Mercurial > repos > iuc > rnaquast
changeset 1:e989670c7fc7 draft
"planemo upload for repository https://git.ufz.de/lehmanju/rnaquast commit dc0a0cf275168c2a88ee3dc47652dd7ca1137871"
author | iuc |
---|---|
date | Thu, 18 Feb 2021 09:32:20 +0000 |
parents | 33c060ec0ac9 |
children | 96f74538896e |
files | rna_quast.xml |
diffstat | 1 files changed, 81 insertions(+), 69 deletions(-) [+] |
line wrap: on
line diff
--- a/rna_quast.xml Mon Oct 19 08:04:52 2020 +0000 +++ b/rna_quast.xml Thu Feb 18 09:32:20 2021 +0000 @@ -1,70 +1,82 @@ <tool id="rna_quast" name="rnaQUAST" version="@TOOL_VERSION@"> <description>A Quality Assessment Tool for De Novo Transcriptome Assemblies</description> <macros> - <token name="@TOOL_VERSION@">2.1.0</token> + <token name="@TOOL_VERSION@">2.2.0</token> <xml name="element_matching_line" token_name="" token_expression=""> <element name="@NAME@"> - <assert_contents><has_line_matching expression="@EXPRESSION@"/></assert_contents> + <assert_contents> + <has_line_matching expression="@EXPRESSION@" /> + </assert_contents> </element> </xml> <xml name="element_has_text" token_name="" token_text=""> <element name="@NAME@"> - <assert_contents><has_text text="@TEXT@"/></assert_contents> + <assert_contents> + <has_text text="@TEXT@" /> + </assert_contents> </element> </xml> <xml name="details_output_test" token_assembler=""> <element name="@ASSEMBLER@"> - <element name="5000%-assembled.list"><assert_contents><has_n_lines n="0"/></assert_contents></element> - <element name="9500%-assembled.list"><assert_contents><has_n_lines n="0"/></assert_contents></element> - <expand macro="element_matching_line" name="alignment_metrics" expression="\s*== ALIGNMENT METRICS \(calculated with reference genome but without gene database\) ==\s*"/> - <expand macro="element_matching_line" name="alignment_multiplicity" expression="unaligned=\d+ aligned=\d+ alignments=\d+\s*"/> - <expand macro="element_matching_line" name="alignments_per_isoform" expression="avg=[\d.]+\s*"/> - <expand macro="element_matching_line" name="basic_metrics" expression="\s*== BASIC TRANSCRIPTS METRICS \(calculated without reference genome and gene database\) ==\s*"/> - <expand macro="element_matching_line" name="block_length" expression="avg=[\d.]+\s*"/> - <expand macro="element_matching_line" name="blocks_per_alignment" expression="avg=[\d.]+\s+tot=\d+\s*"/> - <expand macro="element_matching_line" name="database_metrics" expression="\s*== GENE DATABASE METRICS ==\s*"/> - <expand macro="element_matching_line" name="misassemblies" expression="\s*== ALIGNMENT METRICS FOR MISASSEMBLED \(CHIMERIC\) TRANSCRIPTS \(calculated with reference genome or with gene database\) ==\s*"/> - <expand macro="element_matching_line" name="mismatch_rate" expression="avg=[\d.]+\s+tot=\d+\s*"/> - <expand macro="element_matching_line" name="sensitivity" expression="\s*== ASSEMBLY COMPLETENESS \(SENSITIVITY\) ==\s*"/> - <expand macro="element_matching_line" name="specificity" expression="\s*== ASSEMBLY SPECIFICITY ==\s*"/> - <expand macro="element_matching_line" name="transcript_length" expression="avg=[\d.]+\s*"/> - <expand macro="element_matching_line" name="x-aligned" expression="avg=[\d.]+\s*"/> - <expand macro="element_matching_line" name="x-assembled" expression="avg=[\d.]+\s*"/> - <expand macro="element_matching_line" name="x-assembled_exons" expression="avg=[\d.]+\s*"/> - <expand macro="element_matching_line" name="x-covered" expression="avg=[\d.]+\s*"/> - <expand macro="element_matching_line" name="x-covered_exons" expression="avg=[\d.]+\s*"/> - <expand macro="element_matching_line" name="x-matched" expression="avg=[\d.]+\s*"/> - <expand macro="element_matching_line" name="x-matched_blocks" expression="avg=[\d.]+\s*"/> + <element name="5000%-assembled.list"> + <assert_contents> + <has_n_lines n="0" /> + </assert_contents> + </element> + <element name="9500%-assembled.list"> + <assert_contents> + <has_n_lines n="0" /> + </assert_contents> + </element> + <expand macro="element_matching_line" name="alignment_metrics" expression="\s*== ALIGNMENT METRICS \(calculated with reference genome but without gene database\) ==\s*" /> + <expand macro="element_matching_line" name="alignment_multiplicity" expression="unaligned=\d+ aligned=\d+ alignments=\d+\s*" /> + <expand macro="element_matching_line" name="alignments_per_isoform" expression="avg=[\d.]