Mercurial > repos > iuc > bakta
diff bakta.xml @ 4:3f0aa1b3e816 draft
planemo upload for repository https://github.com/galaxyproject/tools-iuc/blob/master/tools/bakta commit e2c4ab5546b135ff903545073c3223aab166d8f5
| author | iuc |
|---|---|
| date | Mon, 24 Jul 2023 11:22:16 +0000 |
| parents | 865ece5ca178 |
| children | 728dacaf08a9 |
line wrap: on
line diff
--- a/bakta.xml Fri Feb 10 14:20:09 2023 +0000 +++ b/bakta.xml Mon Jul 24 11:22:16 2023 +0000 @@ -11,10 +11,12 @@ <expand macro="version_command"/> <command detect_errors="aggressive"><![CDATA[ + mkdir -p ./database_path/amrfinderplus-db && ln -s '$(input_option.bakta_db_select.fields.path)'/* database_path && ln -s '$(input_option.amrfinder_db_select.fields.path)/' database_path/amrfinderplus-db/latest && - bakta + bakta --verbose + #*====================================== CPU option ======================================*# @@ -22,7 +24,8 @@ #*====================================== Bakta database ======================================*# - --db ./database_path + --db './database_path' + --output 'bakta_output' #if $input_option.min_contig_length --min-contig-length $input_option.min_contig_length #else if $annotation.compliant @@ -88,8 +91,8 @@ <section name="input_option" title="Input/Output options" expanded="true"> <param name="bakta_db_select" type="select" label="The bakta database"> <options from_data_table="bakta_database"> - <filter type="static_value" value="@BAKTA_VERSION@" column="bakta_version"/> - <validator message="No bakta database is available" type="no_options"/> + <filter type="static_value" value="@COMPATIBLE_BAKTA_VERSION@" column="bakta_version"/> + <validator message="No bakta database is available" type="no_options"/> </options> </param> <param name="amrfinder_db_select" type="select" label="The amrfinderplus database"> @@ -128,87 +131,89 @@ <param argument="--replicons" type="data" format="tabular,csv" optional="true" label="Replicon information table (tsv/csv)" help=""/> <param argument="--compliant" type="boolean" truevalue="--compliant" falsevalue="" label="Force Genbank/ENA/DDJB compliance"/> <param argument="--proteins" type="data" format="fasta" optional="true" label="Protein fasta file" help="Fasta file of trusted protein sequences for CDS annotation"/> + <param argument="--meta" type="boolean" truevalue="--meta" falsevalue="" label="Metagenome mode" help="Run in metagenome mode. This only affects CDS prediction"/> </section> <!-- PARAMETER FOR WORKFLOW ANALYSIS --> <section name="workflow" title="Workflow option to skip steps"> <param name="skip_analysis" type="select" display="checkboxes" multiple="true" label="Select steps to skip"> - <option value="--skip-trna"> Skip tRNA detection and annotation </option> - <option value="--skip-tmrna"> Skip tmRNA detection and annotation </option> - <option value="--skip-rrna"> Skip rRNA detection and annotation </option> - <option value="--skip-ncrna"> Skip ncRNA detection and annotation </option> - <option value="--skip-ncrna-region"> Skip ncRNA region detection and annotation </option> - <option value="--skip-crispr"> Skip CRISPR array detection and annotation </option> - <option value="--skip-cds"> Skip CDS detection and annotation </option> - <option value="--skip-pseudo"> Skip pseudogene detection and annotation </option> - <option value="--skip-sorf"> Skip sORF detection and annotation </option> - <option value="--skip-gap"> Skip gap detection and annotation </option> - <option value="--skip-ori"> Skip oriC/oriT detection and annotation </option> + <option value="--skip-trna">Skip tRNA detection and annotation</option> + <option value="--skip-tmrna">Skip tmRNA detection and annotation</option> + <option value="--skip-rrna">Skip rRNA detection and annotation</option> + <option value="--skip-ncrna">Skip ncRNA detection and annotation</option> + <option value="--skip-ncrna-region">Skip ncRNA region detection and annotation</option> + <option value="--skip-crispr">Skip CRISPR array detection and annotation</option> + <option value="--skip-cds">Skip