annotate extract_kraken_reads.xml @ 2:4bf1e2701504 draft default tip

planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/krakentools commit 60eb96ad3ff782075ca1f29e26ffe5487bbb93ed

<tool id="krakentools_extract_kraken_reads" name="Krakentools: Extract Kraken Reads By ID" version="@TOOL_VERSION@+galaxy@VERSION_SUFFIX@" profile="@PROFILE@">
    <description>
        Extract reads that were classified by the Kraken family at specified taxonomic IDs
    </description>
    <macros>
        <import>macros.xml</import>
    </macros>
    <expand macro="requirements">
        <requirement type="package" version="1.12">gzip</requirement>
    </expand>
    <command detect_errors="exit_code">
        <![CDATA[

        ##set input
        #if $library.type == 'paired':
            #set input_1 = $library.input_1
            #set input_2 = $library.input_2

            ## tool needs a file ending with gz to work
            #if $library.input_1.datatype.file_ext.endswith("gz"):
                ln -s '$input_1' input_1.gz &&
                ln -s '$input_2' input_2.gz &&
                #set input_1 = 'input_1.gz'
                #set input_2 = 'input_2.gz'
            #end if 

        #else if $library.type == 'paired_collection'
            #set input_1 = $library.input_1.forward
            #set input_2 = $library.input_1.reverse

            ## tool needs a file ending with gz to work
            #if $library.input_1.forward.datatype.file_ext.endswith("gz"):
                ln -s '$input_1' input_1.gz &&
                ln -s '$input_2' input_2.gz &&
                #set input_1 = 'input_1.gz'
                #set input_2 = 'input_2.gz'
            #end if 


        #else
            #set input_1 = $library.input_1

            ## tool needs a file ending with gz to work
            #if $library.input_1.datatype.file_ext.endswith("gz"):
                ln -s '$input_1' input_1.gz && 
                #set input_1 = 'input_1.gz'
            #end if 

        #end if

        ## name output according to --fastq_output param
        ## tests fails if file does not have correct ending
        #if str($fastq_output) == '':
            #set temp_output_1 = 'output_1.fasta'
            #set temp_output_2 = 'output_2.fasta'
        #else:
            #set temp_output_1 = 'output_1.fastq'
            #set temp_output_2 = 'output_2.fastq'
        #end if
        ## do not quote $taxid
        extract_kraken_reads.py
        -k '$results'
        -s '$input_1'
        -o '$temp_output_1'
        --taxid $taxid
        --max '$max'
        $include_parents
        $include_children
        $exclude
        $fastq_output

        #if str( $library.type ) != "single":
        -s2 '$input_2'
        -o2 '$temp_output_2'
        #end if
        #if $include_parents or $include_children:
        --report '$report'
        #end if

        ##compress output
        && gzip -cvf '$temp_output_1' > output_1.gz

        #if str( $library.type ) != "single":
        && gzip -cvf '$temp_output_2' > output_2.gz
        #end if

