diff --git a/workflows/bacterial_genomics/bacterial_genome_annotation/.dockstore.yml b/workflows/bacterial_genomics/bacterial_genome_annotation/.dockstore.yml new file mode 100644 index 000000000..009a2f9ef --- /dev/null +++ b/workflows/bacterial_genomics/bacterial_genome_annotation/.dockstore.yml @@ -0,0 +1,19 @@ +version: 1.2 +workflows: +- name: main + subclass: Galaxy + publish: true + primaryDescriptorPath: /bacterial_genome_annotation.ga + testParameterFiles: + - /bacterial_genome_annotation-tests.yml + authors: + - name: ABRomics + email: abromics-support@groupes.france-bioinformatique.fr + - name: abromics-consortium + url: https://www.abromics.fr/ + - name: Pierre Marin + alternateName: pimarin + orcid: 0000-0002-8304-138X + - name: Clea Siguret + alternateName: clsiguret + orcid: 0009-0005-6140-0379 diff --git a/workflows/bacterial_genomics/bacterial_genome_annotation/CHANGELOG.md b/workflows/bacterial_genomics/bacterial_genome_annotation/CHANGELOG.md new file mode 100644 index 000000000..7e0b1137f --- /dev/null +++ b/workflows/bacterial_genomics/bacterial_genome_annotation/CHANGELOG.md @@ -0,0 +1,5 @@ +# Changelog + +## [1.0] - 14-06-2024 + +- First release \ No newline at end of file diff --git a/workflows/bacterial_genomics/bacterial_genome_annotation/README.md b/workflows/bacterial_genomics/bacterial_genome_annotation/README.md new file mode 100644 index 000000000..2b685e657 --- /dev/null +++ b/workflows/bacterial_genomics/bacterial_genome_annotation/README.md @@ -0,0 +1,36 @@ +# Bacterial genome annotation workflow (v1.0) + +This workflow uses assembled bacterial genome fasta files (but can be any fasta file) and executes the following steps: +1. Genomic annotation + - **Bakta** to predict CDS and small proteins (sORF) +2. Integron identification + - **IntegronFinder2** to identify CALIN elements, In0 elements, and complete integrons +3. Plasmid gene identification + - **Plasmidfinder** to identify and typing plasmid sequences +4. Inserted sequence (IS) detection + - **ISEScan** to detect IS elements +5. Aggregating outputs into a single JSON file + - **ToolDistillator** to extract and aggregate information from different tool outputs to JSON parsable files + +## Inputs + +1. Assembled bacterial genome in fasta format. + +## Outputs + +1. Genomic annotation: + - genome annotation in tabular, gff and several other formats + - annotation plot + - nucleotide and protein sequences identified + - summary of genomic identified elements +2. Integron identification: + - integron identification in tabular format and a summary +3. Plasmid gene identification: + - plasmid gene identified and associated blast hits +4. Inserted Element (IS) detection: + - IS element list in tabular format + - is hits in fasta format + - ORF hits in protein and nucleotide fasta format + - IS annotation gff format +5. Aggregating outputs: + - JSON file with information about the outputs of **Bakta**, **IntegronFinder2**, **Plasmidfinder**, **ISEScan** \ No newline at end of file diff --git a/workflows/bacterial_genomics/bacterial_genome_annotation/bacterial_genome_annotation-tests.yml b/workflows/bacterial_genomics/bacterial_genome_annotation/bacterial_genome_annotation-tests.yml new file mode 100644 index 000000000..96a7fc4de --- /dev/null +++ b/workflows/bacterial_genomics/bacterial_genome_annotation/bacterial_genome_annotation-tests.yml @@ -0,0 +1,61 @@ +- doc: Test outline for bacterial_genome_annotation.ga + job: + Input sequence fasta: + class: File + path: https://zenodo.org/records/11488310/files/shovill_contigs_fasta + Select a plasmid detection database: plasmidfinder_81c11f4_2023_12_04 + Select a bacterial genome annotation database: V5.0_2023-02-20 + Select a AMRFinderPlus database: amrfinderplus_V3.12_2024-05-02.2 + outputs: + integronfinder2_logfile_text: + assert: + has_text: + text: "Writing out results for replicon" + integronfinder2_summary: + assert: + has_n_columns: + n: 6 + integronfinder2_results_tabular: + assert: + has_n_columns: + n: 14 + bakta_hypothetical_tabular: + assert: + has_n_columns: + n: 9 + bakta_annotation_json: + assert: + has_text: + text: "aa_hexdigest" + bakta_annotation_tabular: + assert: + has_n_columns: + n: 9 + isescan_results_tabular: + assert: + has_n_columns: + n: 24 + isescan_summary_tabular: + assert: + has_text: + text: "nIS" + isescan_logfile_text: + assert: + has_text: + text: "Both complete and partial IS elements are reported." + plasmidfinder_result_json: + assert: + has_text: + text: "positions_in_contig" + plasmidfinder_results_tabular: + assert: + has_n_columns: + n: 8 + tooldistillator_summarize: + assert: + has_text: + text: "CDS12738(DOp1)" + has_text: + text: "CALIN" + has_text: + text: "insertion_sequence" diff --git a/workflows/bacterial_genomics/bacterial_genome_annotation/bacterial_genome_annotation.ga