CDS detection and annotation</option> + <option value="--skip-pseudo">Skip pseudogene detection and annotation</option> + <option value="--skip-sorf">Skip sORF detection and annotation</option> + <option value="--skip-gap">Skip gap detection and annotation</option> + <option value="--skip-ori">Skip oriC/oriT detection and annotation</option> + <option value="--skip-plot">Skip generation of circular genome plots</option> </param> </section> <section name="output_files" title="Selection of the output files"> <param name="output_selection" type="select" display="checkboxes" multiple="true" label="Output files selection"> - <option value="file_tsv" selected="true"> Annotation file in TSV </option> - <option value="file_gff3" selected="true"> Annotation and sequence in GFF3 </option> - <option value="file_gbff" selected="false"> Annotations and sequences in GenBank format </option> - <option value="file_embl" selected="false"> Annotations and sequences in EMBL format </option> - <option value="file_fna" selected="false"> Replicon/contig DNA sequences as FASTA </option> - <option value="file_ffn" selected="true"> Feature nucleotide sequences as FASTA </option> - <option value="file_faa" selected="false"> CDS/sORF amino acid sequences as FASTA </option> - <option value="hypo_tsv" selected="false"> Hypothetical protein CDS in TSV</option> - <option value="hypo_fa" selected="false"> Hypothetical protein CDS amino sequences as FASTA</option> - <option value="sum_txt" selected="false"> Summary as TXT</option> - <option value="file_json" selected="false"> Information on each annotated feature as JSON </option> - <option value="file_plot" selected="true"> Plot of the annotation result as SVG </option> - <option value="log_txt" selected="false"> Log file as TXT </option> + <option value="file_tsv" selected="true">Annotation file in TSV</option> + <option value="file_gff3" selected="true">Annotation and sequence in GFF3</option> + <option value="file_gbff" selected="false">Annotations and sequences in GenBank format</option> + <option value="file_embl" selected="false">Annotations and sequences in EMBL format</option> + <option value="file_fna" selected="false">Replicon/contig DNA sequences as FASTA</option> + <option value="file_ffn" selected="true">Feature nucleotide sequences as FASTA</option> + <option value="file_faa" selected="false">CDS/sORF amino acid sequences as FASTA</option> + <option value="hypo_tsv" selected="false">Hypothetical protein CDS in TSV</option> + <option value="hypo_fa" selected="false">Hypothetical protein CDS amino sequences as FASTA</option> + <option value="sum_txt" selected="false">Summary as TXT</option> + <option value="file_json" selected="false">Information on each annotated feature as JSON</option> + <option value="file_plot" selected="true">Plot of the annotation result as SVG</option> + <option value="log_txt" selected="false">Log file as TXT</option> </param> </section> </inputs> <outputs> - <data name="annotation_tsv" format="tabular" from_work_dir="bakta_output.tsv" label="${tool.name} on ${on_string}: annotation_summary"> - <filter> output_files['output_selection'] and "file_tsv" in output_files['output_selection'] </filter> + <data name="annotation_tsv" format="tabular" from_work_dir="bakta_output/bakta_output.tsv" label="${tool.name} on ${on_string}: annotation_summary"> + <filter>output_files['output_selection'] and "file_tsv" in output_files['output_selection']</filter> </data> - <data name="annotation_gff3" format="gff3" from_work_dir="bakta_output.gff3" label="${tool.name} on ${on_string}: Annotation_and_sequences"> - <filter> output_files['output_selection'] and "file_gff3" in output_files['output_selection'] </filter> + <data name="annotation_gff3" format="gff3" from_work_dir="bakta_output/bakta_output.gff3" label="${tool.name} on ${on_string}: Annotation_and_sequences"> + <filter>output_files['output_selection'] and "file_gff3" in output_files['output_selection']</filter> </data> - <data