Mercurial > repos > iuc > bakta
changeset 5:728dacaf08a9 draft
planemo upload for repository https://github.com/galaxyproject/tools-iuc/blob/master/tools/bakta commit 5ab93133efa5de410e992919c4e841807fb43b55
author | iuc |
---|---|
date | Sat, 16 Sep 2023 09:01:39 +0000 |
parents | 3f0aa1b3e816 |
children | 92eee5f31117 |
files | bakta.xml macro.xml test-data/TEST_1/TEST_1.gff3 test-data/TEST_1/TEST_1.hypotheticals.tsv test-data/TEST_1/TEST_1.log test-data/TEST_1/TEST_1.tsv test-data/TEST_1/TEST_1.txt test-data/TEST_2/TEST_2.gff3 test-data/TEST_2/TEST_2.tsv test-data/TEST_3/TEST_3.gff3 test-data/TEST_3/TEST_3.tsv test-data/TEST_4/TEST_4.gff3 test-data/TEST_4/TEST_4.tsv test-data/TEST_5/TEST_5.log test-data/TEST_5/TEST_5.txt test-data/TEST_6/TEST_6.log |
diffstat | 16 files changed, 157 insertions(+), 435 deletions(-) [+] |
line wrap: on
line diff
--- a/bakta.xml Mon Jul 24 11:22:16 2023 +0000 +++ b/bakta.xml Sat Sep 16 09:01:39 2023 +0000 @@ -212,139 +212,145 @@ </outputs> <tests> <test expect_num_outputs="13"> <!-- TEST_1 database + input --> - <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"/> - <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"/> - <output name="annotation_faa" value="TEST_1/TEST_1.faa"/> - <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" 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="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="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"/> - </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" 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="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,--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"/> - </test> - <test expect_num_outputs="4"> <!-- TEST_4 annotations --> - <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="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" 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="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="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,--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="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"/> + <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"/> + <output name="annotation_faa" value="TEST_1/TEST_1.faa"/> + <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" 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" ftype="txt"> + <expand macro="assert_content_test"/> + </output> + </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="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"/> + </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" 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="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="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 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,--skip-plot"/> </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> + <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"/> + </test> + <test expect_num_outputs="4"> <!-- TEST_4 annotations --> + <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="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" 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="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="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,--skip-plot"/> + </section> + <section name="output_files"> + <param name="output_selection" value="log_txt,sum_txt"/> + </section> + <output name="logfile" ftype="txt"> + <expand macro="assert_content_test"/> + </output> + <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" ftype="txt"> + <expand macro="assert_content_test"/> + </output> + </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.
