diff --git a/workflows/VGP-assembly-v2/Assembly-decontamination-VGP9/Assembly-decontamination-VGP9-tests.yml b/workflows/VGP-assembly-v2/Assembly-decontamination-VGP9/Assembly-decontamination-VGP9-tests.yml index 84faabea1..9ad050ede 100644 --- a/workflows/VGP-assembly-v2/Assembly-decontamination-VGP9/Assembly-decontamination-VGP9-tests.yml +++ b/workflows/VGP-assembly-v2/Assembly-decontamination-VGP9/Assembly-decontamination-VGP9-tests.yml @@ -9,7 +9,7 @@ mito_scaff_names: asserts: has_text: - text: "SCAFFOLD_82" + text: "scaffold_82" final decontaminated assembly: decompress: true asserts: @@ -18,4 +18,4 @@ contaminants_table: asserts: has_text: - text: "SCAFFOLD_200" + text: "scaffold_200" diff --git a/workflows/VGP-assembly-v2/Assembly-decontamination-VGP9/Assembly-decontamination-VGP9.ga b/workflows/VGP-assembly-v2/Assembly-decontamination-VGP9/Assembly-decontamination-VGP9.ga index becfb8caa..4e2cbc599 100644 --- a/workflows/VGP-assembly-v2/Assembly-decontamination-VGP9/Assembly-decontamination-VGP9.ga +++ b/workflows/VGP-assembly-v2/Assembly-decontamination-VGP9/Assembly-decontamination-VGP9.ga @@ -11,7 +11,7 @@ ], "format-version": "0.1", "license": "BSD-3-Clause", - "release": "0.2", + "release": "0.3", "name": "Assembly-decontamination-VGP9", "report": { "markdown": "\n# Workflow Execution Report\n\n### Worflow ran on: \n\n```galaxy\ninvocation_time()\n```\n\n# List of contaminants\n\n\r\n```galaxy\nhistory_dataset_as_table(output=\"contaminants_table\")\n```\r\n\n\n# List of Mitochondrial scaffolds\n\r\n```galaxy\nhistory_dataset_as_table(output=\"mito_scaff_names\")\n```\r\n\n\n\n\n## Workflow\n```galaxy\nworkflow_display()\n```\n" @@ -33,8 +33,8 @@ "name": "Input dataset", "outputs": [], "position": { - "left": 0, - "top": 579.578125 + "left": 0.0, + "top": 573.2100224386197 }, "tool_id": null, "tool_state": "{\"optional\": false, \"format\": [\"fasta\"], \"tag\": null}", @@ -60,7 +60,7 @@ "name": "Input parameter", "outputs": [], "position": { - "left": 72.984375, + "left": 0.5475811709443406, "top": 692.7734375 }, "tool_id": null, @@ -73,70 +73,18 @@ { "label": null, "output_name": "output", - "uuid": "9b1c5517-60c3-49b5-9e9e-f85e883b6a5f" + "uuid": "34f0edb5-742e-4de2-923f-1fb93e511ca9" } ] }, "2": { - "annotation": "", - "content_id": "toolshed.g2.bx.psu.edu/repos/bgruening/text_processing/tp_sed_tool/9.3+galaxy1", - "errors": null, - "id": 2, - "input_connections": { - "infile": { - "id": 0, - "output_name": "output" - } - }, - "inputs": [], - "label": "lower to uppercase", - "name": "Text transformation", - "outputs": [ - { - "name": "output", - "type": "input" - } - ], - "position": { - "left": 342.8124888681364, - "top": 375.78555810947694 - }, - "post_job_actions": { - "ChangeDatatypeActionoutput": { - "action_arguments": { - "newtype": "fasta" - }, - "action_type": "ChangeDatatypeAction", - "output_name": "output" - }, - "HideDatasetActionoutput": { - "action_arguments": {}, - "action_type": "HideDatasetAction", - "output_name": "output" - } - }, - "tool_id": "toolshed.g2.bx.psu.edu/repos/bgruening/text_processing/tp_sed_tool/9.3+galaxy1", - "tool_shed_repository": { - "changeset_revision": "fbf99087e067", - "name": "text_processing", - "owner": "bgruening", - "tool_shed": "toolshed.g2.bx.psu.edu" - }, - "tool_state": "{\"adv_opts\": {\"adv_opts_selector\": \"basic\", \"__current_case__\": 0}, \"code\": \"s/.