name="annotation_gbff" format="tabular" from_work_dir="bakta_output.gbff" label="${tool.name} on ${on_string}: bakta_output.gbff"> - <filter> output_files['output_selection'] and "file_gbff" in output_files['output_selection'] </filter> + <data name="annotation_gbff" format="tabular" from_work_dir="bakta_output/bakta_output.gbff" label="${tool.name} on ${on_string}: bakta_output.gbff"> + <filter>output_files['output_selection'] and "file_gbff" in output_files['output_selection']</filter> </data> - <data name="annotation_embl" format="tabular" from_work_dir="bakta_output.embl" label="${tool.name} on ${on_string}: bakta_output.embl"> - <filter> output_files['output_selection'] and "file_embl" in output_files['output_selection'] </filter> + <data name="annotation_embl" format="tabular" from_work_dir="bakta_output/bakta_output.embl" label="${tool.name} on ${on_string}: bakta_output.embl"> + <filter>output_files['output_selection'] and "file_embl" in output_files['output_selection']</filter> </data> - <data name="annotation_fna" format="fasta" from_work_dir="bakta_output.fna" label="${tool.name} on ${on_string}: Contig_sequences"> - <filter> output_files['output_selection'] and "file_fna" in output_files['output_selection'] </filter> + <data name="annotation_fna" format="fasta" from_work_dir="bakta_output/bakta_output.fna" label="${tool.name} on ${on_string}: Contig_sequences"> + <filter>output_files['output_selection'] and "file_fna" in output_files['output_selection']</filter> </data> - <data name="annotation_ffn" format="fasta" from_work_dir="bakta_output.ffn" label="${tool.name} on ${on_string}: Nucleotide_sequences"> - <filter> output_files['output_selection'] and "file_ffn" in output_files['output_selection'] </filter> + <data name="annotation_ffn" format="fasta" from_work_dir="bakta_output/bakta_output.ffn" label="${tool.name} on ${on_string}: Nucleotide_sequences"> + <filter>output_files['output_selection'] and "file_ffn" in output_files['output_selection']</filter> </data> - <data name="annotation_faa" format="fasta" from_work_dir="bakta_output.faa" label="${tool.name} on ${on_string}: Amino_acid_sequences"> - <filter> output_files['output_selection'] and "file_faa" in output_files['output_selection'] </filter> + <data name="annotation_faa" format="fasta" from_work_dir="bakta_output/bakta_output.faa" label="${tool.name} on ${on_string}: Amino_acid_sequences"> + <filter>output_files['output_selection'] and "file_faa" in output_files['output_selection']</filter> </data> - <data name="hypotheticals_tsv" format="tabular" from_work_dir="bakta_output.hypotheticals.tsv" label="${tool.name} on ${on_string}: hypothetical_annotation_summary"> - <filter> output_files['output_selection'] and "hypo_tsv" in output_files['output_selection'] </filter> + <data name="hypotheticals_tsv" format="tabular" from_work_dir="bakta_output/bakta_output.hypotheticals.tsv" label="${tool.name} on ${on_string}: hypothetical_annotation_summary"> + <filter>output_files['output_selection'] and "hypo_tsv" in output_files['output_selection']</filter> </data> - <data name="hypotheticals_faa" format="fasta" from_work_dir="bakta_output.hypotheticals.faa" label="${tool.name} on ${on_string}: hypothetical_amino_acid_sequences"> - <filter> output_files['output_selection'] and "hypo_fa" in output_files['output_selection'] </filter> + <data name="hypotheticals_faa" format="fasta" from_work_dir="bakta_output/bakta_output.hypotheticals.faa" label="${tool.name} on ${on_string}: hypothetical_amino_acid_sequences"> + <filter>output_files['output_selection'] and "hypo_fa" in output_files['output_selection']</filter> </data> - <data name="summary_txt" format="txt" from_work_dir="bakta_output.txt" label="${tool.name} on ${on_string}: Analysis_summary"> - <filter> output_files['output_selection'] and "sum_txt" in output_files['output_selection'] </filter> + <data name="summary_txt" format="txt" from_work_dir="bakta_output/bakta_output.txt" label="${tool.name} on ${on_string}: Analysis_summary"> + <filter>output_files['output_selection'] and "sum_txt" in