b/workflows/bacterial_genomics/bacterial_genome_annotation/bacterial_genome_annotation.ga new file mode 100644 index 000000000..72e788846 --- /dev/null +++ b/workflows/bacterial_genomics/bacterial_genome_annotation/bacterial_genome_annotation.ga @@ -0,0 +1,1199 @@ +{ + "a_galaxy_workflow": "true", + "annotation": "Annotation of an assembled bacterial genomes to detect genes, potential plasmids, integrons and Insertion sequence (IS) elements.", + "creator": [ + { + "class": "Person", + "email": "mailto:abromics-support@groupes.france-bioinformatique.fr", + "name": "ABRomics" + }, + { + "class": "Organization", + "name": "abromics-consortium", + "url": "https://www.abromics.fr/" + }, + { + "alternateName": "pimarin", + "class": "Person", + "identifier": "https://orcid.org/0000-0002-8304-138X", + "name": "Pierre Marin", + "alternateName": "pimarin" + }, + { + "alternateName": "clsiguret", + "class": "Person", + "identifier": "https://orcid.org/0009-0005-6140-0379", + "name": "Clea Siguret", + "alternateName": "clsiguret" + } + ], + "format-version": "0.1", + "license": "GPL-3.0-or-later", + "release": "1.0", + "name": "bacterial_genome_annotation", + "steps": { + "0": { + "annotation": "Can be any fasta file.", + "content_id": null, + "errors": null, + "id": 0, + "input_connections": {}, + "inputs": [ + { + "description": "Can be any fasta file.", + "name": "Input sequence fasta" + } + ], + "label": "Input sequence fasta", + "name": "Input dataset", + "outputs": [], + "position": { + "left": 0, + "top": 559.2197431502472 + }, + "tool_id": null, + "tool_state": "{\"optional\": false, \"format\": [\"fasta\"], \"tag\": null}", + "tool_version": null, + "type": "data_input", + "uuid": "8afa880e-a04c-4831-b37b-d0f317f767b0", + "when": null, + "workflow_outputs": [] + }, + "1": { + "annotation": "Select a database to identify plasmids with PlasmidFinder.", + "content_id": null, + "errors": null, + "id": 1, + "input_connections": {}, + "inputs": [ + { + "description": "Select a database to identify plasmids with PlasmidFinder.", + "name": "Select a plasmid detection database" + } + ], + "label": "Select a plasmid detection database", + "name": "Input parameter", + "outputs": [], + "position": { + "left": 9.602014342350742, + "top": 734.3939210886799 + }, + "tool_id": null, + "tool_state": "{\"default\": \"plasmidfinder_81c11f4_2023_12_04\", \"restrictions\": [\"plasmidfinder_314d85f_2023_03_17\",\"81c11f4_2023_12_04/\"], \"parameter_type\": \"text\", \"optional\": true}", + "tool_version": null, + "type": "parameter_input", + "uuid": "66c11ad1-7cd5-40b7-b97f-8d15cc097dd9", + "when": null, + "workflow_outputs": [ + { + "label": null, + "output_name": "output", + "uuid": "a2d4e531-c070-45c1-b56a-be4356aabc79" + } + ] + }, + "2": { + "annotation": "Select a database to predict CDS and small proteins (sORF) with Bakta.", + "content_id": null, + "errors": null, + "id": 2, + "input_connections": {}, + "inputs": [ + { + "description": "Select a database to predict CDS and small proteins (sORF) with Bakta.", + "name": "Select a bacterial genome annotation database" + } + ], + "label": "Select a bacterial genome annotation database", + "name": "Input parameter", + "outputs": [], + "position": { + "left": 21.882601498378413, + "top": 859.5166625976562 + }, + "tool_id": null, + "tool_state": "{\"default\": \"V5.1_2024-01-19\", \"restrictions\": [\"V5.0light_2023-02-20\", \"V5.0_2023-02-20\", \"V5.1_2024-01-19\"], \"parameter_type\": \"text\", \"optional\": true}", + "tool_version": null, + "type": "parameter_input", + "uuid": "4de1f52c-078c-4112-86ad-e4e8f3b62e3a", + "when": null, + "workflow_outputs": [ + { + "label": null, + "output_name": "output", + "uuid": "724dc1d5-6f90-4c1c-915c-99dded697740" + } + ] + }, + "3": { + "annotation": "Selecting this database is not necessary if the bacterial genome database (with Bakta) version is greater than 5.0.", + "content_id": null, + "errors": null, + "id": 3, + "input_connections": {}, + "inputs": [ + { + "description": "Selecting this database is not necessary if the bacterial genome database (with Bakta) version is greater than 5.0.", + "name": "Select a AMRFinderPlus database" + } + ], + "label": "Select a AMRFinderPlus database", + "name": "Input parameter", + "outputs": [], + "position": { + "left": 10.643158620281753, + "top": 995.2631409484753 + }, + "tool_id": null, + "tool_state": "{\"default\": \"amrfinderplus_V3.12_2024-05-02.2\", \"restrictions\": [\"amrfinderplus_V3.12_2024-05-02.2\"], \"parameter_type\": \"text\", \"optional\": true}", + "tool_version": null, + "type": "parameter_input", + "uuid": "aec02a2c-6bf7-476d-91aa-3f1ce49083c7", + "when": null, + "workflow_outputs": [ + { + "label": null, + "output_name": "output", + "uuid": "768e962a-f016-41c6-96c5-4b32b26b4856" + } + ] + }, + "4": { + "annotation": "genomic_annotation_insertionelement_isescan", + "content_id": "toolshed.g2.bx.psu.edu/repos/iuc/isescan/isescan/1.7.2.3+galaxy1", + "errors": null, + "id": 