Mercurial > repos > iuc > coverm_genome
changeset 3:bb3f59096c8e draft
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tools/coverm commit 2d02165f40a9f8206a69716b2302bc58f5364982
| author | iuc |
|---|---|
| date | Wed, 26 Jul 2023 07:35:03 +0000 |
| parents | 5bf5792b0996 |
| children | 0ff4b0e5a3bc |
| files | coverm_genome.xml macros.xml |
| diffstat | 2 files changed, 856 insertions(+), 699 deletions(-) [+] |
line wrap: on
line diff
--- a/coverm_genome.xml Tue Mar 28 08:36:25 2023 +0000 +++ b/coverm_genome.xml Wed Jul 26 07:35:03 2023 +0000 @@ -3,555 +3,668 @@ <macros> <import>macros.xml</import> </macros> + <expand macro="bio_tools"/> <expand macro="requirements"/> <command><![CDATA[ - #if $reads.read_type == "single" or $reads.read_type == "interleaved" - mkdir -p reads1 && - #set file_paths1 = [] - #for $input_file in $reads.single - - #set $fname = $input_file.element_identifier.replace(" ","_") - #set $file_path = 'reads1/' + $fname - ln -s '$input_file' '$file_path' && - $file_paths1.append($file_path) - #end for - #else if $reads.read_type == "bam" - mkdir -p bam && - #set bam_files = [] - #for $input_file in $reads.bam - - #set $fname = $input_file.element_identifier.replace(" ","_") - #set $file_path = 'bam/' + $fname - ln -s '$input_file' '$file_path' && - $bam_files.append($file_path) +#import re + +#set $single_fp = [] +#set $fw_fp = [] +#set $rv_fp = [] +#set $interl_fp = [] +#set $ref_fp = [] +#set $bam_fp = [] +#set $genome_fp = [] + +mkdir 'single/' && +mkdir 'fw/' && +mkdir 'rv/' && +mkdir 'interl/' && +mkdir 'ref/' && +mkdir 'bam/' && + +#if $mapped.mapped == 'mapped' + @BAMS@ + #if $mapped.genome.ref_or_genome == 'genomic' + #if $mapped.genome.genomic.source == 'history' + #for $i, $genome in enumerate($mapped.genome.genomic.genome_fasta_files) + #set $fn = re.sub('[^\s\w\-\\.]', '_', str($genome.element_identifier)) + #silent $genome_fp.append( $fn ) +ln -s '$genome' '$fn' && #end for - #else if $reads.read_type == "paired" - mkdir -p paired_reads1 && - #set fw_reads1 = [] - #for $input_file in $reads.read1 - - #set $fname = $input_file.element_identifier.replace(" ","_") - #set $file_path = 'paired_reads1/' + str($fname) - ln -s '$input_file' '$file_path' && - $fw_reads1.append($file_path) - #end for - #set rv_reads1 = [] - #for $input_file in $reads.read2 - - #set $fname = $input_file.element_identifier.replace(" ","_") - #set $file_path = 'paired_reads1/' + str($fname) - ln -s '$input_file' '$file_path' && - $rv_reads1.append($file_path) - #end for - #silent $fw_reads1.sort() - #silent $rv_reads1.sort() #else - mkdir -p paired_reads && - #set paired_reads1 = [] - #for $i, $input_file in enumerate($reads.paired_reads) - #set $file_path = 'paired_reads/fw' + str($i) - ln -s '$input_file.forward' '$file_path' && - $paired_reads1.append($file_path) - #set $file_path = 'paired_reads/rv' + str($i) - ln -s '$input_file.reverse' '$file_path' && - $paired_reads1.append($file_path) - #end for - #end if - #if $add_reads.extra_read.read_type == "single" or $add_reads.extra_read.read_type == "interleaved" - mkdir -p add_reads1 && - #set add_file_paths1 = [] - #for $input_file in $add_reads.extra_read.single - #set $fname = $input_file.element_identifier.replace(" ","_") - #set $file_path = 'add_reads1/' + $fname - ln -s '$input_file' '$file_path' && - $add_file_paths1.append($file_path) - #end for - #else if $add_reads.extra_read.read_type == "bam" - mkdir -p add_bam && - #set add_bam_files = [] - #for $input_file in $reads.bam - #set $fname = $input_file.element_identifier.replace(" ","_") - #set $file_path = 'add_bam/' + $fname - ln -s '$input_file' '$file_path' && - $add_bam_files.append($file_path) - #end for - #else if $add_reads.extra_read.read_type == "paired" - mkdir -p add_paired_reads1 && - #set add_fw_reads1 = [] - #for $input_file in $add_reads.extra_read.read1 - #set $fname = $input_file.element_identifier.replace(" ","_") - #set $file_path = 'add_paired_reads1/' + str($fname) - ln -s '$input_file' '$file_path' && - $add_fw_reads1.append($file_path) - #end for - #set add_rv_reads1 = [] - #for $input_file in $add_reads.extra_read.read2 - #set $fname = $input_file.element_identifier.replace(" ","_") - #set $file_path = 'add_paired_reads1/' + str($fname) - ln -s '$input_file' '$file_path' && - $add_rv_reads1.append($file_path) - #end for - #silent $add_fw_reads1.sort() - #silent $add_rv_reads1.sort() - #else if $add_reads.extra_read.read_type == "paired_collection" - mkdir -p add_paired_reads && - #set add_paired_reads1 = [] - #for $i, $input_file in enumerate($add_reads.extra_read.paired_reads) - #set $ext = $input_file.forward.ext - #set $file_path = 'add_paired_reads/fw' + str($i) + '.' + $ext - ln -s '$input_file.forward' '$file_path' && - $add_paired_reads1.append($file_path) - #set $file_path = 'add_paired_reads/rv' + str($i) + '.' + $ext - ln -s '$input_file.reverse' '$file_path' && - $add_paired_reads1.append($file_path) + #for $i, $genome in enumerate($mapped.genome.genomic.genome_fasta_files) + #set $fn = re.sub('[^\s\w\-\\.]', '_', str($genome.fields.path.element_identifier)) + #silent $genome_fp.append( $fn ) +ln -s '$genome' '$fn' && #end for #end if - #if $reads.genome.ref_or_genome == "genomic" - mkdir -p genomes && - #set genome_files = [] - #if $reads.genome.genomic.source == "history" - #for $input_file in $reads.genome.genomic.fasta_history - - #set $fname = $input_file.element_identifier.replace(" ","_") - #set $file_path = 'genomes/' + $fname - ln -s '$input_file' '$file_path' && - $genome_files.append($file_path) - #end for - #else - #for $input_file in $reads.genome.genomic.fasta_builtin - #set $ext = $input_file.fields.path.ext - #set $fname = $input_file.fields.path.element_identifier.replace(" ","_") - #set $file_path = 'genomes/' + $fname - ln -s '$input_file' '$file_path' && - $genome_files.append($file_path) - #end for + #end if +#else + #if $mapped.mode.mode == 'individual' + @INDIVIDUAL_ASSEMBLY_READS@ + #if $mapped.mode.genome.ref_or_genome == 'genomic' + @GENOME_FOR_READS@ + #else + #set $ref = $mapped.mode.genome.reference + @INDIVIDUAL_ASSEMBLY_REF@ + #end if + #else + @CO_ASSEMBLY_ALL_READS@ + #if $mapped.mode.genome.ref_or_genome == 'genomic' + @GENOME_FOR_READS@ + #else + #set $refs = $mapped.mode.genome.reference + @CO_ASSEMBLY_REF@ + #end if + #end if +#end if + +mkdir 'representative-fasta/' && +coverm + genome +#if $mapped.mapped == 'mapped' + -b + #for $bam in $bam_fp + '$bam' + #end for + #if $mapped.genome.ref_or_genome == 'contigs' + $mapped.genome.cond_single_genome.single_genome + #if $mapped.genome.cond_single_genome.single_genome == '' + #if $mapped.genome.cond_single_genome.genome_contig_definition.choice == 'genome-definition' + --genome-definition '$mapped.genome.cond_single_genome.genome_contig_definition.genome_definition' + #else if $mapped.genome.cond_single_genome.genome_contig_definition.choice == 'separator' + --separator '$mapped.genome.cond_single_genome.genome_contig_definition.separator' #end if - #else if $reads.genome.ref_or_genome != "none" - mkdir -p reference && - #set ref_files = [] - #for $input_file in $reads.genome.ref_source - #set $fname = $input_file.element_identifier.replace(" ","_") - #set $file_path = 'reference/' + $fname - ln -s '$input_file' '$file_path' && - $ref_files.append($file_path) - #end for - #if $reads.genome.add_genome.add_genome == "true" - mkdir -p genomes && - #set genome_files = [] - #if $reads.genome.add_genome.add_genomic == "history" - #for $input_file in $reads.genome.add_genome.add_genomic.fasta_history - #set $fname = $input_file.element_identifier.replace(" ","_") - #set $file_path = 'genomes/' + $fname - ln -s '$input_file' '$file_path' && - $genome_files.append($file_path) - #end for - #else - #for $input_file in $reads.genome.add_genome.add_genomic.fasta_builtin - #set $ext = $input_file.fields.path.ext - #set $fname = $input_file.fields.path.element_identifier.replace(" ","_") - #set $file_path = 'genomes/' + $fname - ln -s '$input_file' '$file_path' && - $genome_files.append($file_path) - #end for - #end if + #end if + $mapped.sharded + #else + --genome-fasta-files + #for $genome in $genome_fp + '$genome' + #end for + #end if +#else + #if $fw_fp + -1 + #for $read in $fw_fp + '$read' + #end for + -2 + #for $read in $rv_fp + '$read' + #end for + #else if $single_fp + --single + #for $read in $single_fp + '$read' + #end for + #else if $interl_fp + --interleaved + #for $read in $interl_fp + '$read' + #end for + #end if + + --mapper '$mapped.mapper' + #if $mapped.mode.genome.ref_or_genome == 'contigs' + --reference + #for $ref in $ref_fp + '$ref' + #end for + $mapped.mode.genome.cond_single_genome.single_genome + #if $mapped.mode.genome.cond_single_genome.single_genome == '' + #if $mapped.mode.genome.cond_single_genome.genome_contig_definition.choice == 'genome-definition' + --genome-definition '$mapped.mode.genome.cond_single_genome.genome_contig_definition.genome_definition' + #else if $mapped.mode.genome.cond_single_genome.genome_contig_definition.choice == 'separator' + --separator '$mapped.mode.genome.cond_single_genome.genome_contig_definition.separator' #end if #end if - - mkdir ./representative-fasta/ && - coverm genome - #if $reads.read_type == 'paired' - -1 - #for $read in $fw_reads1 - '${read}' - #end for - -2 - #for $read in $rv_reads1 - '${read}' - #end for - #else if $reads.read_type == 'paired_collection' - --coupled - #for $read in $paired_reads1 - '${read}' - #end for - #else if $reads.read_type == 'single' - --single - #for $read in $file_paths1 - '${read}' - #end for - #else if $reads.read_type == 'interleaved' - --interleaved - #for $read in $file_paths1 - '${read}' - #end for - #else if $reads.read_type == 'bam' - -b - #for $read in $bam_files - '${read}' - #end for - #end if + #if $mapped.mode.mode == 'co' + $mapped.mode.genome.sharded + #end if + #else + --genome-fasta-files + #for $genome in $genome_fp + '$genome' + #end for + #end if +#end if - #if $add_reads.extra_read.read_type == 'paired' - -1 - #for $read in $add_fw_reads1 - '${read}' - #end for - -2 - #for $read in $add_rv_reads1 - '${read}' - #end for - #else if $add_reads.extra_read.read_type == 'paired_collection' - --coupled - #for $read in $add_paired_reads1 - '${read}' - #end for - #else if $add_reads.extra_read.read_type == 'single' - --single - #for $read in $add_file_paths1 - '${read}' - #end for - #else if $add_reads.extra_read.read_type == 'interleaved' - --interleaved - #for $read in $add_file_paths1 - '${read}' - #end for - #else if $add_reads.extra_read.read_type == 'bam' - #for $read in $add_bam_files - '${read}' - #end for - #end if - + $exclude_genomes_from_deshard + --min-read-aligned-length $alignment.min_read_aligned_length + --min-read-percent-identity $alignment.min_read_percent_identity + --min-read-aligned-percent $alignment.min_read_aligned_percent + $alignment.proper_pairs_only.proper_pairs_only +#if $alignment.proper_pairs_only.proper_pairs_only != '' + --min-read-aligned-length-pair $alignment.proper_pairs_only.min_read_aligned_length_pair + --min-read-percent-identity-pair $alignment.proper_pairs_only.min_read_percent_identity_pair + --min-read-aligned-percent-pair $alignment.proper_pairs_only.min_read_aligned_percent_pair +#end if + + --methods +#for method in $cov.methods + '$method' +#end for + --min-covered-fraction $cov.min_covered_fraction + --contig-end-exclusion $cov.contig_end_exclusion + --trim-min $cov.trim_min + --trim-max $cov.trim_max - #if $reads.genome.ref_or_genome == "genomic": - -f - #for $genome in $genome_files - '${genome}' - #end for - #else if $reads.genome.ref_or_genome != "none" and $reads.genome.ref_or_genome != "genomic": - --reference - #for $reference in $ref_files - '${reference}' - #end for - #if $reads.genome.cond_single_genome.single_genome != "false" - $reads.genome.cond_single_genome.single_genome - #if $reads.genome.cond_single_genome.genome_definition - --genome-definition $reads.genome.cond_single_genome.genome_definition - #end if - #else - #if $reads.genome.cond_single_genome.separator - -s "$reads.genome.cond_single_genome.separator" - #end if - #end if - #if $reads.genome.add_genome.add_genome == "true" - -f - #for $genome in $genome_files - '${genome}' - #end for - #end if - #else if $reads.genome.ref_or_genome == "none": - #if $reads.genome.separator: - -s "$reads.genome.separator" - #end if - $reads.genome.single_genome - #end if + $derep.dereplicate.dereplicate +#if $derep.dereplicate.dereplicate != '' + --dereplication-ani $derep.dereplicate.dereplication_ani + --dereplication-aligned-fraction $derep.dereplicate.dereplication_aligned_fraction + --dereplication-fragment-length $derep.dereplicate.dereplication_fragment_length + --dereplication-prethreshold-ani $derep.dereplicate.dereplication_prethreshold_ani + --dereplication-quality-formula '$derep.dereplicate.dereplication_quality_formula' + --dereplication-precluster-method '$derep.dereplicate.dereplication_precluster_method' +#end if +#if $derep.checkm_tab_table + --chekm-tab-table '$derep.checkm_tab_table' +#end if +#if $derep.genome_info: + --genome-info '$derep.genome_info' +#end if +#if $derep.min_completeness != "": + --min-completeness $derep.min_completeness +#end if +#if $derep.max_contamination != "": + --max-contamination $derep.max_contamination +#end if + + --output-format '$out.output_format' + --output-file '$output' + $out.no_zeros +#if $out.dereplication_output_cluster_definition: + --dereplication-output-cluster-definition '$cluster_definition' +#end if +#if $out.dereplication_output_representative_fasta_directory_copy: + --dereplication-output-representative-fasta-directory-copy './representative-fasta/' +#end if + --threads \${GALAXY_SLOTS:-1} - $derep.dereplicate - #if $derep.checkm_tab_table: - --chekm-tab-table '$derep.checkm_tab_table' - #end if - #if $derep.genome_info: - --genome-info '$derep.genome_info' - #end if - #if $derep.min_completeness != "": - --min-completeness $derep.min_completeness - #end if - #if $derep.max_contamination != "": - --max-contamination $derep.max_contamination - #end if - #if $derep.dereplication_ani != "": - --dereplication-ani $derep.dereplication_ani - #end if - #if $derep.dereplication_aligned_fraction != "": - --dereplication-aligned-fraction $derep.dereplication_aligned_fraction - #end if - #if $derep.dereplication_fragment_length != "": - --dereplication-fragment-length $derep.dereplication_fragment_length - #end if - #if $derep.dereplication_prethreshold_ani != "": - --dereplication-prethreshold-ani $derep.dereplication_prethreshold_ani - #end if - #if $derep.dereplication_quality_formula: - --dereplication-quality-formula $derep.dereplication_quality_formula - #end if - #if $derep.dereplication_precluster_method: - --dereplication-precluster-method $derep.dereplication_precluster_method - #end if - - $shar.sharded - $shar.exclude_genomes_from_deshard - - #if $mapping.mapper: - --mapper $mapping.mapper - #end if - #if $mapping.min_read_aligned_length: - --min-read-aligned-length $mapping.min_read_aligned_length - #end if - #if $mapping.min_read_percent_identity: - --min-read-percent-identity $mapping.min_read_percent_identity - #end if - #if $mapping.min_read_aligned_percent: - --min-read-aligned-percent $mapping.min_read_aligned_percent - #end if - #if $mapping.min_read_aligned_length_pair: - --min-read-aligned-length-pair $mapping.min_read_aligned_length_pair - #end if - #if $mapping.min_read_percent_identity_pair: - --min-read-percent-identity-pair $mapping.min_read_percent_identity_pair - #end if - #if $mapping.min_read_aligned_percent_pair: - --min-read-aligned-percent-pair $mapping.min_read_aligned_percent_pair - #end if - $mapping.proper_pairs_only - $mapping.exclude_supplementary - - --methods $cov.relative_abundance $cov.mean $cov.cond_methods.trimmed_mean $cov.covered_bases $cov.covered_fraction - $cov.variance $cov.length $cov.count $cov.metabat $cov.coverage_histogram $cov.reads_per_base - $cov.rpkm $cov.tpm - #if $cov.min_covered_fraction != "": - --min-covered-fraction $cov.min_covered_fraction - #end if - #if $cov.contig_end_exclusion != "": - --contig-end-exclusion $cov.contig_end_exclusion - #end if - #if $cov.cond_methods.trimmed_mean == "trimmed_mean" - #if $cov.cond_methods.trim_min: - --trim-min $cov.cond_methods.trim_min - #end if - #if $cov.cond_methods.trim_max: - --trim_max $cov.cond_methods.trim_max - #end if - #end if - - #if $out.output_format: - --output-format $out.output_format - #end if - #if $out.dereplication_output_cluster_definition: - --dereplication-output-cluster-definition '$cluster_definition' - #end if - #if $out.dereplication_output_representative_fasta_directory_copy: - --dereplication-output-representative-fasta-directory-copy ./representative-fasta/ - #end if - $out.no_zeros - --output-file output.tsv - --threads \${GALAXY_SLOTS:-1} - - #if $derep.dereplicate and $out.dereplication_output_cluster_definition - && sed -i -e 's@genomes/@@g; s/\.fna//g' '$cluster_definition' - #end if +#if $derep.dereplicate.dereplicate and $out.dereplication_output_cluster_definition + && sed -i -e 's@genomes/@@g; s/\.fna//g' '$cluster_definition' +#end if ]]></command> <inputs> - <expand macro="reads" /> - <expand macro="add_reads" /> - <section name="derep" title="Dereplication options" expanded="false"> - <param argument="--dereplicate" type="boolean" truevalue="--dereplicate" falsevalue="" optional="true" - label="Do genome dereplication via average nucleotide identity (ANI)" - help="Choose a genome to represent all within a small distance, using Dashing for - preclustering and FastANI for final ANI calculation. When this flag is used, - dereplication occurs transparently through the Galah method."