comparison metaphlan.xml @ 12:1a037928504c draft default tip

planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/metaphlan/ commit 671a5fc6d4c02bd3eb830c1886a31ecffd134ceb

11:b6897977d13e

<tool id="metaphlan" name="MetaPhlAn" version="@TOOL_VERSION@+galaxy@VERSION_SUFFIX@" profile="@PROFILE@">
    <description>to profile the composition of microbial communities</description>
    <macros>
        <import>macros.xml</import>
        <xml name="tax_lev">
            <conditional name="tax_lev">

                    <option value="f">Families only</option>
                    <option value="g">Genera only</option>
                    <option value="s">Species only</option>
                </param>
                <when value="a">
                    <param name="split_levels" type='boolean' checked="false" truevalue='true' falsevalue='false' 
                        label="Generate a report for each taxonomic level?" help="It will be in addition to the default output"/>
                </when>
                <when value="k"/>
                <when value="p"/>
                <when value="c"/>
                <when value="o"/>

                        </param>
                        <when value="single">
                            <param name="in" type="data" format="@FILE_FORMATS@" label="Single-end Fasta/FastQ file with microbiota reads"/>
                        </when>
                        <when value="multiple">
                            <param name="in" type="data" format="@FILE_FORMATS@" multiple="true" label="Single-end Fasta/FastQ files with microbiota reads"/>
                        </when>
                        <when value="paired_collection">
                            <param name="in" type="data_collection" format="@FILE_FORMATS@" label="Paired-end Fasta/FastQ file with microbiota reads"/>
                        </when>
                        <when value="paired">
                            <param name="in_f" type="data" format="@FILE_FORMATS@" label="Forward paired-end Fasta/FastQ file with microbiota reads"/>
                            <param name="in_r" type="data" format="@FILE_FORMATS@" label="Reverse paired-end Fasta/FastQ file with microbiota reads"/>
                        </when>

                </when>
                <when value="sam">
                    <param name="in" type="data" format="sam" label="Externally BowTie2-mapped SAM file" help="BowTie2 needs to be used first to map microbiota reads"/>
                </when>
                <when value="bowtie2out">
                    <param name="in" type="data" format="tabular" label="Intermediary mapping file of the microbiota generated by a previous MetaPhlAn run" 
                        help="File needs to be generated with MetaPhlAn versions >3.0"/>
                </when>
            </conditional>
            <conditional name="db">
                <param name="db_selector" type="select" label="Database with clade-specific marker genes">
                    <option value="cached" selected="true">Locally cached</option>

                    <option value="rel_ab" selected="true">rel_ab: Profiling a microbiota in terms of relative abundances</option>
                    <option value="rel_ab_w_read_stats">rel_ab_w_read_stats: Profiling a microbiota in terms of relative abundances and estimate the number of reads comming from each clade</option>
                    <option value="reads_map">reads_map: Mapping from reads to clades (only reads hitting a marker)</option>
                    <option value="clade_profiles">clade_profiles: Normalized marker counts for clades with at least a non-null marker</option>
                    <option value="clade_specific_strain_tracker">clade_specific_strain_tracker: List of markers present for a specific clade and all its subclades</option>
                    <option value="marker_ab_table">marker_ab_table: Normalized marker counts (only when > 0.0 and normalized by microbiota size if number of reads is specified)</option>
                    <option value="marker_counts">marker_counts: Non-normalized marker counts (use with extreme caution)</option>
                    <option value="marker_pres_table">marker_pres_table: List of markers present in the sample (threshold at 1.0 if not differently specified with --pres_th</option>
                </param>
                <when value="rel_ab">
                    <expand macro="tax_lev"/>

