annotate cdhit_analysis.xml @ 2:706b7acdb230 draft

planemo upload for repository https://github.com/Onnodg/Naturalis_NLOOR/tree/main/NLOOR_scripts/process_clusters_tool commit c2020ecc91cea0c8cf7439180cf796743c838b4d-dirty

<tool id="cdhit_cluster_analysis" name="CD-HIT Cluster Analysis" version="1.0.1">
    <description>Analyze CD-HIT clustering results with taxonomic annotation</description>

    <requirements>
        <requirement type="package" version="3.12.3">python</requirement>
        <requirement type="package" version="3.10.6">matplotlib</requirement>
        <requirement type="package" version="2.3.2">pandas</requirement>
        <requirement type="package" version="3.1.5">openpyxl</requirement>
    </requirements>

    <command detect_errors="exit_code"><![CDATA[
bash '$__tool_directory__/cdhit_analysis.sh'
        --input_cluster '$input_cluster'
        --input_annotation '$input_annotation'

        #if $output_options.similarity_output:
            --output_similarity_txt '$similarity_txt'
            --output_similarity_plot '$similarity_plot'
        #end if

        #if $output_options.evalue_output:
            --output_evalue_txt '$evalue_txt'
            --output_evalue_plot '$evalue_plot'
        #end if

        #if $output_options.count_output:
            --output_count '$cluster_count'
        #end if

        #if $output_options.taxa_output:
            --output_taxa_clusters '$cluster_taxa'
            --output_taxa_processed '$processed_taxa'
        #end if

        --simi_plot_y_min '$plot_params.simi_plot_y_min'
        --simi_plot_y_max '$plot_params.simi_plot_y_max'

        --uncertain_taxa_use_ratio '$taxa_params.uncertain_taxa_use_ratio'
        --min_to_split '$taxa_params.min_to_split'
        --min_count_to_split '$taxa_params.min_count_to_split'

        #if $processing_options.show_unannotated_clusters:
            --show_unannotated_clusters
        #end if

        #if $processing_options.make_taxa_in_cluster_split:
            --make_taxa_in_cluster_split
        #end if

        #if $processing_options.print_empty_files:
            --print_empty_files
        #end if
    ]]></command>

    <inputs>
        <param name="input_cluster" type="data" format="txt" label="CD-HIT cluster file"
               help="Output cluster file from cd-hit-est" />
        <param name="input_annotation" type="data" format="xlsx"
               label="Excel Annotations file"
               help="Excel workfile with annotations per header" />

        <section name="output_options" title="Output Options" expanded="true">
            <param name="similarity_output" type="boolean" truevalue="true" falsevalue="false"
                   checked="true" label="Create cluster similarity output"
                   help="Generate similarity analysis and plots" />
            <param name="evalue_output" type="boolean" truevalue="true" falsevalue="false"
                   checked="true" label="Create cluster E-value output"
                   help="Generate E-value analysis and plots" />
            <param name="count_output" type="boolean" truevalue="true" falsevalue="false"
                   checked="true" label="Create cluster count output"
                   help="Generate read count summaries" />
            <param name="taxa_output" type="boolean" truevalue="true" falsevalue="false"
                   checked="true" label="Create taxa annotations output"
                   help="Generate taxonomic analysis" />
        </section>

        <section name="plot_params" title="Plot Parameters" expanded="false">
            <param name="simi_plot_y_min" type="float" value="95.0" min="0" max="100"
                   label="Similarity plot Y-axis minimum"
                   help="Minimum value for similarity plot Y-axis" />
            <param name="simi_plot_y_max" type="float" value="100.0" min="0" max="100"
                   label="Similarity plot Y-axis maximum"
                   help="Maximum value for similarity plot Y-axis" />
        </section>