4, + "input_connections": { + "input_file": { + "id": 0, + "output_name": "output" + } + }, + "inputs": [], + "label": "genomic_annotation_insertionelement_isescan", + "name": "ISEScan", + "outputs": [ + { + "name": "logfile", + "type": "txt" + }, + { + "name": "summary", + "type": "tabular" + }, + { + "name": "all_results", + "type": "tabular" + }, + { + "name": "annotation", + "type": "gff" + }, + { + "name": "is_fasta", + "type": "fasta" + }, + { + "name": "orf_fna", + "type": "fasta" + }, + { + "name": "orf_faa", + "type": "fasta" + } + ], + "position": { + "left": 887.7889628790149, + "top": 105.14125185095409 + }, + "post_job_actions": { + "RenameDatasetActionall_results": { + "action_arguments": { + "newname": "isescan_results_tabular" + }, + "action_type": "RenameDatasetAction", + "output_name": "all_results" + }, + "RenameDatasetActionannotation": { + "action_arguments": { + "newname": "isescan_annotation_gff3" + }, + "action_type": "RenameDatasetAction", + "output_name": "annotation" + }, + "RenameDatasetActionis_fasta": { + "action_arguments": { + "newname": "isescan_is_fasta" + }, + "action_type": "RenameDatasetAction", + "output_name": "is_fasta" + }, + "RenameDatasetActionlogfile": { + "action_arguments": { + "newname": "isescan_logfile_text" + }, + "action_type": "RenameDatasetAction", + "output_name": "logfile" + }, + "RenameDatasetActionorf_faa": { + "action_arguments": { + "newname": "isescan_orf_faa" + }, + "action_type": "RenameDatasetAction", + "output_name": "orf_faa" + }, + "RenameDatasetActionorf_fna": { + "action_arguments": { + "newname": "isescan_orf_fasta" + }, + "action_type": "RenameDatasetAction", + "output_name": "orf_fna" + }, + "RenameDatasetActionsummary": { + "action_arguments": { + "newname": "isescan_summary_tabular" + }, + "action_type": "RenameDatasetAction", + "output_name": "summary" + }, + "TagDatasetActionall_results": { + "action_arguments": { + "tags": "isescan_results_tabular" + }, + "action_type": "TagDatasetAction", + "output_name": "all_results" + }, + "TagDatasetActionannotation": { + "action_arguments": { + "tags": "isescan_annotation_gff3" + }, + "action_type": "TagDatasetAction", + "output_name": "annotation" + }, + "TagDatasetActionis_fasta": { + "action_arguments": { + "tags": "isescan_is_fasta" + }, + "action_type": "TagDatasetAction", + "output_name": "is_fasta" + }, + "TagDatasetActionlogfile": { + "action_arguments": { + "tags": "isescan,logfile" + }, + "action_type": "TagDatasetAction", + "output_name": "logfile" + }, + "TagDatasetActionorf_faa": { + "action_arguments": { + "tags": "isescan_orf_faa" + }, + "action_type": "TagDatasetAction", + "output_name": "orf_faa" + }, + "TagDatasetActionorf_fna": { + "action_arguments": { + "tags": "isescan_orf_fasta" + }, + "action_type": "TagDatasetAction", + "output_name": "orf_fna" + }, + "TagDatasetActionsummary": { + "action_arguments": { + "tags": "isescan_summary_tabular" + }, + "action_type": "TagDatasetAction", + "output_name": "summary" + } + }, + "tool_id": "toolshed.g2.bx.psu.edu/repos/iuc/isescan/isescan/1.7.2.3+galaxy1", + "tool_shed_repository": { + "changeset_revision": "9e776e7fab4f", + "name": "isescan", + "owner": "iuc", + "tool_shed": "toolshed.g2.bx.psu.edu" + }, + "tool_state": "{\"input_file\": {\"__class__\": \"ConnectedValue\"}, \"log_activate\": true, \"remove_short_is\": false, \"__page__\": null, \"__rerun_remap_job_id__\": null}", + "tool_version": "1.7.2.3+galaxy1", + "type": "tool", + "uuid": "f589af2f-9dd9-41c0-b7a2-a499c875cb54", + "when": null, + "workflow_outputs": [ + { + "label": "isescan_summary_tabular", + "output_name": "summary", + "uuid": "a09e2ed7-5b31-4beb-9923-d5ec6910da16" + }, + { + "label": "isescan_annotation_gff3", + "output_name": "annotation", + "uuid": "de82533b-90f8-470d-80a2-e1559be93f0d" + }, + { + "label": "isescan_logfile_text", + "output_name": "logfile", + "uuid": "c0539e24-831e-406f-a5d2-3dd52845a5d7" + }, + { + "label": "isescan_results_tabular", + "output_name": "all_results", + "uuid": "24f7dee0-f50a-4444-83f4-b09623a4a993" + }, + { + "label": "isescan_orf_faa", + "output_name": "orf_faa", + "uuid": "c74754f5-e011-4f55-801f-feeab8dd777c" + }, + { + "label": "isescan_is_fasta", + "output_name": "is_fasta", + "uuid": "a89b0159-ccef-4c10-9b17-d5da62312bda" + }, + { + "label": "isescan_orf_fasta", + "output_name": "orf_fna", + "uuid": "1a91afd7-104d-4807-bffa-61c5df646b85" + } + ] + }, + "5": { + "annotation": "genomic_annotation_integron", + "content_id": "toolshed.g2.bx.psu.edu/repos/iuc/integron_finder/integron_finder/2.0.3+galaxy0", + "errors": null, + "id": 5, + "input_connections": { + "sequence": { + "id": 0, + "output_name": "output" + } + }, + "inputs": [ + { + "description": "runtime parameter for tool Integron