comparison kofamscan.xml @ 3:c3c46f14c7a4 draft

planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/kofamscan commit db30370820c68a8add7974d70ad04585cea5b084

2:95c71179a054

<tool id="kofamscan" name="KofamScan" version="@TOOL_VERSION@+galaxy@VERSION_SUFFIX@">
    <description>gene function annotation based on KEGG orthology and HMM</description>
    <macros>
        <token name="@TOOL_VERSION@">1.3.0</token>
        <token name="@VERSION_SUFFIX@">1</token>
        <xml name="reportannotation" token_selected="">
            <param name="reportannotation" type="boolean" truevalue="--report-unannotated" falsevalue="--no-report-unannotated" checked="@SELECTED@" label="Include sequence name to outputs even if no KOs are assigned?"/>
        </xml>
    </macros>
    <xrefs>

    </xrefs>
    <requirements>
        <requirement type="package" version="@TOOL_VERSION@">kofamscan</requirement>
        <requirement type="package" version="3.0">zip</requirement>
    </requirements>
    <version_command><![CDATA[sansa -v | grep "Sansa " | cut -d "v" -f 3]]></version_command>
    <command detect_errors="exit_code"><![CDATA[
## preprocessing
mkdir ./profile &&
mkdir ./temp_extract &&
#if $p_cond.p_sel == 'compressed'
    tar -xf '${p_cond.p}' -C temp_extract &&
    find ./temp_extract/ -name '*.hmm' -exec mv {} ./profile \; &&
    find ./temp_extract/ -name '*.hal' -exec mv {} ./profile \; &&
#elif $p_cond.p_sel == 'hmm'
    ## input files require prefix 'K' and file extension '.hmm'
    #for $i, $current in enumerate($p_cond.p)
        ln -s '$current' 'profile/K${i}.hmm' &&
    #end for
#end if

## run
exec_annotation
-p 'profile'
-o 'result.txt'
-k '$k'
--cpu \${GALAXY_SLOTS:-4}
-E $E
-T $ap.T
-f '$ap.f_cond.f_sel'
$ap.f_cond.reportannotation

    ]]></command>
    <inputs>
        <param name="query" type="data" format="fasta" label="Select query sequence file" help="Nucleotide sequences are not accepted."/>
        <conditional name="p_cond">
            <param name="p_sel" type="select" label="Select profile database format">
                <option value="compressed" selected="true">Compressed set of HMM and HAL file(s)</option>
                <option value="hmm">HMM file(s)</option>
            </param>
            <when value="compressed">
                <param argument="-p" type="data" format="tar" label="Select a compressed file with HMM and HAL file(s)" help="Compressed archives are available from KofamKOALA web service (https://www.genome.jp/tools/kofamkoala/)."/>
            </when>
            <when value="hmm">
                <param argument="-p" type="data" format="hmm3" multiple="true" label="Select profile HMM file(s)"/>
            </when>
        </conditional>
        <param argument="-k" type="data" format="tabular" label="Select KO list file"/>
        <param argument="-E" type="float" min="0.0" max="1.0" value="0.01" label="Set E-value threshold"/>
        <section name="ap" title="Advanced parameters" expanded="true">
            <param argument="-T" type="integer" value="1" label="Set threshold scale" help="The score thresholds will be multiplied by this value."/>
            <conditional name="f_cond">
                <param name="f_sel" type="select" label="Select output format">

                <option value="tabular">HMMER tabular summary</option>
            </param>
        </section>
    </inputs>
    <outputs>
        <data name="out_alignments" format="zip" from_work_dir="tmp/alignments.zip" label="${tool.name} on ${on_string}: HMMER alignments">
            <filter>'alignments' in ap['out']</filter>
        </data>
        <data name="out_output" format="txt" from_work_dir="tmp/output/output.txt" label="${tool.name} on ${on_string}: HMMER output">
            <filter>'output' in ap['out']</filter>
        </data>
        <data name="out_result" format="txt" from_work_dir="result.txt" label="${tool.name} on ${on_string}: Results">
            <filter>'result' in ap['out']</filter>
        </data>
        <data name="out_tabular" format="txt" from_work_dir="tmp/tabular/tabular.txt" label="${tool.name} on ${on_string}: HMMER tabular">
            <filter>'tabular' in ap['out']</filter>
        </data>
    </outputs>

