From 88c0cf7309a0122b8308e7615bc5a48d7b874e86 Mon Sep 17 00:00:00 2001 From: SantaMcCloud Date: Sun, 26 Apr 2026 23:32:16 +0200 Subject: [PATCH 1/3] Add viral detection from bulk metagenomes --- .../.dockstore.yml | 12 + .../CHANGELOG.md | 5 + .../README.md | 81 + ...l-detection-from-bulk-metagenomes-test.yml | 139 ++ .../viral-detection-from-bulk-metagenomes.ga | 1659 +++++++++++++++++ 5 files changed, 1896 insertions(+) create mode 100755 workflows/microbiome/viral-detection-from-bulk-metagenomes/.dockstore.yml create mode 100644 workflows/microbiome/viral-detection-from-bulk-metagenomes/CHANGELOG.md create mode 100644 workflows/microbiome/viral-detection-from-bulk-metagenomes/README.md create mode 100644 workflows/microbiome/viral-detection-from-bulk-metagenomes/viral-detection-from-bulk-metagenomes-test.yml create mode 100644 workflows/microbiome/viral-detection-from-bulk-metagenomes/viral-detection-from-bulk-metagenomes.ga diff --git a/workflows/microbiome/viral-detection-from-bulk-metagenomes/.dockstore.yml b/workflows/microbiome/viral-detection-from-bulk-metagenomes/.dockstore.yml new file mode 100755 index 0000000000..445d37b4dc --- /dev/null +++ b/workflows/microbiome/viral-detection-from-bulk-metagenomes/.dockstore.yml @@ -0,0 +1,12 @@ +version: 1.2 +workflows: +- name: main + subclass: Galaxy + publish: true + primaryDescriptorPath: /viral-detection-from-bulk-metagenomes.ga + testParameterFiles: + - /viral-detection-from-bulk-metagenomes-test.yml + authors: + - name: Mina Hojat Ansari + orcid: 0000-0002-3602-7884 + - name: "Niklas Stahl" diff --git a/workflows/microbiome/viral-detection-from-bulk-metagenomes/CHANGELOG.md b/workflows/microbiome/viral-detection-from-bulk-metagenomes/CHANGELOG.md new file mode 100644 index 0000000000..bfa513fbc2 --- /dev/null +++ b/workflows/microbiome/viral-detection-from-bulk-metagenomes/CHANGELOG.md @@ -0,0 +1,5 @@ +# Changelog + +## [1.0] - 2026-26-04 + +- First release diff --git a/workflows/microbiome/viral-detection-from-bulk-metagenomes/README.md b/workflows/microbiome/viral-detection-from-bulk-metagenomes/README.md new file mode 100644 index 0000000000..a9fa4b4e69 --- /dev/null +++ b/workflows/microbiome/viral-detection-from-bulk-metagenomes/README.md @@ -0,0 +1,81 @@ +# Viral detection from bulk metagenomes + +## Overview + +This workflow identifies viral contigs from metagenomic assemblies using **geNomad** and performs downstream analyses including **taxonomy**, **functional annotation**, **binning**, **host prediction**, and **coverage estimation**. + +--- + +## Inputs + +- **Assembled contigs** (FASTA, collection) +- **Trimmed paired-end reads** (list:paired) + +### Requirements + +- Reads must be quality-controlled (trimmed, adapters removed) +- Host contamination should be removed + +--- + +## Workflow steps + +### 1. Viral contig prediction +Viral sequences are identified from assembled contigs using **geNomad**. + +### 2. Provirus detection and refinement +**CheckV** is used to identify proviruses. Extracted proviruses are re-analysed with **geNomad**. + +### 3. Merging viral predictions +Viral contigs from both geNomad runs are combined. + +### 4. Clustering and dereplication +Redundant sequences are removed using **MMseqs2** clustering. + +### 5. Quality assessment and filtering +**CheckV** is used to assess sequence quality. Only sequences classified as: + +- Complete +- High-quality +- Medium-quality + +are retained for downstream analysis. + +### 6. Host prediction +Viral contigs are analysed using **iPHoP**. + +### 7. Functional annotation +Viral genomes are annotated using **Pharokka**. + +### 8. Coverage estimation +Reads are mapped using **Bowtie2** and coverage is calculated with **CoverM**. + +### 9. Viral genome binning (vMAGs) +Viral contigs and coverage profiles are used by **vRhyme** to recover viral genomes. + +--- + +## Outputs + +- Viral contigs (geNomad) +- Taxonomy annotations +- Gene annotations +- Nonredundant viral sequences +- CheckV quality reports +- Filtered viral contigs +- Host predictions (iPHoP) +- Functional annotations (Pharokka) +- Coverage table (CoverM) +- vMAG bins (vRhyme) + +--- + +## Notes + +- Only **medium- and high-quality sequences** are used for biological interpretation + +--- + +## License + +MIT License \ No newline at end of file diff --git a/workflows/microbiome/viral-detection-from-bulk-metagenomes/viral-detection-from-bulk-metagenomes-test.yml b/workflows/microbiome/viral-detection-from-bulk-metagenomes/viral-detection-from-bulk-metagenomes-test.yml new file mode 100644 index 0000000000..85e6db94c7 --- /dev/null +++ b/workflows/microbiome/viral-detection-from-bulk-metagenomes/viral-detection-from-bulk-metagenomes-test.yml @@ -0,0 +1,139 @@ +- doc: Test for viral-detection-from-bulk-metagenomes + job: + Assembled contigs: + class: Collection + collection_type: list + elements: + - class: File + identifier: SRR24759598 + location: https://zenodo.org/records/19798600/files/SRR24759598.fasta + - class: File + identifier: SRR24759616 + location: https://zenodo.org/records/19798600/files/SRR24759616.fasta + Trimmed reads: + class: Collection + collection_type: list:paired + elements: + - class: Collection + type: paired + identifier: SRR24759598 + elements: + - class: File + identifier: forward + location: https://zenodo.org/records/19798600/files/SRR24759598_forward.fastqsanger.gz + - class: File + identifier: reverse + location: https://zenodo.org/records/19798600/files/SRR24759598_reverse.fastqsanger.gz + - class: Collection + type: paired + identifier: SRR24759616 + elements: + - class: File + identifier: forward + location: https://zenodo.org/records/19798600/files/SRR24759616_forward.fastqsanger.gz + - class: File + identifier: reverse + location: https://zenodo.org/records/19798600/files/SRR24759616_reverse.fastqsanger.gz + outputs: + output cluster: + asserts: + - that: has_n_lines + n: 3249 + delta: 10 + quality summary: + asserts: + - that: has_n_lines + n: 949 + delta: 10 + complete genomes: + asserts: + - that: has_n_lines + n: 4 + delta: 1 + - that: has_text + text: "contig_id" + coverage: + asserts: + - that: has_n_lines + n: 37 + delta: 5 + - that: has_text + text: "Contig" + output seqs: + asserts: + - that: has_size + size: 6800000 + delta: 50000 + best bins membership: + asserts: + - that: has_n_lines + n: 491 + delta: 25 + - that: has_text + text: "scaffold" + best bins summery: + asserts: + - that: has_n_lines + n: 111 + delta: 10 + - that: has_text + text: "proteins" + coverage file: + asserts: + - that: has_n_lines + n: 694 + delta: 50 + - that: has_text + text: "scaffold" + pharokka gbk: + asserts: + - that: has_size + size: 4400000 + delta: 50000 + pharokka gff: + asserts: + - that: has_size + size: 2700000 + delta: 50000 + genomad fasta: + element_tests: + SRR24759616: + asserts: + - that: has_size + value: 3000000 + delta: 50000 + bam for vRhyme: + element_tests: + SRR24759616: + asserts: + - that: has_size + value: 34900000 + delta: 50000 + best bins genes: + element_tests: + 1: + asserts: + - that: has_size + value: 238100 + delta: 5000 + best bins proteins: + element_tests: + 1: + asserts: + - that: has_size + value: 119200 + delta: 5000 + best bins fasta: + element_tests: + 1: + asserts: + - that: has_size + value: 191600 + delta: 5000 + bam for CoverM: + element_tests: + SRR24759616: + asserts: + - that: has_size + value: 9200000 + delta: 50000 \ No newline at end of file diff --git a/workflows/microbiome/viral-detection-from-bulk-metagenomes/viral-detection-from-bulk-metagenomes.ga b/workflows/microbiome/viral-detection-from-bulk-metagenomes/viral-detection-from-bulk-metagenomes.ga new file mode 100644 index 0000000000..7712c3bd7e --- /dev/null +++ b/workflows/microbiome/viral-detection-from-bulk-metagenomes/viral-detection-from-bulk-metagenomes.ga @@ -0,0 +1,1659 @@ +{ + "a_galaxy_workflow": "true", + "annotation": "This workflow identifies viral contigs from metagenomic assemblies using geNomad and supports taxonomy, functional annotation, binning, and host prediction.", + "comments": [ + { + "child_steps": [ + 5, + 6, + 7, + 9, + 4, + 3, + 2, + 0, + 8 + ], + "color": "none", + "data": { + "title": "Viral contigs prediction" + }, + "id": 0, + "position": [ + 0, + 0 + ], + "size": [ + 1800, + 720 + ], + "type": "frame" + }, + { + "child_steps": [ + 10, + 13, + 11, + 12 + ], + "color": "orange", + "data": { + "title": "Proviruses check" + }, + "id": 1, + "position": [ + 1862, + 17.69999999999999 + ], + "size": [ + 1087, + 705 + ], + "type": "frame" + }, + { + "child_steps": [ + 15, + 16, + 14 + ], + "color": "green", + "data": { + "title": "Clustering" + }, + "id": 2, + "position": [ + 3029.6, + 99.49999999999997 + ], + "size": [ + 515, + 613 + ], + "type": "frame" + }, + { + "child_steps": [ + 21, + 17, + 19 + ], + "color": "blue", + "data": { + "title": "Quality check & Filtering" + }, + "id": 3, + "position": [ + 3605, + 237.39999999999998 + ], + "size": [ + 742, + 356 + ], + "type": "frame" + }, + { + "child_steps": [ + 24 + ], + "color": "yellow", + "data": { + "title": "Host prediction" + }, + "id": 4, + "position": [ + 4523.799999999999, + 36.5 + ], + "size": [ + 370, + 294.9 + ], + "type": "frame" + }, + { + "child_steps": [ + 22 + ], + "color": "pink", + "data": { + "title": "Functional prediction" + }, + "id": 5, + "position": [ + 4517.299999999999, + 357.4 + ], + "size": [ + 309, + 260 + ], + "type": "frame" + }, + { + "child_steps": [ + 23, + 25 + ], + "color": "orange", + "data": { + "title": "Coverage calculation" + }, + "id": 6, + "position": [ + 4511.599999999999, + 644.9 + ], + "size": [ + 468.1, + 224.3 + ], + "type": "frame" + }, + { + "child_steps": [ + 18, + 20 + ], + "color": "red", + "data": { + "title": "Binning viral genomes-vMAGs" + }, + "id": 7, + "position": [ + 4510.299999999999, + 903 + ], + "size": [ + 505, + 641 + ], + "type": "frame" + } + ], + "creator": [ + { + "class": "Person", + "name": "Niklas Stahl" + }, + { + "class": "Person", + "identifier": "https://orcid.org/0000-0002-3602-7884", + "name": "Mina Hojat Ansari" + } + ], + "format-version": "0.1", + "license": "MIT", + "release": "1.0", + "name": "Viral detection from bulk metagenomes", + "readme": "# Viral detection from bulk metagenomes\n\n## Overview\n\nThis workflow identifies viral contigs from metagenomic assemblies using **geNomad** and performs downstream analyses including **taxonomy**, **functional annotation**, **binning**, **host prediction**, and **coverage estimation**.