--- a/macro.xml Mon Jul 24 11:22:16 2023 +0000 +++ b/macro.xml Sat Sep 16 09:01:39 2023 +0000 @@ -1,8 +1,8 @@ <macros> - <token name="@TOOL_VERSION@">1.8.1</token> + <token name="@TOOL_VERSION@">1.8.2</token> <token name="@COMPATIBLE_BAKTA_VERSION@">1.7</token> - <token name="@VERSION_SUFFIX@">1</token> + <token name="@VERSION_SUFFIX@">0</token> <token name="@PROFILE@">21.05</token> <xml name="version_command"> <version_command><![CDATA[bakta --version]]></version_command> @@ -27,4 +27,15 @@ <citation type="doi">10.1099/mgen.0.000685</citation> </citations> </xml> + + <xml name="assert_content_test"> + <assert_contents> + <has_text text="Options and arguments"/> + <has_text text="parse genome sequences"/> + <has_text text="start annotation"/> + <has_text text="genome statistics"/> + <has_text text="annotation summary"/> + <has_text text="export annotation results to"/> + </assert_contents> + </xml> </macros>
--- a/test-data/TEST_1/TEST_1.gff3 Mon Jul 24 11:22:16 2023 +0000 +++ b/test-data/TEST_1/TEST_1.gff3 Sat Sep 16 09:01:39 2023 +0000 @@ -1,7 +1,7 @@ ##gff-version 3 ##feature-ontology https://github.com/The-Sequence-Ontology/SO-Ontologies/blob/v3.1/so.obo # Annotated with Bakta -# Software: v1.8.1 +# Software: v1.8.2 # Database: v5.0, full # DOI: 10.1099/mgen.0.000685 # URL: github.com/oschwengers/bakta
--- a/test-data/TEST_1/TEST_1.hypotheticals.tsv Mon Jul 24 11:22:16 2023 +0000 +++ b/test-data/TEST_1/TEST_1.hypotheticals.tsv Sat Sep 16 09:01:39 2023 +0000 @@ -1,4 +1,4 @@ -#Annotated with Bakta v1.8.1, https://github.com/oschwengers/bakta +#Annotated with Bakta v1.8.2, https://github.com/oschwengers/bakta #Database v5.0, https://doi.org/10.5281/zenodo.4247252 #Sequence Id Start Stop Strand Locus Tag Mol Weight [kDa] Iso El. Point Pfam hits Dbxrefs contig_1 413 736 + IHHALP_00005 12.1 10.4
--- a/test-data/TEST_1/TEST_1.log Mon Jul 24 11:22:16 2023 +0000 +++ /dev/null Thu Jan 01 00:00:00 1970 +0000 @@ -1,107 +0,0 @@ -Bakta v1.8.1 -Options and arguments: - input: /tmp/tmp6wdeee6u/files/3/2/d/dataset_32d4899b-3214-49f6-a57b-29ff0e04425d.dat - db: /tmp/tmp6wdeee6u/job_working_directory/000/2/working/database_path, version 5.0, full - output: /tmp/tmp6wdeee6u/job_working_directory/000/2/working/bakta_output - tmp directory: /tmp/tmp6wdeee6u/tmp/tmpm3wbu37o - prefix: bakta_output - threads: 1 - translation table: 11 - -parse genome sequences... - imported: 1 - filtered & revised: 1 - plasmids: 1 - -start annotation... -predict tRNAs... - found: 0 -predict tmRNAs... - found: 0 -predict rRNAs... - found: 0 -predict ncRNAs... - found: 0 -predict ncRNA regions... - found: 0 -predict CRISPR arrays... - found: 0 -predict & annotate CDSs... - predicted: 2 - discarded spurious: 0 - revised translational exceptions: 0 - detected IPSs: 0 - found PSCs: 0 - found PSCCs: 0 - lookup annotations... - conduct expert systems... - amrfinder: 0 - protein sequences: 0 - combine annotations and mark hypotheticals... - detect pseudogenes... - pseudogene candidates: 0 - found pseudogenes: 0 -analyze hypothetical proteins: 2 - detected Pfam hits: 0 - calculated proteins statistics - revise special cases... -extract sORF... - potential: 22 - discarded due to overlaps: 2 - discarded spurious: 0 - detected IPSs: 0 - found PSCs: 0 - lookup annotations... - filter and combine annotations... - filtered sORFs: 0 -detect gaps... - found: 0 -detect oriCs/oriVs... - found: 0 -detect oriTs... - found: 0 -apply feature overlap filters... -select features and create locus tags... -selected: 2 -improve annotations... - revised gene symbols: 0 - -genome statistics: - Genome size: 1,330 bp - Contigs/replicons: 1 - GC: 45.2 % - N50: 1,330 - N ratio: 0.0 % - coding density: 62.0 % - -annotation summary: - tRNAs: 0 - tmRNAs: 0 - rRNAs: 0 - ncRNAs: 0 - ncRNA regions: 0 - CRISPR arrays: 0 - CDSs: 2 - hypotheticals: 2 - pseudogenes: 0 - signal peptides: 0 - sORFs: 0 - gaps: 0 - oriCs/oriVs: 0 - oriTs: 0 - -export annotation results to: /tmp/tmp6wdeee6u/job_working_directory/000/2/working/bakta_output - human readable TSV... - GFF3... - INSDC GenBank & EMBL... - genome sequences... - feature nucleotide sequences... - translated CDS sequences... - circular genome plot... - hypothetical TSV... - translated hypothetical CDS sequences... - machine readable JSON... - genome and annotation summary... - -If you use these results please cite Bakta: https://doi.org/10.1099/mgen.0.000685 -Annotation successfully finished in 0:01 [mm:ss].