                    <expand macro="tax_lev"/>
                </when>
                <when value="reads_map"/>
                <when value="clade_profiles"/>
                <when value="clade_specific_strain_tracker">
                    <param argument="--clade" type="text" value="" label="Clade for which to extract list of markers present" 
                        help="Markers are also extracted for subclades" />
                    <param argument="--min_ab" type="float" optional="true" label="The minimum percentage abundance for the clade"/>
                </when>
                <when value="marker_ab_table">
                    <param argument="--nreads" type="integer" optional="true" label="Total number of reads in the original microbiota" 
                        help="It is used for normalizing the length-normalized counts with the microbiota size as well. No normalization applied if the value is not specified"/>
                </when>
                <when value="marker_counts"/>
                <when value="marker_pres_table">
                    <param argument="--pres_th" type="integer" optional="true" label="Threshold for calling a marker present"/>
                </when>
            </conditional>
            <param argument="--min_cu_len" type="integer" value="2000" 
                label="Minimum total nucleotide length for the markers in a clade for estimating the abundance without considering sub-clade abundances"/>
            <param argument="--min_alignment_len" type="integer" optional="true" 
                label="Sam records for aligned reads with the longest subalignment length smaller than this threshold will be discarded."/>
            <param name="organism_profiling" type="select" multiple="true" optional="true" label="Organisms to profile">
                <option value="add_viruses" selected="true">Profile viral organisms (add_viruses)</option>
                <option value="ignore_eukaryotes">Ignore eukaryotic organisms (ignore_eukaryotes)</option>
                <option value="ignore_bacteria">Ignore bacteria organisms (ignore_bacteria)</option>
                <option value="ignore_archaea">Ignore archea organisms (ignore_archaea)</option>
            </param>

                <option value="med">med: Median of length-normalized marker counts</option>
            </param>
            <param argument="--stat_q" type="float" value="0.2" label="Quantile value for the robust average"/>
            <param argument="--perc_nonzero" type="float" value="0.33" label="Percentage of markers with a non zero relative abundance for misidentify a species"/>
            <param argument="--ignore_markers" type="data" format="txt,tabular" optional="true" label="File containing a list of markers to ignore" help="One marker per line"/>
            <param argument="--avoid_disqm" type='boolean' checked="true" truevalue='--avoid_disqm' falsevalue='' 
                label="Deactivate the procedure of disambiguating the quasi-markers based on the marker abundance pattern found in the sample?"
                help="It is generally recommended to keep the disambiguation procedure in order to minimize false positives"/>
        </section>
        <conditional name="subsample">
            <param name="selector" type="select" label="Subsample" help="Subsampling only works for fastq input">
                <option value="no">No</option>
                <option value="single">Yes: specify number of reads</option>
                <option value="paired">Yes: specify number of paired reads</option>
            </param>
            <when value="no"/>
            <when value="single">
                <param argument="--subsampling" type="integer" value="" min="1" label="Sumbsample reads" help="Specify the number of reads to be considered"/>
                <expand macro="subsample_common"/>
            </when>
            <when value="paired">
                <param argument="--subsampling_paired" type="integer" value="" min="1" label="Sumbsample reads" help="Specify the number of paired reads to be considered. For N there will be floor(N/2) reads selected from the forward and reverse reads each."/>
                <expand macro="subsample_common"/>
            </when>
        </conditional>
        <conditional name="viral_analysis">
            <param argument="--profile_vsc" type="select" label="Profile Viruses with VSCs approach">