+\s*" /> + <expand macro="element_matching_line" name="basic_metrics" expression="\s*== BASIC TRANSCRIPTS METRICS \(calculated without reference genome and gene database\) ==\s*" /> + <expand macro="element_matching_line" name="block_length" expression="avg=[\d.]+\s*" /> + <expand macro="element_matching_line" name="blocks_per_alignment" expression="avg=[\d.]+\s+tot=\d+\s*" /> + <expand macro="element_matching_line" name="database_metrics" expression="\s*== GENE DATABASE METRICS ==\s*" /> + <expand macro="element_matching_line" name="misassemblies" expression="\s*== ALIGNMENT METRICS FOR MISASSEMBLED \(CHIMERIC\) TRANSCRIPTS \(calculated with reference genome or with gene database\) ==\s*" /> + <expand macro="element_matching_line" name="mismatch_rate" expression="avg=[\d.]+\s+tot=\d+\s*" /> + <expand macro="element_matching_line" name="sensitivity" expression="\s*== ASSEMBLY COMPLETENESS \(SENSITIVITY\) ==\s*" /> + <expand macro="element_matching_line" name="specificity" expression="\s*== ASSEMBLY SPECIFICITY ==\s*" /> + <expand macro="element_matching_line" name="transcript_length" expression="avg=[\d.]+\s*" /> + <expand macro="element_matching_line" name="x-aligned" expression="avg=[\d.]+\s*" /> + <expand macro="element_matching_line" name="x-assembled" expression="avg=[\d.]+\s*" /> + <expand macro="element_matching_line" name="x-assembled_exons" expression="avg=[\d.]+\s*" /> + <expand macro="element_matching_line" name="x-covered" expression="avg=[\d.]+\s*" /> + <expand macro="element_matching_line" name="x-covered_exons" expression="avg=[\d.]+\s*" /> + <expand macro="element_matching_line" name="x-matched" expression="avg=[\d.]+\s*" /> + <expand macro="element_matching_line" name="x-matched_blocks" expression="avg=[\d.]+\s*" /> </element> </xml> <xml name="txt_output_test" token_assembler=""> <output name="short_report_txt"> <assert_contents> - <has_text text="SHORT SUMMARY REPORT"/> + <has_text text="SHORT SUMMARY REPORT" /> </assert_contents> </output> </xml> <xml name="tex_output_test" token_assembler=""> <output name="short_report_tex"> <assert_contents> - <has_text text="Short summary report"/> - <has_text text="end{document}"/> + <has_text text="Short summary report" /> + <has_text text="end{document}" /> </assert_contents> </output> </xml> <xml name="tsv_output_test" token_assembler=""> <output name="short_report_tsv"> <assert_contents> - <has_line_matching expression="^METRICS/TRANSCRIPTS\t.+$"/> + <has_line_matching expression="^METRICS/TRANSCRIPTS\t.+$" /> </assert_contents> </output> </xml> <xml name="pdf_output_test" token_assembler=""> <output name="short_report_pdf"> <assert_contents> - <has_text text="rnaQUAST short report"/> + <has_text text="rnaQUAST short report" /> </assert_contents> </output> </xml> @@ -144,10 +156,10 @@ ## the final `true` seems needed since otherwise the `;` at the end is swallowed && find details/ -name "*.list" -exec mv {} {}.txt \; && true - ]]></command> + ]]> </command> <inputs> - <param name="in_fasta" type="data" format="fasta" multiple="true" label="Chromosomes/scaffolds file"/> - <param name="strand_specific" argument="-ss" type="boolean" truevalue="-ss" falsevalue="" checked="false" label="Strand-specific"/> + <param name="in_fasta" type="data" format="fasta" multiple="true" label="Chromosomes/scaffolds file" /> + <param name="strand_specific" argument="-ss" type="boolean" truevalue="-ss" falsevalue="" checked="false" label="Strand-specific" /> <param name="r" optional="true" argument="-r" type="data" format="fasta" multiple="true" label="Reference genome" /> <conditional name="gene_coordinates"> <param name="use_gtf" type="select" label="Use file with gene coordinates in GTF/GFF format?" help="We recommend to use files downloaded from GENCODE or Ensembl."> @@ -155,21 +167,21 @@ <option value="false">No</option> </param> <when value="true"> - <param name="gtf" argument="--gtf" type="data" format="gtf,gff,gff3" multiple="true" label="GTF/GFF file"/> - <param argument="--disable_infer_genes" type="boolean" truevalue="--disable_infer_genes" falsevalue="" checked="false" label=" GTF file contains genes records?"/> - <param argument="--disable_infer_transcripts" type="boolean" truevalue="--disable_infer_transcripts" falsevalue="" checked="false" label="GTF file contains transcripts records?"