\n\n---\n\n## Inputs\n\n- **Assembled contigs** (FASTA, collection)\n- **Trimmed paired-end reads** (list:paired)\n\n### Requirements\n\n- Reads must be quality-controlled (trimmed, adapters removed)\n- Host contamination should be removed\n\n---\n\n## Workflow steps\n\n### 1. Viral contig prediction\nViral sequences are identified from assembled contigs using **geNomad**.\n\n### 2. Provirus detection and refinement\n**CheckV** is used to identify proviruses. Extracted proviruses are re-analysed with **geNomad**.\n\n### 3. Merging viral predictions\nViral contigs from both geNomad runs are combined.\n\n### 4. Clustering and dereplication\nRedundant sequences are removed using **MMseqs2** clustering.\n\n### 5. Quality assessment and filtering\n**CheckV** is used to assess sequence quality. Only sequences classified as:\n\n- Complete \n- High-quality \n- Medium-quality \n\nare retained for downstream analysis.\n\n### 6. Host prediction\nViral contigs are analysed using **iPHoP**.\n\n### 7. Functional annotation\nViral genomes are annotated using **Pharokka**.\n\n### 8. Coverage estimation\nReads are mapped using **Bowtie2** and coverage is calculated with **CoverM**.\n\n### 9. Viral genome binning (vMAGs)\nViral contigs and coverage profiles are used by **vRhyme** to recover viral genomes.\n\n---\n\n## Outputs\n\n- Viral contigs (geNomad)\n- Taxonomy annotations\n- Gene annotations\n- Nonredundant viral sequences\n- CheckV quality reports\n- Filtered viral contigs\n- Host predictions (iPHoP)\n- Functional annotations (Pharokka)\n- Coverage table (CoverM)\n- vMAG bins (vRhyme)\n\n---\n\n## Notes\n\n- Only **medium- and high-quality sequences** are used for biological interpretation\n\n---\n\n## License\n\nMIT License", + "report": { + "markdown": "\n# Workflow Execution Report\n\n## Workflow Inputs\n```galaxy\ninvocation_inputs()\n```\n\n## Workflow Outputs\n```galaxy\ninvocation_outputs()\n```\n\n## Workflow\n```galaxy\nworkflow_display()\n```\n" + }, + "steps": { + "0": { + "annotation": "A list of assembled contigs from which to detect virus genomes. You may want to employ co-assembly to improve the sensitivity of viral detections.", + "content_id": null, + "errors": null, + "id": 0, + "input_connections": {}, + "inputs": [ + { + "description": "A list of assembled contigs from which to detect virus genomes. You may want to employ co-assembly to improve the sensitivity of viral detections.", + "name": "Assembled contigs" + } + ], + "label": "Assembled contigs", + "name": "Input dataset collection", + "outputs": [], + "position": { + "left": 19.995445984582375, + "top": 67.28403681543367 + }, + "tool_id": null, + "tool_state": "{\"optional\": false, \"tag\": null, \"collection_type\": \"list\", \"fields\": null, \"column_definitions\": null}", + "tool_version": null, + "type": "data_collection_input", + "uuid": "43e313cc-a415-46c8-a520-f55449fa7edc", + "when": null, + "workflow_outputs": [] + }, + "1": { + "annotation": "Sample reads are used for abundance estimation and should be trimmed, adapters removed, and cleaned of host or other contaminants.", + "content_id": null, + "errors": null, + "id": 1, + "input_connections": {}, + "inputs": [ + { + "description": "Sample reads are used for abundance estimation and should be trimmed, adapters removed, and cleaned of host or other contaminants.", + "name": "Trimmed reads" + } + ], + "label": "Trimmed reads", + "name": "Input dataset collection", + "outputs": [], + "position": { + "left": 4084.264095421806, + "top": 655.5927852421926 + }, + "tool_id": null, + "tool_state": "{\"optional\": false, \"tag\": null, \"collection_type\": \"list:paired\", \"fields\": null, \"column_definitions\": null}", + "tool_version": null, + "type": "data_collection_input", + "uuid": "2d387778-836a-4ed6-856f-a580aaff5d2e", + "when": null, + "workflow_outputs": [] + }, + "2": { + "annotation": "", + "content_id": "toolshed.g2.bx.psu.edu/repos/bgruening/text_processing/tp_awk_tool/9.5+galaxy3", + "errors": null, + "id": 2, + "input_connections": { + "infile": { + "id": 0, + "output_name": "output" + } + }, + "inputs": [], + "label": null, + "name": "Text reformatting", + "outputs": [ + { + "name": "outfile", + "type": "input" + } + ], + "position": { + "left": 241.39371310958268, + "top": 43.90149261760183 + }, + "post_job_actions": {}, + "tool_id": "toolshed.g2.bx.psu.edu/repos/bgruening/text_processing/tp_awk_tool/9.5+galaxy3", + "tool_shed_repository": { + "changeset_revision": "ab83aa685821", + "name": "text_processing", + "owner": "bgruening", + "tool_shed": "toolshed.g2.bx.psu.edu" + }, + "tool_state": "{\"code\": \"/^>/ {print \\\">\\\" FILENAME \\\"_\\\" ++i} !/^>/ {print}\", \"infile\": {\"__class__\": \"ConnectedValue\"}, \"variables\": [], \"__page__\": 0, \"__rerun_remap_job_id__\": null}", + "tool_uuid": null, + "tool_version": "9.5+galaxy3", + "type": "tool", + "uuid": "b9c69689-2d73-44c2-8148-8db9db3ecc36", + "when": null, + "workflow_outputs": [] + }, + "3": { + "annotation": "", + "content_id": "toolshed.g2.bx.psu.edu/repos/bgruening/split_file_to_collection/split_file_to_collection/0.5.2", + "errors": null, + "id": 3, + "input_connections": { + "split_parms|input": { + "id": 2, + "output_name": "outfile" + } + }, + "inputs": [ + { + "description": "runtime parameter for tool Split file", + "name": "split_parms" + } + ], + "label": null, + "name": "Split file", + "outputs": [ + { + "name": "list_output_fasta", + "type": "input" + } + ], + "position": { + "left": 509.85305942102536, + "top": 46.54536843297882 + }, + "post_job_actions": {}, + "tool_id": "toolshed.g2.bx.psu.edu/repos/bgruening/split_file_to_collection/split_file_to_collection/0.5.2", + "tool_shed_repository": { + "changeset_revision": "2dae863c8f42", + "name": "split_file_to_collection", + "owner": "bgruening", + "tool_shed": "toolshed.g2.bx.psu.edu" + }, + "tool_state": "{\"split_parms\": {\"select_ftype\": \"fasta\", \"__current_case__\": 3, \"input\": {\"__class__\": \"ConnectedValue\"}, \"select_mode\": {\"mode\": \"chunk\", \"__current_case__\": 0, \"chunksize\": \"50000\"}, \"newfilenames\": \"chunk_\", \"select_allocate\": {\"allocate\": \"byrow\", \"__current_case__\": 2}}, \"__page__\": 0, \"__rerun_remap_job_id__\": null}", + "tool_uuid": null, + "tool_version": "0.5.2", + "type": "tool", + "uuid": "19cc0397-e783-4d3e-a892-c0ccfaccd859", + "when": null, + "workflow_outputs": [] + }, + "4": { + "annotation": "", + "content_id": "toolshed.g2.bx.psu.edu/repos/ufz/genomad_end_to_end/genomad_end_to_end/1.11.1+galaxy0", + "errors": null, + "id": 4, + "input_connections": { + "INPUT": { + "id": 3, + "output_name": "list_output_fasta" + } + }, + "inputs": [], + "label": null, + "name": "geNomad", + "outputs": [ + { + "name": "summary_plasmid_fna", + "type": "fasta" + }, + { + "name": "summary_plasmid_genes", + "type": "tabular" + }, + { + "name": "summary_plasmid_proteins", + "type": "fasta" + }, + { + "name": "summary_plasmid_summary", + "type": "tabular" + }, + { + "name": "summary_virus_fna", + "type": "fasta" + }, + { + "name": "summary_virus_genes", + "type": "tabular" + }, + { + "name": "summary_virus_proteins", + "type": "fasta" + }, + { + "name": "summary_virus_summary", + "type": "tabular" + } + ], + "position": { + "left": 780, + "top": 50 + }, + "post_job_actions": {}, + "tool_id": "toolshed.g2.bx.psu.edu/repos/ufz/genomad_end_to_end/genomad_end_to_end/1.11.1+galaxy0", + "tool_shed_repository": { + "changeset_revision": "26f5822743aa", + "name": "genomad_end_to_end", + "owner": "ufz", + "tool_shed": "toolshed.g2.bx.psu.edu" + }, + "tool_state": "{\"DATABASE\": \"1.9\", \"INPUT\": {\"__class__\": \"ConnectedValue\"}, \"annotation\": {\"lenient_taxonomy\": true, \"full_ictv_lineage\": false, \"sensitivity\": \"4.2\", \"splits\": \"8\"}, \"basic\": {\"disable_find_proviruses\": true, \"disable_nn_classification\": true, \"enable_score_calibration\": false}, \"filter_cond\": {\"filtering_preset\": \"--conservative\", \"__current_case__\": 0}, \"license\": true, \"provirus\": {\"skip_integrase_identification\": false, \"skip_trna_identification\": false}, \"score\": {\"composition\": \"auto\", \"force_auto\": false}, \"__page__\": 0, \"__rerun_remap_job_id__\": null}", + "tool_uuid": null, + "tool_version": "1.11.1+galaxy0", + "type": "tool", + "uuid": "0c99aaab-b08b-4d04-9f1c-7c03eaa27b9b", + "when": null, + "workflow_outputs": [] + }, + "5": { + "annotation": "Additional filtering of geNomad contigs using complex custom rules. If all conditions are AND-conditions you may be able to set them on the tool directly.