            <when value=""/>
        </conditional>
        <section name="out" title="Outputs" expanded="true">
            <param argument="--sample_id_key" type="text" value="SampleID" label="Sample ID key for this analysis"/>
            <param argument="--sample_id" type="text" value="Metaphlan_Analysis" label="Sample ID for this analysis"/>
            <param argument="--use_group_representative" type='boolean' checked="false" truevalue='--use_group_representative' falsevalue='' 
                label="Use a species as representative for species groups?"/>
            <param argument="--legacy-output" type='boolean' checked="false" truevalue='--legacy-output' falsevalue='' 
                label="Old MetaPhlAn2 two columns output?"/>
            <param argument="--CAMI_format_output" type='boolean' checked="false" truevalue='--CAMI_format_output' falsevalue='' 
                label="Report the profiling using the CAMI output format?"/>
            <param argument="--unclassified_estimation" type='boolean' checked="false" truevalue='--unclassified_estimation' falsevalue='' 
                label="Scale relative abundances to the number of reads mapping to known clades in order to estimate unknowness?"/>
            <param name="krona_output" type='boolean' checked="false" truevalue='true' falsevalue='false' label="Output for Krona?"/>
        </section>
        <!-- enabling this in tests will allow metaphlan to download reference data (we do this only with the smallish TOY DB) -->
        <param name="test" type="hidden" value="false"/>
    </inputs>
    <outputs>
        <data name="output_file" format="tabular" label="${tool.name} on ${on_string}: Predicted taxon relative abundances" />
        <data name="bowtie2out" format="tabular" label="${tool.name} on ${on_string}: Bowtie2 output">
            <filter>inputs['in']['selector'] == "raw"</filter>
        </data>
        <data name="sam_output_file" format="sam" label="${tool.name} on ${on_string}: SAM file">
            <filter>inputs['in']['selector'] == "raw"</filter>
        </data>
        <data name="biom_output_file" format="biom1" label="${tool.name} on ${on_string}: BIOM file" />
        <collection name="levels" type="list" label="${tool.name} on ${on_string}: Predicted taxon relative abundances at each taxonomic levels" >
            <discover_datasets pattern="(?P&lt;designation&gt;.+)" directory="split_levels/" format="tabular"/>
            <filter>analysis['analysis_type']['t'] in ['rel_ab', 'rel_ab_w_read_stats'] and analysis['analysis_type']['tax_lev']['tax_lev'] == "a" and analysis['analysis_type']['tax_lev']['split_levels']</filter>
        </collection>
        <data name="krona_output_file" format="tabular" label="${tool.name} on ${on_string}: Predicted taxon relative abundances for Krona">
            <filter>out['krona_output']</filter>

            <output name="biom_output_file" ftype="biom1" file="SRS014464-Anterior_nares.biom" compare="sim_size">
                <assert_contents>
                    <has_text text="k__Bacteria|p__Proteobacteria|c__Gammaproteobacteria|o__Pseudomonadales|f__Moraxellaceae|g__Moraxella|s__Moraxella_lacunata"/>
                </assert_contents>
            </output>
            <output_collection name="levels" type="list" >
                <element name="all" ftype="tabular">
                    <assert_contents>
                        <has_text text="Gammaproteobacteria"/>
                        <has_text text="Corynebacterium accolens"/>
                        <has_n_columns n="17"/>

                    <assert_contents>
                        <has_line_matching expression="^@.*" n="10128"/>
                    </assert_contents>
                </element>
            </output_collection>

            <assert_stderr>
                <has_text text="Downloading" negate="true"/>
            </assert_stderr>
        </test>
        <!-- Paired GZ file as collection, Cached db (note sumsample_paired and the included forward and reverse reads are counted separatelym because they are all statically defined) -->

                    <assert_contents>
                        <has_line_matching expression="^@.*" n="10128"/>
                    </assert_contents>
                </element>
            </output_collection>

            <assert_stderr>
                <has_text text="Downloading" negate="true"/>
            </assert_stderr>
        </test>
        <!-- SAM, cached DB -->

            <output name="biom_output_file" ftype="biom1" file="SRS014464-Anterior_nares.biom" compare="sim_size">
                <assert_contents>
                    <has_text text="k__Bacteria|p__Proteobacteria|c__Gammaproteobacteria|o__Pseudomonadales|f__Moraxellaceae|g__Moraxella|s__Moraxella_lacunata"/>
                </assert_contents>
            </output>
            <output_collection name="levels" type="list" >
                <element name="all" ftype="tabular">
                    <assert_contents>
                        <has_text text="Gammaproteobacteria"/>
                        <has_text text="Corynebacterium accolens"/>
                        <has_n_columns n="9"/>

                <has_text text="--profile_vsc"/>
                <has_text text="--vsc_breadth 0.75"/>
                <has_text text="--vsc_out"/>
            </assert_command>
            <assert_stderr>
                <has_text text="Downloading"/> <!-- due to test=true and the absence of the TOY reference DB Metaphlan will download to ~10MB-->
                <has_text text="No reads aligning to VSC markers"/>
            </assert_stderr>
        </test>
    </tests>
    <help><![CDATA[

