comparison gffcompare.xml @ 1:c80cdc2eac6d draft

planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/gffcompare commit fc3616bd1463afef9681cd7c431ac29f79e37e74

0:3c97c841a443

<tool id="gffcompare" name="GffCompare" version="0.9.8">
    <description>compare assembled transcripts to a reference annotation</description>
    <requirements>
        <requirement type="package" version="0.9.8">gffcompare</requirement>
    </requirements>
    <stdio>

        <exit_code range=":-1" />
        <regex match="Error" />
        <regex match="Exception" />
    </stdio>
    <version_command>gffcompare -v | awk '{print $2}'</version_command>
    <command>
        <![CDATA[
            #set $input_gtf = "' '".join(str($inputs).split(','))
            #if $seq_data.use_seq_data == "Yes":
                #if $seq_data.seq_source.index_source == "history":
                    ln -s '$seq_data.seq_source.ref_file' ref_seq.fa &&
                #else:
                    ln -s '${seq_data.seq_source.index.fields.path}' ref_seq.fa &&
                #end if
            #end if
            gffcompare
            ## Use annotation reference?
            #if $annotation.use_ref_annotation == "Yes":
                -r '$annotation.reference_annotation' $annotation.ignore_nonoverlapping_reference $annotation.ignore_nonoverlapping_transfrags
            #end if

            ## Use sequence data?

            #if $seq_data.use_seq_data == "Yes":
                -s ref_seq.fa
            #end if

            $discard_single_exon -e $max_dist_exon -d $max_dist_group $discard_intron_redundant_transfrags

            '$input_gtf'
        ]]>
    </command>
    <inputs>
        <param format="gtf" name="inputs" type="data" label="GTF inputs for comparison" help="" multiple="true" />
        <conditional name="annotation">
            <param label="Use Reference Annotation" name="use_ref_annotation" type="select">
                <option value="No">No</option>
                <option value="Yes">Yes</option>
            </param>
            <when value="Yes">
                <param argument="-r" format="gff3,gtf" help="Requires an annotation file in GFF3 or GTF format." label="Reference Annotation" name="reference_annotation" type="data" />
                <param argument="-R" falsevalue="" help="consider only the reference transcripts that overlap any of the input transfrags (Sn correction)" label="Ignore reference transcripts that are not overlapped by any input transfrags" name="ignore_nonoverlapping_reference" truevalue="-R" type="boolean" />
                <param argument="-Q" falsevalue="" help="consider only the input transcripts that overlap any of the reference transcripts (Sp correction). Warning: this will discard all 'novel' loci!" label="Ignore input transcripts that are not overlapped by any reference transcripts" name="ignore_nonoverlapping_transfrags" truevalue="-Q" type="boolean" />
            </when>
            <when value="No">
            </when>
        </conditional>
        <conditional name="seq_data">
            <param help="Use sequence data for some optional classification functions, including the addition of the p_id attribute required by Cuffdiff." label="Use Sequence Data" name="use_seq_data" type="select">
                <option value="Yes">Yes</option>
                <option value="No">No</option>
            </param>
            <when value="No" />
            <when value="Yes">
                <conditional name="seq_source">
                    <param label="Choose the source for the reference list" name="index_source" type="select">
                        <option value="cached">Locally cached</option>
                        <option value="history">History</option>
                    </param>
                    <when value="cached">
                        <param argument="-s" label="Using reference genome" name="index" type="select">
                            <options from_data_table="fasta_indexes">
                                <filter column="1" key="dbkey" ref="inputs" type="data_meta" />
                                <validator message="No reference genome is available for the build associated with the selected input dataset" type="no_options" />
                            </options>
                        </param>
                    </when>
                    <when value="history">

