comparison stacks_populations.xml @ 1:9a44832748c5 draft

"planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/stacks2 commit c300b84615660459bb0020fa74ccd3b874d329a4"

0:6fba323a242d

    <expand macro="requirements"/>
    <expand macro="version_cmd"/>
    <command detect_errors="aggressive"><![CDATA[
#import re

mkdir stacks_inputs stacks_outputs

&&

#if str($options_usage.input_type) == 'stacks'
    #for $input_file in $options_usage.input_aln
        #set $filename = str($input_file.element_identifier)
        #if $filename == "catalog.calls" or $filename == "catalog.fa.gz":

    -batch_size '$batch_size'
#end if

## Data filtering

-p $options_filtering.minpop
-r $options_filtering.minperc
-R $options_filtering.min_samples_overall
$options_filtering.filter_haplotype_wise
--min_maf $options_filtering.min_maf
--min_mac $options_filtering.min_mac
#if str($options_filtering.max_obs_het)
    --max_obs_het $options_filtering.max_obs_het

#if str($options_usage.input_type) == 'vcf'
    #if $output_log
        > $output_log
    #end if
    && find stacks_outputs -type f -iname "input.p*" | while read file; do mv "\$file" "\$(echo \$file | sed 's/\/input.p/\/populations/;')"; done
#else
    #if $output_log
        && mv stacks_outputs/populations.log $output_log
    #end if
#end if
    ]]></command>

    <inputs>
        <conditional name="options_usage">

        <param argument="--batch_size" type="integer" value="" optional="true" label="Number of loci to process in a batch"  help="(default: 10,000 in de novo mode; in reference mode, one chromosome per batch). Increase to speed analysis, uses more memory, decrease to save memory)"/>

        <!-- Data Filtering -->
        <section name="options_filtering" title="Data filtering options" expanded="true">

            <param name="minperc" argument="-r" type="float" value="0.0" min="0" max="1" label="Minimum percentage of individuals in a population required to process a locus for that population" />
            <param name="minpop" argument="-p" type="integer" value="1" label="Minimum number of populations a locus must be present in to process a locus" />
            <param name="min_samples_overall" argument="--min-samples-overall" type="float" value="0.0" min="0" max="1" label="minimum percentage of individuals across populations required to process a locus" />
            <param name="filter_haplotype_wise" argument="--filter-haplotype-wise" type="boolean" truevalue="--filter-haplotype-wise" falsevalue="" checked="false" label="apply the above filters haplotype wise" help="unshared SNPs will be pruned to reduce haplotype-wise missing data." />
            <param argument="--min_maf" type="float" value="0" min="0" max="0.5" label="Minimum minor allele frequency" help="specify a minimum minor allele frequency required to process a nucleotide site at a locus" />
            <param argument="--min_mac" type="integer" value="0" min="0" label="Minimum minor allele count" help="specify a minimum minor allele count required to process a nucleotide site at a locus" />
            <param argument="--max_obs_het" type="float" value="" min="0" max="1" optional="true" label="Maximum observed heterozygosity required to process a nucleotide site at a locus." />

                <param name="min_mac" value="1"/>
                <param name="max_obs_het" value="0.8" />
                <param name="blacklist" value="populations/blacklist.tsv" ftype="tabular" />
            </section>
            <assert_command>
                <has_text text="-r 0.1" />
                <has_text text="-p 2" />
                <has_text text="--min-samples-overall 0.01" />
                <has_text text="--filter-haplotype-wise" />
                <has_text text="--min_maf 0.01" />
                <has_text text="--min_mac 1" />
                <has_text text="--max_obs_het 0.8" />

                <param name="minpop" value="2"/>
                <param name="min_samples_overall" value="0.01"/>
                <param name="min_maf" value="0.01" />
                <param name="min_mac" value="1"/>
                <param name="max_obs_het" value="0.8" />
                <!-- since write_random_snp runs in ifinite loop switch to write_single -->
                <param name="filter_single_snp" value="--write_single_snp"/>
                <param name="blacklist" value="populations/blacklist.tsv" ftype="tabular" />
            </section>
            <assert_command>
                <has_text text="-r 0.1" />
                <has_text text="-p 2" />
                <has_text text="--min-samples-overall 0.01" />
                <has_text text="--min_maf 0.01" />
                <has_text text="--min_mac 1" />
                <has_text text="--max_obs_het 0.8" />
                <has_text text="--write_random_snp" />
                <has_text text="-B " />
            </assert_command>
            <output ftype="txt" name="output_log"><assert_contents><has_text text="Populations is done." /></assert_contents></output>
            <output ftype="tabular" name="out_haplotypes"><assert_contents><has_text text="" /></assert_contents></output>
            <output ftype="tabular" name="out_hapstats"><assert_contents><has_text text="" /></assert_contents></output>