\nBy default this step does nothing beyond the conservative preset applied by geNomad.", + "content_id": "toolshed.g2.bx.psu.edu/repos/iuc/query_tabular/query_tabular/3.3.2", + "errors": null, + "id": 5, + "input_connections": { + "tables_0|table": { + "id": 4, + "output_name": "summary_virus_summary" + } + }, + "inputs": [ + { + "description": "runtime parameter for tool Query Tabular", + "name": "add_to_database" + } + ], + "label": null, + "name": "Query Tabular", + "outputs": [ + { + "name": "output", + "type": "tabular" + } + ], + "position": { + "left": 1040, + "top": 60 + }, + "post_job_actions": { + "RenameDatasetActionoutput": { + "action_arguments": { + "newname": "geNomad filtered scores" + }, + "action_type": "RenameDatasetAction", + "output_name": "output" + } + }, + "tool_id": "toolshed.g2.bx.psu.edu/repos/iuc/query_tabular/query_tabular/3.3.2", + "tool_shed_repository": { + "changeset_revision": "cf4397560712", + "name": "query_tabular", + "owner": "iuc", + "tool_shed": "toolshed.g2.bx.psu.edu" + }, + "tool_state": "{\"add_to_database\": {\"withdb\": {\"__class__\": \"RuntimeValue\"}}, \"addqueries\": {\"queries\": []}, \"modify_database\": {\"sql_stmts\": []}, \"query_result\": {\"header\": \"yes\", \"__current_case__\": 0, \"header_prefix\": \"\"}, \"save_db\": false, \"sqlquery\": \"SELECT * from t1;\", \"tables\": [{\"__index__\": 0, \"table\": {\"__class__\": \"ConnectedValue\"}, \"input_opts\": {\"linefilters\": []}, \"tbl_opts\": {\"table_name\": \"\", \"column_names_from_first_line\": true, \"col_names\": \"\", \"load_named_columns\": false, \"pkey_autoincr\": \"\", \"indexes\": []}}], \"workdb\": \"workdb.sqlite\", \"__page__\": 0, \"__rerun_remap_job_id__\": null}", + "tool_uuid": null, + "tool_version": "3.3.2", + "type": "tool", + "uuid": "6f07aa83-23eb-40ff-8d80-c3bda0a8dba2", + "when": null, + "workflow_outputs": [] + }, + "6": { + "annotation": "", + "content_id": "toolshed.g2.bx.psu.edu/repos/nml/collapse_collections/collapse_dataset/5.1.0", + "errors": null, + "id": 6, + "input_connections": { + "input_list": { + "id": 4, + "output_name": "summary_virus_genes" + } + }, + "inputs": [], + "label": null, + "name": "Collapse Collection", + "outputs": [ + { + "name": "output", + "type": "input" + } + ], + "position": { + "left": 1080, + "top": 380 + }, + "post_job_actions": { + "RenameDatasetActionoutput": { + "action_arguments": { + "newname": "geNomad initial gene annotations" + }, + "action_type": "RenameDatasetAction", + "output_name": "output" + } + }, + "tool_id": "toolshed.g2.bx.psu.edu/repos/nml/collapse_collections/collapse_dataset/5.1.0", + "tool_shed_repository": { + "changeset_revision": "90981f86000f", + "name": "collapse_collections", + "owner": "nml", + "tool_shed": "toolshed.g2.bx.psu.edu" + }, + "tool_state": "{\"filename\": {\"add_name\": false, \"__current_case__\": 1}, \"input_list\": {\"__class__\": \"ConnectedValue\"}, \"one_header\": true, \"__page__\": 0, \"__rerun_remap_job_id__\": null}", + "tool_uuid": null, + "tool_version": "5.1.0", + "type": "tool", + "uuid": "9ffbaefd-7ca4-4293-8b28-2ce72ecce978", + "when": null, + "workflow_outputs": [] + }, + "7": { + "annotation": "", + "content_id": "toolshed.g2.bx.psu.edu/repos/nml/collapse_collections/collapse_dataset/5.1.0", + "errors": null, + "id": 7, + "input_connections": { + "input_list": { + "id": 4, + "output_name": "summary_virus_summary" + } + }, + "inputs": [], + "label": null, + "name": "Collapse Collection", + "outputs": [ + { + "name": "output", + "type": "input" + } + ], + "position": { + "left": 1080, + "top": 530 + }, + "post_job_actions": { + "RenameDatasetActionoutput": { + "action_arguments": { + "newname": "geNomad initial taxonomy" + }, + "action_type": "RenameDatasetAction", + "output_name": "output" + } + }, + "tool_id": "toolshed.g2.bx.psu.edu/repos/nml/collapse_collections/collapse_dataset/5.1.0", + "tool_shed_repository": { + "changeset_revision": "90981f86000f", + "name": "collapse_collections", + "owner": "nml", + "tool_shed": "toolshed.g2.bx.psu.edu" + }, + "tool_state": "{\"filename\": {\"add_name\": false, \"__current_case__\": 1}, \"input_list\": {\"__class__\": \"ConnectedValue\"}, \"one_header\": true, \"__page__\": 0, \"__rerun_remap_job_id__\": null}", + "tool_uuid": null, + "tool_version": "5.1.0", + "type": "tool", + "uuid": "f89553d1-2df6-474f-848d-621412fc9df2", + "when": null, + "workflow_outputs": [] + }, + "8": { + "annotation": "", + "content_id": "toolshed.g2.bx.psu.edu/repos/iuc/qiime_filter_fasta/qiime_filter_fasta/1.9.1.0", + "errors": null, + "id": 8, + "input_connections": { + "input_fasta_fp": { + "id": 4, + "output_name": "summary_virus_fna" + }, + "selection|seq_id_fp": { + "id": 5, + "output_name": "output" + } + }, + "inputs": [ + { + "description": "runtime parameter for tool Filter fasta", + "name": "selection" + } + ], + "label": null, + "name": "Filter fasta", + "outputs": [ + { + "name": "fitered_fasta", + "type": "fasta" + } + ], + "position": { + "left": 1320, + "top": 170 + }, + "post_job_actions": {}, + "tool_id": "toolshed.g2.bx.psu.edu/repos/iuc/qiime_filter_fasta/qiime_filter_fasta/1.9.1.0", + "tool_shed_repository": { + "changeset_revision": "11b19edeb3af", + "name": "qiime_filter_fasta", + "owner": "iuc", + "tool_shed": "toolshed.g2.bx.psu.edu" + }, + "tool_state": "{\"input_fasta_fp\": {\"__class__\": \"ConnectedValue\"}, \"negate\": false, \"selection\": {\"type\": \"seq_list\", \"__current_case__\": 1, \"seq_id_fp\": {\"__class__\": \"ConnectedValue\"}}, \"__page__\": 0, \"__rerun_remap_job_id__\": null}", + "tool_uuid": null, + "tool_version": "1.9.1.0", + "type": "tool", + "uuid": "57503892-ed49-41ef-a16e-339afed93270", + "when": null, + "workflow_outputs": [] + }, + "9": { + "annotation": "", + "content_id": "toolshed.g2.bx.psu.edu/repos/nml/collapse_collections/collapse_dataset/5.1.0", + "errors": null, + "id": 9, + "input_connections": { + "input_list": { + "id": 8, + "output_name": "fitered_fasta" + } + }, + "inputs": [], + "label": null, + "name": "Collapse Collection", + "outputs": [ + { + "name": "output", + "type": "input" + } + ], + "position": { + "left": 1580, + "top": 240 + }, + "post_job_actions": { + "RenameDatasetActionoutput": { + "action_arguments": { + "newname": "geNomad sequences" + }, + "action_type": "RenameDatasetAction", + "output_name": "output" + } + }, + "tool_id": "toolshed.g2.bx.psu.edu/repos/nml/collapse_collections/collapse_dataset/5.1.0", + "tool_shed_repository": { + "changeset_revision": "90981f86000f", + "name": "collapse_collections", + "owner": "nml", + "tool_shed": "toolshed.g2.bx.psu.edu" + }, + "tool_state": "{\"filename\": {\"add_name\": false, \"__current_case__\": 1}, \"input_list\": {\"__class__\": \"ConnectedValue\"}, \"one_header\": false, \"__page__\": 0, \"__rerun_remap_job_id__\": null}", + "tool_uuid": null, + "tool_version": "5.1.0", + "type": "tool", + "uuid": "c38f9178-c61e-47c7-9b93-2fe1e5106a95", + "when": null, + "workflow_outputs": [ + { + "label": "genomad fasta", + "output_name": "output", + "uuid": "8bc262c6-2be8-4dc8-9553-afe1a067aa59" + } + ] + }, + "10": { + "annotation": "", + "content_id": "toolshed.g2.bx.psu.edu/repos/ufz/checkv_end_to_end/checkv_end_to_end/1.0.3+galaxy0", + "errors": null, + "id": 10, + "input_connections": { + "input": { + "id": 9, + "output_name": "output" + } + }, + "inputs": [], + "label": "CheckV: Separate proviruses", + "name": "CheckV end to end", + "outputs": [ + { + "name": "quality summary", + "type": "tabular" + }, + { + "name": "complete genomes", + "type": "tabular" + }, + { + "name": "proviruses", + "type": "fasta" + }, + { + "name": "viruses", + "type": "fasta" + } + ], + "position": { + "left": 1881.9763511796455, + "top": 361.6856474246922 + }, + "post_job_actions": { + "HideDatasetActioncomplete_genomes": { + "action_arguments": {}, + "action_type": "HideDatasetAction", + "output_name": "complete genomes" + }, + "HideDatasetActionquality_summary": { + "action_arguments": {}, + "action_type": "HideDatasetAction", + "output_name": "quality summary" + } + }, + "tool_id": "toolshed.g2.bx.psu.edu/repos/ufz/checkv_end_to_end/checkv_end_to_end/1.0.3+galaxy0", + "tool_shed_repository": { + "changeset_revision": "e523d50513a4", + "name": "checkv_end_to_end", + "owner": "ufz", + "tool_shed": "toolshed.g2.bx.psu.edu" + }, + "tool_state": "{\"input\": {\"__class__\": \"ConnectedValue\"}, \"optional_outputs\": null, \"reference\": \"1.5\", \"__page__\": 0, \"__rerun_remap_job_id__\": null}", + "tool_uuid": null, + "tool_version": "1.0.3+galaxy0", + "type": "tool", + "uuid": "ba443f12-57c1-4c82-a0bf-7178dc9de71d", + "when": null, + "workflow_outputs": [] + }, + "11": { + "annotation": "", + "content_id": "__FILTER_EMPTY_DATASETS__", + "errors": null, + "id": 11, + "input_connections": { + "input": { + "id": 10, + "output_name": "proviruses" + } + }, + "inputs": [ + { + "description": "runtime parameter for tool Filter empty datasets", + "name": "replacement" + } + ], + "label": null, + "name": "Filter empty datasets", + "outputs": [ + { + "name": "output", + "type": "input" + } + ], + "position": { + "left": 2174.0800945063515, + "top": 57.749708626126534 + }, + "post_job_actions": {}, + "tool_id": "__FILTER_EMPTY_DATASETS__", + "tool_state": "{\"input\": {\"__class__\": \"ConnectedValue\"}, \"replacement\": {\"__class__\": \"RuntimeValue\"}, \"__page__\": 0, \"__rerun_remap_job_id__\": null}", + "tool_uuid": null, + "tool_version": "1.1.0", + "type": "tool", + "uuid": "5f77a82a-979f-40bf-8134-92b4c8c650e0", + "when": null, + "workflow_outputs": [] + }, + "12": { + "annotation": "", + "content_id": "toolshed.g2.bx.psu.edu/repos/ufz/genomad_end_to_end/genomad_end_to_end/1.11.1+galaxy0", + "errors": null, + "id": 