12:1a037928504c

<tool id="metaphlan" name="MetaPhlAn" version="@TOOL_VERSION@+galaxy1" profile="@PROFILE@">
    <description>to profile the composition of microbial communities</description>
    <macros>
        <import>macros.xml</import>
        <xml name="tax_lev">
            <conditional name="tax_lev">

                    <option value="f">Families only</option>
                    <option value="g">Genera only</option>
                    <option value="s">Species only</option>
                </param>
                <when value="a">
                    <param name="split_levels" type="boolean" truevalue="true" falsevalue="false" checked="false" label="Generate a report for each taxonomic level?" help="It will be in addition to the default output"/>
                </when>
                <when value="k"/>
                <when value="p"/>
                <when value="c"/>
                <when value="o"/>

                        </param>
                        <when value="single">
                            <param name="in" type="data" format="@FILE_FORMATS@" label="Single-end Fasta/FastQ file with microbiota reads"/>
                        </when>
                        <when value="multiple">
                            <param name="in" type="data" format="@FILE_FORMATS@" label="Single-end Fasta/FastQ files with microbiota reads" multiple="true"/>
                        </when>
                        <when value="paired_collection">
                            <param name="in" type="data_collection" format="@FILE_FORMATS@" label="Paired-end Fasta/FastQ file with microbiota reads" collection_type="paired"/>
                        </when>
                        <when value="paired">
                            <param name="in_f" type="data" format="@FILE_FORMATS@" label="Forward paired-end Fasta/FastQ file with microbiota reads"/>
                            <param name="in_r" type="data" format="@FILE_FORMATS@" label="Reverse paired-end Fasta/FastQ file with microbiota reads"/>
                        </when>

                </when>
                <when value="sam">
                    <param name="in" type="data" format="sam" label="Externally BowTie2-mapped SAM file" help="BowTie2 needs to be used first to map microbiota reads"/>
                </when>
                <when value="bowtie2out">
                    <param name="in" type="data" format="tabular" label="Intermediary mapping file of the microbiota generated by a previous MetaPhlAn run" help="File needs to be generated with MetaPhlAn versions &gt;3.0"/>
                </when>
            </conditional>
            <conditional name="db">
                <param name="db_selector" type="select" label="Database with clade-specific marker genes">
                    <option value="cached" selected="true">Locally cached</option>

                    <option value="rel_ab" selected="true">rel_ab: Profiling a microbiota in terms of relative abundances</option>
                    <option value="rel_ab_w_read_stats">rel_ab_w_read_stats: Profiling a microbiota in terms of relative abundances and estimate the number of reads comming from each clade</option>
                    <option value="reads_map">reads_map: Mapping from reads to clades (only reads hitting a marker)</option>
                    <option value="clade_profiles">clade_profiles: Normalized marker counts for clades with at least a non-null marker</option>
                    <option value="clade_specific_strain_tracker">clade_specific_strain_tracker: List of markers present for a specific clade and all its subclades</option>
                    <option value="marker_ab_table">marker_ab_table: Normalized marker counts (only when &gt; 0.0 and normalized by microbiota size if number of reads is specified)</option>
                    <option value="marker_counts">marker_counts: Non-normalized marker counts (use with extreme caution)</option>
                    <option value="marker_pres_table">marker_pres_table: List of markers present in the sample (threshold at 1.0 if not differently specified with --pres_th</option>
                </param>
                <when value="rel_ab">
                    <expand macro="tax_lev"/>

