view decoupler_aucell_score.xml @ 6:a33eb7d3b053 draft

planemo upload for repository https://github.com/ebi-gene-expression-group/container-galaxy-sc-tertiary/ commit 54818daabaf1251642a267e5766f13741cb7faeb

<?xml version="1.0"?>
<tool id="score_genes_aucell" name="Decoupler AUCell" version="1.4.0+galaxy3" profile="20.05">
    <description>
        scores cells using the AUCell method for gene sets.
    </description>
    <requirements>
        <requirement type="package" version="1.4.0">decoupler</requirement>
    </requirements>
    <command>
        python '$__tool_directory__/decoupler_aucell_score.py'
            --input_file '$input_file'
            #if $gene_lists_source.source == "gmt"
            --gmt_file '$gene_lists_source.gmt_file'
            #if $gene_lists_source.gene_sets_to_score
            --gene_sets_to_score '$gene_lists_source.gene_sets_to_score'
            #end if
            #else:
            --gene_lists_to_score '$gene_lists_source.gene_lists_to_score'
            --score_names '$gene_lists_source.score_names'
            #end if
            --gene_symbols_field '$gene_symbols_field'
            $use_raw
            #if $min_n_genes:
            --min_n '$min_n_genes'
            #end if
            #if $write_anndata:
            --write_anndata
            --output_file anndata_aucell.h5ad
            #else:
            --output_file anndata_aucell_per_cell.tsv
            #end if
            --max_threads "\${GALAXY_SLOTS:-4}"
    </command>
    <inputs>
        <param name="input_file" type="data" format="h5ad" label="Input AnnData file" />
        <conditional name="gene_lists_source">
            <param name="source" type="select" label="Source of gene lists to score" help="Choose between using a GMT file and specified gene sets or enumerated genes and gene set names.">
                <option value="gmt" selected="true">Gene sets from GMT file</option>
                <option value="enumerated">Gene sets enumerated manually</option>
            </param>
            <when value="gmt">
                <param name="gmt_file" type="data" format="txt" label="GMT file with gene sets" />
                <param name="gene_sets_to_score" type="text" optional="true" label="Gene sets to score within the GMT file" />
            </when>
            <when value="enumerated">
                <param name="gene_lists_to_score" type="text" label="Genes to score" />
                <param name="score_names" type="text" label="Score names" />
            </when>
        </conditional>
        <param name="min_n_genes" type="integer" label="Minimum number of genes" help="Minimum number of genes to match in each gene set" optional="true" value="5"/>
        <param name="gene_symbols_field" type="text" label="Gene symbols field" help="The field in the AnnData var table where gene symbols are stored."/>
        <param name="use_raw" type="boolean" value="false" truevalue="--use_raw" falsevalue="" label="Use raw data" help="Use RAW data in the AnnData instead of the X matrix."/>
        <param name="write_anndata" type="boolean" value="false" truevalue="--write_anndata" falsevalue="" label="Write the modified AnnData object" help="Whether to write or not the same AnnData file again with the signatures on it. If unselected, a text files of cells in rows and signatures in columns (as in Obs) is produced."/>
    </inputs>
    <outputs>
        <data name="output_ad" format="h5ad" from_work_dir="anndata_aucell.h5ad" label="${tool.name} on ${on_string}: Output AnnData file">
            <filter>write_anndata</filter>
        </data>
        <data name="output_table" format="tabular" from_work_dir="anndata_aucell_per_cell.tsv" label="${tool.name} on ${on_string}: Output AUCell table">
            <filter>not write_anndata</filter>
        </data>
    </outputs>
    <tests>
        <test expect_num_outputs="1">
            <param name="input_file" value="mito_counted_anndata.h5ad"/>
            <param name="gene_symbols_field" value="Symbol"/>
            <param name="write_anndata" value="true"/>
            <conditional name="gene_lists_source">
                <param name="gene_sets_to_score" value="HALLMARK_NOTCH_SIGNALING,HALLMARK_APICAL_SURFACE"/>
                <param name="gmt_file" value="mouse_hallmark_ss.gmt"/>
                <param name="source" value="gmt"/>
            </conditional>
            <output name="output_ad">
                <assert_contents>
                    <has_h5_keys keys="obs/AUCell_HALLMARK_NOTCH_SIGNALING"/>
                    <has_h5_keys keys="obs/AUCell_HALLMARK_APICAL_SURFACE"/>
                </assert_contents>
            </output>