/> - <param argument="--checkm-tab-table" type="data" format="tsv" optional="true" - label="Use checkM table" help="It is used for defining genome quality, which is used both for filtering - and to rank genomes during clustering"/> + <conditional name="mapped"> + <expand macro="mapped"/> + <when value="mapped"> + <expand macro="mapped_params"/> + <conditional name="genome"> + <param name="ref_or_genome" type="select" label="Genome definition"> + <option value="contigs" selected="true">From contigs in the BAM file(s)</option> + <option value="genomic">From FASTA files with each genome</option> + </param> + <when value="contigs"> + <expand macro="cond_single_genome"/> + </when> + <when value="genomic"> + <expand macro="genomic"/> + </when> + </conditional> + </when> + <when value="not-mapped"> + <conditional name="mode"> + <expand macro="assembly_mode"/> + <when value="individual"> + <expand macro="individual_assembly_reads"/> + <conditional name="genome"> + <expand macro="ref_or_genome"/> + <when value="contigs"> + <expand macro="individual_assembly_reference"/> + <expand macro="cond_single_genome"/> + </when> + <when value="genomic"> + <expand macro="genomic"/> + </when> + </conditional> + </when> + <when value="co"> + <expand macro="co_assembly_reads"/> + <repeat name="extra_reads" title="Additional reads"> + <expand macro="co_assembly_reads"/> + </repeat> + <conditional name="genome"> + <expand macro="ref_or_genome"/> + <when value="contigs"> + <expand macro="co_assembly_reference"/> + <expand macro="cond_single_genome"/> + </when> + <when value="genomic"> + <expand macro="genomic"/> + </when> + </conditional> + </when> + </conditional> + <expand macro="mapping"/> + </when> + </conditional> + <param argument="--exclude-genomes-from-deshard" type="boolean" truevalue="--exclude-genomes-from-deshard" falsevalue="" checked="false" label="Exclude genomes from deshard" + help="Ignore genomes whose name appears in this newline-separated file when combining shards." /> + <expand macro="alignment"/> + <section name="cov" title="Coverage calculation options" expanded="false"> + <param argument="--methods" type="select" multiple="true" label="Method(s) for calculating coverage"> + <option value="relative_abundance" selected="true">relative_abundance: Percentage relative abundance of each genome, and the unmapped read percentage</option> + <option value="mean">mean: Average number of aligned reads overlapping each position on the contig</option> + <expand macro="cov_method_options"/> + </param> + <expand macro="coverage_params"/> + </section> + <section name="derep" title="Dereplication / Genome clustering" expanded="false"> + <conditional name="dereplicate"> + <param argument="--dereplicate" type="select" label="Do genome dereplication via average nucleotide identity (ANI)?" help="When this is run, + dereplication occurs transparently through the Galah method."> + <option value="--dereplicate">Yes</option> + <option value="" selected="false">No</option> + </param> + <when value="--dereplicate"> + <param argument="--dereplication-ani" type="float" min="0" max="100" value="99" label="Overall ANI level to dereplicate at with FastANI" /> + <param argument="--dereplication-aligned-fraction" type="float" min="0" value="50" label="Minimum aligned fraction of two genomes for clustering" /> + <param argument="--dereplication-fragment-length" type="integer" min="0" value="3000" label="Length of fragment used in FastANI calculation (i.e. --fragLen)" /> + <param argument="--dereplication-quality-formula" type="select" label="Scoring function for genome quality"> + <option value="Parks2020_reduced" selected="true">Parks2020_reduced: A quality formula described in Parks et. al. 2020</option> + <option value="completeness-4contamination">completeness-4contamination</option> + <option value="completeness-5contamination">completeness-5contamination</option> + <option value="dRep">dRep</option> + </param> + <param argument="--dereplication-prethreshold-ani" type="float" min="0" max="100" value="95" label="Dereplication preclustering threshold" + help="Require at least this dashing-derived ANI for preclustering and to avoid FastANI on distant lineages within preclusters." /> + <param argument="--dereplication-precluster-method" type="select" label="Method of calculating rough ANI for dereplication"> + <option value="dashing" selected="true">dashing: HyperLogLog</option> + <option value="finch">finch: finch MinHash</option> + </param> + </when> + <when value=""/> + </conditional> + <param argument="--checkm-tab-table" type="data" format="tabular" optional="true" label="checkM table for defining genome quality" + help="It is used both for filtering and to rank genomes during clustering"/> <param argument="--genome-info" type="data" format="csv" optional="true" - label="Define quality in dRep style" help="dRep stype genome info table for defining quality" /> + label="dRep style genome info table for defining quality" /> <param argument="--min-completeness" type="float" optional="true" min="0" max="100" - label="Min completeness" help="Ignore genomes with less completeness than this percentage" /> + label="Minimum completeness" help="Genomes with lower completeness percentage will be ignored" /> <param argument="--max-contamination" type="float" optional="true" min="0" max="100" - label="Max contamination" help="Ignore genomes with more contamination than this percentage" /> - <param argument="--dereplication-ani" type="float" optional="true" min="0" max="100" value="99" - label="Overall ANI level" help="Overall ANI level to dereplicate at with FastANI. Default: 99" /> - <param argument="--dereplication-aligned-fraction" type="float" optional="true" min="0" value="50" - label="Dereplication aligned fraction" help="Min aligned fraction of two genomes for clustering. Default: 50" /> - <param argument="--dereplication-fragment-length" type="integer" optional="true" min="0" value="3000" - label="Length of fragment used in FastANI calculation (i.e. --fragLen). Default: 3000" /> - <param argument="--dereplication-prethreshold-ani" type="float" optional="true" min="0" max="100" value="95" - label="Dereplication preclustering threshold" help="Require at least this dashing-derived ANI for - preclustering and to avoid FastANI on distant lineages within preclusters. Default: 95" /> - <param type="select" argument="--dereplication-quality-formula" label="Scoring function for genome quality" help="Default: Parks2020_reduced"> - <option value="Parks2020_reduced">Parks2020_reduced (default)</option> - <option value="completeness-4contamination">completeness-4contamination</option> - <option value="completeness-5contamination">completeness-5contamination</option> - <option value="dRep">dRep</option> - </param> - <param type="select" argument="--dereplication-precluster-method" label="Dereplication precluster method" help="Method of calculating rough ANI for dereplication. Default: dashing"> - <option value="dashing">HyperLogLog</option> - <option value="finch">finch MinHash</option> - </param> + label="Maximum contamination" help="Genomes with higher contamination percentage will be ignored" /> </section> - <section name="shar" title="Sharding options" expanded="false"> - <param argument="--sharded" type="boolean" optional="true" truevalue="--sharded" falsevalue="" label="Shared" help="If -b/--bam-files was used: Input BAM files are read-sorted alignments of a set of reads mapped to multiple reference contig sets. Choose the best hit for each read pair. Otherwise if mapping was carried out: Map reads to each reference, choosing the best hit for each pair." /> - <param argument="--exclude-genomes-from-deshard" type="boolean" optional="true" - truevalue="--exclude-genomes-from-deshard" falsevalue="" label="Exclude genomes from deshard" - help="Ignore genomes whose name appears in this newline-separated file when combining shards." /> + <section name="out" title="Outputs" expanded="false"> + <expand macro="output_format"/> + <param argument="--no-zeros" type="boolean" truevalue="--no-zeros" falsevalue="" label="Omit printing of genomes that have zero coverage?" /> + <param argument="--dereplication-output-cluster-definition" type="boolean" truevalue="--dereplication-output-cluster-definition" falsevalue="" label="Output a tabular files with dereplicated representatives and member lines?" /> + <param argument="--dereplication-output-representative-fasta-directory-copy" type="boolean" truevalue="--dereplication-output-representative-fasta-directory-copy" falsevalue="" label="Output dereplicated representative genomes?" /> </section> - <expand macro="mapping"/> - <expand macro="coverage"/> - <expand macro="out"/> </inputs> <outputs> - <data name="output1" format="tsv" from_work_dir="./output.tsv"/> - <data name="cluster_definition" format="tsv" label="${tool.name} on ${on_string}: cluster definition"> - <filter>derep['dereplicate'] and out['dereplication_output_cluster_definition']</filter> + <data name="output" format="tabular" label="${tool.name} on ${on_string}"/> + <data name="cluster_definition" format="tabular" label="${tool.name} on ${on_string}: Cluster definition"> + <filter>derep['dereplicate']['dereplicate'] and out['dereplication_output_cluster_definition']</filter> </data> - <collection name="representative_fasta" type="list" label="${tool.name} on ${on_string}: representative fasta"> + <collection name="representative_fasta" type="list" label="${tool.name} on ${on_string}: Dereplicated epresentative genomes"> <discover_datasets pattern="(?P<designation>.