annotate concoct.xml @ 0:06c0eb033025 draft

"planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/concoct commit 49b42f61ff37c3c33dd15c195e5705e1db066c37"

<tool id="concoct" name="CONCOCT" version="@TOOL_VERSION@+galaxy@VERSION_SUFFIX@" profile="@PROFILE@">
    <description>metagenome binning</description>
    <macros>
        <import>macros.xml</import>
    </macros>
    <expand macro="requirements"/>
    <command detect_errors="exit_code"><![CDATA[
#set pca_components_file_name = 'PCA_components_data_gt' + str($advanced.length_threshold) + '.csv'
#set pca_transformed_file_name = 'PCA_transformed_data_gt' + str($advanced.length_threshold) + '.csv'
#set clustering_file_name = 'clustering_gt' + str($advanced.length_threshold) + '.csv'

## CONCOCT doesn't handle gzipped files.
#if $composition_file.ext.endswith(".gz")
    gunzip -c '$composition_file' > composition_file.fa &&
#else:
    ln -s '$composition_file' composition_file.fa &&
#end if

mkdir outdir &&
concoct
--coverage_file '$coverage_file'
--composition_file composition_file.fa
--clusters $advanced.clusters
--kmer_length $advanced.kmer_length
--threads \${GALAXY_SLOTS:-4}
--length_threshold $advanced.length_threshold
--read_length $advanced.read_length
--total_percentage_pca $advanced.total_percentage_pca
--basename 'outdir/'
--seed $advanced.seed
--iterations $advanced.iterations
--epsilon $advanced.epsilon
$advanced.no_cov_normalization
$advanced.no_total_coverage
--no_original_data
$advanced.converge_out

## Convert all CONCOCT .csv outputs to tabular.
&& sed 's/\("\([^"]*\)"\)\?,/\2\t/g' outdir/$pca_components_file_name > '$output_pca_components'
&& sed 's/\("\([^"]*\)"\)\?,/\2\t/g' outdir/$pca_transformed_file_name > '$output_pca_transformed'
&& sed 's/\("\([^"]*\)"\)\?,/\2\t/g' outdir/$clustering_file_name > '$output_clustering'
#if str($advanced.output_process_log) == 'yes':
    && mv outdir/log.txt '$process_log'
#end if
    ]]></command>
    <inputs>
        <param argument="--coverage_file" type="data" format="tabular" label="Tabular coverage file" help="Columns correspond to samples and rows to contigs"/>
        <param argument="--composition_file" type="data" format="fasta,fasta.gz" label="Fasta file" help="Used to calculate the kmer composition (the genomic signature) of each contig"/>
        <section name="advanced" title="Advanced options">
            <param argument="--clusters" type="integer" value="400" label="Maximum number of clusters for the Variational Gaussian Mixture Model algorithm"/>
            <param argument="--kmer_length" type="integer" value="4" label="Kmer length"/>
            <param argument="--length_threshold" type="integer" value="1000" label="Sequence length threshold" help="Contigs shorter than this value will not be included"/>
            <param argument="--read_length" type="integer" value="100" label="Read length for coverage"/>
            <param argument="--total_percentage_pca" type="integer" value="100" label="Percentage of variance explained by the principal components for the combined data"/>
            <param argument="--seed" type="integer" min="0" value="1" label="Integer to use as seed for clustering" help="Zero value will use random seed"/>
            <param argument="--iterations" type="integer" value="500" label="Maximum number of iterations for the Variational Bayes Gaussian Mixture Models"/>
            <param argument="--epsilon" type="float" value="0.000001" label="Epsilon for the Variational Gaussian Mixture Model algorithm"/>
            <param argument="--no_cov_normalization" type="boolean" truevalue="--no_cov_normalization" falsevalue="" checked="false" label="Skip normalization and only do log transorm of the coverage?" help="By default, the coverage is normalized for samples, then normalized for contigs and finally log transformed"/>
            <param argument="--no_total_coverage" type="boolean" truevalue="--no_total_coverage" falsevalue="" checked="false" label="Eliminate the total coverage column from the coverage data matrix?" help="By default, total coverage is included, independently of coverage normalization but previous to log transformation"/>
            <param argument="--converge_out" type="boolean" truevalue="--converge_out" falsevalue="" checked="false" label="Output convergence information?"/>
            <param name="output_process_log" type="select" label="Output process log file?">
                <option value="no" selected="true">No</option>
                <option value="yes">Yes</option>
            </param>
        </section>
    </inputs>
    <outputs>
        <data name="process_log" format="txt" label="${tool.name} on ${on_string} (process log)">
            <filter>advanced['output_process_log'] == 'yes'</filter>
        </data>
        <data name="output_pca_components" format="tabular" label="${tool.name} on ${on_string} (PCA components)"/>
        <data name="output_pca_transformed" format="tabular" label="${tool.name} on ${on_string} (PCA transformed)"/>
        <data name="output_clustering" format="tabular" label="${tool.name} on ${on_string} (Clusters)"/>
    </outputs>
    <tests>
        <test expect_num_outputs="4">
            <param name="coverage_file" value="input1.tabular" ftype="tabular"/>
            <param name="composition_file" value="input1.fa.gz" ftype="fasta.gz"/>
            <param name="output_process_log" value="yes"/>
            <output name="process_log" file="process_log.txt" ftype="txt" compare="contains"/>
            <output name="output_pca_components" ftype="tabular">
                <assert_contents>
                    <has_size value="367636"/>
                    <has_text text="7377051e-02"/>
                </assert_contents>
            </output>
            <output name="output_pca_transformed" ftype="tabular">
                <assert_contents>
                    <has_size value="737926"/>
                    <has_text text="NODE_103_length_20202_cov_8.395357.0"/>
                </assert_contents>
            </output>
            <output name="output_clustering" ftype="tabular">
                <assert_contents>
                    <has_size value="12167"/>
                    <has_text text="NODE_103_length_20202_cov_8.395357"/>
                </assert_contents>
            </output>
        </test>
    </tests>
    <help><![CDATA[
**What it does**

CONCOCT (Clustering cONtigs with COverage and ComposiTion) performs unsupervised binning of metagenomic contigs by
using nucleotide composition - kmer frequencies - and coverage data for multiple samples.  CONCOCT can accurately
(up to species level) bin metagenomic contigs. 

The tool accepts 2 inputs; a tabular file where each row corresponds to a contig and each column corresponds to a
sample (the values are the average coverage for this contig in that sample) and a file containing sequences in
fasta format.

Three are produced; clustering of the > 1000 kmer count, the PCA transformed matrix and the PCA components.

    ]]></help>
    <expand macro="citations"/>
</tool>