Mercurial > repos > galaxy-australia > metawrapmg_binning
diff metawrapmg_binning.xml @ 2:2a8bc1d26d06 draft default tip
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/metawrapmg commit 26fe7d23c5c3981c9b737109e5db799cc5d23932
| author | iuc |
|---|---|
| date | Thu, 11 Apr 2024 21:56:14 +0000 |
| parents | 024ea3c4c29f |
| children |
line wrap: on
line diff
--- a/metawrapmg_binning.xml Mon Jan 30 22:30:51 2023 +0000 +++ b/metawrapmg_binning.xml Thu Apr 11 21:56:14 2024 +0000 @@ -6,100 +6,97 @@ <expand macro="xrefs"/> <expand macro="requirements"/> <command detect_errors="exit_code"><![CDATA[ - ## set memory usage - if [ -n "\$GALAXY_MEMORY_MB" ] ; then - GALAXY_MEMORY_GB=\$((GALAXY_MEMORY_MB / 1024)) ; - fi ; + ## set memory usage + if [ -n "\${GALAXY_MEMORY_MB}" ] ; then + export GALAXY_MEMORY_GB="\$((GALAXY_MEMORY_MB / 1024))" ; + fi ; - ################## - ## SET UP FILES ## - ################## - - ## should always be FASTA - #set mg_fn = 'metagenome.' + str($metagenome.ext) - ln -s '$metagenome' $mg_fn - && + ################## + ## SET UP FILES ## + ################## - ## Only FASTQ. Separate files for each sample. Metawrap checks for - ## files named _1.fastq and _2.fastq. - #set input1_fn = 'reads_1.fastq' - ln -s '$input_1' $input1_fn - && + ## only plain FASTA and FASTQ + ln -s '$metagenome' metagenome.fasta + && + ## Metawrap checks for files named _1.fastq and _2.fastq. + ln -s '$input_1' reads_1.fastq + && + ln -s '$input_2' reads_2.fastq + && - #set input2_fn = 'reads_2.fastq' - ln -s '$input_2' $input2_fn - && - - ##################### - ## INITIAL BINNING ## - ##################### + ##################### + ## INITIAL BINNING ## + ##################### - metawrap binning - --metabat2 --maxbin2 --concoct - -a '$mg_fn' - -m \${GALAXY_MEMORY_GB:-16} - -o INITIAL_BINNING - -t \${GALAXY_SLOTS:-4} - '$input1_fn' - '$input2_fn' - && + metawrap binning + --metabat2 --maxbin2 --concoct + -a metagenome.fasta + -m "\${GALAXY_MEMORY_GB:-16}" + -o INITIAL_BINNING + -t "\${GALAXY_SLOTS:-4}" + reads_1.fastq + reads_2.fastq + && - ## Check which binning programs produced bins - bin_dirs=(INITIAL_BINNING/concoct_bins INITIAL_BINNING/maxbin2_bins INITIAL_BINNING/metabat2_bins) && - switches=('-A' '-B' '-C') && + ## Check which binning programs produced bins + bin_dirs=(INITIAL_BINNING/concoct_bins INITIAL_BINNING/maxbin2_bins INITIAL_BINNING/metabat2_bins) && + switches=('-A' '-B' '-C') && - i=0 && - bin_string="" && + i=0 && + bin_string="" && - for dir in "\${bin_dirs[@]}" ; do - if find "\${dir}" -mindepth 1 -maxdepth 1 | read; then - bin_string="\${bin_string} \${switches[\$i]} \${dir}" ; - i+=1 ; - fi - done && + for dir in "\${bin_dirs[@]}" ; do + if [ "\$(find "\$dir" -mindepth 1 -maxdepth 1 -exec echo found \;)" ]; then + bin_string+=" \${switches[\$i]} \$dir" ; + ((i++)) ; + fi + done && - #################### - ## BIN REFINEMENT ## - #################### + #################### + ## BIN REFINEMENT ## + #################### - ## The checkm database is included in the conda package. - ## Requires metawrap-mg_1.3.0--hdfd78af_1 or later. See - ## https://github.com/bioconda/bioconda-recipes/pull/38299. + ## The checkm database is in the conda package, see + ## https://github.com/bioconda/bioconda-recipes/pull/38299. - metawrap bin_refinement - -t \${GALAXY_SLOTS:-4} - -m \${GALAXY_MEMORY_GB:-16} - -c $binning.c - -x $binning.x - -o BIN_REFINEMENT - ## Only run bin_refinement on bins with contigs - \${bin_string} + metawrap bin_refinement + -t "\${GALAXY_SLOTS:-4}" + -m "\${GALAXY_MEMORY_GB:-16}" + '$hidden_quick' + -c '${binning.c}' + -x '${binning.x}' + -o BIN_REFINEMENT + ## Only run bin_refinement on bins with contigs + "\${bin_string}" ]]></command> <inputs> - <param name="metagenome" format="fasta" type="data" label="Metagenome" help="Metagenome co-assembly for binning" /> - <param name="input_1" format="fastqsanger" type="data" label="Read 1" help="Original reads that were used for the assembly: read 1." /> - <param name="input_2" format="fastqsanger" type="data" label="Read 2" help="Original reads that were used for the assembly: read 2." /> + <param name="metagenome" format="fasta" type="data" label="Metagenome" help="Metagenome co-assembly for binning"/> + <param name="input_1" format="fastqsanger" type="data" label="Read 1" help="Original reads that were used for the assembly: read 1."