comparison bcftools_roh.xml @ 5:0be3ea214c4e draft

planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/bcftools commit 10853682ffb2e9776256bb63c899ef5c5fe0007e

4:81049a32c117

<?xml version='1.0' encoding='utf-8'?>
<tool name="bcftools @EXECUTABLE@" id="bcftools_@EXECUTABLE@" version="@VERSION@.0">
    <description>HMM model for detecting runs of autozygosity</description>
    <macros>
        <token name="@EXECUTABLE@">roh</token>
        <import>macros.xml</import>
    </macros>
    <expand macro="requirements" />

    <command detect_errors="aggressive"><![CDATA[
@PREPARE_ENV@
@PREPARE_INPUT_FILE@
#set $section = $sec_restrict
@PREPARE_TARGETS_FILE@
## General section
#set $section = $sec_general
@PREPARE_AF_FILE@

bcftools @EXECUTABLE@

  --genetic-map "${section.genetic_map}"
#end if
#if $section.rec_rate:
  --rec-rate "${section.rec_rate}"
#end if

## HMM section
#set $section = $sec_hmm
#if $section.hw_to_az:
  --hw-to-az "${section.hw_to_az}"

## General section
#set $section = $sec_restrict
@REGIONS@
@TARGETS@

## Primary Input/Outputs
@INPUT_FILE@
> "$output_file"
]]>
    </command>
    <inputs>
        <expand macro="macro_input" />
        <section name="sec_restrict" expanded="false" title="Restrict to">
            <expand macro="macro_regions" />
            <expand macro="macro_targets" />
        </section>
        <section name="sec_general" expanded="true" title="Roh General Options">
            <expand macro="macro_sample" />
            <param name="AF_tag" type="text" value="" label="AF TAG"  optional="True" 
                   help="Use the specified INFO tag TAG as an allele frequency estimate instead of the defaul AC and AN tags. Sites which do not have TAG will be skipped." />

            <expand macro="macro_estimate_AF" />
            <param name="GTs_only" type="float" label="Gts Only" optional="True" help="Use GTs, ignore PLs, use &lt;float&gt; for PL of unseen genotypes. Safe value to use is 30 to account for GT errors." />
            <param name="skip_indels" type="boolean" truevalue="--skip-indels" falsevalue="" label="Skip Indels" help="Skip indels as their genotypes are enriched for errors" />
            <param name="genetic_map" type="data" format="data" label="Genetic Map" optional="True" help="Genetic map in IMPUTE2 format, single file or mask, where string &quot;{CHROM}&quot; is replaced with chromosome name" />
            <param name="rec_rate" type="float" label="Rec Rate" optional="True" help="Constant recombination rate per bp" />
        </section>
        <section name="sec_hmm" expanded="true" title="HMM Options">
            <param name="hw_to_az" type="float" label="Hw To Az" value="6.7e-8" optional="True" help="P(AZ|HW) transition probability from HW (Hardy-Weinberg) to AZ (autozygous) state" />
            <param name="az_to_hw" type="float" label="Az To Hw" value="5e-9" optional="True" help="P(HW|AZ) transition probability from AZ to HW state" />
            <param name="viterbi_training" type="boolean" truevalue="--viterbi-training" falsevalue="" label="Viterbi Training" help="Perform Viterbi training to estimate transition probabilities" />
        </section>
    </inputs>
    <outputs>
        <data name="output_file" format="tabular"/>
    </outputs>
    <tests>
        <!-- Need an actual test input file -->
        <test>
            <param name="input_file" ftype="vcf" value="mpileup.vcf" />
            <param name="sample" value="HG00100" />
            <output name="output_file">
                <assert_contents>
                    <has_text text="HG00100"/>
                    <has_text text="State "/>
                </assert_contents>
            </output>
        </test>
    </tests>
    <help><![CDATA[

5:0be3ea214c4e

<?xml version='1.0' encoding='utf-8'?>
<tool name="bcftools @EXECUTABLE@" id="bcftools_@EXECUTABLE@" version="@VERSION@.0">
    <description>HMM model for detecting runs of homo/autozygosity</description>
    <macros>
        <token name="@EXECUTABLE@">roh</token>
        <import>macros.xml</import>
    </macros>
    <expand macro="requirements" />

