comparison metaphlan.xml @ 2:1e919c4f1822 draft

"planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/metaphlan/ commit f1c6f4fe1e572ace84cf9106bc253603f55aac55"

1:b0aed9401632

python '$__tool_directory__/formatoutput.py'
    split_levels
    --metaphlan_output '$output_file'
    --outdir 'split_levels'
    $out.legacy_output
&&
ls split_levels
#end if

#if $out.krona_output
&&
python '$__tool_directory__/formatoutput.py'

    ]]></command>
    <inputs>
        <section name="inputs" title="Inputs" expanded="true">
            <conditional name="in">
                <param name="selector" type="select" label="Input(s)">
                    <option value="raw" selected="true">Fasta/FastQ file(s) with metagenomic reads</option>
                    <option value="sam">Externally BowTie2-mapped SAM file</option>
                    <option value="bowtie2out">Intermediary mapping file of the metagenome generated by a previous MetaPhlAn run</option>
                </param>
                <when value="raw">
                    <conditional name="raw_in">
                        <param name="selector" type="select" label="Fasta/FastQ file(s) with metagenomic reads">
                            <option value="single" selected="true">One single-end file</option>
                            <option value="multiple">Multiple single-end files</option>
                            <option value="paired">Paired-end files</option>
                        </param>
                        <when value="single">
                            <param name="in" type="data" format="@FILE_FORMATS@" label="Single-end Fasta/FastQ file with metagenomic reads"/>
                        </when>
                        <when value="multiple">
                            <param name="in" type="data" format="@FILE_FORMATS@" multiple="true" label="Single-end Fasta/FastQ files with metagenomic reads"/>
                        </when>
                        <when value="paired">
                            <param name="in_f" type="data" format="@FILE_FORMATS@" label="Forward paired-end Fasta/FastQ file with metagenomic reads"/>
                            <param name="in_r" type="data" format="@FILE_FORMATS@" label="Reverse paired-end Fasta/FastQ file with metagenomic reads"/>
                        </when>
                    </conditional>
                    <param argument="--read_min_len" type="integer" value="70" label="Minimum length of the reads to be considered when parsing the input file"/>
                    <section name="mapping" title="Mapping" expanded="true">
                        <param argument="--bt2_ps" type="select" label="Presets options for BowTie2" help="Applied only with FASTA files">

                        </param>
                        <param argument="--min_mapq_val" type="integer" value="5" label="Minimum mapping quality value (MAPQ)"/>
                    </section>
                </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 metagenom reads"/>
                </when>
                <when value="bowtie2out">
                    <param name="in" type="data" format="tabular" label="Intermediary mapping file of the metagenome 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">

            </conditional>
        </section>
        <section name="analysis" title="Analysis" expanded="true">
            <conditional name="analysis_type">
                <param argument="-t" type="select" label="Type of analysis to perform">
                    <option value="rel_ab" selected="true">rel_ab: Profiling a metagenomes in terms of relative abundances</option>
                    <option value="rel_ab_w_read_stats">rel_ab_w_read_stats: Profiling a metagenomes 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 metagenome 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"/>

                    <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 metagenome" 
                        help="It is used for normalizing the length-normalized counts with the metagenome 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 name="in">
                    <param name="selector" value="raw"/>
                    <conditional name="raw_in">
                        <!-- Single GZ file -->
                        <param name="selector" value="single"/>
                        <param name="in" value="SRS014464-Anterior_nares.fasta.gz"/>
                    </conditional>
                    <param name="read_min_len" value="70"/>
                    <section name="mapping">
                        <param name="bt2_ps" value="sensitive"/>

- unambiguous taxonomic assignments;
- accurate estimation of organismal relative abundance;
- species-level resolution for bacteria, archaea, eukaryotes and viruses;
- strain identification and tracking
- orders of magnitude speedups compared to existing methods.
- metagenomic strain-level population genomics

MetaPhlAn clade-abundance estimation
------------------------------------

The basic usage of MetaPhlAn consists in the identification of the clades (from phyla to species and 
strains in particular cases) present in the metagenome obtained from a microbiome sample and their 
relative abundance.