/> + <param name="input_2" format="fastqsanger" type="data" label="Read 2" help="Original reads that were used for the assembly: read 2."/> <section name="binning" title="Binning parameters" expanded="false"> - <param argument='-c' type="integer" value="70" min="50" max="100" label="Percent completion" help="Minimum % completion of bins" /> - <param argument='-x' type="integer" value="10" min="0" max="100" label="Percent contamination" help="Maximum % contamination of bins that is acceptable" /> + <param argument="-c" type="integer" value="70" min="50" max="100" label="Percent completion" help="Minimum % completion of bins"/> + <param argument="-x" type="integer" value="10" min="0" max="100" label="Percent contamination" help="Maximum % contamination of bins that is acceptable"/> </section> + <!-- the pplacer component requires 40 GB per thread. Skip pplacer for + testing by setting this to "quick" --> + <param name="hidden_quick" type="hidden" value=""/> </inputs> <outputs> <!-- contigs binned into fasta files --> <collection name="metawrap_bins" type="list" label="MetaWRAP on ${on_string}: bins"> - <discover_datasets pattern="metawrap_\d+_\d+_bins/(?P<designation>.+)\.fa" format="fasta" directory="BIN_REFINEMENT" recurse="true" match_relative_path="true" visible="false" /> + <discover_datasets pattern="metawrap_\d+_\d+_bins/(?P<designation>.+)\.fa" format="fasta" directory="BIN_REFINEMENT" recurse="true" match_relative_path="true"/> </collection> <!-- summary figures --> <collection name="metawrap_figures" type="list" label="MetaWRAP on ${on_string}: summary figures"> - <discover_datasets pattern="__designation_and_ext__" directory="BIN_REFINEMENT/figures" visible="false" /> + <discover_datasets pattern="__designation_and_ext__" directory="BIN_REFINEMENT/figures"/> </collection> <!-- statistics on binning --> <collection name="metawrap_stats" type="list" label="MetaWRAP on ${on_string}: stat files"> - <discover_datasets pattern="(?P<designation>.+)\.stats" format="tabular" directory="BIN_REFINEMENT" visible="false" /> + <discover_datasets pattern="(?P<designation>.+)\.stats" format="tabular" directory="BIN_REFINEMENT"/> </collection> <!-- which contig went into which bin --> <collection name="metawrap_contigs" type="list" label="MetaWRAP on ${on_string}: contig assignments"> - <discover_datasets pattern="(?P<designation>.+)\.contigs" format="tabular" directory="BIN_REFINEMENT" visible="false" /> + <discover_datasets pattern="(?P<designation>.+)\.contigs" format="tabular" directory="BIN_REFINEMENT"/> </collection> </outputs> <tests> @@ -110,10 +107,14 @@ <param name="input_2" value="mapped_reads.r2.fastq.gz"/> <param name="c" value="60"/> <param name="x" value="15"/> - <!-- this is the main output, but it's too large to test --> - <!-- <output_collection name="metawrap_bins" type="list"> - <element name="bin.1" file="test02.fa" ftype="fasta"/> - </output_collection> --> + <param name="hidden_quick" value="--quick"/> + <output_collection name="metawrap_bins" type="list"> + <element name="bin.1" ftype="fasta"> + <assert_contents> + <has_text text="NODE_2_length_"/> + </assert_contents> + </element> + </output_collection> <output_collection name="metawrap_stats" type="list"> <element name="metawrap_60_15_bins" file="test02.stats" ftype="tabular"/> </output_collection> @@ -122,7 +123,7 @@ </output_collection> </test> </tests> - <help><![CDATA[ + <help><![CDATA[ MetaWRAP --------