*)\.fna" format="fasta" directory="representative-fasta" /> - <filter>derep['dereplicate'] and out['dereplication_output_representative_fasta_directory_copy']</filter> + <filter>derep['dereplicate']['dereplicate'] and out['dereplication_output_representative_fasta_directory_copy']</filter> </collection> </outputs> <tests> <test expect_num_outputs="1"> - <conditional name="reads"> - <param name="read_type" value="paired_collection"/> - <param name="paired_reads"> - <collection type="list:paired"> - <element name="reads_for_seq1_and_seq2..fq"> - <collection type="paired"> - <element name="forward" value="reads_for_seq1_and_seq2.1.fq.gz"/> - <element name="reverse" value="reads_for_seq1_and_seq2.2.fq.gz"/> + <conditional name="mapped"> + <param name="mapped" value="not-mapped" /> + <conditional name="mode"> + <param name="mode" value="co"/> + <conditional name="read_type"> + <param name="type" value="paired_collection"/> + <param name="paired_reads"> + <collection type="list:paired"> + <element name="reads_for_seq1_and_seq2"> + <collection type="paired"> + <element name="forward" value="reads_for_seq1_and_seq2.1.fq.gz" ftype="fastqsanger.gz"/> + <element name="reverse" value="reads_for_seq1_and_seq2.2.fq.gz" ftype="fastqsanger.gz"/> + </collection> + </element> </collection> - </element> - </collection> - </param> - <conditional name="genome"> - <param name="ref_or_genome" value="reference"/> - <param name="ref_source" value="7seqs.fna"/> + </param> + </conditional> + <repeat name="extra_reads"> + <conditional name="read_type"> + <param name="type" value="single"/> + <param name="single" value="reads_for_seq1_and_seq2.fna"/> + </conditional> + </repeat> + <conditional name="genome"> + <param name="ref_or_genome" value="contigs"/> + <param name="reference" value="7seqs.fna" /> <conditional name="cond_single_genome"> - <param name="single_genome" value="false"/> - <param name="separator" value="~"/> + <param name="single_genome" value=""/> + <conditional name="genome_contig_definition"> + <param name="choice" value="separator"/> + <param name="separator" value="~"/> + </conditional> </conditional> + </conditional> + <param name="sharded" value="" /> </conditional> </conditional> - <section name="add_reads"> - <conditional name="extra_read"> - <param name="read_type" value="single"/> - <param name="single" value="reads_for_seq1_and_seq2.fna"/> + <param name="exclude_genomes_from_deshard" value="false"/> + <section name="alignment"> + <param name="min_read_aligned_length" value="0" /> + <param name="min_read_percent_identity" value="0" /> + <param name="min_read_aligned_percent" value="0" /> + <conditional name="proper_pairs_only"> + <param name="proper_pairs_only" value=""/> </conditional> + <param name="exclude_supplementary" value=""/> </section> <section name="cov"> - <param name="mean" value="true"/> - <param name="relative_abundance" value="true"/> - <param name="variance" value="true"/> + <param name="methods" value="mean,relative_abundance,variance"/> + <param name="trim_min" value="5"/> + <param name="trim_max" value="95"/> + <param name="min_covered_fraction" value="10"/> + <param name="contig_end_exclusion" value="75"/> + </section> + <section name="derep"> + <conditional name="dereplicate"> + <param name="dereplicate" value=""/> + </conditional> </section> <section name="out"> <param name="output_format" value="sparse"/> + <param name="no_zeros" value=""/> + <param name="dereplication_output_cluster_definition" value="" /> + <param name="dereplication_output_representative_fasta_directory_copy" value="" /> </section> - <output name="output1" file="test1.tsv" ftype="tsv" sort="true"/> + <output name="output" ftype="tabular"> + <assert_contents> + <has_text text="Sample"/> + <has_text text="Genome"/> + <has_text text="Relative Abundance (%)"/> + <has_text text="Mean"/> + <has_text text="Variance"/> + <has_text text="7seqs.fna_0/reads_for_seq1_and_seq2_paired_collection_0"/> + <has_text text="unmapped"/> + <has_text text="genome6"/> + </assert_contents> + </output> </test> <test expect_num_outputs="1"> - <conditional name="reads"> - <param name="read_type" value="bam"/> - <param name="bam" value="7seqs.reads_for_seq1_and_seq2.bam"/> - <conditional name="genome"> - <param name="ref_or_genome" value="none"/> - <param name="separator" value="~"/> + <conditional name="mapped"> + <param name="mapped" value="mapped" /> + <conditional name="mode"> + <param name="mode" value="co"/> + <param name="bam_files" value="7seqs.reads_for_seq1_and_seq2.bam"/> + <param name="sharded" value="" /> + <conditional name="genome"> + <param name="ref_or_genome" value="contigs"/> + <conditional name="cond_single_genome"> + <param name="single_genome" value=""/> + <conditional name="genome_contig_definition"> + <param name="choice" value="separator"/> + <param name="separator" value="~"/> + </conditional> + </conditional> + </conditional> + <param name="sharded" value="" /> </conditional> </conditional> - <section name="shar"> - <param name="sharded" value="false"/> - <param name="exclude_genoms_from_deshard" value="false"/> - </section> - <section name="mapping"> - <param name="mapper" value="minimap2-sr"/> - <param name="minimap2_reference_is_index" value="false"/> + <param name="exclude_genomes_from_deshard" value="false"/> + <section name="alignment"> + <param name="min_read_aligned_length" value="0" /> + <param name="min_read_percent_identity" value="0" /> + <param name="min_read_aligned_percent" value="0" /> + <conditional name="proper_pairs_only"> + <param name="proper_pairs_only" value=""/> + </conditional> + <param name="exclude_supplementary" value=""/> </section> <section name="cov"> - <param name="mean" value="true"/> - <param name="relative_abundance" value="true"/> + <param name="methods" value="mean,relative_abundance"/> + <param name="trim_min" value="5"/> + <param name="trim_max" value="95"/> + <param name="min_covered_fraction" value="10"/> + <param name="contig_end_exclusion" value="75"/> + </section> + <section name="derep"> + <conditional name="dereplicate"> + <param name="dereplicate" value=""/> + </conditional> </section> <section name="out"> <param name="output_format" value="sparse"/> + <param name="no_zeros" value=""/> + <param name="dereplication_output_cluster_definition" value="" /> + <param name="dereplication_output_representative_fasta_directory_copy" value="" /> </section> - <output name="output1" file="test2.tsv" ftype="tsv" sort="true"/> + <output name="output" ftype="tabular"> + <assert_contents> + <has_text text="Sample"/> + <has_text text="Genome"/> + <has_text text="Mean"/> + <has_text text="7seqs.reads_for_seq1_and_seq2"/> + <has_text text="genome1"/> + </assert_contents> + </output> </test> <test expect_num_outputs="1"> - <section name="derep"> - <param name="dereplicate" value="true"/> - <param name="genome_info" value="genomeInfo.csv"/> + <conditional name="mapped"> + <param name="mapped" value="not-mapped" /> + <conditional name="mode"> + <param name="mode" value="co"/> + <conditional name="read_type"> + <param name="type" value="single"/> + <param name="single" value="1read.actually_fasta.fq"/> + </conditional> + <conditional name="genome"> + <param name="ref_or_genome" value="genomic"/> + <conditional name="genomic"> + <param name="source" value="history"/> + <param name="genome_fasta_files" value="500kb.fna,1mbp.fna"/> + </conditional> + </conditional> + <param name="sharded" value="" /> + </conditional> + </conditional> + <param name="exclude_genomes_from_deshard" value="false"/> + <section name="alignment"> + <param name="min_read_aligned_length" value="0" /> + <param name="min_read_percent_identity" value="0" /> + <param name="min_read_aligned_percent" value="0" /> + <conditional name="proper_pairs_only"> + <param name="proper_pairs_only" value=""/> + </conditional> + <param name="exclude_supplementary" value=""/> </section> <section name="cov"> - <param name="covered_fraction" value="true"/> + <param name="methods" value="covered_bases"/> + <param name="trim_min" value="5"/> + <param name="trim_max" value="95"/> <param name="min_covered_fraction" value="0"/> + <param name="contig_end_exclusion" value="75"/> </section> - <conditional name="reads"> - <param name="read_type" value="single"/> - <param name="single" value="1read.actually_fasta.fq"/> - <conditional name="genome"> - <param name="ref_or_genome" value="genomic"/> - <conditional name="genomic"> - <param name="source" value="history"/> - <param name="fasta_history" value="500kb.fna,1mbp.fna"/> - </conditional> + <section name="derep"> + <conditional name="dereplicate"> + <param name="dereplicate" value="--dereplicate"/> + <param name="dereplication_ani" value="99" /> + <param name="dereplication_aligned_fraction" value="50" /> + <param name="dereplication_fragment_length" value="3000" /> + <param name="dereplication_quality_formula" value="Parks2020_reduced" /> + <param name="dereplication_prethreshold_ani" value="95" /> + <param name="dereplication_precluster_method" value="finch"/> </conditional> - </conditional> - <output name="output1"> + <param name="genome_info" value="genomeInfo.csv"/> + </section> + <section name="out"> + <param name="output_format" value="sparse"/> + <param name="no_zeros" value=""/> + <param name="dereplication_output_cluster_definition" value="" /> + <param name="dereplication_output_representative_fasta_directory_copy" value="" /> + </section> + <output name="output" ftype="tabular"> <assert_contents> - <has_n_lines n="2"/> + <has_text text="Sample"/> + <has_text text="Genome"/> + <has_text text="Covered Bases"/> + <has_text text="1read.actually_fasta.fq_single_0"/> + <has_text text="1mbp"/> </assert_contents> </output> </test> <test expect_num_outputs="3"> - <conditional name="reads"> - <param name="read_type" value="paired_collection"/> - <param name="paired_reads"> - <collection type="list:paired"> - <element name="reads_for_genome2"> - <collection type="paired"> - <element name="forward" value="reads_for_genome2.1.fa"/> - <element name="reverse" value="reads_for_genome2.2.fa"/> + <conditional name="mapped"> + <param name="mapped" value="not-mapped" /> + <conditional name="mode"> + <param name="mode" value="co"/> + <conditional name="read_type"> + <param name="type" value="paired_collection"/> + <param name="paired_reads"> + <collection type="list:paired"> + <element name="reads_for_genome2"> + <collection type="paired"> + <element name="forward" value="reads_for_genome2.1.fa" ftype="fasta"/> + <element