        <param argument="-F" help="Discard intron-redundant transfrags if they share the 5' end (if they differ only at the 3' end)" truevalue="-F" falsevalue="" label="discard intron-redundant transfrags sharing 5'" name="discard_intron_redundant_transfrags" type="boolean" />
    </inputs>
    <outputs>
        <data format="txt" from_work_dir="gffcmp.stats" label="${tool.name} on ${on_string}: transcript accuracy" name="transcripts_stats" />
        <data format="tabular" from_work_dir="gffcmp.loci" label="${tool.name} on ${on_string}: loci" name="transcripts_loci" />
        <data format="tabular" from_work_dir="gffcmp.tracking" label="${tool.name} on ${on_string}: data ${inputs[0].hid} tracking file" name="transcripts_tracking" />
        <data format="gtf" from_work_dir="gffcmp.combined.gtf" label="${tool.name} on ${on_string}: combined transcripts" name="transcripts_combined">
            <filter>(use_seq_data == 'No')</filter>
        </data>
        <data format="gtf" from_work_dir="gffcmp.annotated.gtf" label="${tool.name} on ${on_string}: annotated transcripts" name="transcripts_annotated">
            <filter>(use_seq_data == 'Yes')</filter>
        </data>
    </outputs>
    <tests>
        <test>
            <param ftype="gtf" name="inputs" value="gffcompare_in1.gtf,gffcompare_in2.gtf" />
            <param name="use_ref_annotation" value="Yes" />
            <param ftype="gtf" name="reference_annotation" value="gffcompare_in3.gtf" />
            <param name="ignore_nonoverlapping_reference" value="Yes" />
            <param name="ignore_nonoverlapping_transfrags" value="No" />
            <param name="use_seq_data" value="No" />
            <param name="discard_single_exon" value="" />
            <param name="max_dist_exon" value="100" />
            <param name="max_dist_group" value="100" />
            <param name="discard_intron_redundant_transfrags" value="No" />
            <output file="gffcompare_out1.stats" name="transcripts_stats" lines_diff="6" />
            <output file="gffcompare_out1.loci" name="transcripts_loci" />
            <output file="gffcompare_out1.tracking" name="transcripts_tracking" />
            <output file="gffcompare_out1.gtf" name="transcripts_combined" />
        </test>
        <test>
            <param ftype="gtf" name="inputs" value="gffcompare_in4.gtf" />
            <param name="use_ref_annotation" value="Yes" />
            <param ftype="gtf" name="reference_annotation" value="gffcompare_in5.gtf" />
            <param name="ignore_nonoverlapping_reference" value="Yes" />
            <param name="ignore_nonoverlapping_transfrags" value="No" />
            <param name="use_seq_data" value="No" />
            <param name="discard_single_exon" value="" />
            <param name="max_dist_exon" value="100" />
            <param name="max_dist_group" value="100" />
            <param name="discard_intron_redundant_transfrags" value="No" />
            <output file="gffcompare_out2.stats" name="transcripts_stats" lines_diff="6" />
            <output file="gffcompare_out2.loci" name="transcripts_loci" lines_diff="2" />
            <output file="gffcompare_out2.tracking" name="transcripts_tracking" />
            <output file="gffcompare_out2.gtf" name="transcripts_annotated" />
        </test>
    </tests>
    <help>

1:c80cdc2eac6d

<tool id="gffcompare" name="GffCompare" version="0.9.8+galaxy1">
    <description>compare assembled transcripts to a reference annotation</description>
    <requirements>
        <requirement type="package" version="0.9.8">gffcompare</requirement>
    </requirements>
    <stdio>

        <exit_code range=":-1" />
        <regex match="Error" />
        <regex match="Exception" />
    </stdio>
    <version_command>gffcompare -v | awk '{print $2}'</version_command>
    <command><![CDATA[
#import re
#set escaped_element_identifiers = [re.sub('[^\w\-]', '_', str(_.element_identifier)) for _ in $gffinputs]
#for $input, $escaped_element_identifier in zip($gffinputs, $escaped_element_identifiers):
    ln -s '$input' '$escaped_element_identifier' &&
#end for
#if $seq_data.use_seq_data == "Yes":
    #if $seq_data.seq_source.index_source == "history":
        ln -s '$seq_data.seq_source.ref_file' ref_seq.fa &&
    #else:
        ln -s '${seq_data.seq_source.index.fields.path}' ref_seq.fa &&
    #end if
#end if

gffcompare
## Use annotation reference?
#if $annotation.use_ref_annotation == "Yes":
    -r '$annotation.reference_annotation'
    $annotation.ignore_nonoverlapping_reference
    $annotation.ignore_nonoverlapping_transfrags
    #if not $annotation.refmap_tmap:
        -T
    #end if
#end if