        </test>
        <test expect_num_outputs="1">
            <param name="input_file" value="mito_counted_anndata.h5ad"/>
            <param name="gene_symbols_field" value="Symbol"/>
            <param name="write_anndata" value="true"/>
            <conditional name="gene_lists_source">
                <param name="source" value="gmt"/>
                <param name="gmt_file" value="mouse_hallmark_ss.gmt"/>
            </conditional>
            <output name="output_ad">
                <assert_contents>
                    <has_h5_keys keys="obs/AUCell_HALLMARK_NOTCH_SIGNALING"/>
                    <has_h5_keys keys="obs/AUCell_HALLMARK_APICAL_SURFACE"/>
                </assert_contents>
            </output>
        </test>
        <test expect_num_outputs="1">
            <param name="input_file" value="mito_counted_anndata.h5ad"/>
            <param name="gene_symbols_field" value="Symbol"/>
            <param name="write_anndata" value="true"/>
            <conditional name="gene_lists_source">
                <param name="source" value="enumerated"/>
                <param name="gene_lists_to_score" value="Cd8b1,Cd8b2,Cd8a,Cd4,Nrp1,Cd80:Il1a,Il1b,Il6,Nos2,Tlr2,Tlr4,Cd80"/>
                <param name="score_names" value="TCell,Macro"/>
            </conditional>
            <output name="output_ad">
                <assert_contents>
                    <has_h5_keys keys="obs/AUCell_TCell"/>
                    <has_h5_keys keys="obs/AUCell_Macro"/>
                </assert_contents>
            </output>
        </test>
        <test expect_num_outputs="1">
            <param name="input_file" value="mito_counted_anndata.h5ad"/>
            <param name="gene_symbols_field" value="Symbol"/>
            <param name="write_anndata" value="False"/>
            <conditional name="gene_lists_source">
                <param name="source" value="gmt"/>
                <param name="gene_sets_to_score" value="HALLMARK_NOTCH_SIGNALING,HALLMARK_APICAL_SURFACE"/>
                <param name="gmt_file" value="mouse_hallmark_ss.gmt"/>
            </conditional>
            <output name="output_table">
                <assert_contents>
                    <has_n_columns n="3"/>
                    <has_text_matching expression="AUCell_HALLMARK_NOTCH_SIGNALING"/>
                </assert_contents>
            </output>
        </test>
        <test expect_num_outputs="1">
            <param name="input_file" value="mito_counted_anndata.h5ad"/>
            <param name="gene_symbols_field" value="Symbol"/>
            <param name="write_anndata" value="False"/>
            <param name="min_n_genes" value="33"/>
            <conditional name="gene_lists_source">
                <param name="source" value="gmt"/>
                <param name="gene_sets_to_score" value="HALLMARK_NOTCH_SIGNALING,HALLMARK_APICAL_SURFACE"/>
                <param name="gmt_file" value="mouse_hallmark_ss.gmt"/>
            </conditional>
            <output name="output_table">
                <assert_contents>
                    <has_n_columns n="2"/>
                    <has_text_matching expression="AUCell_HALLMARK_APICAL_SURFACE"/>
                </assert_contents>
            </output>
        </test>
    </tests>
    <help>
**Description**

This tool scores cells using the AUCell method for gene sets.

**Input**

The input file should be an AnnData object in H5AD format. The tool accepts an H5AD file containing raw or normalized data.

The tool takes one of two input formats for specifying the gene sets to score:

1. A GMT file containing gene sets. You can specify which gene sets to use within the GMT file using the "gene_sets_to_score" parameter.
2. A list of genes and their associated score names. You can specify the genes to score using the "gene_lists_to_score" parameter, and their associated score names using the "score_names" parameter.

In both cases, you must specify the name of the field in the AnnData object that contains the gene symbols using the "gene_symbols_field" parameter.

You can also specify whether to use the raw data in the AnnData object instead of the X matrix using the "use_raw" parameter.

**Output**

The tool outputs an AnnData object containing the scores in the "obs" field, or a tab-separated text file containing the scores for each cell.

If the "write_anndata" parameter is set to "true", the tool will write the modified AnnData object to an H5AD file. Otherwise, it will output a tab-separated text file containing the scores for each cell.

**Example**


    </help>
    <citations>
        <citation type="doi">10.1093/bioadv/vbac016</citation>
    </citations>
</tool>