name="reverse" value="reads_for_genome2.2.fa" ftype="fasta"/> + </collection> + </element> </collection> - </element> - </collection> - </param> - <conditional name="genome"> - <param name="ref_or_genome" value="genomic"/> - <conditional name="genomic"> - <param name="source" value="history"/> - <param name="fasta_history" value="genome1.fna,genome2.fna,genome3.fna"/> + </param> </conditional> + <conditional name="genome"> + <param name="ref_or_genome" value="genomic"/> + <conditional name="genomic"> + <param name="source" value="history"/> + <param name="genome_fasta_files" value="genome1.fna,genome2.fna,genome3.fna"/> + </conditional> + </conditional> + <param name="sharded" value="" /> </conditional> </conditional> + <param name="exclude_genomes_from_deshard" value="false"/> + <section name="alignment"> + <param name="min_read_aligned_length" value="0" /> + <param name="min_read_percent_identity" value="0" /> + <param name="min_read_aligned_percent" value="0" /> + <conditional name="proper_pairs_only"> + <param name="proper_pairs_only" value=""/> + </conditional> + <param name="exclude_supplementary" value=""/> + </section> <section name="cov"> - <param name="mean" value="true"/> + <param name="methods" value="mean"/> + <param name="trim_min" value="5"/> + <param name="trim_max" value="95"/> + <param name="min_covered_fraction" value="0"/> + <param name="contig_end_exclusion" value="75"/> </section> <section name="derep"> - <param name="dereplicate" value="true"/> + <conditional name="dereplicate"> + <param name="dereplicate" value="--dereplicate"/> + <param name="dereplication_ani" value="99" /> + <param name="dereplication_aligned_fraction" value="50" /> + <param name="dereplication_fragment_length" value="3000" /> + <param name="dereplication_quality_formula" value="Parks2020_reduced" /> + <param name="dereplication_prethreshold_ani" value="95" /> + <param name="dereplication_precluster_method" value="finch"/> + </conditional> </section> <section name="out"> - <param name="dereplication_output_cluster_definition" value="true"/> - <param name="dereplication_output_representative_fasta_directory_copy" value="true"/> + <param name="output_format" value="sparse"/> + <param name="no_zeros" value=""/> + <param name="dereplication_output_cluster_definition" value="true" /> + <param name="dereplication_output_representative_fasta_directory_copy" value="true" /> </section> - <output name="output1" file="test3.tsv" ftype="tsv" sort="true"/> - <output name="cluster_definition" ftype="tsv" value="test4_cluster.tsv" sort="true"/> + <output name="output" ftype="tabular"> + <assert_contents> + <has_text text="Genome"/> + <has_text text="Mean"/> + <has_text text="Sample"/> + <has_text text="reads_for_genome2_paired_collection_0"/> + <has_text text="genome2"/> + <has_text text="genome3"/> + </assert_contents> + </output> + <output name="cluster_definition" ftype="tabular"> + <assert_contents> + <has_text text="genome1"/> + <has_text text="genome2"/> + <has_text text="genome3"/> + </assert_contents> + </output> <output_collection name="representative_fasta" type="list" count="3"> - <element name="genome1" file="test4_rep1.fa" ftype="fasta" /> - <element name="genome2" file="test4_rep2.fa" ftype="fasta" /> - <element name="genome3" file="test4_rep3.fa" ftype="fasta" /> + <element name="genome1" ftype="fasta"> + <assert_contents> + <has_text text=">random_sequence_length_500_1"/> + <has_text text=">random_sequence_length_500_2"/> + </assert_contents> + </element> + <element name="genome2" ftype="fasta"> + <assert_contents> + <has_text text=">random_sequence_length_500_1"/> + <has_text text=">random_sequence_length_500_2"/> + </assert_contents> + </element> + <element name="genome3" ftype="fasta"> + <assert_contents> + <has_text text=">random_sequence_length_500_1"/> + <has_text text=">random_sequence_length_500_2"/> + </assert_contents> + </element> </output_collection> </test> <test expect_num_outputs="1"> - <conditional name="reads"> - <param name="read_type" value="bam"/> - <param name="bam" value="2seqs.bad_read.1.with_supplementary.bam"/> - <conditional name="genome"> - <param name="ref_or_genome" value="none"/> - <param name="single_genome" value="true"/> + <conditional name="mapped"> + <param name="mapped" value="mapped" /> + <conditional name="mode"> + <param name="mode" value="co"/> + <param name="bam_files" value="2seqs.bad_read.1.with_supplementary.bam"/> + <param name="sharded" value="" /> + <conditional name="genome"> + <param name="ref_or_genome" value="contigs"/> + <conditional name="cond_single_genome"> + <param name="single_genome" value="true"/> + <conditional name="genome_contig_definition"> + <param name="choice" value="default"/> + </conditional> + </conditional> + </conditional> + <param name="sharded" value="" /> </conditional> </conditional> + <param name="exclude_genomes_from_deshard" value="false"/> + <section name="alignment"> + <param name="min_read_aligned_length" value="0" /> + <param name="min_read_percent_identity" value="0" /> + <param name="min_read_aligned_percent" value="0" /> + <conditional name="proper_pairs_only"> + <param name="proper_pairs_only" value=""/> + </conditional> + <param name="exclude_supplementary" value=""/> + </section> <section name="cov"> - <param name="count" value="true"/> + <param name="methods" value="count"/> + <param name="trim_min" value="5"/> + <param name="trim_max" value="95"/> <param name="min_covered_fraction" value="0"/> + <param name="contig_end_exclusion" value="75"/> </section> - <output name="output1" file="test5.tsv" ftype="tsv" sort="true"/> + <section name="derep" > + <conditional name="dereplicate"> + <param name="dereplicate" value=""/> + </conditional> + </section> + <section name="out"> + <param name="output_format" value="sparse"/> + <param name="no_zeros" value=""/> + <param name="dereplication_output_cluster_definition" value="" /> + <param name="dereplication_output_representative_fasta_directory_copy" value="" /> + </section> + <output name="output" ftype="tabular"> + <assert_contents> + <has_text text="Sample"/> + <has_text text="Genome"/> + <has_text text="Read Count"/> + <has_text text="2seqs.bad_read.1.with_supplementary"/> + <has_text text="genome1"/> + </assert_contents> + </output> </test> - </tests> + </tests> <help><![CDATA[ .. class:: infomark
--- a/macros.xml Tue Mar 28 08:36:25 2023 +0000 +++ b/macros.xml Wed Jul 26 07:35:03 2023 +0000 @@ -1,13 +1,17 @@ <macros> + <token name="@TOOL_VERSION@">0.6.1</token> + <token name="@VERSION_SUFFIX@">1</token> + <token name="@PROFILE@">22.01</token> <xml name="requirements"> <requirements> <requirement type="package" version="@TOOL_VERSION@">coverm</requirement> </requirements> </xml> - <token name="@INPUT_FORMATS@">fasta,fastq,fastq.gz,fasta.gz</token> - <token name="@TOOL_VERSION@">0.6.1</token> - <token name="@VERSION_SUFFIX@">0</token> - <token name="@PROFILE@">22.01</token> + <xml name="bio_tools"> + <xrefs> + <xref type="bio.tools">coverm</xref> + </xrefs> + </xml> <xml name="citation"> <citations> <citation type="bibtex"> @@ -22,275 +26,315 @@ </citation> </citations> </xml> - <xml name="genome_opt"> - <conditional name="genome"> - <param name="ref_or_genome" type="select" label="Select if you want to specify additional genome files."> - <option value="genomic">yes</option> - <option value="none" selected="true">No (Only when BAM files are provided)</option> - </param> - <when value="none"> - <param argument="--single-genome" type="boolean" truevalue="--single-genome" falsevalue="" checked="false" label="All contigs are from the same genome."/> - <param type="text" name="separator" optional="true" label="Character, that separates genome names from contig names in the reference file." > - <sanitizer> - <valid initial="string.punctuation"> - </valid> - </sanitizer> - </param> + <xml name="mapped"> + <param name="mapped" type="select" label="Have the reads already been mapped to contigs?"> + <option value="mapped">Yes (no read mapping algorithm will be undertaken)</option> + <option value="not-mapped" selected="true">No</option> + </param> + </xml> + <xml name="assembly_mode"> + <param name="mode" type="select" label="Assembly mode?" help="Useful to know if contigs have been generated all samples together (co-assembly) or on each sample individually (individual assembly)"> + <option value="individual">Individual assembly (1 contig file per sample)</option> + <option value="co" selected="true">Co-assembly (1 contig file for several samples)</option> + </param> + </xml> + <xml name="mapped_params"> + <conditional name="mode"> + <expand macro="assembly_mode"/> + <when value="individual"> + <param argument="--bam-files" type="data" format="bam" label="BAM file(s)" help="These must be reference sorted (e.g. with samtools sort) unless sharded is specified, in which case they must be read name sorted (e.g. with samtools sort -n)."/> + </when> + <when value="co"> + <param argument="--bam-files" type="data" format="bam" multiple="true" label="BAM file(s)" help="These must be reference sorted (e.g. with samtools sort) unless sharded is specified, in which case they must be read name sorted (e.g. with samtools sort -n)."