Mercurial > repos > iuc > bakta
diff bakta.xml @ 3:865ece5ca178 draft
planemo upload for repository https://github.com/galaxyproject/tools-iuc/blob/master/tools/bakta commit 9f516ce5c84b251b9041cd79129e5b5e1979a738
| author | iuc |
|---|---|
| date | Fri, 10 Feb 2023 14:20:09 +0000 |
| parents | debdc1469b41 |
| children | 3f0aa1b3e816 |
line wrap: on
line diff
--- a/bakta.xml Wed Dec 21 20:59:54 2022 +0000 +++ b/bakta.xml Fri Feb 10 14:20:09 2023 +0000 @@ -1,6 +1,6 @@ <tool id="bakta" name="Bakta" version="@TOOL_VERSION@+galaxy@VERSION_SUFFIX@" profile="@PROFILE@"> <description> - genome annotation via alignment-free sequence identification + Genome annotation via alignment-free sequence identification </description> <macros> <import>macro.xml</import> @@ -11,10 +11,9 @@ <expand macro="version_command"/> <command detect_errors="aggressive"><![CDATA[ - mkdir ./database_path && - ln -s '$(input_option.bakta_db_select.fields.path)/'* database_path && - ln -s '$(input_option.amrfinder_db_select.fields.path)' database_path && - + 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 #*====================================== CPU option @@ -59,9 +58,7 @@ #if $annotation.translation_table --translation-table '$annotation.translation_table' #end if - #if $annotation.gram - --gram '$annotation.gram' - #end if + --gram '?' $annotation.keep_contig_headers #if $annotation.replicons --replicons '$annotation.replicons' @@ -127,13 +124,8 @@ <option value="4">4 Mold, Protozoan, and Coelenterate Mitochondrial Code and the Mycoplasma/Spiroplasma Code</option> <option value="11" selected="true">11 Bacterial, Archaeal and Plant Plastid Code</option> </param> - <param argument="--gram" type="select" optional="true" label="Gram type for signal peptide predictions" help="Gram type +/- or unknown. Default: unknown"> - <option value="+">Gram+</option> - <option value="-">Gram-</option> - <option value="?" selected="true">Unknown</option> - </param> <param name="keep_contig_headers" type="boolean" truevalue="--keep-contig-headers" falsevalue="" label="Keep original contig header (--keep-contig-headers)"/> - <param argument="--replicons" type="data" format="tsv,csv" optional="true" label="Replicon information table (tsv/csv)" help=""/> + <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"/> </section> @@ -215,18 +207,18 @@ </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="amrfinder_db_select" value="V3.6-2020-03-20.1"/> - <param name="input_file" value="NC_002127.1.fna"/> - <param name="min_contig_length" value="250"/> - </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_1/TEST_1.tsv" lines_diff="2"/> - <output name="annotation_gff3" value="TEST_1/TEST_1.gff3" lines_diff="2"/> - <output name="annotation_gbff" value="TEST_1/TEST_1.gbff" lines_diff="8"/> + <section name="input_option" > + <param name="bakta_db_select" value="V0.1_2022-08-29"/> + <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"/> + </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_1/TEST_1.tsv" lines_diff="2"/> + <output name="annotation_gff3" value="TEST_1/TEST_1.gff3" lines_diff="2"/> + <output name="annotation_gbff" value="TEST_1/TEST_1.gbff" lines_diff="8"/> <output name="annotation_embl" value="TEST_1/TEST_1.embl" lines_diff="6"/> <output name="annotation_fna" value="TEST_1/TEST_1.fna"/> <output name="annotation_ffn" value="TEST_1/TEST_1.ffn"/> @@ -235,112 +227,110 @@ <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_json" value="TEST_1/TEST_1.json" lines_diff="6"/> - <output name="logfile" value="TEST_1/TEST_1.log" lines_diff="6"/> - </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="amrfinder_db_select" value="V3.6-2020-03-20.1"/> - <param name="input_file" value="NC_002127.1.fna"/> - <param name="min_contig_length" value="250"/> - </section> - <section name="organism"> - <param name="genus" value="Escherichia"/> - <param name="species" value="coli O157:H7"/> - <param name="strain" value="Sakai"/> - <param name="plasmid" value="pOSAK1"/> - </section> - <section name="annotation"> - <param name="--gram" value="-"/> - <param name="keep_contig_headers" value="true"/> - </section> - <section name="workflow"> - <param name="skip_analysis" value="--skip-trna,--skip-tmrna"/> - </section> - <output name="annotation_tsv" value="TEST_2/TEST_2.tsv" lines_diff="4"> - <assert_contents> - <has_text_matching