Mercurial > repos > iuc > bcftools_annotate
changeset 3:12c14f97429b draft
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/bcftools commit 9df9b52baf62b70fbcfc3fbe965d7197d4e8738e
| author | iuc |
|---|---|
| date | Tue, 31 Jan 2017 12:41:19 -0500 |
| parents | 06a488b9cd34 |
| children | 7b10a015526e |
| files | bcftools_annotate.xml macros.xml |
| diffstat | 2 files changed, 40 insertions(+), 38 deletions(-) [+] |
line wrap: on
line diff
--- a/bcftools_annotate.xml Mon Oct 03 12:16:18 2016 -0400 +++ b/bcftools_annotate.xml Tue Jan 31 12:41:19 2017 -0500 @@ -13,12 +13,12 @@ #set $annotation_file = None #set $annotation_hdr = None #set $section = $sec_annofile -#if $section.annofile.anno_fmt == 'vcf': +#if $section.annofile.anno_fmt == 'vcf': #set $annotation_file = 'annotations.vcf.gz' bgzip -c "$section.annofile.annotations" > $annotation_file && bcftools index $annotation_file && #elif $section.annofile.anno_fmt == 'tab': - #if $section.annofile.annotations.ext == 'bed' + #if $section.annofile.annotations.is_of_type('bed') #set $annotation_file = 'annotations.bed.gz' bgzip -c "$section.annofile.annotations" > $annotation_file && tabix -s 1 -b 2 -e 3 $annotation_file && @@ -87,7 +87,7 @@ <section name="sec_annofile" expanded="false" title="Add Annotations"> <expand macro="macro_columns" /> <conditional name="annofile"> - <param name="anno_fmt" type="select" label="Annotations File"> + <param name="anno_fmt" type="select" label="Annotations File"> <option value="none">None</option> <option value="vcf">From a VCF/BCF file</option> <option value="tab">From a BED or tab-delimited file</option> @@ -99,9 +99,9 @@ <when value="tab"> <param name="annotations" type="data" format="tabular,bed" label="Annotations"> <help><![CDATA[ - BED, or a tab-delimited file with mandatory columns CHROM, POS (or, alternatively, FROM and TO), - optional columns REF and ALT, and arbitrary number of annotation columns. - Note that in case of tab-delimited file, the coordinates POS, FROM and TO are one-based and inclusive. + BED, or a tab-delimited file with mandatory columns CHROM, POS (or, alternatively, FROM and TO), + optional columns REF and ALT, and arbitrary number of annotation columns. + Note that in case of tab-delimited file, the coordinates POS, FROM and TO are one-based and inclusive. ]]></help> </param> <param name="header_file" type="data" format="txt" label="Header Lines File" optional="True" help="lines which should be appended to the VCF header" /> @@ -114,12 +114,12 @@ </param> </when> </conditional> - <param name="mark_sites" type="text" value="" label="Mark Sites TAG" + <param name="mark_sites" type="text" value="" label="Mark Sites TAG" help="add INFO/TAG flag to sites which are ("+") or are not ("-") listed in the annotations file" /> <param name="set_id" type="text" value="" optional="true" label="Set Id"> <help>Assign ID on the fly using the given format. - By default all existing IDs are replaced. - If the format string is preceded by "+", only missing IDs will be set. + By default all existing IDs are replaced. + If the format string is preceded by "+", only missing IDs will be set. For example: '%CHROM\_%POS\_%REF\_%FIRST_ALT' </help> <sanitizer sanitize="False"/> @@ -127,17 +127,17 @@ </param> </section> <section name="sec_annotate" expanded="false" title="Change Annotations"> - <param name="remove" type="text" value="" label="Remove annotations" optional="true"> + <param name="remove" type="text" value="" label="Remove annotations" optional="true"> <help><![CDATA[ - List of annotations to remove. - Use "FILTER" to remove all filters or "FILTER/SomeFilter" to remove a specific filter. - Similarly, "INFO" can