/> </when> - <when value="genomic"> - <conditional name="genomic"> - <param type="select" label="Reference genome source" name="source"> - <option value="history" selected="true">History</option> - <option value="builtin">Built-in</option> - </param> - <when value="history"> - <param type="data" name="fasta_history" multiple="true" label="FASTA files of each genome" format="fasta" /> - </when> - <when value="builtin"> - <param type="select" name="fasta_builtin" multiple="true" label="Reference genome(s)"> - <options from_data_table="all_fasta" /> - </param> - </when> - </conditional> + </conditional> + <param argument="--sharded" type="boolean" truevalue="--sharded" falsevalue="" checked="false" label="BAM file(s) read-sorted alignments of a set of reads mapped to multiple reference contig sets?" help="If set, it will choose the best hit for each read pair" /> + </xml> + <token name="@BAMS@"><![CDATA[ + #if $mapped.mode.mode == 'individual' + #set $fn = 'bam/' + re.sub('[^\s\w\-\\.]', '_', str($mapped.mode.bam_files.element_identifier)) + #silent $bam_fp.append( $fn ) +ln -s '$mapped.mode.bam_files' '$fn' && + #else + #for $i, $bam in enumerate($mapped.mode.bam_files) + #set $fn = 'bam/' + re.sub('[^\s\w\-\\.]', '_', str($bam.element_identifier)) + '_' + str($i) + #silent $bam_fp.append( $fn ) +ln -s '$bam' '$fn' && + #end for + #end if +]]></token> + <xml name="genomic"> + <conditional name="genomic"> + <param type="select" name="source" label="Source of FASTA files with each genome" > + <option value="history" selected="true">History</option> + <option value="builtin">Built-in</option> + </param> + <when value="history"> + <param argument="--genome-fasta-files" type="data" format="fasta" multiple="true" label="FASTA files of each genome"/> + </when> + <when value="builtin"> + <param argument="--genome-fasta-files" type="select" multiple="true" label="Reference genome(s)"> + <options from_data_table="all_fasta" /> + </param> </when> </conditional> </xml> - <xml name="genome"> - <conditional name="genome"> - <param name="ref_or_genome" type="select" label="Reference sequence mode" help="Select if you want to specify genome file(s) or a FASTA reference file or both. NOTE: If genomic FASTA files are specified, then reference is not needed as a reference FASTA file can be derived by concatenating input genomes. However, while not necessary, reference can be specified if an alternate reference sequence set is desired."> - <option value="genomic" selected="true">Reference genome</option> - <option value="reference">Contigs (e.g. concatenated genomes or metagenome assembly)</option> + <xml name="cond_single_genome"> + <conditional name="cond_single_genome"> + <param argument="--single-genome" type="select" label="Are all contigs from the same genome?"> + <option value="--single-genome">True</option> + <option value="">False</option> </param> - <when value="genomic"> - <conditional name="genomic"> - <param type="select" label="Reference genome source" name="source"> - <option value="history" selected="true">History</option> - <option value="builtin">Built-in</option> + <when value="--single-genome"/> + <when value=""> + <conditional name="genome_contig_definition"> + <param argument="choice" type="select" label="How to get genome names and contig names?"> + <option value="default" selected="true">Using default behavior</option> + <option value="genome-definition">Providing a file containing newline-separated list of genome name and contig</option> + <option value="separator">Providing character that separates genome names from contig names in the reference file</option> </param> - <when value="history"> - <param type="data" name="fasta_history" multiple="true" label="FASTA files of each genome" format="fasta" /> + <when value="default"/> + <when value="genome-definition"> + <param argument="--genome-definition" type="data" format="tabular" label="File containing newline-separated list of genome_name and contig, separated by tab, to define the genome of each contig." /> </when> - <when value="builtin"> - <param type="select" name="fasta_builtin" multiple="true" label="Reference genome(s)"> - <options from_data_table="all_fasta" /> - </param> - </when> - </conditional> - </when> - <when value="reference"> - <param type="data" name="ref_source" multiple="true" label="Contigs file(s)" format="fasta" help="If multiple references FASTA files are provided and 'sharded' is specified, then reads will be mapped to references separately as sharded BAMs."/> - <conditional name="cond_single_genome"> - <param name="single_genome" type="select" label="All contigs are from a single genome"> - <option value="--single-genome">True</option> - <option value="false">False</option> - </param> - <when value="--single-genome"> - <param type="data" name="genome_definition" format="tsv" optional="true" label="File containing newline-separated list of genome_name and contig, separated by tab, to define the genome of each contig." /> - </when> - <when value="false"> - <param type="text" argument="--separator" optional="true" label="Character, that separates genome names from contig names in the reference file." > + <when value="separator"> + <param argument="--separator" type="text" label="Character that separates genome names from contig names in the reference file." > <sanitizer> <valid initial="string.punctuation"> </valid> </sanitizer> </param> </when> - </conditional> - <conditional name="add_genome"> - <param name="add_genome" type="select" label="Add additional Genome Files"> - <option value="true">Yes</option> - <option value="false" selected="true">No</option> - </param> - <when value="true"> - <conditional name="add_genomic"> - <param type="select" label="Reference genome source" name="source"> - <option value="history" selected="true">History</option> - <option value="builtin">Built-in</option> - </param> - <when value="history"> - <param type="data" name="fasta_history" multiple="true" label="Single FASTA file of contigs" format="fasta" /> - </when> - <when value="builtin"> - <param type="select" name="fasta_builtin" multiple="true" label="Reference genome"> - <options from_data_table="all_fasta" /> - </param> - </when> - </conditional> - </when> - <when value="false"> - </when> </conditional> </when> </conditional> </xml> - <xml name="reads_for_contig"> - <conditional name="reads"> - <param type="select" label="Read type" name="read_type"> - <option value="paired">Paired end</option> - <option value="paired_collection" selected="true">Paired collection</option> - <option value="single">Single ended</option> - <option value="interleaved">Interleaved</option> - <option value="bam">BAM file(s)</option> - </param> + <token name="@INPUT_FORMATS@">fasta,fastq,fastq.gz,fasta.gz</token> + <xml name="read_type"> + <param name="type" type="select" label="Read type" > + <option value="single">Single end</option> + <option value="paired">Paired end</option> + <option value="paired_collection" selected="true">Paired collection</option> + <option value="interleaved">Interleaved</option> + </param> + </xml> + <xml name="paired_reads"> + <param name="paired_reads" type="data_collection" collection_type="list:paired" format="@INPUT_FORMATS@" label="Collection of paired-end FASTA/Q files(s) for mapping" help="One or more pairs of forward and reverse possibly gzipped FASTA/Q files for mapping in order." /> + </xml> + <xml name="individual_assembly_reads"> + <conditional name="read_type"> + <expand macro="read_type"/> + <when value="single"> + <param argument="--single" type="data" format="@INPUT_FORMATS@" label="Single Read" /> + </when> <when value="paired"> - <param type="data" format="@INPUT_FORMATS@" name="read1" multiple="true" label="Read1" /> - <param type="data" format="@INPUT_FORMATS@" name="read2" multiple="true" label="Read2" /> - <param type="data" name="ref_fasta_history" multiple="true" label="FASTA file(s) of contigs" format="fasta" /> + <param argument="-1" name="read1" type="data" format="@INPUT_FORMATS@" label="Forward FASTA/Q file for mapping" /> + <param argument="-2" name="read2" type="data" format="@INPUT_FORMATS@" label="Reverse FASTA/Q file for mapping" /> </when> <when value="paired_collection"> - <param type="data_collection" collection_type="list:paired" format="@INPUT_FORMATS@" name="paired_reads" label="One or more pairs of forward and reverse possibly gzipped FASTA/Q files for mapping in order" /> - <param type="data" name="ref_fasta_history" multiple="true" label="FASTA file(s) of contigs" format="fasta" /> - </when> - <when value="single"> - <param type="data" format="@INPUT_FORMATS@" multiple="true" name="single" label="Single Read" /> - <param type="data" name="ref_fasta_history" multiple="true" label="FASTA file(s) of contigs" format="fasta" /> + <expand macro="paired_reads"/> </when> <when value="interleaved"> - <param type="data" format="@INPUT_FORMATS@" multiple="true" name="single" label="Interleaved" /> - <param type="data" name="ref_fasta_history" multiple="true" label="FASTA file(s) of contigs" format="fasta" /> - </when> - <when value="bam"> - <param type="data" format="bam" name="bam" multiple="true" label="BAM file(s)" help="BAM file(s). These must be reference sorted (e.g. with samtools sort) unless sharded is specified, in which case they must be read name sorted (e.g. with samtools sort -n). When specified, no read mapping algorithm is undertaken."