        <!-- #2 -->
        <test expect_num_outputs="4">
            <param name="query" value="query.fasta"/>
            <conditional name="p_cond">
                <param name="p_sel" value="hmm"/>
                <param name="p" value="K00001.hmm,K00002.hmm,K00003.hmm"/>
            </conditional>
            <param name="k" value="ko"/>
            <param name="E" value="0.02"/>
            <section name="ap">
                <param name="T" value="2"/>

                <assert_contents>
                    <has_n_lines n="224"/>
                    <has_line line="Internal pipeline statistics summary:"/>
                </assert_contents>
            </output>
            <output name="out_result">
                <assert_contents>
                    <has_n_lines n="9"/>
                    <has_text_matching expression=".+sp\|P19858\|LDHA_BOVIN"/>
                </assert_contents>
            </output>

        <!-- #3 -->
        <test expect_num_outputs="1">
            <param name="query" value="query.fasta"/>
            <conditional name="p_cond">
                <param name="p_sel" value="hmm"/>
                <param name="p" value="K00001.hmm,K00002.hmm,K00003.hmm"/>
            </conditional>
            <param name="k" value="ko"/>
            <section name="ap">
                <conditional name="f_cond">
                    <param name="f_sel" value="mapper"/>
                </conditional>
            </section>
            <output name="out_result">
                <assert_contents>
                    <has_n_lines n="7"/>
                    <has_line line="sp|P19858|LDHA_BOVIN"/>
                </assert_contents>
            </output>

        <!-- #4 -->
        <test expect_num_outputs="1">
            <param name="query" value="query.fasta"/>
            <conditional name="p_cond">
                <param name="p_sel" value="hmm"/>
                <param name="p" value="K00001.hmm,K00002.hmm,K00003.hmm"/>
            </conditional>
            <param name="k" value="ko"/>
            <section name="ap">
                <conditional name="f_cond">
                    <param name="f_sel" value="mapper-one-line"/>

            <param name="k" value="ko"/>
            <output name="out_result">
                <assert_contents>
                    <has_n_lines n="5"/>
                    <has_text_matching expression=".+sp\|P00329\|ADH1_MOUSE.+"/>
                </assert_contents>
            </output>
        </test>
    </tests>
    <help><![CDATA[

3:c3c46f14c7a4

<tool id="kofamscan" name="KofamScan" version="@TOOL_VERSION@+galaxy@VERSION_SUFFIX@">
    <description>gene function annotation based on KEGG orthology and HMM</description>
    <macros>
        <token name="@TOOL_VERSION@">1.3.0</token>
        <token name="@VERSION_SUFFIX@">2</token>
        <xml name="reportannotation" token_selected="">
            <param name="reportannotation" type="boolean" truevalue="--report-unannotated" falsevalue="--no-report-unannotated" checked="@SELECTED@" label="Include sequence name to outputs even if no KOs are assigned?"/>
        </xml>
    </macros>
    <xrefs>

    </xrefs>
    <requirements>
        <requirement type="package" version="@TOOL_VERSION@">kofamscan</requirement>
        <requirement type="package" version="3.0">zip</requirement>
    </requirements>
    <version_command><![CDATA[exec_annotation --version | cut -d " " -f 2]]></version_command>
    <command detect_errors="exit_code"><![CDATA[
#if $p_cond.p_sel != "cached"
    ## preprocessing
    mkdir ./profile &&
    mkdir ./temp_extract &&
    #if $p_cond.p_sel == 'compressed'
        tar -xf '${p_cond.p}' -C temp_extract &&
        find ./temp_extract/ -name '*.hmm' -exec mv {} ./profile \; &&
        find ./temp_extract/ -name '*.hal' -exec mv {} ./profile \; &&
    #elif $p_cond.p_sel == 'hmm'
        ## input files require prefix 'K' and file extension '.hmm'
        #for $i, $current in enumerate($p_cond.p)
            ln -s '$current' 'profile/K${i}.hmm' &&
        #end for
    #end if
#end if

