comparison hydra.xml @ 9:18aad692772a draft default tip

planemo upload for repository https://github.com/phac-nml/quasitools commit 5a9e4c9a582828654893166caf20576f5e0c418e

8:9def47f3c1e4

<tool id="hydra" name="Hydra pipeline" version="0.5.1">
    <description>Identifies drug resistance within an NGS dataset</description>
    <requirements>
          <requirement type="package" version="0.5.1">quasitools</requirement>
    </requirements>
    <command detect_errors="exit_code"><![CDATA[

        quasitools hydra

        ## Preparing file input.

        <data format="bam" label="HyDRA: alignment bam output" name="output_bam" from_work_dir="output/align.bam" />
        <data format="csv" label="HyDRA: coverage output" name="output_coverage" from_work_dir="output/coverage_file.csv" />
        <data format="csv" label="HyDRA: drug resistance output" name="output_dr" from_work_dir="output/dr_report.csv" />
        <data format="fastq" label="HyDRA: filtered reads output" name="output_filtered" from_work_dir="output/filtered.fastq" />
        <data format="vcf" label="HyDRA: variants output" name="output_hydra" from_work_dir="output/hydra.vcf" />
        <data format="vcf" label="HyDRA: aa mutations output" name="output_aa_mt" from_work_dir="output/mutation_report.hmcf" />
        <data format="txt" label="HyDRA: stats output" name="output_stats" from_work_dir="output/stats.txt" />
        <data format="fasta" label="HyDRA: consensus output" name="output_consensus" from_work_dir="output/consensus.fasta" >
            <filter>consensus['consensus_bool'] == "true_consensus"</filter>
        </data>
    </outputs>

                    <has_text_matching expression="hxb2_pol\s958\s.\sc\sa\s100\sPASS\sDP=2503;AC=28;AF=0.0112" />
                </assert_contents>
            </output>
            <output name="output_aa_mt">
                <assert_contents>
                    <has_text_matching expression="#CHROM\sGENE\sTYPE\sWILDTYPE\sPOS\sMUTANT\sFILTER\sMUTANT_FREQ\sCOVERAGE\sINFO"/>
                    <has_text_matching expression="hxb2_pol\sRT\smutation\sK\s101\sP\sPASS\s0.1423\s1574\sWC=aaa;MC=CCa;MCF=0.1423;CAT=NNRTI;SRVL=Yes" />
                    <has_text_matching expression="hxb2_pol\sRT\smutation\sH\s221\sN\sPASS\s0.0113\s2475\sWC=cat;MC=Aat;MCF=0.0113;CAT=.;SRVL=." />
                </assert_contents>
            </output>
           
            <output name="output_stats">
                <assert_contents>

        * align.bam
        * coverage_file.csv
        * dr_report.csv
        * filtered.fastq
        * hydra.vcf
        * mutation_report.hmcf
        * stats.txt

The description of each of these directories/files are as follows:

* __run.conf__: The configuration used when this output was produced.

    * __align.bam__: The alignment file in bam format.
    * __coverage_file.csv__: A file with one entry per line with the AA position and the coverage at the position.
    * __dr_report.csv__: A report detailing the drug resistant mutations found, above the reporting threshold (default: 1%).
    * __filtered.fastq__: The reads remaining after the filtering stage.
    * __hydra.vcf__: The variants found by the pipeline.
    * __mutation_report.hmcf__: The AA mutations found by the pipeline.
    * __stats.txt__: A log file detailing size after filtering and major stages.

The __dr_report.csv__ file lists all found drug resistant mutations (mutations included in the mutation database) which have frequency greater than the reporting threshold. An example of this file is given below.

Example: __dr_report.csv__

    Gene,Category,Surveillance,Wildtype,Position,Mutation,Mutation Frequency,Coverage
    RT,NNRTI,Yes,K,103,N,9.03,155

The __mutation_report.hmcf__ files is our custom VCF like file which details all of the AA mutations found by the pipeline. An example if this file is given below.

Example: __mutation_report.hmcf__

    ##fileformat=HMCFv1
    ##fileDate=20150008
    ##source=HyDRA
    ##reference=/home/ericenns/hydra/var/hxb2_pol.fas
    ##INFO=<ID=MC,Number=.,Description="String">
    ##INFO=<ID=MCF,Number=.,Description="String">
    ##INFO=<ID=WC,Number=.,Description="String">
    ##FILTER=<ID=mf0.01,Description="Mutant freq below 0.01">
    #GENE   CATEGORY        SURVEILLANCE    TYPE    WILDTYPE        POS     MUTANT  FILTER  MUTANT_FREQ     COVERAGE INFO
    RT      NNRTI   Yes     mutation        K       103     N       PASS    0.0903  155     WC=aaa;MC=aaC;MCF=0.0903

    ]]></help>
    <citations>
		<citation type="bibtex">
			@misc{GitHubquasitoolshydra,
			title = {quasitools hydra},
			publisher = {phac-nml},
			journal = {GitHub repository},
			url = {https://github.com/phac-nml/quasitools},
			}
		</citation>
    </citations>
</tool>