/> + <param name="gtf" argument="--gtf" type="data" format="gtf,gff,gff3" multiple="true" label="GTF/GFF file" /> + <param argument="--disable_infer_genes" type="boolean" truevalue="--disable_infer_genes" falsevalue="" checked="false" label=" GTF file contains genes records?" /> + <param argument="--disable_infer_transcripts" type="boolean" truevalue="--disable_infer_transcripts" falsevalue="" checked="false" label="GTF file contains transcripts records?" /> </when> <when value="false"> </when> </conditional> - <param argument="--prokaryote" type="boolean" truevalue="--prokaryote" falsevalue="" checked="false" label="Is genome prokararyotic?"/> - <param argument="--min_alignment" type="integer" value="50" label="Minimal alignment length to be used"/> + <param argument="--prokaryote" type="boolean" truevalue="--prokaryote" falsevalue="" checked="false" label="Is genome prokararyotic?" /> + <param argument="--min_alignment" type="integer" value="50" label="Minimal alignment length to be used" /> <param argument="--blat" type="boolean" truevalue="--blat" falsevalue="" checked="false" label="Run with BLAT alignment tool instead of GMAP?" /> - <param argument="--busco_lineage" type="boolean" truevalue="--busco_lineage" falsevalue="" checked="false" label="Run BUSCO tool?" help="The BUSCO tool detects core genes in the assembly. Use this option to provide path to the BUSCO lineage data (Eukaryota, Metazoa, Arthropoda, Vertebrata or Fungi)."/> + <param argument="--busco_lineage" type="boolean" truevalue="--busco_lineage" falsevalue="" checked="false" label="Run BUSCO tool?" help="The BUSCO tool detects core genes in the assembly. Use this option to provide path to the BUSCO lineage data (Eukaryota, Metazoa, Arthropoda, Vertebrata or Fungi)." /> <!-- GeneMarkS-T is not available in conda <param argument="\-\-gene_mark" type="boolean" truevalue="\-\-gene_mark" falsevalue="" checked="false" label="Run with GeneMarkS-T gene prediction tool?"/>--> - <param argument="--meta" type="boolean" truevalue="--meta" falsevalue="" checked="false" label="Meta Transcriptome" help="Run quality asessment for Meta Transcriptome"/> - <param argument="--lower_threshold" type="integer" value="50" label="Lower threshold for x_assembled/covered/matched metrics."/> - <param argument="--upper_threshold" type="integer" value="95" label="Upper threshold for x_assembled/covered/matched metrics."/> + <param argument="--meta" type="boolean" truevalue="--meta" falsevalue="" checked="false" label="Meta Transcriptome" help="Run quality asessment for Meta Transcriptome" /> + <param argument="--lower_threshold" type="integer" value="50" label="Lower threshold for x_assembled/covered/matched metrics." /> + <param argument="--upper_threshold" type="integer" value="95" label="Upper threshold for x_assembled/covered/matched metrics." /> <param name="out_sr" type="select" multiple="true" label="Short report formats"> <option value="tsv" selected="true">tabular</option> <option value="txt">txt</option> @@ -198,26 +210,26 @@ <data name="short_report_tsv" format="tabular" label="${tool.name} on ${on_string}: tsv report" from_work_dir="outputdir/short_report.tsv"> <filter>"tsv" in out_sr</filter> </data> - <collection name="list_logs" type="list" label="${tool.name} on ${on_string}: logs" > - <discover_datasets ext="txt" pattern="(?P<name>.+)\.log" directory="outputdir/logs/" visible="false" /> + <collection name="list_logs" type="list" label="${tool.name} on ${on_string}: logs"> + <discover_datasets ext="txt" pattern="(?P<name>.+)\.log" directory="outputdir/logs/" visible="false" /> <filter>"logs" in out_add</filter> </collection> <!-- note the output filter of the next two outputs checks if there is more than 1 input for in_fasta (for 1 its a HDA, for more list or HDAs) --> - <collection name="comparison_png" type="list" label="${tool.name} on ${on_string}: comparison plots" > - <discover_datasets ext="png" pattern="(?P<name>.+)\.png" directory="outputdir/comparison_output/" visible="false" recurse="true"/> + <collection name="comparison_png" type="list" label="${tool.name} on ${on_string}: comparison plots"> + <discover_datasets ext="png" pattern="(?P<name>.+)\.png" directory="outputdir/comparison_output/" visible="false" recurse="true" /> <filter> isinstance(in_fasta, list) and "plots" in out_add</filter> </collection> - <collection name="comparison" type="list" label="${tool.name} on ${on_string}: comparison" > - <discover_datasets ext="txt" pattern="(?P<name>.