## run
exec_annotation

#if $p_cond.p_sel != "cached"
    -p 'profile'
    -k '$p_cond.k'
#else
    -p '$p_cond.kofam.fields.profile_dir/#if $p_cond.kofam_subset then $p_cond.kofam_subset else ""#'
    -k '$p_cond.kofam.fields.ko_list'
#end if
-o 'result.txt'
--cpu \${GALAXY_SLOTS:-4}
-E $E
-T $ap.T
-f '$ap.f_cond.f_sel'
$ap.f_cond.reportannotation

    ]]></command>
    <inputs>
        <param name="query" type="data" format="fasta" label="Select query sequence file" help="Nucleotide sequences are not accepted."/>
        <conditional name="p_cond">
            <param name="p_sel" type="select" label="Select profile database format">
                <option value="cached" selected="true">Cached</option>
                <option value="compressed">Compressed set of HMM and HAL file(s)</option>
                <option value="hmm">HMM file(s)</option>
            </param>
            <when value="cached">
                <param name="kofam" type="select">
                    <options from_data_table="kofam"/>
                </param>
                <param name="kofam_subset" type="select" optional="true">
                    <options from_data_table="kofam_subset">
                        <filter type="param_value" column="2" ref="kofam"/>
                        <filter type="sort_by" column="1"/>
                        <filter type="unique_value" column="1"/>
                        <column name="name" index="1"/>
                        <column name="value" index="0"/>
                    </options>
                    <validator type="no_options" message="No option available for this input"/>
                </param>
            </when>
            <when value="compressed">
                <param argument="-p" type="data" format="tar" label="Select a compressed file with HMM and HAL file(s)" help="Compressed archives are available from KofamKOALA web service (https://www.genome.jp/tools/kofamkoala/)."/>
                <param argument="-k" type="data" format="tabular" label="Select KO list file"/>
            </when>
            <when value="hmm">
                <param argument="-p" type="data" format="hmm3" multiple="true" label="Select profile HMM file(s)"/>
                <param argument="-k" type="data" format="tabular" label="Select KO list file"/>
            </when>
        </conditional>
        <param argument="-E" type="float" min="0.0" max="1.0" value="0.01" label="Set E-value threshold"/>
        <section name="ap" title="Advanced parameters" expanded="true">
            <param argument="-T" type="integer" value="1" label="Set threshold scale" help="The score thresholds will be multiplied by this value."/>
            <conditional name="f_cond">
                <param name="f_sel" type="select" label="Select output format">

                <option value="tabular">HMMER tabular summary</option>
            </param>
        </section>
    </inputs>
    <outputs>
        <data name="out_result" format="txt" from_work_dir="result.txt" label="${tool.name} on ${on_string}: Results">
            <filter>'result' in ap['out']</filter>
            <change_format>
                <when input='ap.f_cond.f_sel' value="detail-tsv" format="tabular" />
            </change_format>
        </data>
        <data name="out_alignments" format="zip" from_work_dir="tmp/alignments.zip" label="${tool.name} on ${on_string}: HMMER alignments">
            <filter>'alignments' in ap['out']</filter>
        </data>
        <data name="out_output" format="txt" from_work_dir="tmp/output/output.txt" label="${tool.name} on ${on_string}: HMMER output">
            <filter>'output' in ap['out']</filter>
        </data>
        <data name="out_tabular" format="txt" from_work_dir="tmp/tabular/tabular.txt" label="${tool.name} on ${on_string}: HMMER tabular">
            <filter>'tabular' in ap['out']</filter>
        </data>
    </outputs>