Finder", + "name": "topology_file" + } + ], + "label": "genomic_annotation_integron", + "name": "Integron Finder", + "outputs": [ + { + "name": "integron_log", + "type": "txt" + }, + { + "name": "integrons_table", + "type": "tsv" + }, + { + "name": "summary", + "type": "tsv" + } + ], + "position": { + "left": 581.3510244512896, + "top": 719.4853608141518 + }, + "post_job_actions": { + "RenameDatasetActionintegron_log": { + "action_arguments": { + "newname": "integronfinder2_logfile_text" + }, + "action_type": "RenameDatasetAction", + "output_name": "integron_log" + }, + "RenameDatasetActionintegrons_table": { + "action_arguments": { + "newname": "integronfinder2_results_tabular" + }, + "action_type": "RenameDatasetAction", + "output_name": "integrons_table" + }, + "RenameDatasetActionsummary": { + "action_arguments": { + "newname": "integronfinder2_summary" + }, + "action_type": "RenameDatasetAction", + "output_name": "summary" + }, + "TagDatasetActionintegron_log": { + "action_arguments": { + "tags": "integronfinder,logfile" + }, + "action_type": "TagDatasetAction", + "output_name": "integron_log" + }, + "TagDatasetActionintegrons_table": { + "action_arguments": { + "tags": "integronfinder2_results_tabular" + }, + "action_type": "TagDatasetAction", + "output_name": "integrons_table" + }, + "TagDatasetActionsummary": { + "action_arguments": { + "tags": "integronfinder2_summary" + }, + "action_type": "TagDatasetAction", + "output_name": "summary" + } + }, + "tool_id": "toolshed.g2.bx.psu.edu/repos/iuc/integron_finder/integron_finder/2.0.3+galaxy0", + "tool_shed_repository": { + "changeset_revision": "392f100eebcd", + "name": "integron_finder", + "owner": "iuc", + "tool_shed": "toolshed.g2.bx.psu.edu" + }, + "tool_state": "{\"gbk\": false, \"local_max\": true, \"no_logfile\": false, \"pdf\": false, \"promoter_attI\": true, \"sequence\": {\"__class__\": \"ConnectedValue\"}, \"settings\": {\"attc_settings\": {\"dist_thresh\": \"4000\", \"calin_threshold\": \"2\", \"max_attc_size\": \"200\", \"min_attc_size\": \"40\", \"keep_palindromes\": false, \"covar_matrix\": {\"__class__\": \"RuntimeValue\"}}, \"protein_settings\": {\"no_proteins\": false, \"union_integrases\": false, \"func_annot\": false}}, \"topology_file\": {\"__class__\": \"RuntimeValue\"}, \"type_replicon\": null, \"__page__\": null, \"__rerun_remap_job_id__\": null}", + "tool_version": "2.0.3+galaxy0", + "type": "tool", + "uuid": "0f39c064-cac7-4ee7-9f37-94b7717a033e", + "when": null, + "workflow_outputs": [ + { + "label": "integronfinder2_logfile_text", + "output_name": "integron_log", + "uuid": "dca60f87-9f7a-4631-b197-62ca54f7bafe" + }, + { + "label": "integronfinder2_summary", + "output_name": "summary", + "uuid": "b96d90c3-7678-41b8-9b01-61d5c9da80bc" + }, + { + "label": "integronfinder2_results_tabular", + "output_name": "integrons_table", + "uuid": "cb38191b-3a0e-43d3-823a-0c9563e39d66" + } + ] + }, + "6": { + "annotation": "genomic_annotation_plasmid_plasmidfinder", + "content_id": "toolshed.g2.bx.psu.edu/repos/iuc/plasmidfinder/plasmidfinder/2.1.6+galaxy1", + "errors": null, + "id": 6, + "input_connections": { + "input|database_name": { + "id": 1, + "output_name": "output" + }, + "input|input_file": { + "id": 0, + "output_name": "output" + } + }, + "inputs": [], + "label": "genomic_annotation_plasmid_plasmidfinder", + "name": "PlasmidFinder", + "outputs": [ + { + "name": "json_file", + "type": "json" + }, + { + "name": "hit_file", + "type": "fasta" + }, + { + "name": "plasmid_file", + "type": "fasta" + }, + { + "name": "result_file", + "type": "tabular" + }, + { + "name": "raw_file", + "type": "txt" + } + ], + "position": { + "left": 469.0425884161387, + "top": 0 + }, + "post_job_actions": { + "RenameDatasetActionhit_file": { + "action_arguments": { + "newname": "plasmidfinder_hit_genome_fasta" + }, + "action_type": "RenameDatasetAction", + "output_name": "hit_file" + }, + "RenameDatasetActionjson_file": { + "action_arguments": { + "newname": "plasmidfinder_result_json" + }, + "action_type": "RenameDatasetAction", + "output_name": "json_file" + }, + "RenameDatasetActionplasmid_file": { + "action_arguments": { + "newname": "plasmidfinder_hit_reference_fasta" + }, + "action_type": "RenameDatasetAction", + "output_name": "plasmid_file" + }, + "RenameDatasetActionraw_file": { + "action_arguments": { + "newname": "plasmidfinder_results_raw" + }, + "action_type": "RenameDatasetAction", + "output_name": "raw_file" + }, + "RenameDatasetActionresult_file": { + "action_arguments": { + "newname": "plasmidfinder_results_tabular" + }, + "action_type": "RenameDatasetAction", + "output_name": "result_file" + }, + "TagDatasetActionhit_file": { + "action_arguments": { + "tags": "plasmidfinder_hit_genome_fasta" + }, + "action_type": "TagDatasetAction", + "output_name": "hit_file" + }, + "TagDatasetActionjson_file": { + "action_arguments": { + "tags": "plasmidfinder_result_json" + }, + "action_type": "TagDatasetAction", + "output_name": "json_file" + }, + "TagDatasetActionplasmid_file": { + "action_arguments": { + "tags": "plasmidfinder_hit_reference_fasta" + }, + "action_type": "TagDatasetAction", + "output_name": "plasmid_file" + }, + "TagDatasetActionraw_file": { + "action_arguments": { + "tags": "plasmidfinder_results_raw" + }, + "action_type": "TagDatasetAction", + "output_name": "raw_file" + }, + "TagDatasetActionresult_file": { + "action_arguments": { + "tags": "plasmidfinder_results_tabular" + }, + "action_type": "TagDatasetAction", + "output_name": "result_file" + } + }, + "tool_id": "toolshed.g2.bx.psu.edu/repos/iuc/plasmidfinder/plasmidfinder/2.1.6+galaxy1", + "tool_shed_repository": { + "changeset_revision": "7075b7a5441b", + "name": "plasmidfinder", + "owner": "iuc", + "tool_shed": "toolshed.g2.bx.psu.edu" + }, + "tool_state": "{\"input\": {\"input_file\": {\"__class__\": \"ConnectedValue\"}, \"database_name\": {\"__class__\": \"ConnectedValue\"}}, \"options\": {\"min_cov\": \"0.6\", \"threshold\": \"0.95\"}, \"output_files\": {\"output_selection\": [\"hit_fasta\", \"plasmid_fasta\", \"result_tsv\", \"result_txt\", \"data_json\"]}, \"__page__\": null, \"__rerun_remap_job_id__\": null}", + "tool_version": "2.1.6+galaxy1", + "type": "tool", + "uuid": "0cbd7d74-9525-4fc4-9518-836c99f6d397", + "when": null, + "workflow_outputs": [ + { + "label": "plasmidfinder_results_tabular", + "output_name": "result_file", + "uuid": "696867f7-0700-4ca5-bee4-bf405f44f6fa" + }, + { + "label": "plasmidfinder_result_json", + "output_name": "json_file", + "uuid": "1449c8c3-9621-4ba2-b32e-29a597a63f2d" + }, + { + "label": "plasmidfinder_results_raw", + "output_name": "raw_file", + "uuid": "e4c42f08-1e32-40e0-a0f0-09037299c4a7" + }, + { + "label": "plasmidfinder_hit_genome_fasta", + "output_name": "hit_file", + "uuid": "2924588e-064d-4c31-9011-ef9cfc646c6e" + }, + { + "label": "plasmidfinder_hit_reference_fasta", + "output_name": "plasmid_file", + "uuid": "b70ea191-97da-4e59-b14c-3988284e552e" + } + ] + }, + "7": { + "annotation": "", + "content_id": "toolshed.g2.bx.psu.edu/repos/iuc/bakta/bakta/1.9.3+galaxy0", + "errors": null, + "id": 7, + "input_connections": { + "input_option|amrfinder_db_select": { + "id": 3, + "output_name": "output" + }, + "input_option|bakta_db_select": { + "id": 2, + "output_name": "output" + }, + "input_option|input_file": { + "id": 0, + "output_name": "output" + } + }, + "inputs": [ + { + "description": "runtime parameter for tool Bakta", + "name": "annotation" + }, + { + "description": "runtime parameter for tool Bakta", + "name": "annotation" + }, + { + "description": "runtime parameter for tool Bakta", + "name": "annotation" + }, + { + "description": "runtime parameter for tool Bakta", + "name": "annotation" + }, + { + "description": "runtime parameter for tool Bakta", + "name": "input_option" + } + ], + "label": null, + "name": "Bakta", + "outputs": [ + { + "name": "annotation_tsv", + "type": "tabular" + }, + { + "name": "annotation_gff3", + "type": "gff3" + }, + { + "name": "annotation_gbff", + "type": "tabular" + }, + { + "name": "annotation_embl", + "type": "tabular" + }, + { + "name": "annotation_fna", + "type": "fasta" + }, + { + "name": "annotation_ffn", + "type": "fasta" + }, + { + "name": "annotation_faa", + "type": "fasta" + }, + { + "name": "hypotheticals_tsv", + "type": "tabular" + }, + { + "name": "hypotheticals_faa", + "type": "fasta" + }, + { + "name": "summary_txt", + "type": "txt" + }, + { + "name": "annotation_json", + "type": "json" + }, + { + "name": "annotation_plot", + "type": "svg" + } + ], + "position": { + "left": 1035.0012031530584, + "top": 927.9172491992002 + }, + "post_job_actions": { + "RenameDatasetActionannotation_embl": { + "action_arguments": { + "newname": "bakta_annotation_embl" + }, + "action_type": "RenameDatasetAction", + "output_name": "annotation_embl" + }, + "RenameDatasetActionannotation_faa": { + "action_arguments": { + "newname": "bakta_aminoacid_sequence_faa" + }, + "action_type": "RenameDatasetAction", + "output_name": "annotation_faa" + }, + "RenameDatasetActionannotation_ffn": { + "action_arguments": { + "newname": "bakta_nucleotide_sequence_fasta" + }, + "action_type": "RenameDatasetAction", + "output_name": "annotation_ffn" + }, + "RenameDatasetActionannotation_fna": { + "action_arguments": { + "newname": "bakta_assembly_fasta" + }, + "action_type": "RenameDatasetAction", + "output_name": "annotation_fna" + }, + "RenameDatasetActionannotation_gbff": { + "action_arguments": { + "newname": "bakta_annotation_gbff" + }, + "action_type": "RenameDatasetAction", + "output_name": "annotation_gbff" + }, + "RenameDatasetActionannotation_gff3": { + "action_arguments": { + "newname": "bakta_annotation_gff3" + }, + "action_type": "RenameDatasetAction", + "output_name": "annotation_gff3" + }, + "RenameDatasetActionannotation_json": { + "action_arguments": { + "newname": "bakta_annotation_json" + }, + "action_type": "RenameDatasetAction", + "output_name": "annotation_json" + }, + "RenameDatasetActionannotation_plot": { + "action_arguments": { + "newname": "bakta_annotation_plot" + }, + "action_type": "RenameDatasetAction", + "output_name": "annotation_plot" + }, + "RenameDatasetActionannotation_tsv": { + "action_arguments": { + "newname": "bakta_annotation_tabular" + }, + "action_type": "RenameDatasetAction", + "output_name": "annotation_tsv" + }, + "RenameDatasetActionhypotheticals_faa": { + "action_arguments": { + "newname": "bakta_hypothetical_faa" + }, + "action_type": "RenameDatasetAction", + "output_name": "hypotheticals_faa" + }, + "RenameDatasetActionhypotheticals_tsv": { + "action_arguments": { + "newname": "bakta_hypothetical_tabular" + }, + "action_type": "RenameDatasetAction", + "output_name": "hypotheticals_tsv" + }, + "RenameDatasetActionsummary_txt": { + "action_arguments": { + "newname": "bakta_summary_text" + }, + "action_type": "RenameDatasetAction", + "output_name": "summary_txt" + }, + "TagDatasetActionannotation_embl": { + "action_arguments": { + "tags": "bakta_annotation_embl" + }, + "action_type": "TagDatasetAction", + "output_name": "annotation_embl" + }, + "TagDatasetActionannotation_faa": { + "action_arguments": { + "tags": "bakta_aminoacid_sequence_faa" + }, + "action_type": "TagDatasetAction", + "output_name": "annotation_faa" + }, + "TagDatasetActionannotation_ffn": { + "action_arguments": { + "tags": "bakta_nucleotide_sequence_fasta" + }, + "action_type": "TagDatasetAction", + "output_name": "annotation_ffn" + }, + "TagDatasetActionannotation_fna": { + "action_arguments": { + "tags": "bakta_assembly_fasta" + }, + "action_type": "TagDatasetAction", + "output_name": "annotation_fna" + }, + "TagDatasetActionannotation_gbff": { + "action_arguments": { + "tags": "bakta_annotation_gbff" + }, + "action_type": "TagDatasetAction", + "output_name": "annotation_gbff" + }, + "TagDatasetActionannotation_gff3": { + "action_arguments": { + "tags": "bakta_annotation_gff3" + }, + "action_type": "TagDatasetAction", + "output_name": "annotation_gff3" + }, + "TagDatasetActionannotation_json": { + "action_arguments": { + "tags": "bakta_annotation_json" + }, + "action_type": "TagDatasetAction", + "output_name": "annotation_json" + }, + "TagDatasetActionannotation_plot": { + "action_arguments": { + "tags": "bakta_annotation_plot" + }, + "action_type": "TagDatasetAction", + "output_name": "annotation_plot" + }, + "TagDatasetActionannotation_tsv": { + "action_arguments": { + "tags": "bakta_annotation_tabular" + }, + "action_type": "TagDatasetAction", + "output_name": "annotation_tsv" + }, + "TagDatasetActionhypotheticals_faa": { + "action_arguments": { + "tags": "bakta_hypothetical_faa" + }, + "action_type": "TagDatasetAction", + "output_name": "hypotheticals_faa" + }, + "TagDatasetActionhypotheticals_tsv": { + "action_arguments": { + "tags": "bakta_hypothetical_tabular" + }, + "action_type": "TagDatasetAction", + "output_name": "hypotheticals_tsv" + }, + "TagDatasetActionsummary_txt": { + "action_arguments": { + "tags": "bakta_summary_text" + }, + "action_type": "TagDatasetAction", + "output_name": "summary_txt" + } + }, + "tool_id": "toolshed.g2.bx.psu.edu/repos/iuc/bakta/bakta/1.9.3+galaxy0", + "tool_shed_repository": { + "changeset_revision": "ba6990f72184", + "name": "bakta", + "owner": "iuc", + "tool_shed": "toolshed.g2.bx.psu.edu" + }, + "tool_state": "{\"annotation\": {\"complete\": false, \"prodigal\": {\"__class__\": \"RuntimeValue\"}, \"translation_table\": \"11\", \"keep_contig_headers\": false, \"replicons\": {\"__class__\": \"RuntimeValue\"}, \"compliant\": false, \"proteins\": {\"__class__\": \"RuntimeValue\"}, \"meta\": false, \"regions\": {\"__class__\": \"RuntimeValue\"}}, \"input_option\": {\"input_file\": {\"__class__\": \"RuntimeValue\"}, \"min_contig_length\": null, \"bakta_db_select\": {\"__class__\": \"ConnectedValue\"}, \"amrfinder_db_select\": {\"__class__\": \"ConnectedValue\"}}, \"organism\": {\"genus\": null, \"species\": null, \"strain\": null, \"plasmid\": null}, \"output_files\": {\"output_selection\": [\"file_tsv\", \"file_gff3\", \"file_ffn\", \"file_plot\", \"file_gbff\", \"file_embl\", \"file_fna\", \"file_faa\", \"hypo_tsv\", \"hypo_fa\", \"file_json\", \"sum_txt\"]}, \"workflow\": {\"skip_analysis\": null}, \"__page__\": null, \"__rerun_remap_job_id__\": null}", + "tool_version": "1.9.3+galaxy0", + "type": "tool", + "uuid": "0a32dcad-f456-460e-9e6f-9e306a8fd515", + "when": null, + "workflow_outputs": [ + { + "label": "bakta_nucleotide_sequence_fasta", + "output_name": "annotation_ffn", + "uuid": "31d239a4-5065-49fb-9989-8b83f3b53642" + }, + { + "label": "bakta_aminoacid_sequence_faa", + "output_name": "annotation_faa", + "uuid": "3827a853-ad2a-48ad-89dd-648883467abd" + }, + { + "label": "bakta_hypothetical_tabular", + "output_name": "hypotheticals_tsv", + "uuid": "db4f4056-01ba-42ed-b053-e3c6086011ab" + }, + { + "label": "bakta_assembly_fasta", + "output_name": "annotation_fna", + "uuid": "7d88510c-813b-40f7-8fd6-5b079ff11ab2" + }, + { + "label": "bakta_annotation_tabular", + "output_name": "annotation_tsv", + "uuid": "b84d6b52-d921-42d5-a7df-4abbd523bdc7" + }, + { + "label": "bakta_annotation_gff3", + "output_name": "annotation_gff3", + "uuid": "3af64163-439d-4241-b950-f540e6f18134" + }, + { + "label": "bakta_annotation_gbff", + "output_name": "annotation_gbff", + "uuid": "5a6c32eb-42ca-45c0-afc9-a12cc777247d" + }, + { + "label": "bakta_annotation_embl", + "output_name": "annotation_embl", + "uuid": "e3b70765-90ee-47e9-8870-411e6a263963" + }, + { + "label": "bakta_hypothetical_faa", + "output_name": "hypotheticals_faa", + "uuid": "4aa10d6e-0577-45b3-8759-63f1e0712b0e" + }, + { + "label": "bakta_annotation_json", + "output_name": "annotation_json", + "uuid": "4ab292e3-0eb7-4746-b2aa-e03c2679aa2b" + }, + { + "label": "bakta_annotation_plot", + "output_name": "annotation_plot", + "uuid": "c5b8dc03-6ee6-4d0b-8703-f92b15165d77" + }, + { + "label": "bakta_summary_text", + "output_name": "summary_txt", + "uuid": "12e3ec34-9d84-4924-a8a6-0bc41a9f23f1" + } + ] + }, + "8": { + "annotation": "ToolDistillator extracts results from tools and creates a JSON file for each tool", + "content_id": "toolshed.g2.bx.psu.edu/repos/iuc/tooldistillator/tooldistillator/0.8.5.0+galaxy0", + "errors": null, + "id": 8, + "input_connections": { + "tool_section|tools_0|select_tool|genome_hit_path": { + "id": 6, + "output_name": "hit_file" + }, + "tool_section|tools_0|select_tool|input": { + "id": 6, + "output_name": "json_file" + }, + "tool_section|tools_0|select_tool|plasmid_hit_path": { + "id": 6, + "output_name": "plasmid_file" + }, + "tool_section|tools_0|select_tool|plasmid_result_tabular_path": { + "id": 6, + "output_name": "result_file" + }, + "tool_section|tools_0|select_tool|reference_database_version": { + "id": 1, + "output_name": "output" + }, + "tool_section|tools_1|select_tool|annotation_path": { + "id": 4, + "output_name": "annotation" + }, + "tool_section|tools_1|select_tool|input": { + "id": 4, + "output_name": "all_results" + }, + "tool_section|tools_1|select_tool|is_fna_path": { + "id": 4, + "output_name": "is_fasta" + }, + "tool_section|tools_1|select_tool|orf_faa_path": { + "id": 4, + "output_name": "orf_faa" + }, + "tool_section|tools_1|select_tool|orf_fna_path": { + "id": 4, + "output_name": "orf_fna" + }, + "tool_section|tools_1|select_tool|summary_path": { + "id": 4, + "output_name": "summary" + }, + "tool_section|tools_2|select_tool|input": { + "id": 5, + "output_name": "integrons_table" + }, + "tool_section|tools_2|select_tool|summary_file_path": { + "id": 5, + "output_name": "summary" + }, + "tool_section|tools_3|select_tool|amino_acid_annotation_path": { + "id": 7, + "output_name": "annotation_faa" + }, + "tool_section|tools_3|select_tool|annotation_embl_path": { + "id": 7, + "output_name": "annotation_embl" + }, + "tool_section|tools_3|select_tool|annotation_genbank_path": { + "id": 7, + "output_name": "annotation_gbff" + }, + "tool_section|tools_3|select_tool|annotation_tabular_path": { + "id": 7, + "output_name": "annotation_tsv" + }, + "tool_section|tools_3|select_tool|contig_sequences_path": { + "id": 7, + "output_name": "annotation_fna" + }, + "tool_section|tools_3|select_tool|gff_file_path": { + "id": 7, + "output_name": "annotation_gff3" + }, + "tool_section|tools_3|select_tool|hypothetical_protein_path": { + "id": 7, + "output_name": "hypotheticals_faa" + }, + "tool_section|tools_3|select_tool|hypothetical_tabular_path": { + "id": 7, + "output_name": "hypotheticals_tsv" + }, + "tool_section|tools_3|select_tool|input": { + "id": 7, + "output_name": "annotation_json" + }, + "tool_section|tools_3|select_tool|nucleotide_annotation_path": { + "id": 7, + "output_name": "annotation_ffn" + }, + "tool_section|tools_3|select_tool|plot_file_path": { + "id": 7, + "output_name": "annotation_plot" + }, + "tool_section|tools_3|select_tool|reference_database_version": { + "id": 2, + "output_name": "output" + }, + "tool_section|tools_3|select_tool|summary_result_path": { + "id": 7, + "output_name": "summary_txt" + } + }, + "inputs": [], + "label": "ToolDistillator", + "name": "ToolDistillator", + "outputs": [ + { + "name": "output_json", + "type": "input" + } + ], + "position": { + "left": 1521.7059634117236, + "top": 515.5903476661389 + }, + "post_job_actions": { + "RenameDatasetActionoutput_json": { + "action_arguments": { + "newname": "tooldistillator_results" + }, + "action_type": "RenameDatasetAction", + "output_name": "output_json" + }, + "TagDatasetActionoutput_json": { + "action_arguments": { + "tags": "tooldistillator_results" + }, + "action_type": "TagDatasetAction", + "output_name": "output_json" + } + }, + "tool_id": "toolshed.g2.bx.psu.edu/repos/iuc/tooldistillator/tooldistillator/0.8.5.0+galaxy0", + "tool_shed_repository": { + "changeset_revision": "65a69de1e294", + "name": "tooldistillator", + "owner": "iuc", + "tool_shed": "toolshed.g2.bx.psu.edu" + }, + "tool_state": "{\"log\": false, \"tool_section\": {\"tools\": [{\"__index__\": 0, \"select_tool\": {\"tool_list\": \"plasmidfinder\", \"__current_case__\": 10, \"input\": {\"__class__\": \"ConnectedValue\"}, \"plasmid_result_tabular_path\": {\"__class__\": \"ConnectedValue\"}, \"genome_hit_path\": {\"__class__\": \"ConnectedValue\"}, \"plasmid_hit_path\": {\"__class__\": \"ConnectedValue\"}, \"analysis_software_version\": \"2.1.6\", \"reference_database_version\": {\"__class__\": \"ConnectedValue\"}}}, {\"__index__\": 1, \"select_tool\": {\"tool_list\": \"isescan\", \"__current_case__\": 7, \"input\": {\"__class__\": \"ConnectedValue\"}, \"summary_path\": {\"__class__\": \"ConnectedValue\"}, \"annotation_path\": {\"__class__\": \"ConnectedValue\"}, \"orf_fna_path\": {\"__class__\": \"ConnectedValue\"}, \"orf_faa_path\": {\"__class__\": \"ConnectedValue\"}, \"is_fna_path\": {\"__class__\": \"ConnectedValue\"}, \"analysis_software_version\": \"1.7.2.3\", \"reference_database_version\": null}}, {\"__index__\": 2, \"select_tool\": {\"tool_list\": \"integronfinder2\", \"__current_case__\": 6, \"input\": {\"__class__\": \"ConnectedValue\"}, \"summary_file_path\": {\"__class__\": \"ConnectedValue\"}, \"analysis_software_version\": \"2.0.2\", \"reference_database_version\": null}}, {\"__index__\": 3, \"select_tool\": {\"tool_list\": \"bakta\", \"__current_case__\": 2, \"input\": {\"__class__\": \"ConnectedValue\"}, \"annotation_tabular_path\": {\"__class__\": \"ConnectedValue\"}, \"annotation_genbank_path\": {\"__class__\": \"ConnectedValue\"}, \"annotation_embl_path\": {\"__class__\": \"ConnectedValue\"}, \"contig_sequences_path\": {\"__class__\": \"ConnectedValue\"}, \"hypothetical_protein_path\": {\"__class__\": \"ConnectedValue\"}, \"hypothetical_tabular_path\": {\"__class__\": \"ConnectedValue\"}, \"plot_file_path\": {\"__class__\": \"ConnectedValue\"}, \"summary_result_path\": {\"__class__\": \"ConnectedValue\"}, \"nucleotide_annotation_path\": {\"__class__\": \"ConnectedValue\"}, \"amino_acid_annotation_path\": {\"__class__\": \"ConnectedValue\"}, \"gff_file_path\": {\"__class__\": \"ConnectedValue\"}, \"analysis_software_version\": \"1.9.3\", \"reference_database_version\": {\"__class__\": \"ConnectedValue\"}}}]}, \"__page__\": null, \"__rerun_remap_job_id__\": null}", + "tool_version": "0.8.5.0+galaxy0", + "type": "tool", + "uuid": "678bdbfe-7a3a-4a91-8ea7-1cb17f53daa6", + "when": null, + "workflow_outputs": [ + { + "label": "tooldistillator_results", + "output_name": "output_json", + "uuid": "a8db4b4d-8573-45bf-990c-304868ad5150" + } + ] + }, + "9": { + "annotation": "ToolDistillator summarize groups all JSON file into a unique JSON file", + "content_id": "toolshed.g2.bx.psu.edu/repos/iuc/tooldistillator_summarize/tooldistillator_summarize/0.8.5.0+galaxy0", + "errors": null, + "id": 9, + "input_connections": { + "summarize_data": { + "id": 8, + "output_name": "output_json" + } + }, + "inputs": [], + "label": "ToolDistillator summarize", + "name": "ToolDistillator Summarize", + "outputs": [ + { + "name": "summary_json", + "type": "json" + } + ], + "position": { + "left": 1999.7866424448703, + "top": 1179.174084225585 + }, + "post_job_actions": { + "RenameDatasetActionsummary_json": { + "action_arguments": { + "newname": "tooldistillator_summarize" + }, + "action_type": "RenameDatasetAction", + "output_name": "summary_json" + }, + "TagDatasetActionsummary_json": { + "action_arguments": { + "tags": "tooldistillator_summarize" + }, + "action_type": "TagDatasetAction", + "output_name": "summary_json" + } + }, + "tool_id": "toolshed.g2.bx.psu.edu/repos/iuc/tooldistillator_summarize/tooldistillator_summarize/0.8.5.0+galaxy0", + "tool_shed_repository": { + "changeset_revision": "6ff67d2860e1", + "name": "tooldistillator_summarize", + "owner": "iuc", + "tool_shed": "toolshed.g2.bx.psu.edu" + }, + "tool_state": "{\"summarize_data\": {\"__class__\": \"ConnectedValue\"}, \"__page__\": null, \"__rerun_remap_job_id__\": null}", + "tool_version": "0.8.5.0+galaxy0", + "type": "tool", + "uuid": "3427b1f1-79ce-4ade-a350-baf15ac250c2", + "when": null, + "workflow_outputs": [ + { + "label": "tooldistillator_summarize", + "output_name": "summary_json", + "uuid": "96d63721-4cb5-4879-8984-4eeba8dec36b" + } + ] + } + }, + "tags": [ + "Genomics", + "fasta", + "ABRomics", + "bacterial-genomics", + "Annotation", + "genome-annotation" + ], + "uuid": "d55a9e46-a205-4143-b92f-3783499063ed", + "version": 1 +} \ No newline at end of file