9:18aad692772a

<tool id="hydra" name="Hydra pipeline" version="@TOOL_VERSION@+galaxy@VERSION_SUFFIX@">
    <description>Identifies drug resistance within an NGS dataset</description>
    <macros>
        <import>macros.xml</import>
    </macros>
    <expand macro="requirements"/>
    <command detect_errors="exit_code"><![CDATA[

        quasitools hydra

        ## Preparing file input.

        <data format="bam" label="HyDRA: alignment bam output" name="output_bam" from_work_dir="output/align.bam" />
        <data format="csv" label="HyDRA: coverage output" name="output_coverage" from_work_dir="output/coverage_file.csv" />
        <data format="csv" label="HyDRA: drug resistance output" name="output_dr" from_work_dir="output/dr_report.csv" />
        <data format="fastq" label="HyDRA: filtered reads output" name="output_filtered" from_work_dir="output/filtered.fastq" />
        <data format="vcf" label="HyDRA: variants output" name="output_hydra" from_work_dir="output/hydra.vcf" />
        <data format="txt" label="HyDRA: aa mutations output" name="output_aa_mt" from_work_dir="output/mutation_report.aavf" />
        <data format="txt" label="HyDRA: stats output" name="output_stats" from_work_dir="output/stats.txt" />
        <data format="fasta" label="HyDRA: consensus output" name="output_consensus" from_work_dir="output/consensus.fasta" >
            <filter>consensus['consensus_bool'] == "true_consensus"</filter>
        </data>
    </outputs>

                    <has_text_matching expression="hxb2_pol\s958\s.\sc\sa\s100\sPASS\sDP=2503;AC=28;AF=0.0112" />
                </assert_contents>
            </output>
            <output name="output_aa_mt">
                <assert_contents>
                    <has_text_matching expression="#CHROM\tGENE\tPOS\tREF\tALT\tFILTER\tALT_FREQ\tCOVERAGE\tINFO"/>
                    <has_text_matching expression="hxb2_pol\tRT\t101\tK\tP\tPASS\t0.1423\t1574\tRC=aaa;AC=CCa;ACF=0.1423;CAT=NNRTI;SRVL=Yes" />
                    <has_text_matching expression="hxb2_pol\tRT\t101\tK\tT\tmf0.01\t0.0013\t1574\tRC=aaa;AC=aCa;ACF=0.0013;CAT=.;SRVL=." />
                </assert_contents>
            </output>
           
            <output name="output_stats">
                <assert_contents>

        * align.bam
        * coverage_file.csv
        * dr_report.csv
        * filtered.fastq
        * hydra.vcf
        * mutation_report.aavf
        * stats.txt

The description of each of these directories/files are as follows:

* __run.conf__: The configuration used when this output was produced.

    * __align.bam__: The alignment file in bam format.
    * __coverage_file.csv__: A file with one entry per line with the AA position and the coverage at the position.
    * __dr_report.csv__: A report detailing the drug resistant mutations found, above the reporting threshold (default: 1%).
    * __filtered.fastq__: The reads remaining after the filtering stage.
    * __hydra.vcf__: The variants found by the pipeline.
    * __mutation_report.aavf__: The AA mutations found by the pipeline.
    * __stats.txt__: A log file detailing size after filtering and major stages.

The __dr_report.csv__ file lists all found drug resistant mutations (mutations included in the mutation database) which have frequency greater than the reporting threshold. An example of this file is given below.

Example: __dr_report.csv__

    Gene,Category,Surveillance,Wildtype,Position,Mutation,Mutation Frequency,Coverage
    RT,NNRTI,Yes,K,103,N,9.03,155

The __mutation_report.aavf__ file is in AAVF format (https://github.com/winhiv/aavf-spec), an amino acid variant format inspired by the VCF format. The __mutation_report.aavf__ file details all of the AA mutations found by the pipeline. An example if this file is given below.

Example: __mutation_report.aavf__

    ##fileformat=AAVFv1.0
    ##fileDate=20220615
    ##source=quasitools:hydra
    ##reference=hxb2_pol.fas
    ##INFO=<ID=RC,Number=1,Type=String,Description="Reference Codon">
    ##INFO=<ID=AC,Number=.,Type=String,Description="Alternate Codon">
    ##INFO=<ID=ACF,Number=.,Type=Float,Description="Alternate Codon Frequency,for each Alternate Codon,in the same order aslisted.">
    ##INFO=<ID=CAT,Number=.,Type=String,Description="Drug Resistance Category">
    ##INFO=<ID=SRVL,Number=.,Type=String,Description="Drug Resistance Surveillance">
    ##FILTER=<ID=af0.01,Description="Set if True; alt_freq<0.01">
    #CHROM	GENE	POS	REF	ALT	FILTER	ALT_FREQ	COVERAGE	INFO
    hxb2_pol	RT	101	K	P	PASS	0.1423	1574	RC=aaa;AC=CCa;ACF=0.1423;CAT=NNRTI;SRVL=Yes

    ]]></help>
    <expand macro="citations" />
</tool>