annotate macros.xml @ 2:98d4a7bfec83 draft

planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/bcftools commit 44bebb8a97d64015cbba59f0663e2541035112b6

<macros>
  <token name="@VERSION@">1.3</token>
  <xml name="stdio">
    <stdio>
      <exit_code range="1:" />
      <exit_code range=":-1" />
      <regex match="Error:" />
      <regex match="Exception:" />
    </stdio>
  </xml>
  <xml name="requirements">
    <requirements>
      <requirement type="package" version="1.3">bcftools</requirement>
      <!-- conda dependency -->
      <requirement type="package" version="1.3">htslib</requirement>
      <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&gt;&amp;1 | grep 'Version:'</version_command>
  </xml>
  
  <xml name="citations">
    <citations>
      <citation type="doi">10.1093/bioinformatics/btp352</citation>
      <yield />
    </citations>
  </xml>
  <token name="@BCFTOOLS_WIKI@">https://github.com/samtools/bcftools/wiki</token>
  <token name="@BCFTOOLS_MANPAGE@">http://samtools.github.io/bcftools/bcftools.html</token>
  <token name="@THREADS@">
  --threads \${GALAXY_SLOTS:-4}
  </token>
  <token name="@PREPARE_ENV@">
<![CDATA[
export BCFTOOLS_PLUGINS=`which bcftools | sed 's,bin/bcftools,libexec/bcftools,'`;
]]>
  </token>
  <xml name="macro_input">
    <param name="input_file" type="data" format="vcf,vcf_bgzip,bcf,bcf_bgzip" label="VCF/BCF Data" />
  </xml>
  <token name="@PREPARE_INPUT_FILE@">
<![CDATA[
## May need to symlink input if there is an associated
#set $input_vcf = 'input.vcf.gz'
#if $input_file.datatype.file_ext == 'vcf'
  bgzip -c "$input_file" > $input_vcf &&
  bcftools index $input_vcf &&
#elif $input_file.datatype.file_ext == 'vcf_bgzip'
  ln -s "$input_file" $input_vcf
#elif $input_file.datatype.file_ext == 'bcf'
  #set $input_vcf = 'input.bcf'
  ln -s "$input_file" $input_vcf && 
  #if $input_file.metadata.bcf_index:
    ln -s $input_file.metadata.bcf_index ${input_vcf}.csi &&
  #else 
    bcftools index $input_vcf &&
  #end if
#elif $input_file.datatype.file_ext == 'bcf_bgzip'
  ln -s "$input_file" $input_vcf
#end if
]]>
  </token>
  <token name="@INPUT_FILE@">
$input_vcf
  </token>

  <xml name="macro_inputs">
    <param name="input_files" type="data" format="vcf,bcf" label="Other VCF/BCF Datasets" multiple="True" />
  </xml>
  <token name="@PREPARE_INPUT_FILES@">
<![CDATA[
## May need to symlink input if there is an associated
#set $input_vcfs = []
#set $vcfs_list_file = 'vcfs_list'
#for (i,input_file) in enumerate($input_files):
  #set $input_vcf = 'input' + str($i) + '.vcf.gz'
  #if $input_file.datatype.file_ext == 'vcf'
    bgzip -c "$input_file" > $input_vcf &&
    bcftools index $input_vcf &&
  #elif $input_file.datatype.file_ext == 'vcf_bgz'
    ln -s "$input_file" $input_vcf
  #elif $input_file.datatype.file_ext == '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 
      bcftools index $input_vcf &&
    #end if
  #elif $input_file.datatype.file_ext == 'bcfvcf_bgz'
    ln -s "$input_file" $input_vcf &&
  #end if
  echo '$input_vcf' >> $vcfs_list_file &&
  $input_vcfs.append($input_vcf)
#end for
]]>
  </token>
  <token name="@INPUT_FILES@">
#echo ' '.join($input_vcfs)#
  </token>
  <token name="@INPUT_LIST_FILE@">
$vcfs_list_file
  </token>

  <xml name="macro_fasta_ref">
    <param name="fasta_ref" type="data" format="data" label="Fasta Ref" optional="True" help="reference sequence in fasta format" />
  </xml>
  <token name="@PREPARE_FASTA_REF@">
<![CDATA[
#set $input_fa_ref = None
#if 'fasta_ref' in $section and $section.fasta_ref:
  #set $input_fa_ref = 'ref.fa'
  ln -s $section.fasta_ref $input_fa_ref &&
  samtools faidx $input_fa_ref &&
#end if
]]>
  </token>
  <token name="@FASTA_REF@">
#if $input_fa_ref is not None:
  --fasta-ref  "$input_fa_ref"
#elif 'fasta_ref' in $section and $section.fasta_ref:
  --fasta-ref "${section.fasta_ref}"
#end if
  </token>