                    <expand macro="tax_lev"/>
                </when>
                <when value="reads_map"/>
                <when value="clade_profiles"/>
                <when value="clade_specific_strain_tracker">
                    <param argument="--clade" type="text" value="" label="Clade for which to extract list of markers present" help="Markers are also extracted for subclades"/>
                    <param argument="--min_ab" type="float" optional="true" label="The minimum percentage abundance for the clade"/>
                </when>
                <when value="marker_ab_table">
                    <param argument="--nreads" type="integer" optional="true" label="Total number of reads in the original microbiota" help="It is used for normalizing the length-normalized counts with the microbiota size as well. No normalization applied if the value is not specified"/>
                </when>
                <when value="marker_counts"/>
                <when value="marker_pres_table">
                    <param argument="--pres_th" type="integer" optional="true" label="Threshold for calling a marker present"/>
                </when>
            </conditional>
            <param argument="--min_cu_len" type="integer" value="2000" label="Minimum total nucleotide length for the markers in a clade for estimating the abundance without considering sub-clade abundances"/>
            <param argument="--min_alignment_len" type="integer" optional="true" label="Sam records for aligned reads with the longest subalignment length smaller than this threshold will be discarded."/>
            <param name="organism_profiling" type="select" optional="true" label="Organisms to profile" multiple="true">
                <option value="add_viruses" selected="true">Profile viral organisms (add_viruses)</option>
                <option value="ignore_eukaryotes">Ignore eukaryotic organisms (ignore_eukaryotes)</option>
                <option value="ignore_bacteria">Ignore bacteria organisms (ignore_bacteria)</option>
                <option value="ignore_archaea">Ignore archea organisms (ignore_archaea)</option>
            </param>

                <option value="med">med: Median of length-normalized marker counts</option>
            </param>
            <param argument="--stat_q" type="float" value="0.2" label="Quantile value for the robust average"/>
            <param argument="--perc_nonzero" type="float" value="0.33" label="Percentage of markers with a non zero relative abundance for misidentify a species"/>
            <param argument="--ignore_markers" type="data" format="txt,tabular" optional="true" label="File containing a list of markers to ignore" help="One marker per line"/>
            <param argument="--avoid_disqm" type="boolean" truevalue="--avoid_disqm" falsevalue="" checked="true" label="Deactivate the procedure of disambiguating the quasi-markers based on the marker abundance pattern found in the sample?" help="It is generally recommended to keep the disambiguation procedure in order to minimize false positives"/>
        </section>
        <conditional name="subsample">
            <param name="selector" type="select" label="Subsample" help="Subsampling only works for fastq input">
                <option value="no">No</option>
                <option value="single">Yes: specify number of reads</option>
                <option value="paired">Yes: specify number of paired reads</option>
            </param>
            <when value="no"/>
            <when value="single">
                <param argument="--subsampling" type="integer" min="1" value="" label="Sumbsample reads" help="Specify the number of reads to be considered"/>
                <expand macro="subsample_common"/>
            </when>
            <when value="paired">
                <param argument="--subsampling_paired" type="integer" min="1" value="" label="Sumbsample reads" help="Specify the number of paired reads to be considered. For N there will be floor(N/2) reads selected from the forward and reverse reads each."/>
                <expand macro="subsample_common"/>
            </when>
        </conditional>
        <conditional name="viral_analysis">
            <param argument="--profile_vsc" type="select" label="Profile Viruses with VSCs approach">