        <section name="taxa_params" title="Taxonomic Analysis Parameters" expanded="false">
            <param name="uncertain_taxa_use_ratio" type="float" value="0.5" min="0" max="1"
                   label="Uncertain taxa ratio"
                   help="Ratio at which uncertain taxa count toward the correct taxa" />
            <param name="min_to_split" type="float" value="0.45" min="0" max="1"
                   label="Minimum percentage to split"
                   help="Minimum percentage for taxonomic split" />
            <param name="min_count_to_split" type="integer" value="10" min="1"
                   label="Minimum count to split"
                   help="Minimum count for taxonomic split" />
        </section>

        <section name="processing_options" title="Processing Options" expanded="false">
            <param name="show_unannotated_clusters" type="boolean" truevalue="true" falsevalue="false"
                   checked="false" label="Show unannotated clusters"
                   help="Include unannotated clusters in output" />
            <param name="make_taxa_in_cluster_split" type="boolean" truevalue="true" falsevalue="false"
                   checked="false" label="Split clusters with multiple taxa"
                   help="Split clusters containing multiple taxa instead of marking as uncertain" />
            <param name="print_empty_files" type="boolean" truevalue="true" falsevalue="false"
                   checked="false" label="Print empty file messages"
                   help="Print messages about empty annotation files" />
        </section>
    </inputs>

    <outputs>
        <data name="similarity_txt" format="txt" label="Similarity data" >
            <filter>output_options['similarity_output']</filter>
        </data>

        <data name="similarity_plot" format="png" label="Similarity plot" >
            <filter>output_options['similarity_output']</filter>
        </data>

        <data name="evalue_txt" format="txt" label="E-value data" >
            <filter>output_options['evalue_output']</filter>
        </data>

        <data name="evalue_plot" format="png" label="E-value plot" >
            <filter>output_options['evalue_output']</filter>
        </data>

        <data name="cluster_count" format="txt" label="Count summary" >
            <filter>output_options['count_output']</filter>
        </data>

        <data name="cluster_taxa" format="xlsx" label="Raw taxa per cluster" >
            <filter>output_options['taxa_output']</filter>
        </data>

        <data name="processed_taxa" format="xlsx" label="Processed taxa" >
            <filter>output_options['taxa_output']</filter>
        </data>
    </outputs>

    <tests>
        <test expect_num_outputs="7">
            <param name="input_cluster" value="29-test.clstr.txt" />
            <param name="input_annotation" value="header_anno_29_test.xlsx" />
            <section name="output_options">
                <param name="similarity_output" value="true" />
                <param name="evalue_output" value="true" />
                <param name="count_output" value="true" />
                <param name="taxa_output" value="true" />
            </section>
            <output name="similarity_txt" file="sim_out.txt" />
            <output name="similarity_plot" file="sim_out.png" compare="sim_size"/>
            <output name="evalue_txt" file="evalue_out.txt" />
            <output name="evalue_plot" file="evalue_out.png" compare="sim_size"/>
            <output name="cluster_count" file="count_out.txt" />
            <output name="cluster_taxa" file="taxa_out.xlsx" decompress="true"/>
            <output name="processed_taxa" file="processed.xlsx" decompress="true"/>
        </test>
        <test expect_num_outputs="7">
            <param name="input_cluster" value="input2_test.clstr.txt" />
            <param name="input_annotation" value="header_anno_excel.xlsx" />
            <section name="output_options">
                <param name="similarity_output" value="true" />
                <param name="evalue_output" value="true" />
                <param name="count_output" value="true" />
                <param name="taxa_output" value="true" />
            </section>
            <output name="similarity_txt" file="test2_sim_out.txt" />
            <output name="similarity_plot" file="test2_sim_out.png" compare="sim_size"/>
            <output name="evalue_txt" file="test2_evalue_out.txt" />
            <output name="evalue_plot" file="test2_evalue_out.png" compare="sim_size"/>
            <output name="cluster_count" file="test_2count_out.txt" />
            <output name="cluster_taxa" file="test_2taxa_out.xlsx" decompress="true"/>
            <output name="processed_taxa" file="test_2processed.xlsx" decompress="true"/>
        </test>
        <test expect_num_outputs="5">
            <param name="input_cluster" value="input2_test.clstr.txt" />
            <param name="input_annotation" value="header_anno_excel.xlsx" />
            <section name="output_options">
                <param name="similarity_output" value="true" />
                <param name="count_output" value="true" />
                <param name="taxa_output" value="true" />
                <param name="evalue_output" value="false" />
            </section>
            <section name="processing_options">
                <param name="show_unannotated_clusters" value="true"/>
                <param name="make_taxa_in_cluster_split" value="true"/>
                <param name="print_empty_files" value="true"/>
            </section>
            <section name="taxa_params">
                <param name="uncertain_taxa_use_ratio" value="0.6"/>
                <param name="min_to_split" value="0.6"/>
                <param name="min_count_to_split" value="6"/>
            </section>
            <section name="plot_params">
                <param name="simi_plot_y_min" value="0.4" />
                <param name="simi_plot_y_max"  value="0.4"  />
            </section>
            <output name="similarity_txt" file="test2_sim_extra_out.txt" />
            <output name="similarity_plot" file="test2_sim_extra_out.png" compare="sim_size"/>
            <output name="cluster_count" file="test_2count_extra_out.txt" />
            <output name="cluster_taxa" file="test_2taxa_extra_out.xlsx" decompress="true"/>
            <output name="processed_taxa" file="test_2processed_extra.xlsx" decompress="true"/>
        </test>
    </tests>

