From 46bd5e7e2985cb34bf395b449ccae83d64e1ef29 Mon Sep 17 00:00:00 2001 From: Subina Mehta Date: Mon, 18 Nov 2024 12:39:06 -0500 Subject: [PATCH 01/54] added clinical MP database generation to iwc --- .../.dockstore.yml | 11 + ...c-clinicalmp-database-generation-tests.yml | 39 ++ .../iwc-clinicalmp-database-generation.ga | 347 ++++++++++++++++++ 3 files changed, 397 insertions(+) create mode 100644 workflows/proteomics/clinicalmp/clinicalmp-database-generation/.dockstore.yml create mode 100644 workflows/proteomics/clinicalmp/clinicalmp-database-generation/iwc-clinicalmp-database-generation-tests.yml create mode 100644 workflows/proteomics/clinicalmp/clinicalmp-database-generation/iwc-clinicalmp-database-generation.ga diff --git a/workflows/proteomics/clinicalmp/clinicalmp-database-generation/.dockstore.yml b/workflows/proteomics/clinicalmp/clinicalmp-database-generation/.dockstore.yml new file mode 100644 index 000000000..59310b082 --- /dev/null +++ b/workflows/proteomics/clinicalmp/clinicalmp-database-generation/.dockstore.yml @@ -0,0 +1,11 @@ +version: 1.2 +workflows: +- name: main + subclass: Galaxy + publish: true + primaryDescriptorPath: /iwc-clinicalmp-database-generation.ga + testParameterFiles: + - /iwc-clinicalmp-database-generation-tests.yml + authors: + - name: Subina Mehta + orcid: 0000-0001-9818-0537 diff --git a/workflows/proteomics/clinicalmp/clinicalmp-database-generation/iwc-clinicalmp-database-generation-tests.yml b/workflows/proteomics/clinicalmp/clinicalmp-database-generation/iwc-clinicalmp-database-generation-tests.yml new file mode 100644 index 000000000..85ab277a8 --- /dev/null +++ b/workflows/proteomics/clinicalmp/clinicalmp-database-generation/iwc-clinicalmp-database-generation-tests.yml @@ -0,0 +1,39 @@ +- doc: Test outline for iwc-clinicalmp-database-generation + job: + HUMAN-SwissProt-Protein-Database: + class: File + path: https://zenodo.org/records/14181725/files/HUMAN-SwissProt-Protein-Database.fasta + filetype: fasta + Species_UniProt_FASTA: + class: File + path: https://zenodo.org/records/14181725/files/Species_UniProt_FASTA.fasta + filetype: fasta + Contaminants(cRAP)-Protein-Database: + class: File + path: https://zenodo.org/records/14181725/files/Contaminants(cRAP)-Protein-Database.fasta + filetype: fasta + Input-MGF-files: + class: Collection + collection_type: list + elements: + - class: File + identifier: PTRC_Skubitz_Plex2_F15_9Aug19_Rage_Rep-19-06-08.mgf + path: https://zenodo.org/records/14181725/files/PTRC_Skubitz_Plex2_F15_9Aug19_Rage_Rep-19-06-08.mgf + - class: File + identifier: PTRC_Skubitz_Plex2_F13_9Aug19_Rage_Rep-19-06-08.mgf + path: https://zenodo.org/records/14181725/files/PTRC_Skubitz_Plex2_F13_9Aug19_Rage_Rep-19-06-08.mgf + - class: File + identifier: PTRC_Skubitz_Plex2_F11_9Aug19_Rage_Rep-19-06-08.mgf + path: https://zenodo.org/records/14181725/files/PTRC_Skubitz_Plex2_F11_9Aug19_Rage_Rep-19-06-08.mgf + - class: File + identifier: PTRC_Skubitz_Plex2_F10_9Aug19_Rage_Rep-19-06-08.mgf + path: https://zenodo.org/records/14181725/files/PTRC_Skubitz_Plex2_F10_9Aug19_Rage_Rep-19-06-08.mgf + outputs: + Human-UniProt-Microbial-Proteins-cRAP-for-MetaNovo: + path: https://zenodo.org/records/14181725/files/Human-UniProt-Microbial-Proteins-cRAP-for-MetaNovo.fasta + Metanovo-Compact-database: + path: https://zenodo.org/records/14181725/files/Metanovo-Compact-database.fasta + CSV-database: + path: https://zenodo.org/records/14181725/files/CSV-database.csv + Human-UniProt-Microbial-Proteins-(from-MetaNovo)+cRAP: + path: https://zenodo.org/records/14181725/files/Human-UniProt-Microbial-Proteins-(from-MetaNovo)+cRAP.fasta diff --git a/workflows/proteomics/clinicalmp/clinicalmp-database-generation/iwc-clinicalmp-database-generation.ga b/workflows/proteomics/clinicalmp/clinicalmp-database-generation/iwc-clinicalmp-database-generation.ga new file mode 100644 index 000000000..c4f0d660a --- /dev/null +++ b/workflows/proteomics/clinicalmp/clinicalmp-database-generation/iwc-clinicalmp-database-generation.ga @@ -0,0 +1,347 @@ +{ + "a_galaxy_workflow": "true", + "annotation": "Generating a customized database for clinical metaproteomics", + "comments": [], + "creator": [ + { + "class": "Organization", + "identifier": "0000-0001-9818-0537", + "name": "Subina Mehta" + } + ], + "format-version": "0.1", + "license": "CC-BY-4.0", + "name": "iwc-clinicalmp-database-generation ", + "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": "HUMAN SwissProt Protein Database", + "content_id": null, + "errors": null, + "id": 0, + "input_connections": {}, + "inputs": [ + { + "description": "HUMAN SwissProt Protein Database", + "name": "HUMAN-SwissProt-Protein-Database" + } + ], + "label": "HUMAN-SwissProt-Protein-Database", + "name": "Input dataset", + "outputs": [], + "position": { + "left": 0, + "top": 207.8446261703461 + }, + "tool_id": null, + "tool_state": "{\"optional\": false, \"tag\": null}", + "tool_version": null, + "type": "data_input", + "uuid": "bb037df4-ef56-42ad-8b3e-93425bc7bdfa", + "when": null, + "workflow_outputs": [] + }, + "1": { + "annotation": "Input MGF files (Dataset Collection)", + "content_id": null, + "errors": null, + "id": 1, + "input_connections": {}, + "inputs": [ + { + "description": "Input MGF files (Dataset Collection)", + "name": "Input-MGF-files" + } + ], + "label": "Input-MGF-files", + "name": "Input dataset collection", + "outputs": [], + "position": { + "left": 260.96875, + "top": 0 + }, + "tool_id": null, + "tool_state": "{\"optional\": false, \"tag\": null, \"collection_type\": \"list\"}", + "tool_version": null, + "type": "data_collection_input", + "uuid": "d6bb6e3e-ebf6-4c65-bcf7-ea9527cf8653", + "when": null, + "workflow_outputs": [] + }, + "2": { + "annotation": "FASTA database List of Species", + "content_id": null, + "errors": null, + "id": 2, + "input_connections": {}, + "inputs": [ + { + "description": "FASTA database List of Species", + "name": "Species_UniProt_FASTA" + } + ], + "label": "Species_UniProt_FASTA", + "name": "Input dataset", + "outputs": [], + "position": { + "left": 2.4375, + "top": 373.22882080078125 + }, + "tool_id": null, + "tool_state": "{\"optional\": false, \"tag\": null}", + "tool_version": null, + "type": "data_input", + "uuid": "b4b90dcd-9228-4aad-b51d-2f08b2d4cc0d", + "when": null, + "workflow_outputs": [] + }, + "3": { + "annotation": "Contaminants (cRAP) Protein Database", + "content_id": null, + "errors": null, + "id": 3, + "input_connections": {}, + "inputs": [ + { + "description": "Contaminants (cRAP) Protein