output_files['output_selection']</filter> </data> - <data name="annotation_json" format="json" from_work_dir="bakta_output.json" label="${tool.name} on ${on_string}: annotation_machine_readable"> - <filter> output_files['output_selection'] and "file_json" in output_files['output_selection'] </filter> + <data name="annotation_json" format="json" from_work_dir="bakta_output/bakta_output.json" label="${tool.name} on ${on_string}: annotation_machine_readable"> + <filter>output_files['output_selection'] and "file_json" in output_files['output_selection']</filter> </data> - <data name="annotation_plot" format="svg" from_work_dir="bakta_output.svg" label="${tool.name} on ${on_string}: Plot of the annotation"> - <filter> output_files['output_selection'] and "file_plot" in output_files['output_selection'] </filter> + <data name="annotation_plot" format="svg" from_work_dir="bakta_output/bakta_output.svg" label="${tool.name} on ${on_string}: Plot of the annotation"> + <filter>output_files['output_selection'] and "file_plot" in output_files['output_selection']</filter> </data> <data name="logfile" format="txt" label="${tool.name} on ${on_string}: log file"> - <filter> output_files['output_selection'] and "log_txt" in output_files['output_selection'] </filter> + <filter>output_files['output_selection'] and "log_txt" in output_files['output_selection']</filter> </data> </outputs> <tests> <test expect_num_outputs="13"> <!-- TEST_1 database + input --> <section name="input_option" > - <param name="bakta_db_select" value="V0.1_2022-08-29"/> + <param name="bakta_db_select" value="V5.0_2022-08-19"/> <param name="amrfinder_db_select" value="V3.6-2020-03-20.1"/> <param name="input_file" value="NC_002127.1.fna" ftype="fasta"/> <param name="min_contig_length" value="250"/> @@ -226,17 +231,13 @@ <output name="hypotheticals_tsv" value="TEST_1/TEST_1.hypotheticals.tsv" lines_diff="4"/> <output name="hypotheticals_faa" value="TEST_1/TEST_1.hypotheticals.faa"/> <output name="summary_txt" value="TEST_1/TEST_1.txt" lines_diff="4"/> - <output name="annotation_plot"> - <assert_contents> - <has_size value="418991" delta="1000"/> - </assert_contents> - </output> + <output name="annotation_plot" value="TEST_1/TEST_1_plot.svg" ftype="svg" compare="sim_size"/> <output name="annotation_json" value="TEST_1/TEST_1.json" lines_diff="6"/> - <output name="logfile" value="TEST_1/TEST_1.log" lines_diff="6"/> + <output name="logfile" value="TEST_1/TEST_1.log" lines_diff="15"/> </test> <test expect_num_outputs="4"> <!-- TEST_2 another input, add organism info some annotations and skip 2 steps --> <section name="input_option" > - <param name="bakta_db_select" value="V0.1_2022-08-29"/> + <param name="bakta_db_select" value="V5.0_2022-08-19"/> <param name="amrfinder_db_select" value="V3.6-2020-03-20.1"/> <param name="input_file" value="NC_002127.1.fna" ftype="fasta"/> <param name="min_contig_length" value="250"/> @@ -264,34 +265,25 @@ </assert_contents> </output> <output name="annotation_ffn" value="TEST_2/TEST_2.ffn"/> - <output name="annotation_plot"> - <assert_contents> - <has_size value="418991" delta="1000"/> - </assert_contents> - </output> + <output name="annotation_plot" value="TEST_2/TEST_2_plot.svg" ftype="svg" compare="sim_size"/> </test> <test expect_num_outputs="4"> <!-- TEST_3 test all skip steps --> <section name="input_option" > - <param name="bakta_db_select" value="V0.1_2022-08-29"/> + <param name="bakta_db_select" value="V5.0_2022-08-19"/> <param name="amrfinder_db_select" value="V3.6-2020-03-20.1"/> <param name="input_file" value="NC_002127.1.fna" ftype="fasta"/> <param name="min_contig_length" value="350"/> </section> <section name="workflow"> - <param name="skip_analysis" value="--skip-trna,--skip-tmrna,--skip-rrna,--skip-ncrna,--skip-ncrna-region,--skip-crispr,--skip-cds,--skip-sorf,--skip-gap,--skip-ori"/> + <param name="skip_analysis" value="--skip-trna,--skip-tmrna,--skip-rrna,--skip-ncrna,--skip-ncrna-region,--skip-crispr,--skip-cds,--skip-sorf,--skip-gap,--skip-ori,--skip-plot"/> </section> <output name="annotation_tsv" value="TEST_3/TEST_3.tsv" lines_diff="4"/> <output name="annotation_gff3" value="TEST_3/TEST_3.gff3" lines_diff="4"/> <output name="annotation_ffn" value="TEST_3/TEST_3.ffn"/> - <output name="annotation_plot"> - <assert_contents> - <has_size value="418399" delta="1000"/> - </assert_contents> - </output> </test> <test expect_num_outputs="4"> <!