be used to remove all INFO tags and "FORMAT" to remove all FORMAT tags except GT. - To remove all INFO tags except "FOO" and "BAR", use "^INFO/FOO,INFO/BAR" (and similarly for FORMAT and FILTER). - "INFO" can be abbreviated to "INF" and "FORMAT" to "FMT". + List of annotations to remove. + Use "FILTER" to remove all filters or "FILTER/SomeFilter" to remove a specific filter. + Similarly, "INFO" can be used to remove all INFO tags and "FORMAT" to remove all FORMAT tags except GT. + To remove all INFO tags except "FOO" and "BAR", use "^INFO/FOO,INFO/BAR" (and similarly for FORMAT and FILTER). + "INFO" can be abbreviated to "INF" and "FORMAT" to "FMT". ]]></help> <validator type="regex" message="">^(\^?[A-Z]+(/\w+)?(,\^?[A-Z]+(/\w+)?)*)?$</validator> </param> - <param name="rename_chrs" type="data" format="tabular" label="Rename CHROM" optional="True" + <param name="rename_chrs" type="data" format="tabular" label="Rename CHROM" optional="True" help="rename chromosomes according to the map in file, with old_name new_name pairs separated by whitespaces, each on a separate line." /> </section> <section name="sec_restrict" expanded="false" title="Restrict to">
--- a/macros.xml Mon Oct 03 12:16:18 2016 -0400 +++ b/macros.xml Tue Jan 31 12:41:19 2017 -0500 @@ -14,14 +14,16 @@ <requirement type="package" version="1.3">bcftools</requirement> <!-- conda dependency --> <requirement type="package" version="1.3">htslib</requirement> + <!-- htslib provides tabix and bgzip <requirement type="package" version="0.2.6">tabix</requirement> + --> <requirement type="package" version="1.2">samtools</requirement> </requirements> </xml> <xml name="version_command"> <version_command>bcftools 2>&1 | grep 'Version:'</version_command> </xml> - + <xml name="citations"> <citations> <citation type="doi">10.1093/bioinformatics/btp352</citation> @@ -45,20 +47,20 @@ <![CDATA[ ## May need to symlink input if there is an associated #set $input_vcf = 'input.vcf.gz' -#if $input_file.datatype.file_ext == 'vcf' +#if $input_file.is_of_type('vcf') bgzip -c "$input_file" > $input_vcf && bcftools index $input_vcf && -#elif $input_file.datatype.file_ext == 'vcf_bgzip' +#elif $input_file.is_of_type('vcf_bgzip') ln -s "$input_file" $input_vcf -#elif $input_file.datatype.file_ext == 'bcf' +#elif $input_file.is_of_type('bcf') #set $input_vcf = 'input.bcf' - ln -s "$input_file" $input_vcf && + ln -s "$input_file" $input_vcf && #if $input_file.metadata.bcf_index: ln -s $input_file.metadata.bcf_index ${input_vcf}.csi && - #else + #else bcftools index $input_vcf && #end if -#elif $input_file.datatype.file_ext == 'bcf_bgzip' +#elif $input_file.is_of_type('bcf_bgzip') ln -s "$input_file" $input_vcf #end if ]]> @@ -77,21 +79,21 @@ #set $vcfs_list_file = 'vcfs_list' #for (i,input_file) in enumerate($input_files): #set $input_vcf = 'input' + str($i) + '.vcf.gz' - #if $input_file.datatype.file_ext == 'vcf' + #if $input_file.is_of_type('vcf') bgzip -c "$input_file" > $input_vcf && bcftools index $input_vcf && - #elif $input_file.datatype.file_ext == 'vcf_bgz' + #elif $input_file.is_of_type('vcf_bgz') ln -s "$input_file" $input_vcf - #elif $input_file.datatype.file_ext == 'bcf' + #elif $input_file.is_of_type('bcf') #set $input_vcf = 'input' + str($i) + '.bcf.gz' ## bgzip -c "$input_file" > $input_vcf && ln -s "$input_file" $input_vcf && #if $input_file.metadata.bcf_index: ln -s $input_file.metadata.bcf_index ${input_vcf}.csi && - #else + #else bcftools index $input_vcf && #end if - #elif $input_file.datatype.file_ext == 'bcfvcf_bgz' + #elif $input_file.is_of_type('bcfvcf_bgz') ln -s "$input_file" $input_vcf && #end if echo '$input_vcf' >> $vcfs_list_file && @@ -225,7 +227,7 @@ </token> <xml name="macro_apply_filters"> - <param name="apply_filters" type="text" value="" label="Apply Filters" optional="true" + <param name="apply_filters" type="text" value="" label="Apply Filters" optional="true" help="(-f --apply-filters) Skip sites where FILTER column does not contain any of the strings listed (e.g. "PASS,.")"