Database", + "name": "Contaminants(cRAP)-Protein-Database" + } + ], + "label": "Contaminants(cRAP)-Protein-Database", + "name": "Input dataset", + "outputs": [], + "position": { + "left": 14.40625, + "top": 471.45147705078125 + }, + "tool_id": null, + "tool_state": "{\"optional\": false, \"tag\": null}", + "tool_version": null, + "type": "data_input", + "uuid": "ca7de659-6e60-4bd5-aa4c-a88f2860e8c9", + "when": null, + "workflow_outputs": [] + }, + "4": { + "annotation": "", + "content_id": "toolshed.g2.bx.psu.edu/repos/galaxyp/fasta_merge_files_and_filter_unique_sequences/fasta_merge_files_and_filter_unique_sequences/1.2.0", + "errors": null, + "id": 4, + "input_connections": { + "batchmode|input_fastas_0|input_fasta": { + "id": 0, + "output_name": "output" + }, + "batchmode|input_fastas_1|input_fasta": { + "id": 2, + "output_name": "output" + }, + "batchmode|input_fastas_2|input_fasta": { + "id": 3, + "output_name": "output" + } + }, + "inputs": [], + "label": "Human-UniProt-Microbial-Proteins-cRAP-for-MetaNovo", + "name": "FASTA Merge Files and Filter Unique Sequences", + "outputs": [ + { + "name": "output", + "type": "fasta" + } + ], + "position": { + "left": 369.32421875, + "top": 137.68359736327898 + }, + "post_job_actions": { + "EmailActionoutput": { + "action_arguments": { + "host": "usegalaxy.eu" + }, + "action_type": "EmailAction", + "output_name": "output" + }, + "RenameDatasetActionoutput": { + "action_arguments": { + "newname": "Human-UniProt-Microbial-Proteins-cRAP-for-MetaNovo" + }, + "action_type": "RenameDatasetAction", + "output_name": "output" + } + }, + "tool_id": "toolshed.g2.bx.psu.edu/repos/galaxyp/fasta_merge_files_and_filter_unique_sequences/fasta_merge_files_and_filter_unique_sequences/1.2.0", + "tool_shed_repository": { + "changeset_revision": "f546e7278f04", + "name": "fasta_merge_files_and_filter_unique_sequences", + "owner": "galaxyp", + "tool_shed": "toolshed.g2.bx.psu.edu" + }, + "tool_state": "{\"accession_parser\": \"^>([^ ]+).*$\", \"batchmode\": {\"processmode\": \"individual\", \"__current_case__\": 0, \"input_fastas\": [{\"__index__\": 0, \"input_fasta\": {\"__class__\": \"ConnectedValue\"}}, {\"__index__\": 1, \"input_fasta\": {\"__class__\": \"ConnectedValue\"}}, {\"__index__\": 2, \"input_fasta\": {\"__class__\": \"ConnectedValue\"}}]}, \"uniqueness_criterion\": \"sequence\", \"__page__\": null, \"__rerun_remap_job_id__\": null}", + "tool_version": "1.2.0", + "type": "tool", + "uuid": "4c1b21ac-9ceb-49be-9c48-771a3fda8db4", + "when": null, + "workflow_outputs": [ + { + "label": "Human-UniProt-Microbial-Proteins-cRAP-for-MetaNovo", + "output_name": "output", + "uuid": "9e590019-6897-4b0e-bc63-ef0599a48578" + } + ] + }, + "5": { + "annotation": "Generating Customized Database", + "content_id": "toolshed.g2.bx.psu.edu/repos/galaxyp/metanovo/metanovo/1.9.4+galaxy4", + "errors": null, + "id": 5, + "input_connections": { + "input_fasta": { + "id": 4, + "output_name": "output" + }, + "input_type|input_mgf_collection": { + "id": 1, + "output_name": "output" + } + }, + "inputs": [ + { + "description": "runtime parameter for tool MetaNovo", + "name": "input_type" + } + ], + "label": "Metanovo", + "name": "MetaNovo", + "outputs": [ + { + "name": "output_fasta", + "type": "fasta" + }, + { + "name": "output_csv", + "type": "csv" + } + ], + "position": { + "left": 651.57421875, + "top": 90.94140986327898 + }, + "post_job_actions": { + "RenameDatasetActionoutput_csv": { + "action_arguments": { + "newname": "CSV-database" + }, + "action_type": "RenameDatasetAction", + "output_name": "output_csv" + }, + "RenameDatasetActionoutput_fasta": { + "action_arguments": { + "newname": "Metanovo-Compact-database" + }, + "action_type": "RenameDatasetAction", + "output_name": "output_fasta" + } + }, + "tool_id": "toolshed.g2.bx.psu.edu/repos/galaxyp/metanovo/metanovo/1.9.4+galaxy4", + "tool_shed_repository": { + "changeset_revision": "d6dcd3173bdf", + "name": "metanovo", + "owner": "galaxyp", + "tool_shed": "toolshed.g2.bx.psu.edu" + }, + "tool_state": "{\"directag\": {\"directag_tic_cutoff\": \"85\", \"directag_max_peak_count\": \"400\", \"directag_intensity_classes\": \"3\", \"directag_adjust_precursor\": false, \"directag_min_adjustment\": \"-2.5\", \"directag_max_adjustment\": \"2.5\", \"directag_adjustment_step\": \"0.1\", \"directag_charge_states\": \"3\", \"directag_ms_charge_state\": false, \"directag_duplicate_spectra\": true, \"directag_deisotoping\": \"0\", \"directag_isotope_tolerance\": \"0.25\", \"directag_complement_tolerance\": \"0.5\", \"directag_tag_length\": \"4\", \"directag_max_var_mods\": \"2\", \"directag_max_tag_count\": \"5\", \"directag_intensity_weight\": \"1.0\", \"directag_fidelity_weight\": \"1.0\", \"directag_complement_weight\": \"1.0\"}, \"fraction_analysis\": {\"protein_fraction_mw_confidence\": \"95.0\"}, \"gene_annotation\": {\"useGeneMapping\": true, \"updateGeneMapping\": true}, \"import_filters\": {\"import_peptide_length_min\": \"8\", \"import_peptide_length_max\": \"50\", \"import_precursor_mz_ppm\": \"0\", \"exclude_unknown_ptms\": true}, \"input_fasta\": {\"__class__\": \"ConnectedValue\"}, \"input_type\": {\"type\": \"collection\", \"__current_case__\": 1, \"input_mgf_collection\": {\"__class__\": \"ConnectedValue\"}}, \"metanovo_parameters\": {\"mn_specificity\": \"specific\", \"mn_enzymes\": \"Trypsin, no P rule\", \"mn_max_missed_cleavages\": \"2\"}, \"processing_control\": {\"CHUNKSIZE\": \"100000\"}, \"protein_inference\": {\"simplify_groups\": true, \"simplify_score\": true, \"simplify_enzymaticity\": true, \"simplify_evidence\": true, \"simplify_uncharacterized\": true}, \"ptm_localization\": {\"ptm_score\": \"1\", \"score_neutral_losses\": false, \"ptm_sequence_matching_type\": \"1\", \"ptm_alignment\": true}, \"sequence_matching\": {\"sequence_index_type\": \"0\", \"sequence_matching_type\": \"2\", \"sequence_matching_x\": \"0.25\"}, \"spectrum_annotation\": {\"annotation_level\": \"0.75\", \"annotation_high_resolution\": true}, \"spectrum_matching_parameters\": {\"prec_tol\": \"10.0\", \"prec_ppm\": \"1\", \"frag_tol\": \"0.01\", \"frag_ppm\": \"0\", \"digestion\": \"0\", \"enzyme\": [\"Trypsin (no P rule)\"], \"specificity\": \"0\", \"mc\": \"2\", \"fixed_mods\": [\"Carbamidomethylation of C\", \"TMT 10-plex of K\", \"TMT 10-plex of peptide N-term\"], \"variable_mods\": [\"Oxidation of