        ]]>
    </command>
    <inputs>
        <!-- Reads -->
        <conditional name="library">
            <param name="type" type="select" label="Single or paired reads?">
                <option value="single">
                    Single
                </option>
                <option value="paired">
                    Paired
                </option>
                <option value="paired_collection">
                    Paired Collection
                </option>
            </param>
            <when value="single">
                <param name="input_1" format="fastq,fasta,fastq.gz,fasta.gz" type="data" label="FASTQ/A file" help="FASTQ or FASTQ input reads (may be gzipped)" />
            </when>
            <when value="paired">
                <param name="input_1" format="fastq,fasta,fastq.gz,fasta.gz" type="data" label="FASTQ/A forward file" help="FASTQ or FASTQ input reads (may be gzipped)" />
                <param name="input_2" format="fastq,fasta,fastq.gz,fasta.gz" type="data" label="FASTQ/A reverse file" help="FASTQ or FASTQ input reads (for paired reads, may be gzipped)" />
            </when>
            <when value="paired_collection">
                <param name="input_1" format="fastq,fasta,fastq.gz,fasta.gz" type="data_collection" collection_type="paired" label="Paired Collection" help="FASTQ or FASTA read pair collection (may be gzipped)" />
            </when>
        </conditional>
        <param name="results" argument="-k" format="tabular" type="data" label="Results" help="Results (classification) file from Kraken/KrakenUniq/Kraken2" />
        <param argument="--report" format="tabular" type="data" label="Report" optional="true" help="Report file from Kraken/KrakenUniq/Kraken2" />
        <param  argument="--taxid" type="text" value="" label="Taxonomic ID(s) to match" help="Space-delimited list of taxonomic IDs for which to extract matching reads">
            <validator type="regex" message="Enter a space-separated list of numeric tax IDs">^\d+[\d ]*$</validator>
        </param>
        <param argument="--max" type="integer" value="100000000" min="1" label="Maximum reads to save" help="Maximum number of reads to save for each ID" />
        <param argument="--exclude" type="boolean" value="False" truevalue="--exclude" falsevalue="" label="Invert output" help="Instead of finding reads that match given taxonomic IDs, find all reads that DO NOT match given IDs" />
        <param argument="--fastq_output" type="boolean" value="False" truevalue="--fastq-output" falsevalue="" label="Output as FASTQ" help="Write output as FASTQ instead of the default FASTA" />
        <param argument="--include_parents" type="boolean" value="False" truevalue="--include-parents" falsevalue="" label="Include parents" help="Include reads classified at parent levels of the specified tax IDs" />
        <param argument="--include_children" type="boolean" value="False" truevalue="--include-children" falsevalue="" label="Include children" help="Include reads classified more specifically than the specified tax IDs" />
    </inputs>
    <outputs>
        <data name="output_1" format="fasta.gz" from_work_dir="output_1.gz" metadata_source="input_1" label="${tool.name} on ${on_string}: forward reads">
            <filter>
                (library['type'] == 'single' or library['type'] == 'paired')
            </filter>
            <change_format>
                <when input="fastq_output" value="--fastq-output" format="fastq.gz" />
            </change_format>
        </data>
        <data name="output_2" format="fasta.gz" from_work_dir="output_2.gz" metadata_source="input_2" label="${tool.name} on ${on_string}: reverse reads">
            <filter>
                (library['type'] == 'paired')
            </filter>
            <change_format>
                <when input="fastq_output" value="--fastq-output" format="fastq.gz" />
            </change_format>
        </data>
        <collection type="paired" name="output_collection" label="${tool.name} on ${on_string}: collection">
            <filter>(library['type'] == 'paired_collection')</filter>
            <data name="forward" format="fasta.gz" metadata_source="input_1" from_work_dir="output_1.gz" >
            <change_format>
                <when input="fastq_output" value="--fastq-output" format="fastq.gz" />
            </change_format>
            </data>
            <data name="reverse" format="fasta.gz" metadata_source="input_2" from_work_dir="output_2.gz" >
            <change_format>
                <when input="fastq_output" value="--fastq-output" format="fastq.gz" />
            </change_format>
            </data>
        </collection>
    </outputs>
    <tests>
        <!-- test Kraken2 input, single input, unzipped -->
        <test expect_num_outputs="1">
            <param name="input_1" value="extract_kraken_reads/R1.fq" ftype="fastq" />
            <param name="library|type" value="single" />
            <param name="results" value="extract_kraken_reads/kraken2.results" ftype="tabular" />
            <param name="taxid" value="11176" />
            <output name="output_1" file="extract_kraken_reads/out1.k2.11176.fa" decompress="true" ftype="fasta.gz"  />
        </test>        
        <!-- test Kraken2 input, single input, zipped -->
        <test expect_num_outputs="1">
            <param name="input_1" value="extract_kraken_reads/R1.fq.gz" ftype="fastq.gz" />
            <param name="library|type" value="single" />
            <param name="results" value="extract_kraken_reads/kraken2.results" ftype="tabular" />
            <param name="taxid" value="11176" />
            <output name="output_1" file="extract_kraken_reads/out1.k2.11176.fa" decompress="true" ftype="fasta.gz"  />
        </test>
        <!-- test paired input -->
        <test expect_num_outputs="2">
            <param name="input_1" value="extract_kraken_reads/R1.fq.gz" ftype="fastq.gz" />
            <param name="input_2" value="extract_kraken_reads/R2.fq.gz" ftype="fastq.gz" />
            <param name="library|type" value="paired" />
            <param name="results" value="extract_kraken_reads/kraken2.results" ftype="tabular" />
            <param name="taxid" value="11176" />