12, + "input_connections": { + "INPUT": { + "id": 11, + "output_name": "output" + } + }, + "inputs": [], + "label": null, + "name": "geNomad", + "outputs": [ + { + "name": "summary_plasmid_fna", + "type": "fasta" + }, + { + "name": "summary_plasmid_genes", + "type": "tabular" + }, + { + "name": "summary_plasmid_proteins", + "type": "fasta" + }, + { + "name": "summary_plasmid_summary", + "type": "tabular" + }, + { + "name": "summary_virus_fna", + "type": "fasta" + }, + { + "name": "summary_virus_genes", + "type": "tabular" + }, + { + "name": "summary_virus_proteins", + "type": "fasta" + }, + { + "name": "summary_virus_summary", + "type": "tabular" + } + ], + "position": { + "left": 2420, + "top": 90 + }, + "post_job_actions": {}, + "tool_id": "toolshed.g2.bx.psu.edu/repos/ufz/genomad_end_to_end/genomad_end_to_end/1.11.1+galaxy0", + "tool_shed_repository": { + "changeset_revision": "26f5822743aa", + "name": "genomad_end_to_end", + "owner": "ufz", + "tool_shed": "toolshed.g2.bx.psu.edu" + }, + "tool_state": "{\"DATABASE\": \"1.9\", \"INPUT\": {\"__class__\": \"ConnectedValue\"}, \"annotation\": {\"lenient_taxonomy\": true, \"full_ictv_lineage\": true, \"sensitivity\": \"4.2\", \"splits\": \"4\"}, \"basic\": {\"disable_find_proviruses\": true, \"disable_nn_classification\": true, \"enable_score_calibration\": false}, \"filter_cond\": {\"filtering_preset\": \"--conservative\", \"__current_case__\": 0}, \"license\": true, \"provirus\": {\"skip_integrase_identification\": false, \"skip_trna_identification\": false}, \"score\": {\"composition\": \"auto\", \"force_auto\": false}, \"__page__\": 0, \"__rerun_remap_job_id__\": null}", + "tool_uuid": null, + "tool_version": "1.11.1+galaxy0", + "type": "tool", + "uuid": "3a1e9e1a-b2c8-4acf-a56f-fae383674536", + "when": null, + "workflow_outputs": [] + }, + "13": { + "annotation": "", + "content_id": "toolshed.g2.bx.psu.edu/repos/bgruening/text_processing/tp_cat/9.5+galaxy3", + "errors": null, + "id": 13, + "input_connections": { + "inputs": { + "id": 12, + "output_name": "summary_virus_fna" + }, + "queries_0|inputs2": { + "id": 10, + "output_name": "viruses" + } + }, + "inputs": [], + "label": null, + "name": "Concatenate datasets", + "outputs": [ + { + "name": "out_file1", + "type": "input" + } + ], + "position": { + "left": 2720, + "top": 420 + }, + "post_job_actions": { + "RenameDatasetActionout_file1": { + "action_arguments": { + "newname": "All viral predictions" + }, + "action_type": "RenameDatasetAction", + "output_name": "out_file1" + } + }, + "tool_id": "toolshed.g2.bx.psu.edu/repos/bgruening/text_processing/tp_cat/9.5+galaxy3", + "tool_shed_repository": { + "changeset_revision": "ab83aa685821", + "name": "text_processing", + "owner": "bgruening", + "tool_shed": "toolshed.g2.bx.psu.edu" + }, + "tool_state": "{\"inputs\": {\"__class__\": \"ConnectedValue\"}, \"queries\": [{\"__index__\": 0, \"inputs2\": {\"__class__\": \"ConnectedValue\"}}], \"__page__\": 0, \"__rerun_remap_job_id__\": null}", + "tool_uuid": null, + "tool_version": "9.5+galaxy3", + "type": "tool", + "uuid": "ee98372c-aac2-4623-bc08-79f25ffd3697", + "when": null, + "workflow_outputs": [] + }, + "14": { + "annotation": "", + "content_id": "toolshed.g2.bx.psu.edu/repos/yhoogstrate/segmentation_fold/smf_utils_fix-fasta-headers/smf-v1.7-0_utils-v2.1.1-1", + "errors": null, + "id": 14, + "input_connections": { + "fasta_input": { + "id": 13, + "output_name": "out_file1" + } + }, + "inputs": [], + "label": null, + "name": "fix-fasta-headers", + "outputs": [ + { + "name": "fasta_output", + "type": "fasta" + } + ], + "position": { + "left": 3082.6318180040385, + "top": 182.9941495308109 + }, + "post_job_actions": {}, + "tool_id": "toolshed.g2.bx.psu.edu/repos/yhoogstrate/segmentation_fold/smf_utils_fix-fasta-headers/smf-v1.7-0_utils-v2.1.1-1", + "tool_shed_repository": { + "changeset_revision": "4d16cf9414cf", + "name": "segmentation_fold", + "owner": "yhoogstrate", + "tool_shed": "toolshed.g2.bx.psu.edu" + }, + "tool_state": "{\"fasta_input\": {\"__class__\": \"ConnectedValue\"}, \"__page__\": 0, \"__rerun_remap_job_id__\": null}", + "tool_uuid": null, + "tool_version": "smf-v1.7-0_utils-v2.1.1-1", + "type": "tool", + "uuid": "fc71e43a-f90d-4fc0-a4c1-41783a118868", + "when": null, + "workflow_outputs": [] + }, + "15": { + "annotation": "", + "content_id": "toolshed.g2.bx.psu.edu/repos/iuc/mmseqs2_easy_linclust_clustering/mmseqs2_easy_linclust_clustering/17-b804f+galaxy0", + "errors": null, + "id": 15, + "input_connections": { + "input_fasta": { + "id": 14, + "output_name": "fasta_output" + } + }, + "inputs": [], + "label": null, + "name": "MMseqs2 Sequence Clustering", + "outputs": [ + { + "name": "output_rep_seq", + "type": "fasta" + }, + { + "name": "output cluster", + "type": "tabular" + } + ], + "position": { + "left": 3170.21574724644, + "top": 326.77994775895024 + }, + "post_job_actions": { + "HideDatasetActionoutput_rep_seq": { + "action_arguments": {}, + "action_type": "HideDatasetAction", + "output_name": "output_rep_seq" + }, + "RenameDatasetActionoutput_cluster": { + "action_arguments": { + "newname": "MMseqs2: Adjecency list" + }, + "action_type": "RenameDatasetAction", + "output_name": "output cluster" + }, + "RenameDatasetActionoutput_rep_seq": { + "action_arguments": { + "newname": "MMseqs2: Dereplicated sequences (has trailing spaces)" + }, + "action_type": "RenameDatasetAction", + "output_name": "output_rep_seq" + } + }, + "tool_id": "toolshed.g2.bx.psu.edu/repos/iuc/mmseqs2_easy_linclust_clustering/mmseqs2_easy_linclust_clustering/17-b804f+galaxy0", + "tool_shed_repository": { + "changeset_revision": "b174c3405549", + "name": "mmseqs2_easy_linclust_clustering", + "owner": "iuc", + "tool_shed": "toolshed.g2.bx.psu.edu" + }, + "tool_state": "{\"align\": {\"convertalis\": false, \"alignment_output_mode\": \"0\", \"wrapped_scoring\": false, \"min_aln_len\": \"0\", \"seq_id_mode\": \"0\", \"alt_ali\": \"0\", \"score_bias\": \"0.0\", \"realign\": false, \"realign_score_bias\": \"-0.2\", \"realign_max_seqs\": \"2147483647\", \"corr_score_weight\": \"0.0\", \"alignment_mode\": \"0\", \"evalue\": \"0.001\", \"max_rejected\": \"2147483647\", \"max_accept\": \"2147483647\"}, \"alph_type\": {\"dbtype\": \"0\", \"__current_case__\": 0}, \"cluster\": {\"cluster_mode\": \"0\", \"max_iterations\": \"1000\", \"similarity_type\": \"2\"}, \"common\": {\"max_seq_len\": \"65535\"}, \"cov\": \"0.85\", \"cov_mode\": \"0\", \"expert\": {\"filter_hits\": false, \"sort_results\": \"0\"}, \"input_fasta\": {\"__class__\": \"ConnectedValue\"}, \"kmermatcher\": {\"cluster_weight_threshold\": \"0.9\", \"kmer_per_seq\": \"21\", \"hash_shift\": \"67\", \"include_only_extendable\": false, \"ignore_multi_kmer\": false}, \"min_seq_id\": \"0.95\", \"misc\": {\"rescore_mode\": \"0\", \"shuffle\": true, \"id_offset\": \"0\"}, \"output_files\": {\"output_selection\": [\"file_rep_seq\", \"file_cluster_tsv\"]}, \"prefilter\": {\"add_self_matches\": false, \"kmer_length\": \"0\", \"mask\": \"1\", \"mask_prob\": \"0.9\", \"mask_lower_case\": \"0\", \"mask_n_repeat\": \"0\", \"spaced_kmer_mode\": \"0\"}, \"__page__\": 0, \"__rerun_remap_job_id__\": null}", + "tool_uuid": null, + "tool_version": "17-b804f+galaxy0", + "type": "tool", + "uuid": "1459a99e-c209-4b8e-91a2-e541cc51fefc", + "when": null, + "workflow_outputs": [ + { + "label": "output cluster", + "output_name": "output cluster", + "uuid": "ee93c9f9-66e1-435d-a57a-3204efa076dd" + } + ] + }, + "16": { + "annotation": "Strip trailing spaces added by MMseqs2.", + "content_id": "toolshed.g2.bx.psu.edu/repos/galaxyp/regex_find_replace/regex1/1.0.3", + "errors": null, + "id": 16, + "input_connections": { + "input": { + "id": 15, + "output_name": "output_rep_seq" + } + }, + "inputs": [], + "label": null, + "name": "Regex Find And Replace", + "outputs": [ + { + "name": "out_file1", + "type": "input" + } + ], + "position": { + "left": 3308.9571775826985, + "top": 520.4733430628843 + }, + "post_job_actions": { + "RenameDatasetActionout_file1": { + "action_arguments": { + "newname": "Final nonredundant virus sequences" + }, + "action_type": "RenameDatasetAction", + "output_name": "out_file1" + } + }, + "tool_id": "toolshed.g2.bx.psu.edu/repos/galaxyp/regex_find_replace/regex1/1.0.3", + "tool_shed_repository": { + "changeset_revision": "503bcd6ebe4b", + "name": "regex_find_replace", + "owner": "galaxyp", + "tool_shed": "toolshed.g2.bx.psu.edu" + }, + "tool_state": "{\"checks\": [{\"__index__\": 0, \"pattern\": \" +\\\\n\", \"replacement\": \"\\\\n\"}], \"input\": {\"__class__\": \"ConnectedValue\"}, \"__page__\": 0, \"__rerun_remap_job_id__\": null}", + "tool_uuid": null, + "tool_version": "1.0.3", + "type": "tool", + "uuid": "d1c9852c-53c0-4051-9917-4da70b00b7a9", + "when": null, + "workflow_outputs": [ + { + "label": "output seqs", + "output_name": "out_file1", + "uuid": "d6a81aa1-2777-4e1f-9834-4f9e762a6494" + } + ] + }, + "17": { + "annotation": "", + "content_id": "toolshed.g2.bx.psu.edu/repos/ufz/checkv_end_to_end/checkv_end_to_end/1.0.3+galaxy0", + "errors": null, + "id": 17, + "input_connections": { + "input": { + "id": 16, + "output_name": "out_file1" + } + }, + "inputs": [], + "label": null, + "name": "CheckV end to end", + "outputs": [ + { + "name": "quality summary", + "type": "tabular" + }, + { + "name": "complete genomes", + "type": "tabular" + }, + { + "name": "proviruses", + "type": "fasta" + }, + { + "name": "viruses", + "type": "fasta" + } + ], + "position": { + "left": 