*/\\\\U&/\", \"infile\": {\"__class__\": \"ConnectedValue\"}, \"__page__\": null, \"__rerun_remap_job_id__\": null}", - "tool_version": "9.3+galaxy1", - "type": "tool", - "uuid": "b9b3d9b9-1716-486d-b65c-b0fb196cbc01", - "when": null, - "workflow_outputs": [] - }, - "3": { "annotation": "", "content_id": "toolshed.g2.bx.psu.edu/repos/devteam/ncbi_blast_plus/ncbi_dustmasker_wrapper/2.14.1+galaxy2", "errors": null, - "id": 3, + "id": 2, "input_connections": { "db_opts|subject": { - "id": 2, + "id": 0, "output_name": "output" } }, @@ -150,8 +98,8 @@ } ], "position": { - "left": 652.953125, - "top": 323.6484375 + "left": 463.79758117094434, + "top": 292.69140625 }, "post_job_actions": { "HideDatasetActionoutfile": { @@ -174,14 +122,14 @@ "when": null, "workflow_outputs": [] }, - "4": { + "3": { "annotation": "", "content_id": "toolshed.g2.bx.psu.edu/repos/bgruening/text_processing/tp_sed_tool/9.3+galaxy1", "errors": null, - "id": 4, + "id": 3, "input_connections": { "infile": { - "id": 3, + "id": 2, "output_name": "outfile" } }, @@ -195,8 +143,8 @@ } ], "position": { - "left": 972.0000745777726, - "top": 355.5823870316441 + "left": 827.4147686709443, + "top": 312.24609375 }, "post_job_actions": { "ChangeDatatypeActionoutput": { @@ -214,30 +162,30 @@ }, "tool_id": "toolshed.g2.bx.psu.edu/repos/bgruening/text_processing/tp_sed_tool/9.3+galaxy1", "tool_shed_repository": { - "changeset_revision": "fbf99087e067", + "changeset_revision": "86755160afbf", "name": "text_processing", "owner": "bgruening", "tool_shed": "toolshed.g2.bx.psu.edu" }, - "tool_state": "{\"adv_opts\": {\"adv_opts_selector\": \"basic\", \"__current_case__\": 0}, \"code\": \"s/[a-z]/N/g\", \"infile\": {\"__class__\": \"ConnectedValue\"}, \"__page__\": null, \"__rerun_remap_job_id__\": null}", + "tool_state": "{\"adv_opts\": {\"adv_opts_selector\": \"basic\", \"__current_case__\": 0}, \"code\": \"/^>/!y/atcgn/NNNNN/\", \"infile\": {\"__class__\": \"RuntimeValue\"}, \"__page__\": null, \"__rerun_remap_job_id__\": null}", "tool_version": "9.3+galaxy1", "type": "tool", "uuid": "5089350b-c1a9-498a-9786-9864d484f77a", "when": null, "workflow_outputs": [] }, - "5": { + "4": { "annotation": "", "content_id": "toolshed.g2.bx.psu.edu/repos/iuc/kraken2/kraken2/2.1.3+galaxy1", "errors": null, - "id": 5, + "id": 4, "input_connections": { "kraken2_database": { "id": 1, "output_name": "output" }, "single_paired|input_sequences": { - "id": 4, + "id": 3, "output_name": "output" } }, @@ -259,7 +207,7 @@ } ], "position": { - "left": 1372.5625, + "left": 1300.1257061709443, "top": 147.58203125 }, "post_job_actions": { @@ -289,14 +237,14 @@ } ] }, - "6": { + "5": { "annotation": "", "content_id": "toolshed.g2.bx.psu.edu/repos/devteam/ncbi_blast_plus/ncbi_blastn_wrapper/2.14.1+galaxy2", "errors": null, - "id": 6, + "id": 5, "input_connections": { "query": { - "id": 4, + "id": 3, "output_name": "output" } }, @@ -310,7 +258,7 @@ } ], "position": { - "left": 1365.8984375, + "left": 1293.4616436709443, "top": 