            <output name="output_1" file="extract_kraken_reads/out1.k2.11176.fa" decompress="true" ftype="fasta.gz" />
            <output name="output_2" file="extract_kraken_reads/out2.k2.11176.fa" decompress="true" ftype="fasta.gz" />
        </test>
        <!-- test paired collection input -->
        <test expect_num_outputs="3">
            <param name="input_1">
                <collection type="paired">
                    <element name="forward" value="extract_kraken_reads/R1.fq.gz" ftype="fastq.gz" />
                    <element name="reverse" value="extract_kraken_reads/R2.fq.gz" ftype="fastq.gz" />
                </collection>
            </param>
            <param name="library|type" value="paired_collection" />
            <param name="results" value="extract_kraken_reads/kraken2.results" ftype="tabular" />
            <param name="taxid" value="11176" />
            <output_collection name="output_collection" type="paired">
                <element name="forward" file="extract_kraken_reads/out1.k2.11176.fa" decompress="true" ftype="fasta.gz" />
                <element name="reverse" file="extract_kraken_reads/out2.k2.11176.fa" decompress="true" ftype="fasta.gz" />
            </output_collection>
        </test>
        <!-- test Kraken1 input, include children -->
        <test expect_num_outputs="1">
            <param name="input_1" value="extract_kraken_reads/R1.fq.gz" ftype="fastq.gz" />
            <param name="library|type" value="single" />
            <param name="results" value="extract_kraken_reads/kraken1.results" ftype="tabular" />
            <param name="report" value="extract_kraken_reads/kraken1.report" ftype="tabular" />
            <param name="taxid" value="11176" />
            <param name="include_children" value="True" />
            <output name="output_1" file="extract_kraken_reads/out1.k1.11176.children.fa" decompress="true" ftype="fasta.gz" />
        </test>
        <!-- test exclude -->
        <test expect_num_outputs="1">
            <param name="input_1" value="extract_kraken_reads/R1.fq.gz" ftype="fastq.gz" />
            <param name="library|type" value="single" />
            <param name="results" value="extract_kraken_reads/kraken1.results" ftype="tabular" />
            <param name="report" value="extract_kraken_reads/kraken1.report" ftype="tabular" />
            <param name="taxid" value="10386" />
            <param name="include_children" value="True" />
            <param name="exclude" value="True" />
            <output name="output_1" file="extract_kraken_reads/out1.k1.e10386.children.fa" decompress="true" ftype="fasta.gz" />
        </test>
        <!-- test max -->
        <test expect_num_outputs="1">
            <param name="input_1" value="extract_kraken_reads/R1.fq.gz" ftype="fastq.gz" />
            <param name="library|type" value="single" />
            <param name="results" value="extract_kraken_reads/kraken2.results" ftype="tabular" />
            <param name="taxid" value="11176" />
            <param name="max" value="2" />
            <output name="output_1" file="extract_kraken_reads/out1.k2.11176.max2.fa" decompress="true" ftype="fasta.gz" />
        </test>
        <!-- test include parents -->
        <test expect_num_outputs="1">
            <param name="input_1" value="extract_kraken_reads/R1.fq.gz" ftype="fastq.gz" />
            <param name="library|type" value="single" />
            <param name="results" value="extract_kraken_reads/kraken2.results" ftype="tabular" />
            <param name="taxid" value="11176" />
            <param name="include_parents" value="True" />
            <param name="report" value="extract_kraken_reads/kraken2.report" ftype="tabular" />
            <output name="output_1" file="extract_kraken_reads/out1.k2.11176.parents.fa" decompress="true" ftype="fasta.gz" />
        </test>
        <!-- test multiple tax IDs -->
        <test expect_num_outputs="1">
            <param name="input_1" value="extract_kraken_reads/R1.fq.gz" ftype="fastq.gz" />
            <param name="library|type" value="single" />
            <param name="results" value="extract_kraken_reads/kraken2.results" ftype="tabular" />
            <param name="taxid" value="10386 11176" />
            <param name="exclude" value="True" />
            <param name="include_parents" value="True" />
            <param name="report" value="extract_kraken_reads/kraken2.report" ftype="tabular" />
            <output name="output_1" file="extract_kraken_reads/out1.k2.exclude_both.fa" decompress="true" ftype="fasta.gz" />
        </test>
        <!-- test multiple tax IDs -->
        <test expect_failure="true">
            <param name="input_1" value="extract_kraken_reads/R1.fq.gz" ftype="fastq.gz" />
            <param name="library|type" value="single" />
            <param name="results" value="extract_kraken_reads/kraken2.results" ftype="tabular" />
            <param name="taxid" value="10386 f5" />
        </test>
        <!-- test FASTQ output -->
        <test expect_num_outputs="1">
            <param name="input_1" value="extract_kraken_reads/R1.fq.gz" ftype="fastq.gz" />
            <param name="library|type" value="single" />
            <param name="results" value="extract_kraken_reads/kraken2.results" ftype="tabular" />
            <param name="taxid" value="11176" />
            <param name="fastq_output" value="true" />
            <output name="output_1" file="extract_kraken_reads/out1.k2.11176.fq" decompress="true" ftype="fastq.gz" />
        </test>
    </tests>
    <help>
        <![CDATA[
**What it does**
-------------------
After running Kraken, Kraken2, or KrakenUniq, users may use the
`extract_kraken_reads.py` program to extract the FASTA or FASTQ reads
classified as a specific taxonomy ID. For example, this program can be used to
extract all bacterial reads or only reads assigned to Escherichia coli. Users
must provide (at minimum) the original sequence file(s), at least one taxonomy
ID, and the Kraken output file.
        ]]>
    </help>
    <expand macro="citations" />
    <creator>
        <person givenName="Jeremy" familyName="Volkening" url="https://github.com/jvolkening" />
        <person givenName="Paul" familyName="Zierep" email="[e-mail]" />
    </creator>
</tool>