/> - <param type="data" name="ref_fasta_history" optional="true" multiple="true" label="FASTA file(s) of contigs" format="fasta" /> + <param argument="--interleaved" type="data" format="@INPUT_FORMATS@" label="Interleaved FASTA/Q files for mapping" /> </when> </conditional> - </xml> - <xml name="reads"> - <conditional name="reads"> - <param type="select" label="Read type" name="read_type"> - <option value="single">Single ended</option> - <option value="paired">Paired end</option> - <option value="paired_collection" selected="true">Paired collection</option> - <option value="interleaved">Interleaved</option> - <option value="bam">BAM file(s)</option> - </param> + </xml> + <xml name="ref_or_genome"> + <param name="ref_or_genome" type="select" label="Genome definition"> + <option value="contigs" selected="true">From contigs (e.g. concatenated genomes or metagenome assembly)</option> + <option value="genomic">From FASTA files with each genome</option> + </param> + </xml> + <xml name="individual_assembly_reference"> + <param argument="--reference" type="data" format="fasta" label="Contigs"/> + </xml> + <token name="@INDIVIDUAL_ASSEMBLY_READS@"><![CDATA[ + #set $reads = $mapped.mode.read_type + #if $reads.type == 'single' + #set $fn = "single/" + re.sub('[^\s\w\-\\.]', '_', str($reads.single.element_identifier)) + #silent $single_fp.append( $fn ) +ln -s '$reads.single' '$single_fp' && + #else if $reads.type == 'paired' + #set $fn = "fw/" + re.sub('[^\s\w\-\\.]', '_', str($reads.read1.element_identifier)) + #silent $fw_fp.append( $fn ) +ln -s '$reads.read1' '$fn' && + #set $fn = "rv/" + re.sub('[^\s\w\-\\.]', '_', str($reads.read2.element_identifier)) +ln -s '$reads.read2' '$fn' && + #silent $rv_fp.append( $fn ) + #else if $reads.type == 'paired_collection' + #set $id = re.sub('[^\s\w\-\\.]', '_', str($reads.paired_reads.element_identifier)) + #set $fn = "fw/" + $id + #silent $fw_fp.append( $fn ) +ln -s '$reads.paired_reads.forward' '$fn' && + #set $fn = "rv/" + $id + #silent $rv_fp.append( $fn ) +ln -s '$mreads.paired_reads.reverse' '${fn}' && + #else if $reads.type == 'interleaved' + #set $fn = "interl/" + re.sub('[^\s\w\-\\.]', '_', str($reads.interleaved.element_identifier)) + #silent $interl_fp.append( $fn ) +ln -s '$reads.interleaved' '$fn' && + #end if +]]></token> + <token name="@INDIVIDUAL_ASSEMBLY_REF@"><![CDATA[ + #set $fn = "ref/" + re.sub('[^\s\w\-\\.]', '_', str($ref.element_identifier)) + #silent $ref_fp.append( $fn ) +ln -s '$ref' '${fn}' && +]]></token> + <token name="@GENOME_FOR_READS@"><![CDATA[ + #if $mapped.mode.genome.genomic.source == 'history' + #for $i, $genome in enumerate($mapped.mode.genome.genomic.genome_fasta_files) + #set $fn = re.sub('[^\s\w\-\\.]', '_', str($genome.element_identifier)) + #silent $genome_fp.append( $fn ) +ln -s '$genome' '$fn' && + #end for + #else + #for $i, $genome in enumerate($mapped.mode.genome.genomic.genome_fasta_files) + #set $fn = re.sub('[^\s\w\-\\.]', '_', str($genome.fields.path.element_identifier)) + #silent $genome_fp.append( $fn ) +ln -s '$genome' '$fn' && + #end for + #end if +]]></token> + <xml name="co_assembly_reads"> + <conditional name="read_type"> + <expand macro="read_type"/> + <when value="single"> + <param argument="--single" type="data" format="@INPUT_FORMATS@" multiple="true" label="Single Read" /> + </when> <when value="paired"> - <param type="data" format="@INPUT_FORMATS@" name="read1" multiple="true" label="Read1" /> - <param type="data" format="@INPUT_FORMATS@" name="read2" multiple="true" label="Read2" /> - <expand macro="genome"/> + <param argument="-1" name="read1" type="data" format="@INPUT_FORMATS@" multiple="true" label="Forward FASTA/Q file(s) for mapping" /> + <param argument="-2" name="read2" type="data" format="@INPUT_FORMATS@" multiple="true" label="Reverse FASTA/Q file(s) for mapping" /> </when> <when value="paired_collection"> - <param type="data_collection" collection_type="list:paired" format="@INPUT_FORMATS@" name="paired_reads" label="Collection of paired-reads" help="One or more pairs of forward and reverse possibly gzipped FASTA/Q files for mapping in order." /> - <expand macro="genome"/> - </when> - <when value="single"> - <param type="data" format="@INPUT_FORMATS@" multiple="true" name="single" label="Single Read" /> - <expand macro="genome"/> + <expand macro="paired_reads"/> </when> <when value="interleaved"> - <param type="data" format="@INPUT_FORMATS@" multiple="true" name="single" label="Interleaved" /> - <expand macro="genome"/> - </when> - <when value="bam"> - <param type="data" format="bam" name="bam" multiple="true" label="BAM file(s)" help="BAM file(s). These must be reference sorted (e.g. with samtools sort) unless sharded is specified, in which case they must be read name sorted (e.g. with samtools sort -n). When specified, no read mapping algorithm is undertaken."/> - <expand macro="genome_opt"/> + <param argument="--interleaved" type="data" format="@INPUT_FORMATS@" multiple="true" label="Interleaved FASTA/Q files(s) for mapping" /> </when> </conditional> </xml> - <xml name="add_reads"> - <section name="add_reads" title="Add an additional read"> - <conditional name="extra_read"> - <param type="select" label="Read type" name="read_type"> - <option value="none" selected="true">None</option> - <option value="paired">Paired end</option> - <option value="paired_collection">Paired collection</option> - <option value="single">Single ended</option> - <option value="interleaved">Interleaved</option> - <option value="bam">BAM file(s)</option> - </param> - <when value="none"> - </when> - <when value="paired"> - <param type="data" format="@INPUT_FORMATS@" name="read1" multiple="true" label="Read1" /> - <param type="data" format="@INPUT_FORMATS@" name="read2" multiple="true" label="Read2" /> - </when> - <when value="paired_collection"> - <param type="data_collection" collection_type="list:paired" format="@INPUT_FORMATS@" name="paired_reads" label="One or more pairs of forward and reverse possibly gzipped FASTA/Q files for mapping in order" /> - </when> - <when value="single"> - <param type="data" format="@INPUT_FORMATS@" name="single" multiple="true" label="Single read" /> - </when> - <when value="interleaved"> - <param type="data" format="@INPUT_FORMATS@" multiple="true" name="single" label="Interleaved" /> - </when> - <when value="bam"> - <param type="data" format="bam" name="bam" multiple="true" label="BAM file(s)" /> - </when> - </conditional> - </section> + <xml name="co_assembly_reference"> + <param argument="--reference" type="data" format="fasta" multiple="true" label="Contigs" /> + <param argument="--sharded" type="boolean" truevalue="--sharded" falsevalue="" checked="false" label="Mapping reads to references separately as sharded BAMs?" /> + </xml> + <token name="@CO_ASSEMBLY_READS@"><![CDATA[ + #if $reads.type == 'single' + #for $i, $read in enumerate($reads.single) + #set $fn = "single/" + re.sub('[^\s\w\-\\.]', '_', str($read.element_identifier)) + "_single_" + str($i) + $extra + #silent $single_fp.append( $fn ) +ln -s '$read' '$fn' && + #end for + #else if $reads.type == 'paired' + #for $i, $read in enumerate($reads.read1) + #set $id = re.sub('[^\s\w\-\\.]', '_', str($read.element_identifier)) + #set $fn = "fw/" + $id + "_paired_" + str($i) + $extra + #silent $fw_fp.append( $fn ) +ln -s '$read' '$fn' && + #end for + #for $i, $read in enumerate($reads.read2) + #set $id = re.sub('[^\s\w\-\\.]', '_', str($read.element_identifier)) + #set $fn = "rv/" + $id + "_paired_" + str($i) + $extra + #silent $rv_fp.append( $fn ) +ln -s '$read' '$fn' && + #end for + #else if $reads.type == 'paired_collection' + #for $i, $read in enumerate($reads.paired_reads) + #set $id = re.sub('[^\s\w\-\\.]', '_', str($read.element_identifier)) + #set $fn = "fw/" + $id + "_paired_collection_" + str($i) + $extra + #silent $fw_fp.append( $fn ) +ln -s '$read.forward' '$fn' && + #set $fn = "rv/" + $id + "_paired_collection_" + str($i) + $extra + #silent $rv_fp.append( $fn ) +ln -s '$read.reverse' '$fn' && + #end for + #else if $reads.type == 'interleaved' + #for $i, $read in enumerate($reads.interleaved) + #set $id = re.sub('[^\s\w\-\\.]', '_', str($read.element_identifier)) + #set $fn = "interl/" + $id + "_interleaved_" + str($i) + $extra + #silent $interl_fp.append( $fn ) +ln -s '$read' '$fn' && + #end for + #end if + ]]></token> + <token name="@CO_ASSEMBLY_ALL_READS@"><![CDATA[ + #set $reads = $mapped.mode.read_type + #set $extra = '' + @CO_ASSEMBLY_READS@ + #for $j, $s in enumerate($mapped.mode.extra_reads) + #set $reads = $s.read_type + #set $extra = str($j) + @CO_ASSEMBLY_READS@ + #end for + ]]></token> + <token name="@CO_ASSEMBLY_REF@"><![CDATA[ + #for $i, $ref in enumerate($refs) + #set $fn = "ref/" + re.sub('[^\s\w\-\\.]', '_', str($ref.element_identifier)) + "_" + str($i) + #silent $ref_fp.append( $fn ) +ln -s '$ref' '${fn}' && + #end for + ]]></token> + <xml name="sharded"> + <param name="sharded" type="boolean" truevalue="--sharded" falsevalue="" checked="false" label="Input BAM files are read-sorted alignments of a set of reads mapped to multiple reference contig sets. Choose the best hit for each read pair. Otherwise if mapping was carried out: Map reads to each reference, choosing the best hit for each pair." /> </xml> <xml name="mapping"> - <section name="mapping" title="Mapping options" expanded="false"> - <param argument="--mapper" optional="true" type="select" label="Mapper" help="Underlying mapping software used. Default: minimap2-sr" > - <option value="minimap2-sr">minimap2 with '-x sr' option</option> - <option value="minimap2-ont">minimap2 with '-x map-ont' option</option> - <option value="minimap2-pb">minimap2 with '-x map-pb' option</option> - <option value="minimap2-no-preset">minimap2 with no '-x' option</option> - <option value="bwa-mem">BWA-MEM