539.6171875 }, "post_job_actions": {}, @@ -328,14 +276,14 @@ "when": null, "workflow_outputs": [] }, - "7": { + "6": { "annotation": "", "content_id": "Cut1", "errors": null, - "id": 7, + "id": 6, "input_connections": { "input": { - "id": 5, + "id": 4, "output_name": "output" } }, @@ -349,7 +297,7 @@ } ], "position": { - "left": 1727.19921875, + "left": 1654.7624249209443, "top": 53.078125 }, "post_job_actions": { @@ -367,59 +315,14 @@ "when": null, "workflow_outputs": [] }, - "8": { - "annotation": "", - "content_id": "toolshed.g2.bx.psu.edu/repos/bgruening/text_processing/tp_grep_tool/9.3+galaxy1", - "errors": null, - "id": 8, - "input_connections": { - "infile": { - "id": 5, - "output_name": "classified_out_s" - } - }, - "inputs": [], - "label": "contaminant scaffolds", - "name": "Search in textfiles", - "outputs": [ - { - "name": "output", - "type": "input" - } - ], - "position": { - "left": 1727.8671875, - "top": 204.953125 - }, - "post_job_actions": { - "HideDatasetActionoutput": { - "action_arguments": {}, - "action_type": "HideDatasetAction", - "output_name": "output" - } - }, - "tool_id": "toolshed.g2.bx.psu.edu/repos/bgruening/text_processing/tp_grep_tool/9.3+galaxy1", - "tool_shed_repository": { - "changeset_revision": "fbf99087e067", - "name": "text_processing", - "owner": "bgruening", - "tool_shed": "toolshed.g2.bx.psu.edu" - }, - "tool_state": "{\"case_sensitive\": \"-i\", \"color\": \"NOCOLOR\", \"infile\": {\"__class__\": \"ConnectedValue\"}, \"invert\": \"\", \"lines_after\": \"0\", \"lines_before\": \"0\", \"regex_type\": \"-G\", \"url_paste\": \"scaffold\", \"__page__\": null, \"__rerun_remap_job_id__\": null}", - "tool_version": "9.3+galaxy1", - "type": "tool", - "uuid": "372a2507-7844-43e7-9be0-7add6d5f6def", - "when": null, - "workflow_outputs": [] - }, - "9": { + "7": { "annotation": "", "content_id": "toolshed.g2.bx.psu.edu/repos/iuc/parse_mito_blast/parse_mito_blast/1.0.2+galaxy0", "errors": null, - "id": 9, + "id": 7, "input_connections": { "blastout": { - "id": 6, + "id": 5, "output_name": "output1" } }, @@ -437,8 +340,8 @@ } ], "position": { - "left": 1741, - "top": 516.84375 + "left": 1821.3783868183484, + "top": 482.19337215633186 }, "post_job_actions": {}, "tool_id": "toolshed.g2.bx.psu.edu/repos/iuc/parse_mito_blast/parse_mito_blast/1.0.2+galaxy0", @@ -461,14 +364,14 @@ } ] }, - "10": { + "8": { "annotation": "", "content_id": "Filter1", "errors": null, - "id": 10, + "id": 8, "input_connections": { "input": { - "id": 7, + "id": 6, "output_name": "out_file1" } }, @@ -482,7 +385,7 @@ } ], "position": { - "left": 2074.40625, + "left": 2001.9694561709443, "top": 0 }, "post_job_actions": { @@ -513,162 +416,59 @@ } ] }, - "11": { + "9": { "annotation": "", - "content_id": "toolshed.g2.bx.psu.edu/repos/bgruening/text_processing/tp_sed_tool/9.3+galaxy1", + "content_id": "Cut1", "errors": null, - "id": 11, + "id": 9, "input_connections": { - "infile": { + "input": { "id": 8, - "output_name": "output" - } - }, - "inputs": [], - "label": "remove > + lowercase", - "name": "Text transformation", - "outputs": [ - { - "name": "output", - "type": "input" - } - ], - "position": { - "left": 2061.3515625, - "top": 