M\"], \"min_charge\": \"2\", \"max_charge\": \"5\", \"fi\": \"b\", \"ri\": \"y\", \"min_isotope\": \"0\", \"max_isotope\": \"1\"}, \"validation_levels\": {\"psm_fdr\": \"1\", \"peptide_fdr\": \"1\", \"protein_fdr\": \"1\", \"group_psms\": true, \"group_peptides\": true, \"merge_subgroups\": true}, \"__page__\": null, \"__rerun_remap_job_id__\": null}", + "tool_version": "1.9.4+galaxy4", + "type": "tool", + "uuid": "07d51088-eb68-4ffd-b505-7228a21de93c", + "when": null, + "workflow_outputs": [ + { + "label": "CSV-database", + "output_name": "output_csv", + "uuid": "d7208cb6-a907-4a8b-b8b7-cf44c103d14a" + }, + { + "label": "Metanovo-Compact-database", + "output_name": "output_fasta", + "uuid": "da55e450-b86a-46a0-bc92-f602e8e8242a" + } + ] + }, + "6": { + "annotation": "Merge-all-FASTA", + "content_id": "toolshed.g2.bx.psu.edu/repos/galaxyp/fasta_merge_files_and_filter_unique_sequences/fasta_merge_files_and_filter_unique_sequences/1.2.0", + "errors": null, + "id": 6, + "input_connections": { + "batchmode|input_fastas_0|input_fasta": { + "id": 0, + "output_name": "output" + }, + "batchmode|input_fastas_1|input_fasta": { + "id": 5, + "output_name": "output_fasta" + }, + "batchmode|input_fastas_2|input_fasta": { + "id": 3, + "output_name": "output" + } + }, + "inputs": [], + "label": "Merge-all-FASTA", + "name": "FASTA Merge Files and Filter Unique Sequences", + "outputs": [ + { + "name": "output", + "type": "fasta" + } + ], + "position": { + "left": 924.9069441945012, + "top": 322.62533209947645 + }, + "post_job_actions": { + "EmailActionoutput": { + "action_arguments": { + "host": "usegalaxy.eu" + }, + "action_type": "EmailAction", + "output_name": "output" + }, + "RenameDatasetActionoutput": { + "action_arguments": { + "newname": "Human-UniProt-Microbial-Proteins-(from-MetaNovo)+cRAP" + }, + "action_type": "RenameDatasetAction", + "output_name": "output" + } + }, + "tool_id": "toolshed.g2.bx.psu.edu/repos/galaxyp/fasta_merge_files_and_filter_unique_sequences/fasta_merge_files_and_filter_unique_sequences/1.2.0", + "tool_shed_repository": { + "changeset_revision": "f546e7278f04", + "name": "fasta_merge_files_and_filter_unique_sequences", + "owner": "galaxyp", + "tool_shed": "toolshed.g2.bx.psu.edu" + }, + "tool_state": "{\"__input_ext\": \"fasta\", \"accession_parser\": \"^>([^ ]+).*$\", \"batchmode\": {\"processmode\": \"individual\", \"__current_case__\": 0, \"input_fastas\": [{\"__index__\": 0, \"input_fasta\": {\"__class__\": \"ConnectedValue\"}}, {\"__index__\": 1, \"input_fasta\": {\"__class__\": \"ConnectedValue\"}}, {\"__index__\": 2, \"input_fasta\": {\"__class__\": \"ConnectedValue\"}}]}, \"chromInfo\": \"/opt/galaxy/tool-data/shared/ucsc/chrom/?.len\", \"uniqueness_criterion\": \"sequence\", \"__page__\": null, \"__rerun_remap_job_id__\": null}", + "tool_version": "1.2.0", + "type": "tool", + "uuid": "3880c712-4f3c-4edc-bda0-ee348ab1a2c4", + "when": null, + "workflow_outputs": [ + { + "label": "Human-UniProt-Microbial-Proteins-(from-MetaNovo)+cRAP", + "output_name": "output", + "uuid": "cf10a376-8dce-44f1-b473-028444968f9e" + } + ] + } + }, + "tags": [ + "name:clinicalMP" + ], + "uuid": "9f8a8ec3-fc1f-4470-824a-9eb69d61e20e", + "version": 8 +} \ No newline at end of file From 0e0527675035220723b12f590e46d5dc3596bada Mon Sep 17 00:00:00 2001 From: Subina Mehta Date: Mon, 18 Nov 2024 12:59:06 -0500 Subject: [PATCH 02/54] Create README.md --- .../clinicalmp-database-generation/README.md | 28 +++++++++++++++++++ 1 file changed, 28 insertions(+) create mode 100644 workflows/proteomics/clinicalmp/clinicalmp-database-generation/README.md diff --git a/workflows/proteomics/clinicalmp/clinicalmp-database-generation/README.md b/workflows/proteomics/clinicalmp/clinicalmp-database-generation/README.md new file mode 100644 index 000000000..ac28a2fd3 --- /dev/null +++ b/workflows/proteomics/clinicalmp/clinicalmp-database-generation/README.md @@ -0,0 +1,28 @@ +# Clinical Metaproteomics 1: Database Generation +Metaproteomics involves the large-scale identification and analysis of all proteins expressed by microbiota. However, analyzing clinical samples using metaproteomics is complicated by the presence of abundant human (host) proteins, which can obscure the detection of less abundant microbial proteins. + +To overcome this challenge, we developed a metaproteomics workflow using tandem mass spectrometry (MS/MS) and bioinformatics tools on the Galaxy platform. This workflow enables the characterization of metaproteomes in clinical samples. + +The first step in this workflow is the Database Generation process. The Galaxy-P team has created a workflow that compiles a large database by downloading protein sequences of known disease-causing microorganisms. From this extensive database, a compact, relevant database is then created using the Metanovo tool. +A GTN has been developed for this workflow. [https://training.galaxyproject.org/training-material/topics/proteomics/tutorials/clinical-mp-4-quantitation/tutorial.html](https://training.galaxyproject.org/training-material/topics/proteomics/tutorials/clinical-mp-1-database-generation/tutorial.html) + +## Inputs dataset + +### Search Databases (FASTA) +- `HUMAN_SwissProt_Protein_Database.fasta` +- `Species_UniProt_FASTA.fasta` +- `Contaminants_(cRAP)_Protein_Database.fasta` +### MSMS files +- `PTRC_Skubitz_Plex2_F10_9Aug19_Rage_Rep-19-06-08.mgf` +- `PTRC_Skubitz_Plex2_F11_9Aug19_Rage_Rep-19-06-08.mgf` +- `PTRC_Skubitz_Plex2_F13_9Aug19_Rage_Rep-19-06-08.mgf` +- `PTRC_Skubitz_Plex2_F15_9Aug19_Rage_Rep-19-06-08.mgf` + +## Input Values +For Metanovo +- Peptide Length +- Variable modifications +- Labeled element + +## Processing +- Merge all the resultant FASTA files From 5fcca17d922561c15eab7cf9a12452c4e415df21 Mon Sep 17 00:00:00 2001 From: Subina Mehta Date: Mon, 18 Nov 2024 13:16:20 -0500 Subject: [PATCH 03/54] Create CHANGELOG.md --- .../clinicalmp/clinicalmp-database-generation/CHANGELOG.md | 4 ++++ 1 file changed, 4 insertions(+) create mode 100644 workflows/proteomics/clinicalmp/clinicalmp-database-generation/CHANGELOG.md diff --git a/workflows/proteomics/clinicalmp/clinicalmp-database-generation/CHANGELOG.md b/workflows/proteomics/clinicalmp/clinicalmp-database-generation/CHANGELOG.md new file mode 100644 index 000000000..8ec28ce1e --- /dev/null +++ b/workflows/proteomics/clinicalmp/clinicalmp-database-generation/CHANGELOG.md @@ -0,0 +1,4 @@ +# Changelog + +## [0.1] 2024-11-18 +First release. From d8ac68757a727b82c2b072f7cdb72f95870b8db4 Mon Sep 17 00:00:00 2001 From: Subina Mehta Date: Mon, 18 Nov 2024 13:19:00 -0500 Subject: [PATCH 04/54] Update iwc-clinicalmp-database-generation.ga --- .../iwc-clinicalmp-database-generation.ga | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/workflows/proteomics/clinicalmp/clinicalmp-database-generation/iwc-clinicalmp-database-generation.ga b/workflows/proteomics/clinicalmp/clinicalmp-database-generation/iwc-clinicalmp-database-generation.ga index c4f0d660a..c16dd143f 100644 --- a/workflows/proteomics/clinicalmp/clinicalmp-database-generation/iwc-clinicalmp-database-generation.ga +++ b/workflows/proteomics/clinicalmp/clinicalmp-database-generation/iwc-clinicalmp-database-generation.ga @@ -125,7 +125,7 @@ "workflow_outputs": [] }, "4": { - "annotation": "", + "annotation": "Fasta-merge", "content_id": "toolshed.g2.bx.psu.edu/repos/galaxyp/fasta_merge_files_and_filter_unique_sequences/fasta_merge_files_and_filter_unique_sequences/1.2.0", "errors": null, "id": 4, @@ -344,4 +344,4 @@ ], "uuid": "9f8a8ec3-fc1f-4470-824a-9eb69d61e20e", "version": 8 -} \ No newline at end of file +} From 6b00a4a005194336c240064ddf2c86c26ef7138c Mon Sep 17 00:00:00 2001 From: Subina Mehta Date: Mon, 18 Nov 2024 13:28:07 -0500 Subject: [PATCH 05/54] Update iwc-clinicalmp-database-generation.ga --- .../iwc-clinicalmp-database-generation.ga | 1 + 1 file changed, 1 insertion(+) diff --git a/workflows/proteomics/clinicalmp/clinicalmp-database-generation/iwc-clinicalmp-database-generation.ga b/workflows/proteomics/clinicalmp/clinicalmp-database-generation/iwc-clinicalmp-database-generation.ga index c16dd143f..43aaf2fa4 100644 --- a/workflows/proteomics/clinicalmp/clinicalmp-database-generation/iwc-clinicalmp-database-generation.ga +++ b/workflows/proteomics/clinicalmp/clinicalmp-database-generation/iwc-clinicalmp-database-generation.ga @@ -11,6 +11,7 @@ ], "format-version": "0.1", "license": "CC-BY-4.0", + "release": "0.1", "name": "iwc-clinicalmp-database-generation ", "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" From edbcc90b1ad07db3a501a92b79eef7137e699afb Mon Sep 17 00:00:00 2001 From: Subina Mehta Date: Mon, 18 Nov 2024 14:52:22 -0500 Subject: [PATCH 06/54] Update iwc-clinicalmp-database-generation.ga --- .../iwc-clinicalmp-database-generation.ga | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/workflows/proteomics/clinicalmp/clinicalmp-database-generation/iwc-clinicalmp-database-generation.ga b/workflows/proteomics/clinicalmp/clinicalmp-database-generation/iwc-clinicalmp-database-generation.ga index 43aaf2fa4..fffe9311a 100644 --- a/workflows/proteomics/clinicalmp/clinicalmp-database-generation/iwc-clinicalmp-database-generation.ga +++ b/workflows/proteomics/clinicalmp/clinicalmp-database-generation/iwc-clinicalmp-database-generation.ga @@ -12,7 +12,7 @@ "format-version": "0.1", "license": "CC-BY-4.0", "release": "0.1", - "name": "iwc-clinicalmp-database-generation ", + "name": "iwc-clinicalmp-database-generation", "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" }, From fa151514289568ae0a4c3ef34fd73271f1cc9918 Mon Sep 17 00:00:00 2001 From: Subina Mehta Date: Tue, 19 Nov 2024 11:02:00 -0500 Subject: [PATCH 07/54] Update iwc-clinicalmp-database-generation-tests.yml ADDED ASSERTS --- ...iwc-clinicalmp-database-generation-tests.yml | 17 +++++++++++++---- 1 file changed, 13 insertions(+), 4 deletions(-) diff --git a/workflows/proteomics/clinicalmp/clinicalmp-database-generation/iwc-clinicalmp-database-generation-tests.yml