            <when value=""/>
        </conditional>
        <section name="out" title="Outputs" expanded="true">
            <param argument="--sample_id_key" type="text" value="SampleID" label="Sample ID key for this analysis"/>
            <param argument="--sample_id" type="text" value="Metaphlan_Analysis" label="Sample ID for this analysis"/>
            <param argument="--use_group_representative" type="boolean" truevalue="--use_group_representative" falsevalue="" checked="false" label="Use a species as representative for species groups?"/>
            <param argument="--legacy-output" type="boolean" truevalue="--legacy-output" falsevalue="" checked="false" label="Old MetaPhlAn2 two columns output?"/>
            <param argument="--CAMI_format_output" type="boolean" truevalue="--CAMI_format_output" falsevalue="" checked="false" label="Report the profiling using the CAMI output format?"/>
            <param argument="--unclassified_estimation" type="boolean" truevalue="--unclassified_estimation" falsevalue="" checked="false" label="Scale relative abundances to the number of reads mapping to known clades in order to estimate unknowness?"/>
            <param name="krona_output" type="boolean" truevalue="true" falsevalue="false" checked="false" label="Output for Krona?"/>
        </section>
        <!-- enabling this in tests will allow metaphlan to download reference data (we do this only with the smallish TOY DB) -->
        <param name="test" type="hidden" value="false"/>
    </inputs>
    <outputs>
        <data name="output_file" format="tabular" label="${tool.name} on ${on_string}: Predicted taxon relative abundances"/>
        <data name="bowtie2out" format="tabular" label="${tool.name} on ${on_string}: Bowtie2 output">
            <filter>inputs['in']['selector'] == "raw"</filter>
        </data>
        <data name="sam_output_file" format="sam" label="${tool.name} on ${on_string}: SAM file">
            <filter>inputs['in']['selector'] == "raw"</filter>
        </data>
        <data name="biom_output_file" format="biom1" label="${tool.name} on ${on_string}: BIOM file"/>
        <collection name="levels" type="list" label="${tool.name} on ${on_string}: Predicted taxon relative abundances at each taxonomic levels">
            <discover_datasets pattern="(?P&lt;designation&gt;.+)" directory="split_levels/" format="tabular"/>
            <filter>analysis['analysis_type']['t'] in ['rel_ab', 'rel_ab_w_read_stats'] and analysis['analysis_type']['tax_lev']['tax_lev'] == "a" and analysis['analysis_type']['tax_lev']['split_levels']</filter>
        </collection>
        <data name="krona_output_file" format="tabular" label="${tool.name} on ${on_string}: Predicted taxon relative abundances for Krona">
            <filter>out['krona_output']</filter>

            <output name="biom_output_file" ftype="biom1" file="SRS014464-Anterior_nares.biom" compare="sim_size">
                <assert_contents>
                    <has_text text="k__Bacteria|p__Proteobacteria|c__Gammaproteobacteria|o__Pseudomonadales|f__Moraxellaceae|g__Moraxella|s__Moraxella_lacunata"/>
                </assert_contents>
            </output>
            <output_collection name="levels" type="list">
                <element name="all" ftype="tabular">
                    <assert_contents>
                        <has_text text="Gammaproteobacteria"/>
                        <has_text text="Corynebacterium accolens"/>
                        <has_n_columns n="17"/>

                    <assert_contents>
                        <has_line_matching expression="^@.*" n="10128"/>
                    </assert_contents>
                </element>
            </output_collection>
            <assert_stderr>
                <has_text text="Downloading" negate="true"/>
            </assert_stderr>
        </test>
        <!-- Paired GZ file as collection, Cached db (note sumsample_paired and the included forward and reverse reads are counted separatelym because they are all statically defined) -->

                    <assert_contents>
                        <has_line_matching expression="^@.*" n="10128"/>
                    </assert_contents>
                </element>
            </output_collection>
            <assert_stderr>
                <has_text text="Downloading" negate="true"/>
            </assert_stderr>
        </test>
        <!-- SAM, cached DB -->

            <output name="biom_output_file" ftype="biom1" file="SRS014464-Anterior_nares.biom" compare="sim_size">
                <assert_contents>
                    <has_text text="k__Bacteria|p__Proteobacteria|c__Gammaproteobacteria|o__Pseudomonadales|f__Moraxellaceae|g__Moraxella|s__Moraxella_lacunata"/>
                </assert_contents>
            </output>
            <output_collection name="levels" type="list">
                <element name="all" ftype="tabular">
                    <assert_contents>
                        <has_text text="Gammaproteobacteria"/>
                        <has_text text="Corynebacterium accolens"/>
                        <has_n_columns n="9"/>

                <has_text text="--profile_vsc"/>
                <has_text text="--vsc_breadth 0.75"/>
                <has_text text="--vsc_out"/>
            </assert_command>
            <assert_stderr>
                <has_text text="Downloading"/>
                <!-- due to test=true and the absence of the TOY reference DB Metaphlan will download to ~10MB-->
                <has_text text="No reads aligning to VSC markers"/>
            </assert_stderr>
        </test>
    </tests>
    <help><![CDATA[