-- TEST_4 annotations --> <section name="input_option" > - <param name="bakta_db_select" value="V0.1_2022-08-29"/> + <param name="bakta_db_select" value="V5.0_2022-08-19"/> <param name="amrfinder_db_select" value="V3.6-2020-03-20.1"/> <param name="input_file" value="NC_002127.1.fna" ftype="fasta"/> </section> @@ -306,15 +298,11 @@ <output name="annotation_tsv" value="TEST_4/TEST_4.tsv" lines_diff="4"/> <output name="annotation_gff3" value="TEST_4/TEST_4.gff3" lines_diff="4"/> <output name="annotation_ffn" value="TEST_4/TEST_4.ffn"/> - <output name="annotation_plot"> - <assert_contents> - <has_size value="418399" delta="1000"/> - </assert_contents> - </output> + <output name="annotation_plot" value="TEST_4/TEST_4_plot.svg" ftype="svg" compare="sim_size"/> </test> <test expect_num_outputs="2"> <!-- TEST_5 skip all steps and keep only the logfile and summary --> <section name="input_option" > - <param name="bakta_db_select" value="V0.1_2022-08-29"/> + <param name="bakta_db_select" value="V5.0_2022-08-19"/> <param name="amrfinder_db_select" value="V3.6-2020-03-20.1"/> <param name="input_file" value="NC_002127.1.fna" ftype="fasta"/> </section> @@ -323,14 +311,40 @@ <param name="translation_table" value="4"/> </section> <section name="workflow"> - <param name="skip_analysis" value="--skip-trna,--skip-tmrna,--skip-rrna,--skip-ncrna,--skip-ncrna-region,--skip-crispr,--skip-cds,--skip-sorf,--skip-gap,--skip-ori"/> + <param name="skip_analysis" value="--skip-trna,--skip-tmrna,--skip-rrna,--skip-ncrna,--skip-ncrna-region,--skip-crispr,--skip-cds,--skip-sorf,--skip-gap,--skip-ori,--skip-plot"/> </section> <section name="output_files"> <param name="output_selection" value="log_txt,sum_txt"/> </section> - <output name="logfile" value="TEST_5/TEST_5.log" lines_diff="6"/> + <output name="logfile" value="TEST_5/TEST_5.log" lines_diff="13"/> <output name="summary_txt" value="TEST_5/TEST_5.txt" lines_diff="4"/> </test> + <test expect_num_outputs="13"> <!-- TEST_6 metagenome option --> + <section name="input_option" > + <param name="bakta_db_select" value="V5.0_2022-08-19"/> + <param name="amrfinder_db_select" value="V3.6-2020-03-20.1"/> + <param name="input_file" value="NC_002127.1.fna" ftype="fasta"/> + </section> + <section name="annotation"> + <param name="meta" value="true"/> + </section> + <section name="output_files"> + <param name="output_selection" value="file_tsv,file_gff3,file_gbff,file_embl,file_fna,file_ffn,file_faa,hypo_tsv,hypo_fa,sum_txt,file_json,file_plot,log_txt"/> + </section> + <output name="annotation_tsv" value="TEST_6/TEST_6.tsv" lines_diff="2"/> + <output name="annotation_gff3" value="TEST_6/TEST_6.gff3" lines_diff="2"/> + <output name="annotation_gbff" value="TEST_6/TEST_6.gbff" lines_diff="8"/> + <output name="annotation_embl" value="TEST_6/TEST_6.embl" lines_diff="6"/> + <output name="annotation_fna" value="TEST_6/TEST_6.fna"/> + <output name="annotation_ffn" value="TEST_6/TEST_6.ffn"/> + <output name="annotation_faa" value="TEST_6/TEST_6.faa"/> + <output name="hypotheticals_tsv" value="TEST_6/TEST_6.hypotheticals.tsv" lines_diff="4"/> + <output name="hypotheticals_faa" value="TEST_6/TEST_6.hypotheticals.faa"/> + <output name="summary_txt" value="TEST_6/TEST_6.txt" lines_diff="4"/> + <output name="annotation_plot" value="TEST_6/TEST_6_plot.svg" ftype="svg" compare="sim_size"/> + <output name="annotation_json" value="TEST_6/TEST_6.json" lines_diff="6"/> + <output name="logfile" value="TEST_6/TEST_6.log" lines_diff="15"/> + </test> </tests> <help><![CDATA[**What it does** Bakta is a tool for the rapid & standardized annotation of bacterial genomes and plasmids from both isolates and MAGs.