  <xml name="macro_ref_fasta">
    <conditional name="reference_source">
       <param name="reference_source_selector" type="select" label="Choose the source for the reference genome">
         <option value="cached">Locally cached</option>
         <option value="history">History</option>
       </param>
       <when value="cached">
         <param name="ref_file" type="select" label="Select reference genome">
           <options from_data_table="fasta_indexes">
             <!--<filter type="data_meta" key="dbkey" ref="input_bam" column="value"/>-->
           </options>
           <validator type="no_options" message="A built-in reference genome is not available for the build associated with the selected input file"/>
         </param>
       </when>
       <when value="history"> <!-- FIX ME!!!! -->
         <param name="ref_file" type="data" format="fasta" label="Using reference file" />
       </when>
     </conditional>
  </xml>


  <xml name="macro_AF_file">
    <param name="AF_file" type="data" format="data" label="Af File" optional="True" help="read allele frequencies from file (CHR\tPOS\tREF,ALT\tAF)" />
  </xml>
  <!-- This may need to bgzip and tabix the file -->
  <token name="@PREPARE_AF_FILE@">
<![CDATA[
#if 'AF_file' in $section and $section.AF_file:
#pass
#end if
]]>
  </token>
  <token name="@AF_FILE@">
#if 'AF_file' in $section and $section.AF_file:
  --AF-file "${section.AF_file}"
#end if
  </token>

  <xml name="macro_estimate_AF">
      <param name="estimate_AF" type="data" format="data" label="Estimate Af" optional="True" help="calculate AC,AN counts on the fly, using either all samples (&quot;-&quot;) or samples listed in &lt;file&gt;" />
  </xml>
  <token name="@ESTIMATE_AF@">
#if 'estimate_AF' in $section and $section.estimate_AF:
  --estimate-AF "${section.estimate_AF}"
#end if
  </token>

  <xml name="macro_exons_file">
    <param name="exons_file" type="data" format="tabular" label="exons file" optional="True" help="tab-delimited file with exons for indel frameshifts (chr,from,to; 1-based, inclusive, bgzip compressed)" />
  </xml>
  <token name="@PREPARE_EXONS_FILE@">
<![CDATA[
#set $exons_path = None
#if 'exons_file' in $section and $section.exons_file:
    #set $exons_path = 'exons_file.tab.gz'
    bgzip -c "$section.exons_file" > $exons_path &&
    tabix -s 1 -b 2 -e 3 $exons_path &&
#end if
]]>
  </token>
  <token name="@EXONS_FILE@">
#if 'exons_file' in $section and $section.exons_file:
  --exons $exons_path
#end if
  </token>

  <xml name="macro_ploidy_file">
    <param name="ploidy_file" type="data" format="tabular" label="Ploidy file" optional="True" help="tab-delimited list of CHROM,FROM,TO,SEX,PLOIDY" />
  </xml>
  <token name="@PLOIDY_FILE@">
#if 'ploidy_file' in $section and $section.ploidy_file:
  --ploidy "${section.ploidy_file}"
#end if
  </token>

  <xml name="macro_collapse_opt_none">
      <option value="none">none - require the exact same set of alleles in all files</option>
  </xml>
  <xml name="macro_collapse_opt_id">
      <option value="id">id - only records with identical ID column are compatible. </option>
  </xml>
  <xml name="macro_collapse">
    <param name="collapse" type="select" label="Collapse" optional="True" help="Controls how to treat records with duplicate positions and defines compatible records across multiple input files">
      <option value="snps">snps - allow different alleles, as long as they all are SNPs</option>
      <option value="indels">indels - allow different alleles, as long as they all are indels</option>
      <option value="both">both - indels and snps </option>
      <option value="some">some - at least some of the ALTs must match</option>
      <option value="any">any - any combination of alleles</option>
      <yield/>
    </param>
  </xml>
  <token name="@COLLAPSE@">
#if $section.collapse:
  --collapse "${section.collapse}"
#end if
  </token>

  <xml name="macro_apply_filters">
    <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. &quot;PASS,.&quot;)">
      <validator type="regex" message="FILTER terms separated by commas">^([^ \t\n\r\f\v,]+(,[^ \t\n\r\f\v,]+)*)?$</validator>
    </param>
  </xml>
  <token name="@APPLY_FILTERS@">
#if $section.apply_filters:
  --apply-filters "${section.apply_filters}"
#end if
  </token>