233.5703125 - }, - "post_job_actions": { - "ChangeDatatypeActionoutput": { - "action_arguments": { - "newtype": "csv" - }, - "action_type": "ChangeDatatypeAction", - "output_name": "output" - }, - "HideDatasetActionoutput": { - "action_arguments": {}, - "action_type": "HideDatasetAction", - "output_name": "output" - } - }, - "tool_id": "toolshed.g2.bx.psu.edu/repos/bgruening/text_processing/tp_sed_tool/9.3+galaxy1", - "tool_shed_repository": { - "changeset_revision": "fbf99087e067", - "name": "text_processing", - "owner": "bgruening", - "tool_shed": "toolshed.g2.bx.psu.edu" - }, - "tool_state": "{\"adv_opts\": {\"adv_opts_selector\": \"basic\", \"__current_case__\": 0}, \"code\": \"s/>//g\\ns/[A-Z]/\\\\L&/g\", \"infile\": {\"__class__\": \"ConnectedValue\"}, \"__page__\": null, \"__rerun_remap_job_id__\": null}", - "tool_version": "9.3+galaxy1", - "type": "tool", - "uuid": "f11170d4-82b0-4582-902e-133de9c17218", - "when": null, - "workflow_outputs": [] - }, - "12": { - "annotation": "", - "content_id": "toolshed.g2.bx.psu.edu/repos/bgruening/text_processing/tp_sed_tool/9.3+galaxy1", - "errors": null, - "id": 12, - "input_connections": { - "infile": { - "id": 9, - "output_name": "mito_scaff_names" - } - }, - "inputs": [], - "label": "to lowercase", - "name": "Text transformation", - "outputs": [ - { - "name": "output", - "type": "input" - } - ], - "position": { - "left": 2259.0390625, - "top": 518.3359375 - }, - "post_job_actions": { - "HideDatasetActionoutput": { - "action_arguments": {}, - "action_type": "HideDatasetAction", - "output_name": "output" - } - }, - "tool_id": "toolshed.g2.bx.psu.edu/repos/bgruening/text_processing/tp_sed_tool/9.3+galaxy1", - "tool_shed_repository": { - "changeset_revision": "fbf99087e067", - "name": "text_processing", - "owner": "bgruening", - "tool_shed": "toolshed.g2.bx.psu.edu" - }, - "tool_state": "{\"adv_opts\": {\"adv_opts_selector\": \"basic\", \"__current_case__\": 0}, \"code\": \"s/[A-Z]/\\\\L&/g\", \"infile\": {\"__class__\": \"ConnectedValue\"}, \"__page__\": null, \"__rerun_remap_job_id__\": null}", - "tool_version": "9.3+galaxy1", - "type": "tool", - "uuid": "0c4be94e-a0a5-46e7-a586-e45ce92411d2", - "when": null, - "workflow_outputs": [] - }, - "13": { - "annotation": "", - "content_id": "toolshed.g2.bx.psu.edu/repos/bgruening/text_processing/tp_find_and_replace/9.3+galaxy1", - "errors": null, - "id": 13, - "input_connections": { - "infile": { - "id": 11, - "output_name": "output" + "output_name": "out_file1" } }, "inputs": [], - "label": "isolate scaffolds names ", - "name": "Replace", + "label": null, + "name": "Cut", "outputs": [ { - "name": "outfile", - "type": "input" + "name": "out_file1", + "type": "tabular" } ], "position": { - "left": 2321.61328125, - "top": 342.76953125 + "left": 2237.4640689838916, + "top": 241.19478945940944 }, "post_job_actions": { - "HideDatasetActionoutfile": { + "HideDatasetActionout_file1": { "action_arguments": {}, "action_type": "HideDatasetAction", - "output_name": "outfile" + "output_name": "out_file1" } }, - "tool_id": "toolshed.g2.bx.psu.edu/repos/bgruening/text_processing/tp_find_and_replace/9.3+galaxy1", - "tool_shed_repository": { - "changeset_revision": "fbf99087e067", - "name": "text_processing", - "owner": "bgruening", - "tool_shed": "toolshed.g2.bx.psu.edu" - }, - "tool_state": "{\"find_and_replace\": [{\"__index__\": 