1:9a44832748c5

    <expand macro="requirements"/>
    <expand macro="version_cmd"/>
    <command detect_errors="aggressive"><![CDATA[
#import re

mkdir stacks_inputs stacks_outputs &&

#if $output_log
    ln -s '$output_log' stacks_outputs/populations.log &&
#end if

#if str($options_usage.input_type) == 'stacks'
    #for $input_file in $options_usage.input_aln
        #set $filename = str($input_file.element_identifier)
        #if $filename == "catalog.calls" or $filename == "catalog.fa.gz":

    -batch_size '$batch_size'
#end if

## Data filtering

--min-populations $options_filtering.minpop
--min-samples-per-pop $options_filtering.minperc
--min-samples-overall $options_filtering.min_samples_overall
$options_filtering.filter_haplotype_wise
--min_maf $options_filtering.min_maf
--min_mac $options_filtering.min_mac
#if str($options_filtering.max_obs_het)
    --max_obs_het $options_filtering.max_obs_het

#if str($options_usage.input_type) == 'vcf'
    #if $output_log
        > $output_log
    #end if
    && find stacks_outputs -type f -iname "input.p*" | while read file; do mv "\$file" "\$(echo \$file | sed 's/\/input.p/\/populations/;')"; done
#end if
    ]]></command>

    <inputs>
        <conditional name="options_usage">

        <param argument="--batch_size" type="integer" value="" optional="true" label="Number of loci to process in a batch"  help="(default: 10,000 in de novo mode; in reference mode, one chromosome per batch). Increase to speed analysis, uses more memory, decrease to save memory)"/>

        <!-- Data Filtering -->
        <section name="options_filtering" title="Data filtering options" expanded="true">

            <param name="minperc" argument="--min-samples-per-pop" type="float" value="0.0" min="0" max="1" label="Minimum percentage of individuals in a population required to process a locus for that population" />
            <param name="minpop" argument="--min-populations" type="integer" value="1" label="Minimum number of populations a locus must be present in to process a locus" />
            <param name="min_samples_overall" argument="--min-samples-overall" type="float" value="0.0" min="0" max="1" label="minimum percentage of individuals across populations required to process a locus" />
            <param name="filter_haplotype_wise" argument="--filter-haplotype-wise" type="boolean" truevalue="--filter-haplotype-wise" falsevalue="" checked="false" label="apply the above filters haplotype wise" help="unshared SNPs will be pruned to reduce haplotype-wise missing data." />
            <param argument="--min_maf" type="float" value="0" min="0" max="0.5" label="Minimum minor allele frequency" help="specify a minimum minor allele frequency required to process a nucleotide site at a locus" />
            <param argument="--min_mac" type="integer" value="0" min="0" label="Minimum minor allele count" help="specify a minimum minor allele count required to process a nucleotide site at a locus" />
            <param argument="--max_obs_het" type="float" value="" min="0" max="1" optional="true" label="Maximum observed heterozygosity required to process a nucleotide site at a locus." />

                <param name="min_mac" value="1"/>
                <param name="max_obs_het" value="0.8" />
                <param name="blacklist" value="populations/blacklist.tsv" ftype="tabular" />
            </section>
            <assert_command>
                <has_text text="--min-samples-per-pop 0.1" />
                <has_text text="--min-populations 2" />
                <has_text text="--min-samples-overall 0.01" />
                <has_text text="--filter-haplotype-wise" />
                <has_text text="--min_maf 0.01" />
                <has_text text="--min_mac 1" />
                <has_text text="--max_obs_het 0.8" />

                <param name="minpop" value="2"/>
                <param name="min_samples_overall" value="0.01"/>
                <param name="min_maf" value="0.01" />
                <param name="min_mac" value="1"/>
                <param name="max_obs_het" value="0.8" />
                <!-- since write_random_snp runs in infinite loop switch to write_single -->
                <param name="filter_single_snp" value="--write_single_snp"/>
                <param name="blacklist" value="populations/blacklist.tsv" ftype="tabular" />
            </section>
            <assert_command>
                <has_text text="--min-samples-per-pop 0.1" />
                <has_text text="--min-populations 2" />
                <has_text text="--min-samples-overall 0.01" />
                <has_text text="--min_maf 0.01" />
                <has_text text="--min_mac 1" />
                <has_text text="--max_obs_het 0.8" />
                <not_has_text text="--write_random_snp" />
                <has_text text="-B " />
            </assert_command>
            <output ftype="txt" name="output_log"><assert_contents><has_text text="Populations is done." /></assert_contents></output>
            <output ftype="tabular" name="out_haplotypes"><assert_contents><has_text text="" /></assert_contents></output>
            <output ftype="tabular" name="out_hapstats"><assert_contents><has_text text="" /></assert_contents></output>