3625.04858992705, + "top": 277.43579463867934 + }, + "post_job_actions": { + "RenameDatasetActioncomplete_genomes": { + "action_arguments": { + "newname": "CheckV: Complete Genomes" + }, + "action_type": "RenameDatasetAction", + "output_name": "complete genomes" + }, + "RenameDatasetActionquality_summary": { + "action_arguments": { + "newname": "CheckV: Quality summary" + }, + "action_type": "RenameDatasetAction", + "output_name": "quality summary" + } + }, + "tool_id": "toolshed.g2.bx.psu.edu/repos/ufz/checkv_end_to_end/checkv_end_to_end/1.0.3+galaxy0", + "tool_shed_repository": { + "changeset_revision": "e523d50513a4", + "name": "checkv_end_to_end", + "owner": "ufz", + "tool_shed": "toolshed.g2.bx.psu.edu" + }, + "tool_state": "{\"input\": {\"__class__\": \"ConnectedValue\"}, \"optional_outputs\": null, \"reference\": \"1.5\", \"__page__\": 0, \"__rerun_remap_job_id__\": null}", + "tool_uuid": null, + "tool_version": "1.0.3+galaxy0", + "type": "tool", + "uuid": "2f497eab-34ab-4a70-a916-7efbcb92f907", + "when": null, + "workflow_outputs": [ + { + "label": "quality summary", + "output_name": "quality summary", + "uuid": "cd5769f7-22af-4587-bda1-5c0be3365a2c" + }, + { + "label": "complete genomes", + "output_name": "complete genomes", + "uuid": "2d12da96-c84f-44e8-b5ad-a740436f5624" + } + ] + }, + "18": { + "annotation": "", + "content_id": "toolshed.g2.bx.psu.edu/repos/devteam/bowtie2/bowtie2/2.5.4+galaxy0", + "errors": null, + "id": 18, + "input_connections": { + "library|input_1": { + "id": 1, + "output_name": "output" + }, + "reference_genome|own_file": { + "id": 16, + "output_name": "out_file1" + } + }, + "inputs": [ + { + "description": "runtime parameter for tool Bowtie2", + "name": "library" + }, + { + "description": "runtime parameter for tool Bowtie2", + "name": "reference_genome" + } + ], + "label": null, + "name": "Bowtie2", + "outputs": [ + { + "name": "output", + "type": "bam" + } + ], + "position": { + "left": 4533.227954896794, + "top": 972.5366890982673 + }, + "post_job_actions": { + "RenameDatasetActionoutput": { + "action_arguments": { + "newname": "Bowtie2: alignments" + }, + "action_type": "RenameDatasetAction", + "output_name": "output" + } + }, + "tool_id": "toolshed.g2.bx.psu.edu/repos/devteam/bowtie2/bowtie2/2.5.4+galaxy0", + "tool_shed_repository": { + "changeset_revision": "f76cbb84d67f", + "name": "bowtie2", + "owner": "devteam", + "tool_shed": "toolshed.g2.bx.psu.edu" + }, + "tool_state": "{\"analysis_type\": {\"analysis_type_selector\": \"simple\", \"__current_case__\": 0, \"presets\": \"no_presets\"}, \"library\": {\"type\": \"paired_collection\", \"__current_case__\": 1, \"input_1\": {\"__class__\": \"ConnectedValue\"}, \"unaligned_file\": false, \"aligned_file\": false, \"paired_options\": {\"paired_options_selector\": \"yes\", \"__current_case__\": 0, \"I\": \"0\", \"X\": \"500\", \"fr_rf_ff\": \"--fr\", \"no_mixed\": false, \"no_discordant\": true, \"dovetail\": false, \"no_contain\": false, \"no_overlap\": false}}, \"reference_genome\": {\"source\": \"history\", \"__current_case__\": 1, \"own_file\": {\"__class__\": \"ConnectedValue\"}}, \"rg\": {\"rg_selector\": \"set_id_auto\", \"__current_case__\": 2}, \"sam_options\": {\"sam_options_selector\": \"yes\", \"__current_case__\": 0, \"sam_opt\": false, \"no_unal\": true, \"omit_sec_seq\": false, \"sam_no_qname_trunc\": false, \"xeq\": false, \"soft_clipped_unmapped_tlen\": false, \"reorder\": false}, \"save_mapping_stats\": false, \"__page__\": 0, \"__rerun_remap_job_id__\": null}", + "tool_uuid": null, + "tool_version": "2.5.4+galaxy0", + "type": "tool", + "uuid": "abdb17f7-9b80-4436-86ca-a349566c313c", + "when": null, + "workflow_outputs": [ + { + "label": "bam for vRhyme", + "output_name": "output", + "uuid": "a20e4d10-0f40-4878-8dd9-7d446b41344b" + } + ] + }, + "19": { + "annotation": "Additional filtering of VirSorter contigs using complex custom rules. If all conditions are AND-conditions you may be able to set them on the tool directly.\nBy default this step imposes a stricter score threshold of 0.9 on sequences shorter than 3000 bp, instead of the standard threshold of 0.5.", + "content_id": "toolshed.g2.bx.psu.edu/repos/iuc/query_tabular/query_tabular/3.3.2", + "errors": null, + "id": 19, + "input_connections": { + "tables_0|table": { + "id": 17, + "output_name": "quality summary" + } + }, + "inputs": [ + { + "description": "runtime parameter for tool Query Tabular", + "name": "add_to_database" + } + ], + "label": null, + "name": "Query Tabular", + "outputs": [ + { + "name": "output", + "type": "tabular" + } + ], + "position": { + "left": 3869.375509068681, + "top": 307.2337817706831 + }, + "post_job_actions": { + "RenameDatasetActionoutput": { + "action_arguments": { + "newname": "VirSorter filtered scores" + }, + "action_type": "RenameDatasetAction", + "output_name": "output" + } + }, + "tool_id": "toolshed.g2.bx.psu.edu/repos/iuc/query_tabular/query_tabular/3.3.2", + "tool_shed_repository": { + "changeset_revision": "cf4397560712", + "name": "query_tabular", + "owner": "iuc", + "tool_shed": "toolshed.g2.bx.psu.edu" + }, + "tool_state": "{\"add_to_database\": {\"withdb\": {\"__class__\": \"RuntimeValue\"}}, \"addqueries\": {\"queries\": []}, \"modify_database\": {\"sql_stmts\": []}, \"query_result\": {\"header\": \"yes\", \"__current_case__\": 0, \"header_prefix\": \"\"}, \"save_db\": false, \"sqlquery\": \"SELECT *\\nFROM t1\\nWHERE \\\"checkv_quality\\\" IN ('Complete', 'High-quality', 'Medium-quality');\", \"tables\": [{\"__index__\": 0, \"table\": {\"__class__\": \"ConnectedValue\"}, \"input_opts\": {\"linefilters\": []}, \"tbl_opts\": {\"table_name\": \"\", \"column_names_from_first_line\": true, \"col_names\": \"\", \"load_named_columns\": false, \"pkey_autoincr\": \"\", \"indexes\": []}}], \"workdb\": \"workdb.sqlite\", \"__page__\": 0, \"__rerun_remap_job_id__\": null}", + "tool_uuid": null, + "tool_version": "3.3.2", + "type": "tool", + "uuid": "ce48ba6e-ecfc-41bd-bf62-50973968a76b", + "when": null, + "workflow_outputs": [] + }, + "20": { + "annotation": "", + "content_id": "toolshed.g2.bx.psu.edu/repos/bgruening/vrhyme/vrhyme/1.1.0+galaxygalaxy2", + "errors": null, + "id": 20, + "input_connections": { + "input_fasta": { + "id": 16, + "output_name": "out_file1" + }, + "input_types|input|BAM_inputs": { + "id": 18, + "output_name": "output" + } + }, + "inputs": [ + { + "description": "runtime parameter for tool vRhyme", + "name": "optional_genes" + }, + { + "description": "runtime parameter for tool vRhyme", + "name": "optional_proteins" + } + ], + "label": null, + "name": "vRhyme", + "outputs": [ + { + "name": "best bins fasta", + "type": "input" + }, + { + "name": "best bins genes", + "type": "input" + }, + { + "name": "best bins proteins", + "type": "input" + }, + { + "name": "circular", + "type": "tabular" + }, + { + "name": "best bins membership", + "type": "tabular" + }, + { + "name": "best bins summery", + "type": "tabular" + }, + { + "name": "machine", + "type": "tabular" + }, + { + "name": "logfile", + "type": "txt" + }, + { + "name": "bin_scoring", + "type": "tabular" + }, + { + "name": "coverage file", + "type": "tabular" + } + ], + "position": { + "left": 4769.420068128869, + "top": 943.146638863737 + }, + "post_job_actions": {}, + "tool_id": "toolshed.g2.bx.psu.edu/repos/bgruening/vrhyme/vrhyme/1.1.0+galaxygalaxy2", + "tool_shed_repository": { + "changeset_revision": "b7edb37100af", + "name": "vrhyme", + "owner": "bgruening", + "tool_shed": "toolshed.g2.bx.psu.edu" + }, + "tool_state": "{\"bin_filters\": {\"bin\": {\"customize_bin_output\": \"default_options\", \"__current_case__\": 1}}, \"dereplication_options\": {\"dereplication\": {\"customize_dereplication\": \"default_options\", \"__current_case__\": 1}}, \"input_fasta\": {\"__class__\": \"ConnectedValue\"}, \"input_types\": {\"input\": {\"selector\": \"BAM_input\", \"__current_case__\": 0, \"BAM_inputs\": {\"__class__\": \"ConnectedValue\"}}}, \"min_length\": \"2000\", \"optional_genes\": {\"__class__\": \"RuntimeValue\"}, \"optional_proteins\": {\"__class__\": \"RuntimeValue\"}, \"read_alignment\": {\"alignment\": {\"customize_read_alignment\": \"default_options\", \"__current_case__\": 1}}, \"__page__\": 0, \"__rerun_remap_job_id__\": null}", + "tool_uuid": null, + "tool_version": "1.1.0+galaxygalaxy2", + "type": "tool", + "uuid": "4eeabe48-db0d-4765-9f22-8e661721d2ed", + "when": null, + "workflow_outputs": [ + { + "label": "best bins summery", + "output_name": "best bins summery", + "uuid": "b25af276-eaa7-4b76-ab21-3bde63fa5ea9" + }, + { + "label": "coverage file", + "output_name": "coverage file", + "uuid": "dfaca211-afab-4366-a8d5-7208366fd340" + }, + { + "label": "best bins fasta", + "output_name": "best bins fasta", + "uuid": "c6378a6d-bdbb-47b3-aad3-6b9c9233e02d" + }, + { + "label": "best bins genes", + "output_name": "best bins genes", + "uuid": "17ec40b2-bf58-4227-a30b-fd7e62241107" + }, + { + "label": "best bins membership", + "output_name": "best bins membership", + "uuid": "873f42c1-4285-4a4a-bb69-ab27e1140775" + }, + { + "label": "best bins proteins", + "output_name": "best bins proteins", + "uuid": "85e02f14-04ed-47f3-b7d1-9563a6b07c19" + } + ] + }, + "21": { + "annotation": "", + "content_id": "toolshed.g2.bx.psu.edu/repos/iuc/qiime_filter_fasta/qiime_filter_fasta/1.9.1.0", + "errors": null, + "id": 21, + "input_connections": { + "input_fasta_fp": { + "id": 17, + "output_name": "viruses" + }, + "selection|seq_id_fp": { + "id": 