0, \"find_pattern\": \" kraken:taxid\\\\|[0-9]+\", \"replace_pattern\": null, \"is_regex\": true, \"global\": true, \"caseinsensitive\": false, \"wholewords\": true, \"skip_first_line\": false, \"searchwhere\": {\"searchwhere_select\": \"line\", \"__current_case__\": 0}}], \"infile\": {\"__class__\": \"ConnectedValue\"}, \"__page__\": null, \"__rerun_remap_job_id__\": null}", - "tool_version": "9.3+galaxy1", + "tool_id": "Cut1", + "tool_state": "{\"columnList\": \"c2\", \"delimiter\": \"T\", \"input\": {\"__class__\": \"RuntimeValue\"}, \"__page__\": null, \"__rerun_remap_job_id__\": null}", + "tool_version": "1.0.2", "type": "tool", - "uuid": "c37db543-a966-4ed2-88b9-87b317465144", + "uuid": "8cc3e58f-2940-454a-9cf6-b32c1ab19016", "when": null, "workflow_outputs": [] }, - "14": { + "10": { "annotation": "", "content_id": "toolshed.g2.bx.psu.edu/repos/bgruening/text_processing/tp_cat/9.3+galaxy1", "errors": null, - "id": 14, + "id": 10, "input_connections": { "inputs": [ { - "id": 12, - "output_name": "output" + "id": 7, + "output_name": "mito_scaff_names" }, { - "id": 13, - "output_name": "outfile" + "id": 9, + "output_name": "out_file1" } ] }, @@ -682,13 +482,13 @@ } ], "position": { - "left": 2611.0546875, + "left": 2538.6178936709443, "top": 423.9453125 }, "post_job_actions": {}, "tool_id": "toolshed.g2.bx.psu.edu/repos/bgruening/text_processing/tp_cat/9.3+galaxy1", "tool_shed_repository": { - "changeset_revision": "fbf99087e067", + "changeset_revision": "86755160afbf", "name": "text_processing", "owner": "bgruening", "tool_shed": "toolshed.g2.bx.psu.edu" @@ -706,18 +506,18 @@ } ] }, - "15": { + "11": { "annotation": "", "content_id": "toolshed.g2.bx.psu.edu/repos/bgruening/gfastats/gfastats/1.3.6+galaxy0", "errors": null, - "id": 15, + "id": 11, "input_connections": { "input_file": { "id": 0, "output_name": "output" }, "target_condition|exclude_bed": { - "id": 14, + "id": 10, "output_name": "out_file1" } }, @@ -731,7 +531,7 @@ } ], "position": { - "left": 3050.21875, + "left": 2977.7819561709443, "top": 798.078125 }, "post_job_actions": {}, @@ -759,6 +559,6 @@ "tags": [ "VGP_curated" ], - "uuid": "3f6673a2-caf4-4156-b5da-cc6bde2ddc8d", - "version": 8 + "uuid": "aa4960d9-198d-4990-a393-a98efcd3070a", + "version": 3 } \ No newline at end of file diff --git a/workflows/VGP-assembly-v2/Assembly-decontamination-VGP9/CHANGELOG.md b/workflows/VGP-assembly-v2/Assembly-decontamination-VGP9/CHANGELOG.md index ee2feefeb..f9eaf2e64 100644 --- a/workflows/VGP-assembly-v2/Assembly-decontamination-VGP9/CHANGELOG.md +++ b/workflows/VGP-assembly-v2/Assembly-decontamination-VGP9/CHANGELOG.md @@ -1,5 +1,10 @@ # Changelog +## [0.3] 2024-08-26 + +- Changed the regex to only change the sequences. The workflow is now more robust to different (non VGP) scaffold names and VGP names with prefixes. +- Reduce the number of steps in the workflow. + ## [0.2] 2024-08-15 - Bug Fix: a missing regex caused the list of contaminants to empty out and the contaminants were not removed.