using default parameters</option> - </param> - <param argument="--min_read-aligned-length" type="integer" min="0" value="0" - label="Min read aligned length" help="Exclude reads with smaller numbers of aligned bases. Default: 0" /> - <param argument="--min_read-percent-identity" type="float" min="0" max="100" value="0" - label="Min read percent identity" help="Exclude reads by overall percent identity e.g. 95 for 95%. Default: 0" /> - <param argument="--min_read-aligned-percent" type="float" min="0" max="100" value="0" - label="Min read aligned percentage" help="Exclude reads by percent aligned bases e.g. 95 means 95% - of the read's bases must be aligned. Default: 0" /> - <param argument="--min_read-aligned-length-pair" type="integer" min="0" value="0" - label="Min read aligned length pair" help="Exclude pairs with smaller numbers of aligned bases. - Implies --proper-pairs-only. Default: 0" /> - <param argument="--min_read-percent-identity-pair" type="float" min="0" max="100" value="0" - label="Min read percent identity pair" help="Exclude pairs by overall percent identity e.g. 95 for 95%. - Implies --proper-pairs-only. Default: 0" /> - <param argument="--min_read-aligned-percent-pair" type="float" min="0" max="100" value="0" - label="Min read aligned percentage pair" help="Exclude reads by percent aligned bases e.g. 95 means 95% of - the read's bases must be aligned. Implies --proper-pairs-only. Default: 0" /> - <param argument="--proper-pairs-only" type="boolean" truevalue="--proper-pairs-only" falsevalue="" - label="Require reads to be mapped as proper pairs" help="Default: not set"/> - <param argument="--exclude-supplementary" type="boolean" truevalue="--exclude-supplementary" falsevalue="" - label="Exclude supplementary alignments" help="Default: not set"/> - </section> + <param argument="--mapper" type="select" label="Underlying mapping software used"> + <option value="minimap2-sr" selected="true">minimap2 with '-x sr' option</option> + <option value="minimap2-ont">minimap2 with '-x map-ont' option</option> + <option value="minimap2-pb">minimap2 with '-x map-pb' option</option> + <option value="minimap2-no-preset">minimap2 with no '-x' option</option> + <option value="bwa-mem">BWA-MEM using default parameters</option> + </param> </xml> - <xml name="coverage"> - <section name="cov" title="Coverage calculation options" expanded="false"> - <param name="relative_abundance" type="boolean" falsevalue="" truevalue="relative_abundance" label="Relative abundance (default)"/> - <param name="mean" type="boolean" falsevalue="" truevalue="mean" label="Mean"/> - <conditional name="cond_methods"> - <param name="trimmed_mean" type="select" label="Trimmed mean"> - <option value="trimmed_mean">Yes</option> + <xml name="alignment"> + <section name="alignment" title="Alignment thresholding" expanded="false"> + <param argument="--min-read-aligned-length" type="integer" min="0" value="0" + label="Minimum number of aligned bases" help="Reads with smaller numbers of aligned bases will be excluded" /> + <param argument="--min-read-percent-identity" type="float" min="0" max="100" value="0" + label="Minimum overall percent identity" help="Reads with lower overall percent identity will be excluded." /> + <param argument="--min-read-aligned-percent" type="float" min="0" max="100" value="0" + label="Minimum aligned base percent" help="Reads with lower percent aligned bases will be excluded" /> + <conditional name="proper_pairs_only"> + <param argument="--proper-pairs-only" type="select" label="Require reads to be mapped as proper pairs?"> + <option value="--proper-pairs-only">Yes</option> <option value="" selected="true">No</option> </param> - <when value="trimmed_mean"> - <param name="trim_min" type="integer" min="0" value="5" label="Trim min" help="Remove this smallest fraction of positions when calculating trimmed_mean default: 5"/> - <param name="trim_max" type="integer" min="0" value="95" label="Trim max" help="Maximum fraction for trimmed_mean calculations default: 95"/> + <when value="--proper-pairs-only"> + <param argument="--min_read-aligned-length-pair" type="integer" min="0" value="0" + label="Minimum number of aligned bases for pairs" help="Pairs with smaller numbers of aligned bases will be excluded." /> + <param argument="--min-read-percent-identity-pair" type="float" min="0" max="100" value="0" + label="Minimum overall percent identity pair for pairs" help="Pairs by lower overall percent identity will be excluded" /> + <param argument="--min-read-aligned-percent-pair" type="float" min="0" max="100" value="0" + label="Minimum percent of read aligned bases for pair" help="Pairs with lower reads percent aligned bases will be excluded" /> </when> <when value=""/> </conditional> - <param name="covered_bases" type="boolean" falsevalue="" truevalue="covered_bases" label="Covered bases"/> - <param name="covered_fraction" type="boolean" falsevalue="" truevalue="covered_fraction" label="Covered fraction"/> - <param name="variance" type="boolean" falsevalue="" truevalue="variance" label="Variance"/> - <param name="length" type="boolean" falsevalue="" truevalue="length" label="Length"/> - <param name="count" type="boolean" falsevalue="" truevalue="count" label="Count"/> - <param name="metabat" type="boolean" falsevalue="" truevalue="metabat" label="MetaBAT"/> - <param name="coverage_histogram" type="boolean" falsevalue="" truevalue="coverage_histogram" label="Coverage histogram"/> - <param name="reads_per_base" type="boolean" falsevalue="" truevalue="reads_per_base" label="Reads per base"/> - <param name="rpkm" type="boolean" falsevalue="" truevalue="rpkm" label="RPKM"/> - <param name="tpm" type="boolean" falsevalue="" truevalue="tpm" label="TPKM"/> - <param name="min_covered_fraction" type="integer" min="0" optional="true" - label="Min covered fraction" help="Genomes with less coverage than this reported as having zero coverage. Default: 10"/> - <param name="contig_end_exclusion" type="integer" min="0" optional="true" - label="Contig end exclusion" help="Exclude bases at the ends of reference sequences from calculation. Default: 75"/> + <param argument="--exclude-supplementary" type="boolean" truevalue="--exclude-supplementary" falsevalue="" checked="false" + label="Exclude supplementary alignments"/> </section> </xml> - <xml name="out"> - <section name="out" title="Output options" expanded="false"> - <param name="output_format" type="select" label="Shape of output" help="'Sparse' for long format, 'dense' for species-by-site. Default: dense]"> - <option value="dense" selected="true">Dense</option> - <option value="sparse">Sparse</option> - </param> - <param name="no_zeros" type="boolean" truevalue="--no-zeros" falsevalue="" optional="true" label="Omit printing of genomes that have zero coverage" /> - <param argument="--dereplication-output-cluster-definition" type="boolean" truevalue="--dereplication-output-cluster-definition" falsevalue="" label="Output a file of representative TAB member lines." /> - <param argument="--dereplication-output-representative-fasta-directory-copy" type="boolean" truevalue="--dereplication-output-representative-fasta-directory-copy" falsevalue="" label="Output representative genomes" /> - </section> + <xml name="cov_method_options"> + <option value="trimmed_mean">trimmed_mean: Average number of aligned reads overlapping each position after removing the most deeply and shallow-ly covered positions. </option> + <option value="coverage_histogram">coverage_histogram: Histogram of coverage depths</option> + <option value="covered_bases">covered_bases: Number of bases covered by 1 or more reads</option> + <option value="variance">variance: Variance of coverage depths</option> + <option value="length">length: Length of each contig in base pairs</option> + <option value="count">count: Number of reads aligned toq each contig. Note that a single read may be aligned to multiple contigs with supplementary alignments</option> + <option value="metabat">metabat: ("MetaBAT adjusted coverage") Coverage as defined in Kang et al 2015</option> + <option value="reads_per_base">reads_per_base: Number of reads aligned divided by the length of the contig</option> + <option value="rpkm">rpkm: Reads mapped per kilobase of contig, per million mapped reads</option> + <option value="tpm">tpm: Transcripts Per Million as described in Li et al 2010</option> + </xml> + <xml name="coverage_params"> + <param argument="--trim-min" type="integer" min="0" value="5" label="Smallest fraction of positions to remove when calculating" help="Only used with trimmed_mean method"/> + <param argument="--trim-max" type="integer" min="0" value="95" label="Maximum fraction of positions to remove when calculating" help="Only used with trimmed_mean method"/> + <param argument="--min-covered-fraction" type="integer" min="0" value="10" label="Minimum covered fraction" help="Genomes with less coverage than this reported as having zero coverage"/> + <param argument="--contig-end-exclusion" type="integer" min="0" value="75" label="Base to exclude at contig ends" help="Bases at the ends of reference sequences will be excluded from calculation"/> + </xml> + <xml name="output_format"> + <param argument="--output-format" type="select" label="Shape of output"> + <option value="dense" selected="true">Dense for species-by-site</option> + <option value="sparse">Sparse for long format</option> + </param> </xml> <xml name="citations"> <citations>