## Use sequence data?
#if $seq_data.use_seq_data == "Yes":
    -s ref_seq.fa
#end if

$discard_single_exon
-e $max_dist_exon
-d $max_dist_group
$discard_intron_redundant_transfrags

#for $escaped_element_identifier in $escaped_element_identifiers:
    '$escaped_element_identifier'
#end for
    ]]></command>
    <inputs>
        <param format="gtf" name="gffinputs" type="data" label="GTF inputs for comparison" help="" multiple="true" />
        <conditional name="annotation">
            <param label="Use Reference Annotation" name="use_ref_annotation" type="select">
                <option value="No">No</option>
                <option value="Yes">Yes</option>
            </param>
            <when value="Yes">
                <param argument="-r" format="gff3,gtf" help="Requires an annotation file in GFF3 or GTF format." label="Reference Annotation" name="reference_annotation" type="data" />
                <param argument="-R" falsevalue="" help="consider only the reference transcripts that overlap any of the input transfrags (Sn correction)" label="Ignore reference transcripts that are not overlapped by any input transfrags" name="ignore_nonoverlapping_reference" truevalue="-R" type="boolean" />
                <param argument="-Q" falsevalue="" help="consider only the input transcripts that overlap any of the reference transcripts (Sp correction). Warning: this will discard all 'novel' loci!" label="Ignore input transcripts that are not overlapped by any reference transcripts" name="ignore_nonoverlapping_transfrags" truevalue="-Q" type="boolean" />
                <param argument="-T" name="refmap_tmap" label="Generate tmap and refmap files for each input file" type="select" multiple="True">
                    <option value="refmap" selected="True">refmap</option>
                    <option value="tmap" selected="True">tmap</option>
                </param>
            </when>
            <when value="No">
            </when>
        </conditional>
        <conditional name="seq_data">
            <param help="Use sequence data for some optional classification functions, including the addition of the p_id attribute required by Cuffdiff." label="Use Sequence Data" name="use_seq_data" type="select">
                <option value="Yes">Yes</option>
                <option value="No">No</option>
            </param>
            <when value="No"/>
            <when value="Yes">
                <conditional name="seq_source">
                    <param label="Choose the source for the reference list" name="index_source" type="select">
                        <option value="cached">Locally cached</option>
                        <option value="history">History</option>
                    </param>
                    <when value="cached">
                        <param argument="-s" label="Using reference genome" name="index" type="select">
                            <options from_data_table="fasta_indexes">
                                <filter column="1" key="dbkey" ref="gffinputs" type="data_meta" />
                                <validator message="No reference genome is available for the build associated with the selected input dataset" type="no_options" />
                            </options>
                        </param>
                    </when>
                    <when value="history">