> <validator type="regex" message="FILTER terms separated by commas">^([^ \t\n\r\f\v,]+(,[^ \t\n\r\f\v,]+)*)?$</validator> </param> @@ -272,7 +274,7 @@ </param> <when value="__none__"/> <when value="regions"> - <param name="regions" type="text" value="" label="restrict to comma-separated list of regions" optional="true" + <param name="regions" type="text" value="" label="restrict to comma-separated list of regions" optional="true" help="Each region is specifed as: chr or chr:pos or chr:from-to"> <validator type="regex" message="">^(\w+(:\d+(-\d+)?)?(,\w+(:\d+(-\d+)?)?)*)?$</validator> </param> @@ -299,7 +301,7 @@ <token name="@PREPARE_TARGETS_FILE@"> <![CDATA[ #set $targets_path = None -#if 'targets' in $section +#if 'targets' in $section #if $section.targets.targets_src == 'targets_file': #set $targets_path = 'targets_file.tab.gz' bgzip -c "$section.targets.targets_file" > $targets_path && @@ -331,7 +333,7 @@ </param> <when value="__none__"/> <when value="targets"> - <param name="targets" type="text" value="" label="Restrict to comma-separated list of targets" optional="true" + <param name="targets" type="text" value="" label="Restrict to comma-separated list of targets" optional="true" help="Each target is specifed as: chr or chr:pos or chr:from-to"> <validator type="regex" message="">^(\w+(:\d+(-\d+)?)?(,\w+(:\d+(-\d+)?)?)*)?$</validator> </param> @@ -358,15 +360,15 @@ </token> <xml name="macro_samples"> - <param name="samples" type="text" value="" label="Samples" optional="true" + <param name="samples" type="text" value="" label="Samples" optional="true" help="(-s) comma separated list of samples to annotate (or exclude with "^" prefix)"> <validator type="regex" message="">^(\w+(,\w+)*)?$</validator> </param> - <param name="invert_samples" type="boolean" truevalue="^" falsevalue="" checked="false" label="Invert Samples" + <param name="invert_samples" type="boolean" truevalue="^" falsevalue="" checked="false" label="Invert Samples" help="inverts the query/filtering applied by Samples" /> - <param name="samples_file" type="data" format="tabular" label="Samples File" optional="True" + <param name="samples_file" type="data" format="tabular" label="Samples File" optional="True" help="(-S) file of samples to include" /> - <param name="invert_samples_file" type="boolean" truevalue="^" falsevalue="" checked="false" label="Invert Samples File" + <param name="invert_samples_file" type="boolean" truevalue="^" falsevalue="" checked="false" label="Invert Samples File" help="inverts the query/filtering applied by Samples File" /> </xml> <token name="@SAMPLES@"> @@ -416,7 +418,7 @@ </token> <xml name="macro_columns"> - <param name="columns" type="text" value="" label="Columns" optional="true" + <param name="columns" type="text" value="" label="Columns" optional="true" help="list of columns in the annotation file, e.g. CHROM,POS,REF,ALT,-,INFO/TAG. See man page for details"> <validator type="regex" message="COLUMN names separated by commas">^([^,]+(,[^,]+)*)?$</validator> </param> @@ -443,7 +445,7 @@ Output Type ----------- -Output compressed BCF (b), or uncompressed VCF (v). +Output compressed BCF (b), or uncompressed VCF (v). Use the BCF option when piping between bcftools subcommands to speed up performance by removing unecessary compression/decompression and VCF<->BCF conversion.