--- a/test-data/TEST_1/TEST_1.tsv Mon Jul 24 11:22:16 2023 +0000 +++ b/test-data/TEST_1/TEST_1.tsv Sat Sep 16 09:01:39 2023 +0000 @@ -1,5 +1,5 @@ # Annotated with Bakta -# Software: v1.8.1 +# Software: v1.8.2 # Database: v5.0, full # DOI: 10.1099/mgen.0.000685 # URL: github.com/oschwengers/bakta
--- a/test-data/TEST_1/TEST_1.txt Mon Jul 24 11:22:16 2023 +0000 +++ b/test-data/TEST_1/TEST_1.txt Sat Sep 16 09:01:39 2023 +0000 @@ -24,7 +24,7 @@ oriTs: 0 Bakta: -Software: v1.8.1 +Software: v1.8.2 Database: v5.0, full DOI: 10.1099/mgen.0.000685 URL: github.com/oschwengers/bakta
--- a/test-data/TEST_2/TEST_2.gff3 Mon Jul 24 11:22:16 2023 +0000 +++ b/test-data/TEST_2/TEST_2.gff3 Sat Sep 16 09:01:39 2023 +0000 @@ -2,7 +2,7 @@ ##feature-ontology https://github.com/The-Sequence-Ontology/SO-Ontologies/blob/v3.1/so.obo # organism Escherichia coli o157:h7 Sakai # Annotated with Bakta -# Software: v1.8.1 +# Software: v1.8.2 # Database: v5.0, full # DOI: 10.1099/mgen.0.000685 # URL: github.com/oschwengers/bakta
--- a/test-data/TEST_2/TEST_2.tsv Mon Jul 24 11:22:16 2023 +0000 +++ b/test-data/TEST_2/TEST_2.tsv Sat Sep 16 09:01:39 2023 +0000 @@ -1,5 +1,5 @@ # Annotated with Bakta -# Software: v1.8.1 +# Software: v1.8.2 # Database: v5.0, full # DOI: 10.1099/mgen.0.000685 # URL: github.com/oschwengers/bakta
--- a/test-data/TEST_3/TEST_3.gff3 Mon Jul 24 11:22:16 2023 +0000 +++ b/test-data/TEST_3/TEST_3.gff3 Sat Sep 16 09:01:39 2023 +0000 @@ -1,7 +1,7 @@ ##gff-version 3 ##feature-ontology https://github.com/The-Sequence-Ontology/SO-Ontologies/blob/v3.1/so.obo # Annotated with Bakta -# Software: v1.8.1 +# Software: v1.8.2 # Database: v5.0, full # DOI: 10.1099/mgen.0.000685 # URL: github.com/oschwengers/bakta
--- a/test-data/TEST_3/TEST_3.tsv Mon Jul 24 11:22:16 2023 +0000 +++ b/test-data/TEST_3/TEST_3.tsv Sat Sep 16 09:01:39 2023 +0000 @@ -1,5 +1,5 @@ # Annotated with Bakta -# Software: v1.8.1 +# Software: v1.8.2 # Database: v5.0, full # DOI: 10.1099/mgen.0.000685 # URL: github.com/oschwengers/bakta
--- a/test-data/TEST_4/TEST_4.gff3 Mon Jul 24 11:22:16 2023 +0000 +++ b/test-data/TEST_4/TEST_4.gff3 Sat Sep 16 09:01:39 2023 +0000 @@ -1,7 +1,7 @@ ##gff-version 3 ##feature-ontology https://github.com/The-Sequence-Ontology/SO-Ontologies/blob/v3.1/so.obo # Annotated with Bakta -# Software: v1.8.1 +# Software: v1.8.2 # Database: v5.0, full # DOI: 10.1099/mgen.0.000685 # URL: github.com/oschwengers/bakta
--- a/test-data/TEST_4/TEST_4.tsv Mon Jul 24 11:22:16 2023 +0000 +++ b/test-data/TEST_4/TEST_4.tsv Sat Sep 16 09:01:39 2023 +0000 @@ -1,5 +1,5 @@ # Annotated with Bakta -# Software: v1.8.1 +# Software: v1.8.2 # Database: v5.0, full # DOI: 10.1099/mgen.0.000685 # URL: github.com/oschwengers/bakta
--- a/test-data/TEST_5/TEST_5.log Mon Jul 24 11:22:16 2023 +0000 +++ /dev/null Thu Jan 01 00:00:00 1970 +0000 @@ -1,81 +0,0 @@ -Bakta v1.8.1 -Options and arguments: - input: /tmp/tmp6wdeee6u/files/0/2/9/dataset_0293aae0-943d-4d1b-af6c-e5ed41b419da.dat - db: /tmp/tmp6wdeee6u/job_working_directory/000/13/working/database_path, version 5.0, full - output: /tmp/tmp6wdeee6u/job_working_directory/000/13/working/bakta_output - tmp directory: /tmp/tmp6wdeee6u/tmp/tmpigp60rnb - prefix: bakta_output - threads: 1 - translation table: 4 - complete replicons: True - skip tRNA: True - skip tmRNA: True - skip rRNA: True - skip ncRNA: True - skip ncRNA region: True - skip CRISPR: True - skip CDS: True - skip sORF: True - skip gap: True - skip oriC/V/T: True - skip plot: True - -parse genome sequences... - imported: 1 - filtered & revised: 1 - plasmids: 1 - -start annotation... -skip tRNA prediction... -skip tmRNA prediction... -skip rRNA prediction... -skip ncRNA prediction... -skip ncRNA region prediction... -skip CRISPR array prediction... -skip CDS prediction... -skip sORF prediction... -skip gap annotation... -skip oriC/T annotation... -apply feature overlap filters... -select features and create locus tags... -selected: 0 -improve annotations... - revised gene symbols: 0 - -genome statistics: - Genome size: 1,330 bp - Contigs/replicons: 1 - GC: 45.2 % - N50: 1,330 - N ratio: 0.0 % - coding density: 0.0 % - -annotation summary: - tRNAs: 0 - tmRNAs: 0 - rRNAs: 0 - ncRNAs: 0 - ncRNA regions: 0 - CRISPR arrays: 0 - CDSs: 0 - hypotheticals: 0 - pseudogenes: 0 - signal peptides: 0 - sORFs: 0 - gaps: 0 - oriCs/oriVs: 0 - oriTs: 0 - -export annotation results to: /tmp/tmp6wdeee6u/job_working_directory/000/13/working/bakta_output - human readable TSV... - GFF3... - INSDC GenBank & EMBL... - genome sequences... - feature nucleotide sequences... - translated CDS sequences... - skip generation of circular genome plot... - machine readable JSON... - genome and annotation summary... - -If you use these results please cite Bakta: https://doi.org/10.1099/mgen.0.000685 -Annotation successfully finished in 0:00 [mm:ss].