        <param argument="-F" help="Discard intron-redundant transfrags if they share the 5' end (if they differ only at the 3' end)" truevalue="-F" falsevalue="" label="discard intron-redundant transfrags sharing 5'" name="discard_intron_redundant_transfrags" type="boolean" />
    </inputs>
    <outputs>
        <data format="txt" from_work_dir="gffcmp.stats" label="${tool.name} on ${on_string}: transcript accuracy" name="transcripts_stats" />
        <data format="tabular" from_work_dir="gffcmp.loci" label="${tool.name} on ${on_string}: loci" name="transcripts_loci" />
        <data format="tabular" from_work_dir="gffcmp.tracking" label="${tool.name} on ${on_string}: data ${gffinputs[0].hid} tracking file" name="transcripts_tracking" />
        <data format="gtf" from_work_dir="gffcmp.combined.gtf" label="${tool.name} on ${on_string}: combined transcripts" name="transcripts_combined">
            <filter>isinstance(gffinputs, list)</filter>
        </data>
        <data format="gtf" from_work_dir="gffcmp.annotated.gtf" label="${tool.name} on ${on_string}: annotated transcripts" name="transcripts_annotated">
            <filter>not isinstance(gffinputs, list)</filter>
        </data>
        <collection name="refmap_output" type="list" label="${tool.name} on ${on_string}: refmap">
            <discover_datasets pattern="gffcmp\.(?P&lt;designation&gt;.+)\.refmap" ext="tabular" />
            <filter>annotation['use_ref_annotation'] == 'Yes' and annotation['refmap_tmap'] != None and 'refmap' in annotation['refmap_tmap']</filter>
        </collection>
        <collection name="tmap_output" type="list" label="${tool.name} on ${on_string}: tmap">
            <discover_datasets pattern="gffcmp\.(?P&lt;designation&gt;.+)\.tmap" ext="tabular" />
            <filter>annotation['use_ref_annotation'] == 'Yes' and annotation['refmap_tmap'] != None and 'tmap' in annotation['refmap_tmap']</filter>
        </collection>
    </outputs>
    <tests>
        <test expect_num_outputs="6">
            <param ftype="gtf" name="gffinputs" value="gffcompare_in1.gtf,gffcompare_in2.gtf" />
            <param name="use_ref_annotation" value="Yes" />
            <conditional name="annotation">
                <param ftype="gtf" name="reference_annotation" value="gffcompare_in3.gtf" />
                <param name="ignore_nonoverlapping_reference" value="Yes" />
                <param name="ignore_nonoverlapping_transfrags" value="No" />
            </conditional>
            <param name="use_seq_data" value="No" />
            <param name="discard_single_exon" value="" />
            <param name="max_dist_exon" value="100" />
            <param name="max_dist_group" value="100" />
            <param name="discard_intron_redundant_transfrags" value="No" />
            <output file="gffcompare_out1.stats" name="transcripts_stats" lines_diff="6" />
            <output file="gffcompare_out1.loci" name="transcripts_loci" lines_diff="2" />
            <output file="gffcompare_out1.tracking" name="transcripts_tracking" />
            <output file="gffcompare_out1.gtf" name="transcripts_combined" />
            <output_collection name="refmap_output" type="list" count="2">
                <element name="gffcompare_in1_gtf" file="gffcompare_out1-1.refmap" ftype="tabular" />
                <element name="gffcompare_in2_gtf" file="gffcompare_out1-2.refmap" ftype="tabular" />
            </output_collection>
            <output_collection name="tmap_output" type="list" count="2">
                <element name="gffcompare_in1_gtf" file="gffcompare_out1-1.tmap" ftype="tabular" />
                <element name="gffcompare_in2_gtf" file="gffcompare_out1-2.tmap" ftype="tabular" />
            </output_collection>
        </test>
        <test expect_num_outputs="4">
            <param ftype="gtf" name="gffinputs" value="gffcompare_in4.gtf" />
            <param name="use_ref_annotation" value="Yes" />
            <conditional name="annotation">
                <param ftype="gtf" name="reference_annotation" value="gffcompare_in5.gtf" />
                <param name="ignore_nonoverlapping_reference" value="Yes" />
                <param name="ignore_nonoverlapping_transfrags" value="No" />
                <param name="refmap_tmap" value="" />
            </conditional>
            <param name="use_seq_data" value="No" />
            <param name="discard_single_exon" value="" />
            <param name="max_dist_exon" value="100" />
            <param name="max_dist_group" value="100" />
            <param name="discard_intron_redundant_transfrags" value="No" />
            <output file="gffcompare_out2.stats" name="transcripts_stats" lines_diff="6" />
            <output file="gffcompare_out2.loci" name="transcripts_loci" />
            <output file="gffcompare_out2.tracking" name="transcripts_tracking" />
            <output file="gffcompare_out2.gtf" name="transcripts_annotated" />
        </test>
    </tests>
    <help>