  <xml name="macro_select_output_type">
    <param name="output_type" type="select">
      <option value="b">compressed BCF</option>
      <!-- no galaxy datatypes for these
      <option value="u">uncompressed BCF</option>
      <option value="z">compressed VCF</option>
      -->
      <option value="v">uncompressed VCF</option>
    </param>
  </xml>
  <token name="@OUTPUT_TYPE@">
#if str($output_type) != "__none__":
  --output-type "${output_type}"
#end if
  </token>

  <xml name="macro_vcf_output">
      <data name="output_file" format="vcf">
        <change_format>
          <when input="output_type" value="b" format="bcf" />
          <when input="output_type" value="u" format="bcf" />
          <when input="output_type" value="z" format="vcf_bgzip" />
          <when input="output_type" value="v" format="vcf" />
        </change_format>
      </data>
  </xml>

  <xml name="macro_regions">
    <conditional name="regions">
        <param name="regions_src" type="select" label="Regions">
            <option value="__none__">None</option>
            <option value="regions">regions</option>
            <option value="regions_file">regions-file</option>
        </param>
        <when value="__none__"/>
        <when value="regions">
            <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>
        </when>
        <when value="regions_file">
            <param name="regions_file" type="data" format="vcf,bed,tabular" label="Regions File" optional="True" help="restrict to regions listed in a file" />
        </when>
    </conditional>
  </xml>
  <token name="@REGIONS@">
#if $section.regions.regions_src == 'regions' and $section.regions.regions != '':
  --regions "$section.regions.regions"
#elif $section.regions.regions_src == 'regions_file' and $section.regions.regions_file:
  --regions-file "$section.regions.regions_file"
#end if
  </token>

  <xml name="macro_targets_file">
            <param name="targets_file" type="data" format="tabular" label="Targets File" help="restrict to targets listed in a file" >
              <yield/>
            </param>
            <param name="invert_targets_file" type="boolean" truevalue="^" falsevalue="" label="Invert Targets" help="inverts the query/filtering applied by the target file selection" />
  </xml>
  <token name="@PREPARE_TARGETS_FILE@">
<![CDATA[
#set $targets_path = None
#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 &&
    tabix -s 1 -b 2 -e 2 $targets_path &&
  #end if
#elif $tgts_sec.targets_file:
  #set $targets_path = 'targets_file.tab.gz'
  bgzip -c "$section.targets_file" > $targets_path &&
  tabix -s 1 -b 2 -e 2 $targets_path &&
#end if
]]>
  </token>
  <token name="@TARGETS_FILE@">
<![CDATA[
#if $targets_path is not None:
  --targets-file "${section.invert_targets_file}${targets_path}"
#elif $section.targets_file:
  --targets-file "${section.invert_targets_file}${section.targets_file}"
#end if
]]>
  </token>

  <xml name="macro_targets">
    <conditional name="targets">
        <param name="targets_src" type="select" label="Targets">
            <option value="__none__">None</option>
            <option value="targets">targets</option>
            <option value="targets_file">targets-file</option>
        </param>
        <when value="__none__"/>
        <when value="targets">
            <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>
            <param name="invert_targets_file" type="boolean" truevalue="^" falsevalue="" label="Invert Targets" help="inverts the query/filtering applied by the targets" />
        </when>
        <when value="targets_file">
            <expand macro="macro_targets_file">
            </expand>
        </when>
    </conditional>
  </xml>
  <token name="@TARGETS@">
<![CDATA[
#if $targets_path:
  --targets-file "${section.targets.invert_targets_file}${targets_path}"
#else:
  #if $section.targets.targets_src == 'targets' and $section.targets.targets != '':
    --targets "${section.targets.invert_targets_file}${section.targets.targets}"
  #elif $section.targets.targets_src == 'targets_file' and $section.targets.targets_file:
    --targets-file "${section.targets.invert_targets_file}${section.targets.targets_file}"
  #end if
#end if
]]>
  </token>

  <xml name="macro_samples">
      <param name="samples" type="text" value="" label="Samples" optional="true" 
             help="(-s) comma separated list of samples to annotate (or exclude with &quot;^&quot; prefix)">
          <validator type="regex" message="">^(\w+(,\w+)*)?$</validator>
      </param>
      <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" 
             help="(-S) file of samples to include" />
      <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@">
#set $samples_defined = False
#if str($section.samples) != '':
  #set $samples_defined = True
  --samples "${section.invert_samples}${section.samples}"
#end if
#if $section.samples_file:
  #set $samples_defined = True
  --samples-file "${section.invert_samples_file}${section.samples_file}"
#end if
  </token>