19, + "output_name": "output" + } + }, + "inputs": [ + { + "description": "runtime parameter for tool Filter fasta", + "name": "selection" + } + ], + "label": null, + "name": "Filter fasta", + "outputs": [ + { + "name": "fitered_fasta", + "type": "fasta" + } + ], + "position": { + "left": 4115.842618683897, + "top": 318.55527508289947 + }, + "post_job_actions": {}, + "tool_id": "toolshed.g2.bx.psu.edu/repos/iuc/qiime_filter_fasta/qiime_filter_fasta/1.9.1.0", + "tool_shed_repository": { + "changeset_revision": "11b19edeb3af", + "name": "qiime_filter_fasta", + "owner": "iuc", + "tool_shed": "toolshed.g2.bx.psu.edu" + }, + "tool_state": "{\"input_fasta_fp\": {\"__class__\": \"ConnectedValue\"}, \"negate\": false, \"selection\": {\"type\": \"seq_list\", \"__current_case__\": 1, \"seq_id_fp\": {\"__class__\": \"ConnectedValue\"}}, \"__page__\": 0, \"__rerun_remap_job_id__\": null}", + "tool_uuid": null, + "tool_version": "1.9.1.0", + "type": "tool", + "uuid": "d2376dc7-ba7b-451e-a9d2-a0c728157142", + "when": null, + "workflow_outputs": [] + }, + "22": { + "annotation": "", + "content_id": "toolshed.g2.bx.psu.edu/repos/iuc/pharokka/pharokka/1.3.2+galaxy0", + "errors": null, + "id": 22, + "input_connections": { + "fasta": { + "id": 21, + "output_name": "fitered_fasta" + } + }, + "inputs": [], + "label": null, + "name": "pharokka", + "outputs": [ + { + "name": "pharokka gbk", + "type": "genbank" + }, + { + "name": "pharokka gff", + "type": "gff" + }, + { + "name": "archive_output", + "type": "zip" + } + ], + "position": { + "left": 4535.593895679425, + "top": 401.61772335355647 + }, + "post_job_actions": { + "RenameDatasetActionpharokka_gbk": { + "action_arguments": { + "newname": "Pharokka: Genome annotations (Genbank)" + }, + "action_type": "RenameDatasetAction", + "output_name": "pharokka gbk" + }, + "RenameDatasetActionpharokka_gff": { + "action_arguments": { + "newname": "Pharokka: Genome annotations (GFF)" + }, + "action_type": "RenameDatasetAction", + "output_name": "pharokka gff" + } + }, + "tool_id": "toolshed.g2.bx.psu.edu/repos/iuc/pharokka/pharokka/1.3.2+galaxy0", + "tool_shed_repository": { + "changeset_revision": "2f40d2ccb0eb", + "name": "pharokka", + "owner": "iuc", + "tool_shed": "toolshed.g2.bx.psu.edu" + }, + "tool_state": "{\"db_cached\": \"db_from_2023-08-27T050123Z\", \"evalue\": \"1e-05\", \"fasta\": {\"__class__\": \"ConnectedValue\"}, \"gene_predictor\": \"-g phanotate\", \"meta\": true, \"terminase\": {\"terminase_selector\": \"no_terminase\", \"__current_case__\": 0}, \"zip_output\": true, \"__page__\": 0, \"__rerun_remap_job_id__\": null}", + "tool_uuid": null, + "tool_version": "1.3.2+galaxy0", + "type": "tool", + "uuid": "5d0ffbdb-8ae8-4f6e-895b-a2c940b3745b", + "when": null, + "workflow_outputs": [ + { + "label": "pharokka gff", + "output_name": "pharokka gff", + "uuid": "9f7059be-0524-4da1-819e-5a951f73746c" + }, + { + "label": "pharokka gbk", + "output_name": "pharokka gbk", + "uuid": "d5ba6663-f58e-480c-afa4-06a95966b46f" + } + ] + }, + "23": { + "annotation": "", + "content_id": "toolshed.g2.bx.psu.edu/repos/devteam/bowtie2/bowtie2/2.5.4+galaxy0", + "errors": null, + "id": 23, + "input_connections": { + "library|input_1": { + "id": 1, + "output_name": "output" + }, + "reference_genome|own_file": { + "id": 21, + "output_name": "fitered_fasta" + } + }, + "inputs": [ + { + "description": "runtime parameter for tool Bowtie2", + "name": "library" + }, + { + "description": "runtime parameter for tool Bowtie2", + "name": "reference_genome" + } + ], + "label": null, + "name": "Bowtie2", + "outputs": [ + { + "name": "output", + "type": "bam" + } + ], + "position": { + "left": 4531.567180702245, + "top": 684.9071348381411 + }, + "post_job_actions": { + "RenameDatasetActionoutput": { + "action_arguments": { + "newname": "Bowtie2: alignments" + }, + "action_type": "RenameDatasetAction", + "output_name": "output" + } + }, + "tool_id": "toolshed.g2.bx.psu.edu/repos/devteam/bowtie2/bowtie2/2.5.4+galaxy0", + "tool_shed_repository": { + "changeset_revision": "f76cbb84d67f", + "name": "bowtie2", + "owner": "devteam", + "tool_shed": "toolshed.g2.bx.psu.edu" + }, + "tool_state": "{\"analysis_type\": {\"analysis_type_selector\": \"simple\", \"__current_case__\": 0, \"presets\": \"no_presets\"}, \"library\": {\"type\": \"paired_collection\", \"__current_case__\": 1, \"input_1\": {\"__class__\": \"ConnectedValue\"}, \"unaligned_file\": false, \"aligned_file\": false, \"paired_options\": {\"paired_options_selector\": \"yes\", \"__current_case__\": 0, \"I\": \"0\", \"X\": \"500\", \"fr_rf_ff\": \"--fr\", \"no_mixed\": false, \"no_discordant\": true, \"dovetail\": false, \"no_contain\": false, \"no_overlap\": false}}, \"reference_genome\": {\"source\": \"history\", \"__current_case__\": 1, \"own_file\": {\"__class__\": \"ConnectedValue\"}}, \"rg\": {\"rg_selector\": \"set_id_auto\", \"__current_case__\": 2}, \"sam_options\": {\"sam_options_selector\": \"yes\", \"__current_case__\": 0, \"sam_opt\": false, \"no_unal\": true, \"omit_sec_seq\": false, \"sam_no_qname_trunc\": false, \"xeq\": false, \"soft_clipped_unmapped_tlen\": false, \"reorder\": false}, \"save_mapping_stats\": false, \"__page__\": 0, \"__rerun_remap_job_id__\": null}", + "tool_uuid": null, + "tool_version": "2.5.4+galaxy0", + "type": "tool", + "uuid": "ffc1c233-921b-4748-a7f4-c6cc4e55a877", + "when": null, + "workflow_outputs": [ + { + "label": "bam for CoverM", + "output_name": "output", + "uuid": "96542944-6883-4f4f-81de-8613b4938252" + } + ] + }, + "24": { + "annotation": "", + "content_id": "toolshed.g2.bx.psu.edu/repos/ufz/iphop_predict/iphop_predict/1.4.2+galaxy0", + "errors": null, + "id": 24, + "input_connections": { + "fa_file": { + "id": 21, + "output_name": "fitered_fasta" + } + }, + "inputs": [], + "label": null, + "name": "iPHoP predict", + "outputs": [ + { + "name": "detailed_per_tool", + "type": "csv" + }, + { + "name": "host_genome", + "type": "csv" + }, + { + "name": "host_genus", + "type": "csv" + } + ], + "position": { + "left": 4605.5315171229, + "top": 88.77053687137217 + }, + "post_job_actions": {}, + "tool_id": "toolshed.g2.bx.psu.edu/repos/ufz/iphop_predict/iphop_predict/1.4.2+galaxy0", + "tool_shed_repository": { + "changeset_revision": "be0d13020aec", + "name": "iphop_predict", + "owner": "ufz", + "tool_shed": "toolshed.g2.bx.psu.edu" + }, + "tool_state": "{\"db_dir\": \"iPHoP_db_Jun25_rw\", \"fa_file\": {\"__class__\": \"ConnectedValue\"}, \"min_score\": \"90\", \"no_qc\": false, \"__page__\": 0, \"__rerun_remap_job_id__\": null}", + "tool_uuid": null, + "tool_version": "1.4.2+galaxy0", + "type": "tool", + "uuid": "911e9ff7-7eb1-4bb6-9d0d-aecfd1ce8721", + "when": null, + "workflow_outputs": [] + }, + "25": { + "annotation": "", + "content_id": "toolshed.g2.bx.psu.edu/repos/iuc/coverm_contig/coverm_contig/0.7.0+galaxy0", + "errors": null, + "id": 25, + "input_connections": { + "mapped|mode|bam_files": { + "id": 23, + "output_name": "output" + } + }, + "inputs": [], + "label": null, + "name": "CoverM contig", + "outputs": [ + { + "name": "output", + "type": "tabular" + } + ], + "position": { + "left": 4760, + "top": 690 + }, + "post_job_actions": { + "RenameDatasetActionoutput": { + "action_arguments": { + "newname": "CoverM_coverage" + }, + "action_type": "RenameDatasetAction", + "output_name": "output" + } + }, + "tool_id": "toolshed.g2.bx.psu.edu/repos/iuc/coverm_contig/coverm_contig/0.7.0+galaxy0", + "tool_shed_repository": { + "changeset_revision": "28d740f2c0b0", + "name": "coverm_contig", + "owner": "iuc", + "tool_shed": "toolshed.g2.bx.psu.edu" + }, + "tool_state": "{\"alignment\": {\"min_read_aligned_length\": \"0\", \"min_read_percent_identity\": \"0.0\", \"min_read_aligned_percent\": \"0.0\", \"proper_pairs_only\": {\"proper_pairs_only\": \"\", \"__current_case__\": 1}, \"exclude_supplementary\": false}, \"cov\": {\"methods\": [\"count\"], \"trim_min\": \"5\", \"trim_max\": \"95\", \"min_covered_fraction\": \"0\", \"contig_end_exclusion\": \"75\"}, \"mapped\": {\"mapped\": \"mapped\", \"__current_case__\": 0, \"mode\": {\"mode\": \"co\", \"__current_case__\": 1, \"bam_files\": {\"__class__\": \"ConnectedValue\"}}, \"sharded\": false}, \"output_format\": \"dense\", \"__page__\": 0, \"__rerun_remap_job_id__\": null}", + "tool_uuid": null, + "tool_version": "0.7.0+galaxy0", + "type": "tool", + "uuid": "475e8080-1b4c-4a8d-8bfa-184b4e419fef", + "when": null, + "workflow_outputs": [ + { + "label": "coverage", + "output_name": "output", + "uuid": "18d8dff8-2c54-4284-b416-229943013604" + } + ] + } + }, + "tags": [ + "name:FAIRyMAGs", + "microbiome", + "name:metagenomics", + "virus" + ], + "uuid": "3c3c4954-890c-4c12-a45e-f3fbf06d32c4", + "version": 1 +} \ No newline at end of file From 4575fb5c4c31d266d34581cf6dfd12652ba17969 Mon Sep 17 00:00:00 2001 From: SantaMcCloud Date: Mon, 27 Apr 2026 23:27:29 +0200 Subject: [PATCH 2/3] change input to a smaller input --- ...l-detection-from-bulk-metagenomes-test.yml | 71 ++++++------------- 1 file changed, 22 insertions(+), 49 deletions(-) diff --git a/workflows/microbiome/viral-detection-from-bulk-metagenomes/viral-detection-from-bulk-metagenomes-test.yml b/workflows/microbiome/viral-detection-from-bulk-metagenomes/viral-detection-from-bulk-metagenomes-test.yml index 85e6db94c7..3b46d97b62 100644 --- a/workflows/microbiome/viral-detection-from-bulk-metagenomes/viral-detection-from-bulk-metagenomes-test.yml +++ b/workflows/microbiome/viral-detection-from-bulk-metagenomes/viral-detection-from-bulk-metagenomes-test.yml @@ -6,10 +6,10 @@ elements: - class: File