    <help><![CDATA[
**CD-HIT Cluster Analysis**

This tool analyzes CD-HIT clustering results and provides various outputs including taxonomic analysis, similarity analysis, E-value analysis, and read count summaries.

**Input Files:**

1. **CD-HIT cluster file (.txt/.clstr)**: Required. The cluster file output from cd-hit-est containing clustered sequences.

2. **Annotation file (.xlsx)**: Tab-separated file containing sequence annotations with columns:

**Output Options:**

- **Cluster similarity output**: Creates similarity analysis with plots and text files showing intra-cluster similarity distributions
- **Cluster e-value output**: Creates E-value analysis with plots and text files showing E-value distributions
- **Cluster count output**: Creates summary tables with annotated/unannotated read counts per cluster
- **Taxa annotations output**: Creates taxonomic analysis determining the most likely taxa for each cluster

**Parameters:**

- **Plot Parameters**: Control the size of similarity plots (X and Y-axis limits)
- **Taxonomic Analysis Parameters**: Control how uncertain taxa are handled and when clusters are split
- **Processing Options**: Control display of unannotated clusters and verbose output

**Output Files:**

- **Similarity data**: Tab-separated file with similarity statistics
- **Similarity plot**: PNG image showing similarity distribution across clusters
- **E-value data**: Tab-separated file with E-value statistics
- **E-value plot**: PNG image showing E-value distribution
- **Count summary**: Tab-separated file with read counts per cluster
- **Raw taxa per cluster**: Excel file showing all taxa found in each cluster
- **Processed taxa**: Excel file with clusters where a taxon was assigned

**Note**: The tool expects that sequence counts are included in the cluster file headers in the format "header(count)".

-------------

.. class:: infomark

**Credits**

Based on a script by Nick Kortleven, translated, modified and wrapped by Onno de Gorter,
Developed for the New light on old remedies project, a PhD research by Anja Fischer.

Link to the project website:

* https://ahm.uva.nl/funded-research-projects/new-lights-on-old-remedies/new-lights-on-old-remedies.html

    ]]></help>
    <creator>
        <organization name="Naturalis Biodiversity Center" url="https://www.naturalis.nl/en/science" />
        <person givenName="Onno" familyName="de Gorter" url="https://github.com/Onnodg"/>
        <person givenName="Nick" familyName="Kortleven" url="https://github.com/tombkingsts" />
    </creator>
</tool>