  <xml name="macro_sample">
      <param name="sample" type="text" label="Sample" optional="True" help="apply variants of the given sample" />
  </xml>
  <token name="@SAMPLE@">
#if $section.sample:
  --sample "${section.sample}"
#end if
  </token>


  <xml name="macro_include">
    <param name="include" type="text" label="Include" optional="True" help="(-i) select sites for which the expression is true">
        <validator type="regex" message="Single quote not allowed">^[^']*$</validator>
        <sanitizer sanitize="False"/>
    </param>
  </xml>
  <token name="@INCLUDE@">
#if $section.include:
  --include '${section.include}'
#end if
  </token>

  <xml name="macro_exclude">
    <param name="exclude" type="text" label="Exclude" optional="True" help="(-e) exclude sites for which the expression is true">
        <validator type="regex" message="Single quote not allowed">^[^']*$</validator>
        <sanitizer sanitize="False"/>
    </param>
  </xml>
  <token name="@EXCLUDE@">
#if $section.exclude:
  --exclude '${section.exclude}'
#end if
  </token>

  <xml name="macro_columns">
    <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>
  </xml>
  <token name="@COLUMNS@">
#if $section.columns != '':
  --columns "${section.columns}"
#end if
  </token>

  <xml name="macro_haploid2diploid">
    <param name="haploid2diploid" type="boolean" truevalue="--haploid2diploid" falsevalue="" label="Haploid2Diploid" help="convert haploid genotypes to diploid homozygotes" />
  </xml>

  <xml name="macro_vcf_ids">
    <param name="vcf_ids" type="boolean" truevalue="--vcf-ids" falsevalue="" label="Vcf Ids" help="output VCF IDs instead of CHROM:POS_REF_ALT" />
  </xml>
  <token name="@VCF_IDS@">
${section.vcf_ids}
  </token>

  <token name="@OUTPUT_HELP@">
      <![CDATA[
Output Type
-----------

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.

This Galaxy tool recommends using the compressed BCF format
as piping is not implemented, and uncompressed data would
use unnecessary amounts of space.

]]></token>
  <token name="@REGIONS_HELP@">
      <![CDATA[
Region Selections
-----------------

Regions can be specified in a VCF,
BED, or tab-delimited file (the default). The columns of the
tab-delimited file are: CHROM, POS, and, optionally, POS_TO,
where positions are 1-based and inclusive. Uncompressed
files are stored in memory, while bgzip-compressed and
tabix-indexed region files are streamed. Note that sequence
names must match exactly, "chr20" is not the same as "20".
Also note that chromosome ordering in FILE will be
respected, the VCF will be processed in the order in which
chromosomes first appear in FILE. However, within
chromosomes, the VCF will always be processed in ascending
genomic coordinate order no matter what order they appear in
FILE. Note that overlapping regions in FILE can result in
duplicated out of order positions in the output. This option
requires indexed VCF/BCF files.

]]></token>
  <token name="@TARGETS_HELP@"><![CDATA[
Targets
-------

Similar to regions, but the next position is accessed by streaming the whole
VCF/BCF rather than using the tbi/csi index. Both regions and targets options can be
applied simultaneously: regions uses the index to jump to a region and targets discards
positions which are not in the targets. Unlike regions, targets can be prefixed with
"^" to request logical complement. For example, "^X,Y,MT" indicates that
sequences X, Y and MT should be skipped. Yet another difference between the two
is that regions checks both start and end positions of indels, whereas targets checks
start positions only.

For the bcftools call command, with the option -C alleles, third column of the
targets file must be comma-separated list of alleles, starting with the
reference allele. Note that the file must be compressed and index. Such a file
can be easily created from a VCF using::

    bcftools query -f'%CHROM\t%POS\t%REF,%ALT\n' file.vcf | bgzip -c > als.tsv.gz && tabix -s1 -b2 -e2 als.tsv.gz
      ]]>
      <!-- TODO: galaxy-ify -->
  </token>


  <token name="@COLLAPSE_HELP@">
Collapse
--------

Controls how to treat records with duplicate positions and defines compatible
records across multiple input files. Here by "compatible" we mean records which
should be considered as identical by the tools. For example, when performing
line intersections, the desire may be to consider as identical all sites with
matching positions (bcftools isec -c all), or only sites with matching variant
type (bcftools isec -c snps  -c indels), or only sites with all alleles
identical (bcftools isec -c none).