+)\.txt" directory="outputdir/comparison_output/" visible="false" recurse="true" /> + <collection name="comparison" type="list" label="${tool.name} on ${on_string}: comparison"> + <discover_datasets ext="txt" pattern="(?P<name>.+)\.txt" directory="outputdir/comparison_output/" visible="false" recurse="true" /> <filter> isinstance(in_fasta, list) and "comparison" in out_add</filter> </collection> <collection name="details" type="list:list" label="${tool.name} on ${on_string}: detailed output"> - <discover_datasets pattern="(?P<identifier_0>.+)_____(?P<identifier_1>.+)\.(?P<ext>txt)" directory="details/" visible="false"/> + <discover_datasets pattern="(?P<identifier_0>.+)_____(?P<identifier_1>.+)\.(?P<ext>txt)" directory="details/" visible="false" /> <filter>"details" in out_add</filter> </collection> <collection name="details_png" type="list:list" label="${tool.name} on ${on_string}: detailed output plots"> - <discover_datasets pattern="(?P<identifier_0>.+)_____(?P<identifier_1>.+)\.(?P<ext>png)" directory="details/" visible="false"/> + <discover_datasets pattern="(?P<identifier_0>.+)_____(?P<identifier_1>.+)\.(?P<ext>png)" directory="details/" visible="false" /> <filter>"details_plots" in out_add</filter> </collection> </outputs> @@ -228,20 +240,20 @@ <conditional name="gene_coordinates"> <param name="use_gtf" value="true" /> <param name="gtf" value="Saccharomyces_cerevisiae.R64-1-1.75.gtf" ftype="gtf" /> - <param name="disable_infer_genes" value="true"/> - <param name="disable_infer_transcripts" value="true"/> + <param name="disable_infer_genes" value="true" /> + <param name="disable_infer_transcripts" value="true" /> </conditional> <param name="out_sr" value="txt,tex,tsv" /> <param name="out_add" value="logs,comparison,plots,details" /> - <expand macro="txt_output_test"/> - <expand macro="tex_output_test"/> - <expand macro="tsv_output_test"/> - <output_collection name="comparison_png" type="list" count="15"/> - <output_collection name="comparison" type="list" count="19"/> - <output_collection name="list_logs" type="list" count="8"/> + <expand macro="txt_output_test" /> + <expand macro="tex_output_test" /> + <expand macro="tsv_output_test" /> + <output_collection name="comparison_png" type="list" count="15" /> + <output_collection name="comparison" type="list" count="19" /> + <output_collection name="list_logs" type="list" count="8" /> <output_collection name="details" type="list:list" count="2"> - <expand macro="details_output_test" assembler="Trinity"/> - <expand macro="details_output_test" assembler="idba"/> + <expand macro="details_output_test" assembler="Trinity" /> + <expand macro="details_output_test" assembler="idba" /> </output_collection> </test> <test expect_num_outputs="6"> @@ -251,22 +263,22 @@ </conditional> <param name="min_alignment" value="30" /> <param name="lower_threshold" value="45" /> - <param name="upper_threshold" value="95"/> + <param name="upper_threshold" value="95" /> <param name="out_sr" value="txt,tex,tsv,pdf" /> <param name="out_add" value="logs,details_plots" /> - <expand macro="pdf_output_test"/> - <expand macro="tex_output_test"/> - <expand macro="tsv_output_test"/> - <expand macro="txt_output_test"/> + <expand macro="pdf_output_test" /> + <expand macro="tex_output_test" /> + <expand macro="tsv_output_test" /> + <expand macro="txt_output_test" /> <output_collection name="list_logs" type="list"> - <expand macro="element_has_text" name="Trinity.GeneMarkS_T.err" text=""/> - <expand macro="element_matching_line" name="rnaQUAST" expression="Thank you for using rnaQUAST!"/> + <expand macro="element_has_text" name="Trinity.GeneMarkS_T.err" text="" /> + <expand macro="element_matching_line" name="rnaQUAST" expression="Thank you for using rnaQUAST!" /> </output_collection> <output_collection name="details_png" type="list:list" count="1"> <element name="Trinity"> - <expand macro="element_has_text" name="Nx" text="PNG"/> - <expand macro="element_has_text" name="transcript_length" text="PNG"/> + <expand macro="element_has_text" name="Nx" text="PNG" /> + <expand macro="element_has_text" name="transcript_length" text="PNG" /> </element> </output_collection> </test> @@ -325,7 +337,7 @@ - Database Metrics - Alignment multiplicity More informations, see citations. - ]]></help> + ]]> </help> <citations> <citation type="doi">10.1093/bioinformatics/btw218 </citation> </citations>