--- a/test-data/TEST_5/TEST_5.txt Mon Jul 24 11:22:16 2023 +0000 +++ b/test-data/TEST_5/TEST_5.txt Sat Sep 16 09:01:39 2023 +0000 @@ -24,7 +24,7 @@ oriTs: 0 Bakta: -Software: v1.8.1 +Software: v1.8.2 Database: v5.0, full DOI: 10.1099/mgen.0.000685 URL: github.com/oschwengers/bakta
--- a/test-data/TEST_6/TEST_6.log Mon Jul 24 11:22:16 2023 +0000 +++ /dev/null Thu Jan 01 00:00:00 1970 +0000 @@ -1,107 +0,0 @@ -Bakta v1.8.1 -Options and arguments: - input: /tmp/tmp6wdeee6u/files/4/2/7/dataset_4276a0b6-bcea-42e6-a1e2-9f880300f5a1.dat - db: /tmp/tmp6wdeee6u/job_working_directory/000/15/working/database_path, version 5.0, full - output: /tmp/tmp6wdeee6u/job_working_directory/000/15/working/bakta_output - tmp directory: /tmp/tmp6wdeee6u/tmp/tmpkzvj8z8k - prefix: bakta_output - threads: 1 - translation table: 11 - -parse genome sequences... - imported: 1 - filtered & revised: 1 - plasmids: 1 - -start annotation... -predict tRNAs... - found: 0 -predict tmRNAs... - found: 0 -predict rRNAs... - found: 0 -predict ncRNAs... - found: 0 -predict ncRNA regions... - found: 0 -predict CRISPR arrays... - found: 0 -predict & annotate CDSs... - predicted: 2 - discarded spurious: 0 - revised translational exceptions: 0 - detected IPSs: 0 - found PSCs: 0 - found PSCCs: 0 - lookup annotations... - conduct expert systems... - amrfinder: 0 - protein sequences: 0 - combine annotations and mark hypotheticals... - detect pseudogenes... - pseudogene candidates: 0 - found pseudogenes: 0 -analyze hypothetical proteins: 2 - detected Pfam hits: 0 - calculated proteins statistics - revise special cases... -extract sORF... - potential: 22 - discarded due to overlaps: 2 - discarded spurious: 0 - detected IPSs: 0 - found PSCs: 0 - lookup annotations... - filter and combine annotations... - filtered sORFs: 0 -detect gaps... - found: 0 -detect oriCs/oriVs... - found: 0 -detect oriTs... - found: 0 -apply feature overlap filters... -select features and create locus tags... -selected: 2 -improve annotations... - revised gene symbols: 0 - -genome statistics: - Genome size: 1,330 bp - Contigs/replicons: 1 - GC: 45.2 % - N50: 1,330 - N ratio: 0.0 % - coding density: 62.0 % - -annotation summary: - tRNAs: 0 - tmRNAs: 0 - rRNAs: 0 - ncRNAs: 0 - ncRNA regions: 0 - CRISPR arrays: 0 - CDSs: 2 - hypotheticals: 2 - pseudogenes: 0 - signal peptides: 0 - sORFs: 0 - gaps: 0 - oriCs/oriVs: 0 - oriTs: 0 - -export annotation results to: /tmp/tmp6wdeee6u/job_working_directory/000/15/working/bakta_output - human readable TSV... - GFF3... - INSDC GenBank & EMBL... - genome sequences... - feature nucleotide sequences... - translated CDS sequences... - circular genome plot... - hypothetical TSV... - translated hypothetical CDS sequences... - machine readable JSON... - genome and annotation summary... - -If you use these results please cite Bakta: https://doi.org/10.1099/mgen.0.000685 -Annotation successfully finished in 0:01 [mm:ss].