Marker level analysis
---------------------

Metaphlan takes as input either:

- one or several sequence files in Fasta, FastQ (compressed or not)
- a BowTie2 produced SAM file
- an intermediary mapping file of the metagenome generated by a previous MetaPhlAn run

It also need the reference database, which can be locally installed or customized using the dedicated tools.

Outputs
=======

2:1e919c4f1822

python '$__tool_directory__/formatoutput.py'
    split_levels
    --metaphlan_output '$output_file'
    --outdir 'split_levels'
    $out.legacy_output

#end if

#if $out.krona_output
&&
python '$__tool_directory__/formatoutput.py'

    ]]></command>
    <inputs>
        <section name="inputs" title="Inputs" expanded="true">
            <conditional name="in">
                <param name="selector" type="select" label="Input(s)">
                    <option value="raw" selected="true">Fasta/FastQ file(s) with microbiota reads</option>
                    <option value="sam">Externally BowTie2-mapped SAM file</option>
                    <option value="bowtie2out">Intermediary mapping file of the microbiota generated by a previous MetaPhlAn run</option>
                </param>
                <when value="raw">
                    <conditional name="raw_in">
                        <param name="selector" type="select" label="Fasta/FastQ file(s) with microbiota reads">
                            <option value="single" selected="true">One single-end file</option>
                            <option value="multiple">Multiple single-end files</option>
                            <option value="paired">Paired-end files</option>
                        </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">
                            <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>
                    </conditional>
                    <param argument="--read_min_len" type="integer" value="70" label="Minimum length of the reads to be considered when parsing the input file"/>
                    <section name="mapping" title="Mapping" expanded="true">
                        <param argument="--bt2_ps" type="select" label="Presets options for BowTie2" help="Applied only with FASTA files">

                        </param>
                        <param argument="--min_mapq_val" type="integer" value="5" label="Minimum mapping quality value (MAPQ)"/>
                    </section>
                </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">

            </conditional>
        </section>
        <section name="analysis" title="Analysis" expanded="true">
            <conditional name="analysis_type">
                <param argument="-t" type="select" label="Type of analysis to perform">
                    <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"/>