expression="IHHALP_00005"/> - </assert_contents> - </output> - <output name="annotation_gff3" value="TEST_2/TEST_2.gff3" lines_diff="4"> - <assert_contents> - <has_text_matching expression="ID=NC_002127.1;Name=NC_002127.1;Is_circular=true"/> - </assert_contents> - </output> - <output name="annotation_ffn" value="TEST_2/TEST_2.ffn"/> + <assert_contents> + <has_size value="418991" delta="1000"/> + </assert_contents> + </output> + <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"/> + </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="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"/> + </section> + <section name="organism"> + <param name="genus" value="Escherichia"/> + <param name="species" value="coli O157:H7"/> + <param name="strain" value="Sakai"/> + <param name="plasmid" value="pOSAK1"/> + </section> + <section name="annotation"> + <param name="keep_contig_headers" value="true"/> + </section> + <section name="workflow"> + <param name="skip_analysis" value="--skip-trna,--skip-tmrna"/> + </section> + <output name="annotation_tsv" value="TEST_2/TEST_2.tsv" lines_diff="4"> + <assert_contents> + <has_text_matching expression="IHHALP_00005"/> + </assert_contents> + </output> + <output name="annotation_gff3" value="TEST_2/TEST_2.gff3" lines_diff="4"> + <assert_contents> + <has_text_matching expression="ID=NC_002127.1;Name=NC_002127.1;Is_circular=true"/> + </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> + </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="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"/> + </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="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="complete" value="true"/> + <param name="prodigal" value="prodigal.tf"/> + <param name="translation_table" value="4"/> + <param name="replicons" value="replicons.tsv" ftype="tabular"/> + <param name="compliant" value="true"/> + <param name="proteins" value="user-proteins.faa" ftype="fasta"/> + </section> + <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="418991" delta="1000"/> - </assert_contents> - </output> - </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="amrfinder_db_select" value="V3.6-2020-03-20.1"/> - <param name="input_file" value="NC_002127.1.fna"/> - <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"/> - </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="amrfinder_db_select" value="V3.6-2020-03-20.1"/> - <param name="input_file" value="NC_002127.1.fna"/> - </section> - <section name="annotation"> - <param name="complete" value="true"/> - <param name="prodigal" value="prodigal.tf"/> - <param name="translation_table" value="4"/> - <param name="replicons" value="replicons.tsv"/> - <param name="compliant" value="true"/> - <param name="proteins" value="user-proteins.faa"/> - </section> - <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> - </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="amrfinder_db_select" value="V3.6-2020-03-20.1"/> - <param name="input_file" value="NC_002127.1.fna"/> - </section> - <section name="annotation"> - <param name="complete" value="true"/> - <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"/> - </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="summary_txt" value="TEST_5/TEST_5.txt" lines_diff="4"/> - </test> + <assert_contents> + <has_size value="418399" delta="1000"/> + </assert_contents> + </output> + </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="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="complete" value="true"/> + <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"/> + </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="summary_txt" value="TEST_5/TEST_5.txt" lines_diff="4"/> + </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. @@ -390,7 +380,7 @@ 1. You can specify if all sequences (chromosome or plasmids) are complete or not 2. You can add your own prodigal training file for CDS predictionœ 3. The translation table could be modified, default is the 11th for bacteria - 4. You can specify if bacteria is gram -/+ or unknonw (default value unknow) + 4. You can specify if bacteria is gram -/+ or unknonw (default value is unknow) 5. You can keep the name of contig present in the input file 6. You can specify your own replicon table as a TSV/CSV file 7. The compliance option is for ready to submit annotation file to Public database