0\t.\tDP=4;I16=3,1,0,0,106,2934,0,0,194,9938,0,0,28,440,0,0;QS=1,0;MQSB=1;MQ0F=0\tPL:DP:DV\t0,12,94:4:0\t0,0,0:0:0\t0,0,0:0:0\n+17\t4082\t.\tC\t<X>\t0\t.\tDP=3;I16=2,1,0,0,110,4042,0,0,134,6338,0,0,25,387,0,0;QS=1,0;MQSB=1;MQ0F=0\tPL:DP:DV\t0,9,103:3:0\t0,0,0:0:0\t0,0,0:0:0\n+17\t4083\t.\tC\t<X>\t0\t.\tDP=3;I16=2,1,0,0,104,3648,0,0,134,6338,0,0,22,340,0,0;QS=1,0;MQSB=1;MQ0F=0\tPL:DP:DV\t0,9,98:3:0\t0,0,0:0:0\t0,0,0:0:0\n+17\t4084\t.\tA\t<X>\t0\t.\tDP=2;I16=1,1,0,0,78,3050,0,0,97,4969,0,0,20,298,0,0;QS=1,0;MQSB=1;MQ0F=0\tPL:DP:DV\t0,6,74:2:0\t0,0,0:0:0\t0,0,0:0:0\n+17\t4085\t.\tC\t<X>\t0\t.\tDP=2;I16=1,1,0,0,62,1940,0,0,97,4969,0,0,18,260,0,0;QS=1,0;MQSB=1;MQ0F=0\tPL:DP:DV\t0,6,62:2:0\t0,0,0:0:0\t0,0,0:0:0\n+17\t4086\t.\tG\t<X>\t0\t.\tDP=2;I16=1,1,0,0,56,1640,0,0,97,4969,0,0,16,226,0,0;QS=1,0;MQSB=1;MQ0F=0\tPL:DP:DV\t0,6,56:2:0\t0,0,0:0:0\t0,0,0:0:0\n+17\t4087\t.\tC\t<X>\t0\t.\tDP=2;I16=1,1,0,0,69,2405,0,0,97,4969,0,0,14,196,0,0;QS=1,0;MQSB=1;MQ0F=0\tPL:DP:DV\t0,6,68:2:0\t0,0,0:0:0\t0,0,0:0:0\n+17\t4088\t.\tA\t<X>\t0\t.\tDP=1;I16=1,0,0,0,39,1521,0,0,37,1369,0,0,13,169,0,0;QS=1,0;MQ0F=0\tPL:DP:DV\t0,3,37:1:0\t0,0,0:0:0\t0,0,0:0:0\n+17\t4089\t.\tC\t<X>\t0\t.\tDP=1;I16=1,0,0,0,36,1296,0,0,37,1369,0,0,12,144,0,0;QS=1,0;MQ0F=0\tPL:DP:DV\t0,3,36:1:0\t0,0,0:0:0\t0,0,0:0:0\n+17\t4090\t.\tC\t<X>\t0\t.\tDP=1;I16=1,0,0,0,33,1089,0,0,37,1369,0,0,11,121,0,0;QS=1,0;MQ0F=0\tPL:DP:DV\t0,3,33:1:0\t0,0,0:0:0\t0,0,0:0:0\n+17\t4091\t.\tT\t<X>\t0\t.\tDP=1;I16=1,0,0,0,36,1296,0,0,37,1369,0,0,10,100,0,0;QS=1,0;MQ0F=0\tPL:DP:DV\t0,3,36:1:0\t0,0,0:0:0\t0,0,0:0:0\n+17\t4092\t.\tG\t<X>\t0\t.\tDP=1;I16=1,0,0,0,37,1369,0,0,37,1369,0,0,9,81,0,0;QS=1,0;MQ0F=0\tPL:DP:DV\t0,3,37:1:0\t0,0,0:0:0\t0,0,0:0:0\n+17\t4093\t.\tC\t<X>\t0\t.\tDP=1;I16=1,0,0,0,35,1225,0,0,37,1369,0,0,8,64,0,0;QS=1,0;MQ0F=0\tPL:DP:DV\t0,3,35:1:0\t0,0,0:0:0\t0,0,0:0:0\n+17\t4094\t.\tT\t<X>\t0\t.\tDP=1;I16=1,0,0,0,40,1600,0,0,37,1369,0,0,7,49,0,0;QS=1,0;MQ0F=0\tPL:DP:DV\t0,3,37:1:0\t0,0,0:0:0\t0,0,0:0:0\n+17\t4095\t.\tA\t<X>\t0\t.\tDP=1;I16=1,0,0,0,35,1225,0,0,37,1369,0,0,6,36,0,0;QS=1,0;MQ0F=0\tPL:DP:DV\t0,3,35:1:0\t0,0,0:0:0\t0,0,0:0:0\n+17\t4096\t.\tC\t<X>\t0\t.\tDP=1;I16=1,0,0,0,32,1024,0,0,37,1369,0,0,5,25,0,0;QS=1,0;MQ0F=0\tPL:DP:DV\t0,3,32:1:0\t0,0,0:0:0\t0,0,0:0:0\n+17\t4097\t.\tA\t<X>\t0\t.\tDP=1;I16=1,0,0,0,35,1225,0,0,37,1369,0,0,4,16,0,0;QS=1,0;MQ0F=0\tPL:DP:DV\t0,3,35:1:0\t0,0,0:0:0\t0,0,0:0:0\n+17\t4098\t.\tC\t<X>\t0\t.\tDP=1;I16=1,0,0,0,31,961,0,0,37,1369,0,0,3,9,0,0;QS=1,0;MQ0F=0\tPL:DP:DV\t0,3,31:1:0\t0,0,0:0:0\t0,0,0:0:0\n+17\t4099\t.\tT\t<X>\t0\t.\tDP=1;I16=1,0,0,0,32,1024,0,0,37,1369,0,0,2,4,0,0;QS=1,0;MQ0F=0\tPL:DP:DV\t0,3,32:1:0\t0,0,0:0:0\t0,0,0:0:0\n+17\t4100\t.\tC\t<X>\t0\t.\tDP=1;I16=1,0,0,0,27,729,0,0,37,1369,0,0,1,1,0,0;QS=1,0;MQ0F=0\tPL:DP:DV\t0,3,27:1:0\t0,0,0:0:0\t0,0,0:0:0\n+17\t4101\t.\tC\t<X>\t0\t.\tDP=1;I16=1,0,0,0,26,676,0,0,37,1369,0,0,0,0,0,0;QS=1,0;MQ0F=0\tPL:DP:DV\t0,3,26:1:0\t0,0,0:0:0\t0,0,0:0:0\n' |
| b |
| diff -r 000000000000 -r a531317a3527 tool_dependencies.xml --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/tool_dependencies.xml Mon May 02 17:27:10 2016 -0400 |
| b |
| @@ -0,0 +1,6 @@ +<?xml version="1.0"?> +<tool_dependency> + <package name="samtools" version="0.1.19"> + <repository changeset_revision="95d2c4aefb5f" name="package_samtools_0_1_19" owner="devteam" toolshed="https://toolshed.g2.bx.psu.edu" /> + </package> +</tool_dependency> |