    <command detect_errors="aggressive"><![CDATA[
@PREPARE_ENV@
@PREPARE_INPUT_FILE@
#set $section = $sec_restrict
@PREPARE_TARGETS_FILE@
@PREPARE_REGIONS_FILE@
## General section
#set $section = $sec_general
@PREPARE_AF_FILE@

bcftools @EXECUTABLE@

  --genetic-map "${section.genetic_map}"
#end if
#if $section.rec_rate:
  --rec-rate "${section.rec_rate}"
#end if
#if $section.buffer_size:
  #if $section.buffer_overlap:
    --buffer-size "${section.buffer_size},${section.buffer_overlap}"
  #else:
    --buffer-size "${section.buffer_size}"
  #end if
#end if

## HMM section
#set $section = $sec_hmm
#if $section.hw_to_az:
  --hw-to-az "${section.hw_to_az}"

## General section
#set $section = $sec_restrict
@REGIONS@
@TARGETS@
@SAMPLES@

#if str($output_type) in ('r','s'):
  --output-type $output_type
#end if

## Primary Input/Outputs
@INPUT_FILE@
> '$output_file'
]]>
    </command>
    <inputs>
        <expand macro="macro_input" />
        <section name="sec_restrict" expanded="false" title="Restrict to">
            <expand macro="macro_regions" />
            <expand macro="macro_targets" />
            <expand macro="macro_samples" />
        </section>
        <section name="sec_general" expanded="true" title="Roh General Options">
            <expand macro="macro_sample" />
            <param name="AF_tag" type="text" value="" label="AF TAG"  optional="True" 
                   help="Use the specified INFO tag TAG as an allele frequency estimate instead of the defaul AC and AN tags. Sites which do not have TAG will be skipped." />

            <expand macro="macro_estimate_AF" />
            <param name="GTs_only" type="float" label="Gts Only" optional="True" help="Use GTs, ignore PLs, use &lt;float&gt; for PL of unseen genotypes. Safe value to use is 30 to account for GT errors." />
            <param name="skip_indels" type="boolean" truevalue="--skip-indels" falsevalue="" label="Skip Indels" help="Skip indels as their genotypes are enriched for errors" />
            <param name="genetic_map" type="data" format="data" label="Genetic Map" optional="True" help="Genetic map in IMPUTE2 format, single file or mask, where string &quot;{CHROM}&quot; is replaced with chromosome name" />
            <param name="rec_rate" type="float" label="Rec Rate" optional="True" help="Constant recombination rate per bp" />
            <param name="buffer_size" type="integer" label="Sliding Buffer Size" optional="True">
                <help>
Use when the entire many-sample file cannot fit into memory. 
The number of sites to keep in memory. 
If negative, it is interpreted as the maximum memory to use, in MB.
                </help>
            </param>
            <param name="buffer_overlap" type="integer" min="0" label="Sliding Buffer Overlap" optional="True">
                <help>
The number of overlapping sites for the sliding buffer. The default overlap is set to roughly 1% of the buffer size. 
                </help>
            </param>
        </section>
        <section name="sec_hmm" expanded="true" title="HMM Options">
            <param name="hw_to_az" type="float" label="Hw To Az" value="6.7e-8" optional="True" help="P(AZ|HW) transition probability from HW (Hardy-Weinberg) to AZ (autozygous) state" />
            <param name="az_to_hw" type="float" label="Az To Hw" value="5e-9" optional="True" help="P(HW|AZ) transition probability from AZ to HW state" />
            <param name="viterbi_training" type="boolean" truevalue="--viterbi-training" falsevalue="" label="Viterbi Training" help="Perform Viterbi training to estimate transition probabilities" />
        </section>
        <param name="output_type" type="select" optional="true" label="limit output">
            <option value="s">s:per-site</option>
            <option value="r">r:regions</option>
        </param>
    </inputs>
    <outputs>
        <data name="output_file" format="tabular"/>
    </outputs>
    <tests>
        <test>
            <param name="input_file" ftype="vcf" value="roh.vcf" />
            <param name="AF_dflt" value="0.4" />
            <param name="GTs_only" value="30" />
            <output name="output_file">
                <assert_contents>
                    <has_text_matching expression="ST\tsample\t1"/>
                    <has_text_matching expression="RG\tsample\t1"/>
                </assert_contents>
            </output>
        </test>
        <test>
            <param name="input_file" ftype="vcf" value="roh.vcf" />
            <param name="AF_dflt" value="0.4" />
            <param name="GTs_only" value="30" />
            <param name="output_type" value="r" />
            <output name="output_file">
                <assert_contents>
                    <not_has_text text="ST"/>
                    <has_text_matching expression="RG\tsample\t1"/>
                </assert_contents>
            </output>
        </test>
    </tests>
    <help><![CDATA[