                    <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 name="in">
                    <param name="selector" value="raw"/>
                    <conditional name="raw_in">
                        <!-- Single GZ file -->
                        <param name="selector" value="single"/>
                        <param name="in" value="no_taxon_input.fasta"/>
                    </conditional>
                    <param name="read_min_len" value="70"/>
                    <section name="mapping">
                        <param name="bt2_ps" value="sensitive"/>
                        <param name="min_mapq_val" value="5"/>
                    </section>
                </conditional>
                <conditional name="db">
                    <!-- Cached db -->
                    <param name="db_selector" value="cached"/>
                    <param name="cached_db" value="test-db-20210409"/>
                </conditional>
            </section>
            <section name="analysis">
                <conditional name="analysis_type">
                    <param name="t" value="rel_ab"/>
                    <conditional name="tax_lev">
                        <param name="tax_lev" value="a"/>
                        <param name="split_levels" value="true"/>
                    </conditional>
                </conditional>
                <param name="min_cu_len" value="2000"/>
                <param name="organism_profiling" value="add_viruses"/>
                <param name="stat" value="avg_g"/>
                <param name="stat_q" value="0.2"/>
                <param name="perc_nonzero" value="0.33"/>
                <param name="avoid_disqm" value="true"/>
            </section>
            <section name="out">
                <param name="sample_id_key" value="SampleID"/>
                <param name="sample_id" value="Metaphlan_Analysis"/>
                <param name="use_group_representative" value="false"/>
                <param name="legacy_output" value="false"/>
                <param name="CAMI_format_output" value="false"/>
                <param name="unknown_estimation" value="false"/>
                <param name="krona_output" value="true"/>
            </section>
            <output name="output_file" ftype="tabular">
                <assert_contents>
                    <has_text text="UNKNOWN"/>
                </assert_contents>
            </output>
            <output name="bowtie2out" ftype="tabular">
                <assert_contents>
                    <not_has_text text="HWI-EAS109_102883399:3:104:7342:14360/1"/>
                    <has_n_lines n="2"/>
                </assert_contents>
            </output>
            <output name="sam_output_file" ftype="sam">
                <assert_contents>
                    <has_text text="SN:13076__A0A2I1PE66__CYJ72_10760"/>
                </assert_contents>
            </output>
            <output name="biom_output_file" ftype="biom1">
                <assert_contents>
                    <not_has_text text="k__Bacteria"/>
                    <not_has_text text="p__Actinobacteria"/>
                </assert_contents>
            </output>
            <output_collection name="levels" type="list" >
                <element name="all" ftype="tabular">
                    <assert_contents>
                        <has_text text="class"/>
                        <has_n_columns n="17"/>
                        <has_n_lines n="1"/>
                    </assert_contents>
                </element>
                <element name="kingdom" ftype="tabular">
                    <assert_contents>
                        <has_text text="kingdom_id"/>
                        <has_n_columns n="3"/>
                        <has_n_lines n="1"/>
                    </assert_contents>
                </element>
                <element name="phylum" ftype="tabular">
                    <assert_contents>
                        <has_text text="phylum_id"/>
                        <not_has_text text="kingdom_id"/>
                        <has_n_columns n="3"/>
                        <has_n_lines n="1"/>
                    </assert_contents>
                </element>
                <element name="class" ftype="tabular">
                    <assert_contents>
                        <has_text text="class_id"/>
                        <not_has_text text="phylum_id"/>
                        <has_n_columns n="3"/>
                        <has_n_lines n="1"/>
                    </assert_contents>
                </element>
                <element name="order" ftype="tabular">
                    <assert_contents>
                        <has_text text="order_id"/>
                        <not_has_text text="class_id"/>
                        <has_n_columns n="3"/>
                        <has_n_lines n="1"/>
                    </assert_contents>
                </element>
                <element name="family" ftype="tabular">
                    <assert_contents>
                        <has_text text="family_id"/>
                        <not_has_text text="order"/>
                        <has_n_columns n="3"/>
                        <has_n_lines n="1"/>
                    </assert_contents>
                </element>
                <element name="genus" ftype="tabular">
                    <assert_contents>
                        <has_text text="genus_id"/>
                        <not_has_text text="family"/>
                        <has_n_columns n="3"/>
                        <has_n_lines n="1"/>
                    </assert_contents>
                </element>
                <element name="species" ftype="tabular">
                    <assert_contents>
                        <has_text text="species_id"/>
                        <not_has_text text="genus"/>
                        <has_n_columns n="3"/>
                        <has_n_lines n="1"/>
                    </assert_contents>
                </element>
                <element name="strains" ftype="tabular">
                    <assert_contents>
                        <has_text text="strains_id"/>
                        <not_has_text text="species_id"/>
                        <has_n_columns n="3"/>
                        <has_n_lines n="1"/>
                    </assert_contents>
                </element>
            </output_collection>
            <output name="krona_output_file" ftype="tabular">
                <assert_contents>
                    <not_has_text text="k__Bacteria"/>
                    <has_n_lines n="0"/>
                </assert_contents>
            </output>
        </test>
        <test expect_num_outputs="6">
            <section name="inputs">
                <conditional name="in">
                    <param name="selector" value="raw"/>
                    <conditional name="raw_in">
                        <!-- Single GZ file -->
                        <param name="selector" value="single"/>
                        <param name="in" value="SRS014464-Anterior_nares.fasta.gz"/>
                    </conditional>
                    <param name="read_min_len" value="70"/>
                    <section name="mapping">
                        <param name="bt2_ps" value="sensitive"/>

- unambiguous taxonomic assignments;
- accurate estimation of organismal relative abundance;
- species-level resolution for bacteria, archaea, eukaryotes and viruses;
- strain identification and tracking
- orders of magnitude speedups compared to existing methods.
- microbiota strain-level population genomics

MetaPhlAn clade-abundance estimation
------------------------------------

The basic usage of MetaPhlAn consists in the identification of the clades (from phyla to species and 
strains in particular cases) present in the microbiota obtained from a microbiome sample and their 
relative abundance.

Marker level analysis
---------------------

Metaphlan takes as input either:

- one or several sequence files in Fasta, FastQ (compressed or not)
- a BowTie2 produced SAM file
- an intermediary mapping file of the microbiota generated by a previous MetaPhlAn run

It also need the reference database, which can be locally installed or customized using the dedicated tools.

Outputs
=======