+------------+----------------------------------------------------------------+
| Flag value | Result                                                         |
+============+================================================================+
| none       | only records with identical REF and ALT alleles are compatible |
+------------+----------------------------------------------------------------+
| some       | only records where some subset of ALT alleles match are        |
|            | compatible                                                     |
+------------+----------------------------------------------------------------+
| all        | all records are compatible, regardless of whether the ALT      |
|            | alleles match or not. In the case of records with the same     |
|            | position, only the first wil lbe considered and appear on      |
|            | output.                                                        |
+------------+----------------------------------------------------------------+
| snps       | any SNP records are compatible, regardless of whether the ALT  |
|            | alleles match or not. For duplicate positions, only the first  |
|            | SNP record will be considered and appear on output.            |
+------------+----------------------------------------------------------------+
| indels     | all indel records are compatible, regardless of whether the    |
|            | REF and ALT alleles match or not. For duplicate positions,     |
|            | only the first indel record will be considered and appear on   |
|            | output.                                                        |
+------------+----------------------------------------------------------------+
| both       | abbreviation of "-c indels  -c snps"                           |
+------------+----------------------------------------------------------------+
| id         | only records with identical ID column are compatible.          |
|            | Supportedby bcftools merge only.                               |
+------------+----------------------------------------------------------------+

  </token>

  <token name="@EXPRESSIONS_HELP@">
      <![CDATA[
Expressions
-----------

Valid expressions may contain:

-  numerical constants, string constants

   ::

      1, 1.0, 1e-4
      "String"

-  arithmetic operators

   ::

      +,*,-,/

-  comparison operators

   ::

      == (same as =), >, >=, <=, <, !=

-  regex operators "~" and its negation "!~"

   ::

      INFO/HAYSTACK ~ "needle"

-  parentheses

   ::

      (, )

-  logical operators

   ::

      && (same as &), ||,  |

-  INFO tags, FORMAT tags, column names

   ::

      INFO/DP or DP
      FORMAT/DV, FMT/DV, or DV
      FILTER, QUAL, ID, REF, ALT[0]

-  1 (or 0) to test the presence (or absence) of a flag

   ::

      FlagA=1 && FlagB=0

-  "." to test missing values

   ::

      DP=".", DP!=".", ALT="."

-  missing genotypes can be matched regardless of phase and ploidy (".|.", "./.", ".") using this expression

   ::

      GT="."

-  TYPE for variant type in REF,ALT columns (indel,snp,mnp,ref,other)

   ::

      TYPE="indel" | TYPE="snp"

-  array subscripts, "*" for any field

   ::

      (DP4[0]+DP4[1])/(DP4[2]+DP4[3]) > 0.3
      DP4[*] == 0
      CSQ[*] ~ "missense_variant.*deleterious"

-  function on FORMAT tags (over samples) and INFO tags (over vector fields)

   ::

      MAX, MIN, AVG, SUM, STRLEN, ABS

-  variables calculated on the fly if not present: number of alternate alleles; number of samples; count of alternate alleles; minor allele count (similar to AC but is always smaller than 0.5); frequency of alternate alleles (AF=AC/AN); frequency of minor alleles (MAF=MAC/AN); number of alleles in called genotypes

   ::

      N_ALT, N_SAMPLES, AC, MAC, AF, MAF, AN

**Notes:**

-  String comparisons and regular expressions are case-insensitive
-  If the subscript "*" is used in regular expression search, the whole field
   is treated as one string. For example, the regex ``STR[*]~"B,C"`` will be
   true for the string vector INFO/STR=AB,CD.
-  Variables and function names are case-insensitive, but not tag names. For
   example, "qual" can be used instead of "QUAL", "strlen()" instead of
   "STRLEN()" , but not "dp" instead of "DP".

**Examples:**

   ::

      MIN(DV)>5
      MIN(DV/DP)>0.3
      MIN(DP)>10 & MIN(DV)>3
      FMT/DP>10  & FMT/GQ>10 .. both conditions must be satisfied within one sample
      FMT/DP>10 && FMT/GQ>10 .. the conditions can be satisfied in different samples
      QUAL>10 |  FMT/GQ>10   .. selects only GQ>10 samples
      QUAL>10 || FMT/GQ>10   .. selects all samples at QUAL>10 sites
      TYPE="snp" && QUAL>=10 && (DP4[2]+DP4[3] > 2)
      MIN(DP)>35 && AVG(GQ)>50
      ID=@file       .. selects lines with ID present in the file
      ID!=@~/file    .. skip lines with ID present in the ~/file
      MAF[0]<0.05    .. select rare variants at 5% cutoff

]]></token>




</macros>