        <!-- #2 -->
        <test expect_num_outputs="4">
            <param name="query" value="query.fasta"/>
            <conditional name="p_cond">
                <param name="p_sel" value="hmm"/>
                <param name="p" value="profiles/K00001.hmm,profiles/K00002.hmm,profiles/K00003.hmm"/>
            </conditional>
            <param name="k" value="ko"/>
            <param name="E" value="0.02"/>
            <section name="ap">
                <param name="T" value="2"/>

                <assert_contents>
                    <has_n_lines n="224"/>
                    <has_line line="Internal pipeline statistics summary:"/>
                </assert_contents>
            </output>
            <output name="out_result" ftype="tabular">
                <assert_contents>
                    <has_n_lines n="9"/>
                    <has_text_matching expression=".+sp\|P19858\|LDHA_BOVIN"/>
                </assert_contents>
            </output>

        <!-- #3 -->
        <test expect_num_outputs="1">
            <param name="query" value="query.fasta"/>
            <conditional name="p_cond">
                <param name="p_sel" value="hmm"/>
                <param name="p" value="profiles/K00001.hmm,profiles/K00002.hmm,profiles/K00003.hmm"/>
            </conditional>
            <param name="k" value="ko"/>
            <section name="ap">
                <conditional name="f_cond">
                    <param name="f_sel" value="mapper"/>
                </conditional>
            </section>
            <output name="out_result" ftype="txt">
                <assert_contents>
                    <has_n_lines n="7"/>
                    <has_line line="sp|P19858|LDHA_BOVIN"/>
                </assert_contents>
            </output>

        <!-- #4 -->
        <test expect_num_outputs="1">
            <param name="query" value="query.fasta"/>
            <conditional name="p_cond">
                <param name="p_sel" value="hmm"/>
                <param name="p" value="profiles/K00001.hmm,profiles/K00002.hmm,profiles/K00003.hmm"/>
            </conditional>
            <param name="k" value="ko"/>
            <section name="ap">
                <conditional name="f_cond">
                    <param name="f_sel" value="mapper-one-line"/>

            <param name="k" value="ko"/>
            <output name="out_result">
                <assert_contents>
                    <has_n_lines n="5"/>
                    <has_text_matching expression=".+sp\|P00329\|ADH1_MOUSE.+"/>
                </assert_contents>
            </output>
        </test>
        <!-- #6 test with cached data -->
        <test expect_num_outputs="1">
            <param name="query" value="query.fasta"/>
            <conditional name="p_cond">
                <param name="p_sel" value="cached"/>
                <param name="kofam" value="test_value"/>
            </conditional>
            <param name="k" value="ko"/>
            <section name="ap">
                <conditional name="f_cond">
                    <param name="f_sel" value="mapper-one-line"/>
                </conditional>
            </section>
            <output name="out_result" ftype="txt">
                <assert_contents>
                    <has_n_lines n="7"/>
                    <has_line line="sp|P19858|LDHA_BOVIN"/>
                </assert_contents>
            </output>
        </test>
        <!-- #6 test with cached data + subset -->
        <test expect_num_outputs="1">
            <param name="query" value="query.fasta"/>
            <conditional name="p_cond">
                <param name="p_sel" value="cached"/>
                <param name="kofam" value="test_value"/>
                <param name="kofam_subset" value="SUBSET"/>
            </conditional>
            <param name="k" value="ko"/>
            <section name="ap">
                <conditional name="f_cond">
                    <param name="f_sel" value="mapper-one-line"/>
                </conditional>
            </section>
            <output name="out_result" ftype="txt">
                <assert_contents>
                    <has_n_lines n="7"/>
                    <has_line line="sp|P19858|LDHA_BOVIN"/>
                </assert_contents>
            </output>
        </test>
    </tests>
    <help><![CDATA[