identifier: SRR24759598 - location: https://zenodo.org/records/19798600/files/SRR24759598.fasta + location: https://zenodo.org/records/19831629/files/SRR24759598.fasta - class: File identifier: SRR24759616 - location: https://zenodo.org/records/19798600/files/SRR24759616.fasta + location: https://zenodo.org/records/19831629/files/SRR24759616.fasta Trimmed reads: class: Collection collection_type: list:paired @@ -20,120 +20,93 @@ elements: - class: File identifier: forward - location: https://zenodo.org/records/19798600/files/SRR24759598_forward.fastqsanger.gz + location: https://zenodo.org/records/19831629/files/SRR24759598_forward.fastqsanger.gz - class: File identifier: reverse - location: https://zenodo.org/records/19798600/files/SRR24759598_reverse.fastqsanger.gz + location: https://zenodo.org/records/19831629/files/SRR24759598_reverse.fastqsanger.gz - class: Collection type: paired identifier: SRR24759616 elements: - class: File identifier: forward - location: https://zenodo.org/records/19798600/files/SRR24759616_forward.fastqsanger.gz + location: https://zenodo.org/records/19831629/files/SRR24759616_forward.fastqsanger.gz - class: File identifier: reverse - location: https://zenodo.org/records/19798600/files/SRR24759616_reverse.fastqsanger.gz + location: https://zenodo.org/records/19831629/files/SRR24759616_reverse.fastqsanger.gz outputs: output cluster: asserts: - that: has_n_lines - n: 3249 + n: 315 delta: 10 quality summary: asserts: - that: has_n_lines - n: 949 + n: 300 delta: 10 complete genomes: asserts: - that: has_n_lines - n: 4 + n: 2 delta: 1 - that: has_text text: "contig_id" coverage: asserts: - that: has_n_lines - n: 37 - delta: 5 + n: 6 + delta: 1 - that: has_text text: "Contig" output seqs: asserts: - that: has_size - size: 6800000 + size: 776500 delta: 50000 best bins membership: asserts: - that: has_n_lines - n: 491 - delta: 25 - - that: has_text - text: "scaffold" + n: 0 best bins summery: asserts: - that: has_n_lines - n: 111 - delta: 10 - - that: has_text - text: "proteins" + n: 0 coverage file: asserts: - that: has_n_lines - n: 694 - delta: 50 + n: 83 + delta: 10 - that: has_text text: "scaffold" pharokka gbk: asserts: - that: has_size - size: 4400000 + size: 557600 delta: 50000 pharokka gff: asserts: - that: has_size - size: 2700000 + size: 342800 delta: 50000 genomad fasta: element_tests: SRR24759616: asserts: - that: has_size - value: 3000000 + value: 434300 delta: 50000 bam for vRhyme: element_tests: SRR24759616: asserts: - that: has_size - value: 34900000 - delta: 50000 - best bins genes: - element_tests: - 1: - asserts: - - that: has_size - value: 238100 - delta: 5000 - best bins proteins: - element_tests: - 1: - asserts: - - that: has_size - value: 119200 - delta: 5000 - best bins fasta: - element_tests: - 1: - asserts: - - that: has_size - value: 191600 + value: 65500 delta: 5000 bam for CoverM: element_tests: SRR24759616: asserts: - that: has_size - value: 9200000 - delta: 50000 \ No newline at end of file + value: 24900 + delta: 5000 \ No newline at end of file From a6ff2273718d6c24cde47fb1b893dee27243bead Mon Sep 17 00:00:00 2001 From: SantaMcCloud Date: Tue, 28 Apr 2026 01:47:20 +0200 Subject: [PATCH 3/3] fix test --- .../viral-detection-from-bulk-metagenomes.ga | 295 ++++++++---------- 1 file changed, 127 insertions(+), 168 deletions(-) diff --git a/workflows/microbiome/viral-detection-from-bulk-metagenomes/viral-detection-from-bulk-metagenomes.ga b/workflows/microbiome/viral-detection-from-bulk-metagenomes/viral-detection-from-bulk-metagenomes.ga index 7712c3bd7e..79edb68c73 100644 --- a/workflows/microbiome/viral-detection-from-bulk-metagenomes/viral-detection-from-bulk-metagenomes.ga +++ b/workflows/microbiome/viral-detection-from-bulk-metagenomes/viral-detection-from-bulk-metagenomes.ga @@ -3,17 +3,6 @@ "annotation": "This workflow identifies viral contigs from metagenomic assemblies using geNomad and supports taxonomy, functional annotation, binning, and host prediction.", "comments": [ { - "child_steps": [ - 5, - 6, - 7, - 9, - 4, - 3, - 2, - 0, - 8 - ], "color": "none", "data": { "title": "Viral contigs prediction" @@ -30,73 +19,54 @@ "type": "frame" }, { - "child_steps": [ - 10, - 13, - 11, - 12 - ], - "color": "orange", + "color": "red", "data": { - "title": "Proviruses check" + "title": "Binning viral genomes-vMAGs" }, - "id": 1, + "id": 7, "position": [ - 1862, - 17.69999999999999 + 4510.299999999999, + 903 ], "size": [ - 1087, - 705 + 505, + 641 ], "type": "frame" }, { - "child_steps": [ - 15, - 16, - 14 - ], - "color": "green", + "color": "orange", "data": { - "title": "Clustering" + "title": "Coverage calculation" }, - "id": 2, + "id": 6, "position": [ - 3029.6, - 99.49999999999997 + 4511.599999999999, + 644.9 ], "size": [ - 515, - 613 + 468.1, + 224.3 ], "type": "frame" }, { - "child_steps": [ - 21, - 17, - 19 - ], - "color": "blue", + "color": "pink", "data": { - "title": "Quality check & Filtering" + "title": "Functional prediction" }, - "id": 3, + "id": 5, "position": [ - 3605, - 237.39999999999998 + 4517.299999999999, + 357.4 ], "size": [ - 742, - 356 + 309, + 260 ], "type": "frame" }, { - "child_steps": [ - 24 - ], "color": "yellow", "data": { "title": "Host prediction" @@ -113,61 +83,50 @@ "type": "frame" }, { - "child_steps": [ - 22 - ], - "color": "pink", + "color": "blue", "data": { - "title": "Functional prediction" + "title": "Quality check & Filtering" }, - "id": 5, + "id": 3, "position": [ - 4517.299999999999, - 357.4 + 3605, + 237.39999999999998 ], "size": [ - 309, - 260 + 742, + 356 ], "type": "frame" }, { - "child_steps": [ - 23, - 25 - ], - "color": "orange", + "color": "green", "data": { - "title": "Coverage calculation" + "title": "Clustering" }, - "id": 6, + "id": 2, "position": [ - 4511.599999999999, - 644.9 + 3029.6, + 99.49999999999997 ], "size": [ - 468.1, - 224.3 + 515, + 613 ], "type": "frame" }, { - "child_steps": [ - 18, - 20 - ], - "color": "red", + "color": "orange", "data": { - "title": "Binning viral genomes-vMAGs" + "title": "Proviruses check" }, - "id": 7, + "id": 1, "position": [ - 4510.299999999999, - 903 + 1862, + 17.69999999999999 ], "size": [ - 505, - 641 + 1087, + 705 ], "type": "frame" } @@ -215,7 +174,7 @@ "tool_state": "{\"optional\": false, \"tag\": null, \"collection_type\": \"list\", \"fields\": null, \"column_definitions\": null}", "tool_version": null, "type": "data_collection_input", - "uuid": "43e313cc-a415-46c8-a520-f55449fa7edc", + "uuid": "4c284fbc-00c3-49d8-a7de-02a4db95e383", "when": null, "workflow_outputs": [] }, @@ -242,7 +201,7 @@ "tool_state": "{\"optional\": false, \"tag\": null, \"collection_type\": \"list:paired\", \"fields\": null, \"column_definitions\": null}", "tool_version": null, "type": "data_collection_input", - "uuid": "2d387778-836a-4ed6-856f-a580aaff5d2e", + "uuid": "aff7c920-4da5-4f56-b174-76b34aa921e1", "when": null, "workflow_outputs": [] }, @@ -282,7 +241,7 @@ "tool_uuid": null, "tool_version": "9.5+galaxy3", "type": "tool", - "uuid": "b9c69689-2d73-44c2-8148-8db9db3ecc36", + "uuid": "7cf2bd2a-7d7e-4257-afca-e1b29baf6659", "when": null, "workflow_outputs": [] }, @@ -327,7 +286,7 @@ "tool_uuid": null, "tool_version": "0.5.2", "type": "tool", - "uuid": "19cc0397-e783-4d3e-a892-c0ccfaccd859", + "uuid": "b1e286ef-1efc-4d47-8e33-2b1ada9ae4bd", "when": null, "workflow_outputs": [] }, @@ -395,7 +354,7 @@ "tool_uuid": null, "tool_version": "1.11.1+galaxy0", "type": "tool", - "uuid": "0c99aaab-b08b-4d04-9f1c-7c03eaa27b9b", + "uuid": "ac6f9dfc-55bd-42d9-bd39-a082eb5422f0", "when": null, "workflow_outputs": [] }, @@ -448,7 +407,7 @@ "tool_uuid": null, "tool_version": "3.3.2", "type": "tool", - "uuid": "6f07aa83-23eb-40ff-8d80-c3bda0a8dba2", + "uuid": "328fde9f-8eef-4902-bab7-8cf9d7ca8542", "when": null, "workflow_outputs": [] }, @@ -496,7 +455,7 @@ "tool_uuid": null, "tool_version": "5.1.0", "type": "tool", - "uuid": "9ffbaefd-7ca4-4293-8b28-2ce72ecce978", + "uuid": "dc2113d7-7734-442b-a442-f60e1bc929db", "when": null, "workflow_outputs": [] }, @@ -544,7 +503,7 @@ "tool_uuid": null, "tool_version": "5.1.0", "type": "tool", - "uuid": "f89553d1-2df6-474f-848d-621412fc9df2", + "uuid": "7fe022a4-92e2-4b8b-80ac-b073f995c0ea", "when": null, "workflow_outputs": [] }, @@ -593,7 +552,7 @@ "tool_uuid": null, "tool_version": "1.9.1.0", "type": "tool", - "uuid": "57503892-ed49-41ef-a16e-339afed93270", + "uuid": "e0cd4ae8-4cc1-4f9f-8549-0518a9257e3f", "when": null, "workflow_outputs": [] }, @@ -641,13 +600,13 @@ "tool_uuid": null, "tool_version": "5.1.0", "type": "tool", - "uuid": "c38f9178-c61e-47c7-9b93-2fe1e5106a95", + "uuid": "cce91c2c-37b0-4e49-a767-bf06ab7369d2", "when": null, "workflow_outputs": [ { "label": "genomad fasta", "output_name": "output", - "uuid": "8bc262c6-2be8-4dc8-9553-afe1a067aa59" + "uuid": "344fca38-f9b3-49c8-919a-51e9828aa23b" } ] }, @@ -667,11 +626,11 @@ "name": "CheckV end to end", "outputs": [ { - "name": "quality summary", + "name": "quality_summary", "type": "tabular" }, { - "name": "complete genomes", + "name": "complete_genomes", "type": "tabular" }, { @@ -691,12 +650,12 @@ "HideDatasetActioncomplete_genomes": { "action_arguments": {}, "action_type": "HideDatasetAction", - "output_name": "complete genomes" + "output_name": "complete_genomes" }, "HideDatasetActionquality_summary": { "action_arguments": {}, "action_type": "HideDatasetAction", - "output_name": "quality summary" + "output_name": "quality_summary" } }, "tool_id": "toolshed.g2.bx.psu.edu/repos/ufz/checkv_end_to_end/checkv_end_to_end/1.0.3+galaxy0", @@ -710,7 +669,7 @@ "tool_uuid": null, "tool_version": "1.0.3+galaxy0", "type": "tool", - "uuid": "ba443f12-57c1-4c82-a0bf-7178dc9de71d", + "uuid": "150a207e-ce8c-463f-9871-ecf61a668b71", "when": null, "workflow_outputs": [] }, @@ -749,7 +708,7 @@ "tool_uuid": null, "tool_version": "1.1.0", "type": "tool", - "uuid": "5f77a82a-979f-40bf-8134-92b4c8c650e0", + "uuid": "fabcc081-1d28-4a2b-992c-5470cb25ae90", "when": null, "workflow_outputs": [] }, @@ -817,7 +776,7 @@ "tool_uuid": null, "tool_version": "1.11.1+galaxy0", "type": "tool", - "uuid": "3a1e9e1a-b2c8-4acf-a56f-fae383674536", + "uuid": "a94316b7-5431-4863-9b2f-1618b574200c", "when": null, "workflow_outputs": [] }, @@ -869,7 +828,7 @@ "tool_uuid": null, "tool_version": "9.5+galaxy3", "type": "tool", - "uuid": "ee98372c-aac2-4623-bc08-79f25ffd3697", + "uuid": "f4cf1e57-dcc8-4603-91e4-3ccab491b349", "when": null, "workflow_outputs": [] }, @@ -909,7 +868,7 @@ "tool_uuid": null, "tool_version": "smf-v1.7-0_utils-v2.1.1-1", "type": "tool", - "uuid": "fc71e43a-f90d-4fc0-a4c1-41783a118868", + "uuid": "c947e2e3-a0eb-4128-8e1b-6310d42e4a35", "when": null, "workflow_outputs": [] }, @@ -933,7 +892,7 @@ "type": "fasta" }, { - "name": "output cluster", + "name": "output_cluster", "type": "tabular" } ], @@ -952,7 +911,7 @@ "newname": "MMseqs2: Adjecency list" }, "action_type": "RenameDatasetAction", - "output_name": "output cluster" + "output_name": "output_cluster" }, "RenameDatasetActionoutput_rep_seq": { "action_arguments": { @@ -973,13 +932,13 @@ "tool_uuid": null, "tool_version": "17-b804f+galaxy0", "type": "tool", - "uuid": "1459a99e-c209-4b8e-91a2-e541cc51fefc", + "uuid": "b6fc98c7-c0a4-4464-b5e1-dcc14f91d6e7", "when": null, "workflow_outputs": [ { "label": "output cluster", - "output_name": "output cluster", - "uuid": "ee93c9f9-66e1-435d-a57a-3204efa076dd" + "output_name": "output_cluster", + "uuid": "ff713c24-ddef-4320-bed6-a58912d27e8d" } ] }, @@ -1027,13 +986,13 @@ "tool_uuid": null, "tool_version": "1.0.3", "type": "tool", - "uuid": "d1c9852c-53c0-4051-9917-4da70b00b7a9", + "uuid": "f9fa9b1e-c8e9-41be-b968-353e1e838eba", "when": null, "workflow_outputs": [ { "label": "output seqs", "output_name": "out_file1", - "uuid": "d6a81aa1-2777-4e1f-9834-4f9e762a6494" + "uuid": "a32fa5a6-f8f0-488f-8708-bb3f5968e68e" } ] }, @@ -1053,11 +1012,11 @@ "name": "CheckV end to end", "outputs": [ { - "name": "quality summary", + "name": "quality_summary", "type": "tabular" }, { - "name": "complete genomes", + "name": "complete_genomes", "type": "tabular" }, { @@ -1079,14 +1038,14 @@ "newname": "CheckV: Complete Genomes" }, "action_type": "RenameDatasetAction", - "output_name": "complete genomes" + "output_name": "complete_genomes" }, "RenameDatasetActionquality_summary": { "action_arguments": { "newname": "CheckV: Quality summary" }, "action_type": "RenameDatasetAction", - "output_name": "quality summary" + "output_name": "quality_summary" } }, "tool_id": "toolshed.g2.bx.psu.edu/repos/ufz/checkv_end_to_end/checkv_end_to_end/1.0.3+galaxy0", @@ -1100,18 +1059,18 @@ "tool_uuid": null, "tool_version": "1.0.3+galaxy0", "type": "tool", - "uuid": "2f497eab-34ab-4a70-a916-7efbcb92f907", + "uuid": "13fc84f7-d6b6-4c4b-837c-e97157f04817", "when": null, "workflow_outputs": [ { - "label": "quality summary", - "output_name": "quality summary", - "uuid": "cd5769f7-22af-4587-bda1-5c0be3365a2c" + "label": "complete genomes", + "output_name": "complete_genomes", + "uuid": "44556190-176b-4d7d-bdbb-a59aa82e0a1a" }, { - "label": "complete genomes", - "output_name": "complete genomes", - "uuid": "2d12da96-c84f-44e8-b5ad-a740436f5624" + "label": "quality summary", + "output_name": "quality_summary", + "uuid": "ba97dddb-f174-4f49-8c14-48c81b5ba88f" } ] }, @@ -1172,13 +1131,13 @@ "tool_uuid": null, "tool_version": "2.5.4+galaxy0", "type": "tool", - "uuid": "abdb17f7-9b80-4436-86ca-a349566c313c", + "uuid": "a20b3a03-0c80-4c54-8c14-bad719f464d2", "when": null, "workflow_outputs": [ { "label": "bam for vRhyme", "output_name": "output", - "uuid": "a20e4d10-0f40-4878-8dd9-7d446b41344b" + "uuid": "0809a215-76d4-4f58-b0e3-7f8b1824edbc" } ] }, @@ -1190,7 +1149,7 @@ "input_connections": { "tables_0|table": { "id": 17, - "output_name": "quality summary" + "output_name": "quality_summary" } }, "inputs": [ @@ -1231,7 +1190,7 @@ "tool_uuid": null, "tool_version": "3.3.2", "type": "tool", - "uuid": "ce48ba6e-ecfc-41bd-bf62-50973968a76b", + "uuid": "9a09c016-9c18-4aaf-bf4a-49ea9af91bb3", "when": null, "workflow_outputs": [] }, @@ -1264,15 +1223,15 @@ "name": "vRhyme", "outputs": [ { - "name": "best bins fasta", + "name": "best_bins_fasta", "type": "input" }, { - "name": "best bins genes", + "name": "best_bins_genes", "type": "input" }, { - "name": "best bins proteins", + "name": "best_bins_proteins", "type": "input" }, { @@ -1280,11 +1239,11 @@ "type": "tabular" }, { - "name": "best bins membership", + "name": "best_bins_membership", "type": "tabular" }, { - "name": "best bins summery", + "name": "best_bins_summery", "type": "tabular" }, { @@ -1300,7 +1259,7 @@ "type": "tabular" }, { - "name": "coverage file", + "name": "coverage_file", "type": "tabular" } ], @@ -1320,38 +1279,38 @@ "tool_uuid": null, "tool_version": "1.1.0+galaxygalaxy2", "type": "tool", - "uuid": "4eeabe48-db0d-4765-9f22-8e661721d2ed", + "uuid": "edeef418-03d9-47f7-ac13-194502521f0e", "when": null, "workflow_outputs": [ { - "label": "best bins summery", - "output_name": "best bins summery", - "uuid": "b25af276-eaa7-4b76-ab21-3bde63fa5ea9" + "label": "best bins proteins", + "output_name": "best_bins_proteins", + "uuid": "5dbc207a-cfab-4263-82ca-32e24f61515b" }, { - "label": "coverage file", - "output_name": "coverage file", - "uuid": "dfaca211-afab-4366-a8d5-7208366fd340" + "label": "best bins membership", + "output_name": "best_bins_membership", + "uuid": "b238ea34-73b1-4307-a770-5c09c3c8e2d8" }, { - "label": "best bins fasta", - "output_name": "best bins fasta", - "uuid": "c6378a6d-bdbb-47b3-aad3-6b9c9233e02d" + "label": "best bins summery", + "output_name": "best_bins_summery", + "uuid": "59b41d73-29eb-413d-8c97-1691da7babc8" }, { - "label": "best bins genes", - "output_name": "best bins genes", - "uuid": "17ec40b2-bf58-4227-a30b-fd7e62241107" + "label": "best bins fasta", + "output_name": "best_bins_fasta", + "uuid": "429c2906-76ac-4ab5-960c-9c19b4c21590" }, { - "label": "best bins membership", - "output_name": "best bins membership", - "uuid": "873f42c1-4285-4a4a-bb69-ab27e1140775" + "label": "coverage file", + "output_name": "coverage_file", + "uuid": "dbefe59e-2f56-423d-8037-3a26ba21a8a4" }, { - "label": "best bins proteins", - "output_name": "best bins proteins", - "uuid": "85e02f14-04ed-47f3-b7d1-9563a6b07c19" + "label": "best bins genes", + "output_name": "best_bins_genes", + "uuid": "0ab1f1a5-4c7c-471b-a9ac-0f4f6341bc56" } ] }, @@ -1400,7 +1359,7 @@ "tool_uuid": null, "tool_version": "1.9.1.0", "type": "tool", - "uuid": "d2376dc7-ba7b-451e-a9d2-a0c728157142", + "uuid": "0258abb1-d6a0-45d1-a0ca-c51f5b3640a6", "when": null, "workflow_outputs": [] }, @@ -1420,11 +1379,11 @@ "name": "pharokka", "outputs": [ { - "name": "pharokka gbk", + "name": "pharokka_gbk", "type": "genbank" }, { - "name": "pharokka gff", + "name": "pharokka_gff", "type": "gff" }, { @@ -1442,14 +1401,14 @@ "newname": "Pharokka: Genome annotations (Genbank)" }, "action_type": "RenameDatasetAction", - "output_name": "pharokka gbk" + "output_name": "pharokka_gbk" }, "RenameDatasetActionpharokka_gff": { "action_arguments": { "newname": "Pharokka: Genome annotations (GFF)" }, "action_type": "RenameDatasetAction", - "output_name": "pharokka gff" + "output_name": "pharokka_gff" } }, "tool_id": "toolshed.g2.bx.psu.edu/repos/iuc/pharokka/pharokka/1.3.2+galaxy0", @@ -1463,18 +1422,18 @@ "tool_uuid": null, "tool_version": "1.3.2+galaxy0", "type": "tool", - "uuid": "5d0ffbdb-8ae8-4f6e-895b-a2c940b3745b", + "uuid": "5e03edea-0846-4ad6-82b9-6763488449c3", "when": null, "workflow_outputs": [ { - "label": "pharokka gff", - "output_name": "pharokka gff", - "uuid": "9f7059be-0524-4da1-819e-5a951f73746c" + "label": "pharokka gbk", + "output_name": "pharokka_gbk", + "uuid": "80b8e9e1-2161-4a2a-83f5-68acb708fc9d" }, { - "label": "pharokka gbk", - "output_name": "pharokka gbk", - "uuid": "d5ba6663-f58e-480c-afa4-06a95966b46f" + "label": "pharokka gff", + "output_name": "pharokka_gff", + "uuid": "c5d167ef-e726-492d-a492-ee4056ec470e" } ] }, @@ -1535,13 +1494,13 @@ "tool_uuid": null, "tool_version": "2.5.4+galaxy0", "type": "tool", - "uuid": "ffc1c233-921b-4748-a7f4-c6cc4e55a877", + "uuid": "0d736918-5359-4494-8416-e32a20b566c8", "when": null, "workflow_outputs": [ { "label": "bam for CoverM", "output_name": "output", - "uuid": "96542944-6883-4f4f-81de-8613b4938252" + "uuid": "4b65cdd1-aa58-413b-9f03-9b5225637c51" } ] }, @@ -1589,7 +1548,7 @@ "tool_uuid": null, "tool_version": "1.4.2+galaxy0", "type": "tool", - "uuid": "911e9ff7-7eb1-4bb6-9d0d-aecfd1ce8721", + "uuid": "08681d8f-a9a8-4bfc-b1e6-3c6694907756", "when": null, "workflow_outputs": [] }, @@ -1637,13 +1596,13 @@ "tool_uuid": null, "tool_version": "0.7.0+galaxy0", "type": "tool", - "uuid": "475e8080-1b4c-4a8d-8bfa-184b4e419fef", + "uuid": "0bdf913a-cb73-489e-909e-04f101b7b82e", "when": null, "workflow_outputs": [ { "label": "coverage", "output_name": "output", - "uuid": "18d8dff8-2c54-4284-b416-229943013604" + "uuid": "acbb0c84-91c8-4340-ac95-49b54402124e" } ] } @@ -1654,6 +1613,6 @@ "name:metagenomics", "virus" ], - "uuid": "3c3c4954-890c-4c12-a45e-f3fbf06d32c4", + "uuid": "242b286a-e9da-4156-8121-3028d7105647", "version": 1 } \ No newline at end of file