b/workflows/proteomics/clinicalmp/clinicalmp-database-generation/iwc-clinicalmp-database-generation-tests.yml index 85ab277a8..92a24a04f 100644 --- a/workflows/proteomics/clinicalmp/clinicalmp-database-generation/iwc-clinicalmp-database-generation-tests.yml +++ b/workflows/proteomics/clinicalmp/clinicalmp-database-generation/iwc-clinicalmp-database-generation-tests.yml @@ -30,10 +30,19 @@ path: https://zenodo.org/records/14181725/files/PTRC_Skubitz_Plex2_F10_9Aug19_Rage_Rep-19-06-08.mgf outputs: Human-UniProt-Microbial-Proteins-cRAP-for-MetaNovo: - path: https://zenodo.org/records/14181725/files/Human-UniProt-Microbial-Proteins-cRAP-for-MetaNovo.fasta + asserts: + has_text: + text: ">sp" Metanovo-Compact-database: - path: https://zenodo.org/records/14181725/files/Metanovo-Compact-database.fasta + asserts: + has_text: + text: ">sp" CSV-database: - path: https://zenodo.org/records/14181725/files/CSV-database.csv + asserts: + has_text: + text: " index Accession File ID Length Organism PeptideCount Peptides Record SAF PTRC_Skubitz_Plex2_F10_9Aug19_Rage_Rep-19-06-08 SAF PTRC_Skubitz_Plex2_F11_9Aug19_Rage_Rep-19-06-08 SAF PTRC_Skubitz_Plex2_F13_9Aug19_Rage_Rep-19-06-08 SAF PTRC_Skubitz_Plex2_F15_9Aug19_Rage_Rep-19-06-08 Sample PTRC_Skubitz_Plex2_F10_9Aug19_Rage_Rep-19-06-08 (msms) Sample PTRC_Skubitz_Plex2_F11_9Aug19_Rage_Rep-19-06-08 (msms) Sample PTRC_Skubitz_Plex2_F13_9Aug19_Rage_Rep-19-06-08 (msms) Sample PTRC_Skubitz_Plex2_F15_9Aug19_Rage_Rep-19-06-08 (msms) ScanCount Scans NSAF PTRC_Skubitz_Plex2_F10_9Aug19_Rage_Rep-19-06-08 NSAF PTRC_Skubitz_Plex2_F11_9Aug19_Rage_Rep-19-06-08 NSAF PTRC_Skubitz_Plex2_F13_9Aug19_Rage_Rep-19-06-08 NSAF PTRC_Skubitz_Plex2_F15_9Aug19_Rage_Rep-19-06-08 Summed_NSAF Protein_Prob Organism_Prob MSMS_Percent Combined_Prob" Human-UniProt-Microbial-Proteins-(from-MetaNovo)+cRAP: - path: https://zenodo.org/records/14181725/files/Human-UniProt-Microbial-Proteins-(from-MetaNovo)+cRAP.fasta + asserts: + has_text: + text: ">sp" + From e7cf9dbeba488f960b9eb26196bf59b53f00adc1 Mon Sep 17 00:00:00 2001 From: Subina Mehta Date: Tue, 19 Nov 2024 11:16:13 -0500 Subject: [PATCH 08/54] Update workflows/proteomics/clinicalmp/clinicalmp-database-generation/iwc-clinicalmp-database-generation.ga Co-authored-by: Marius van den Beek --- .../iwc-clinicalmp-database-generation.ga | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/workflows/proteomics/clinicalmp/clinicalmp-database-generation/iwc-clinicalmp-database-generation.ga b/workflows/proteomics/clinicalmp/clinicalmp-database-generation/iwc-clinicalmp-database-generation.ga index fffe9311a..ad3ceda98 100644 --- a/workflows/proteomics/clinicalmp/clinicalmp-database-generation/iwc-clinicalmp-database-generation.ga +++ b/workflows/proteomics/clinicalmp/clinicalmp-database-generation/iwc-clinicalmp-database-generation.ga @@ -12,7 +12,7 @@ "format-version": "0.1", "license": "CC-BY-4.0", "release": "0.1", - "name": "iwc-clinicalmp-database-generation", + "name": "Generate a Clinical Metaproteomics Database", "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" }, From 57f1a20c89e341ba4b6888d65b0f5b66fd1b80e1 Mon Sep 17 00:00:00 2001 From: Subina Mehta Date: Tue, 19 Nov 2024 11:17:19 -0500 Subject: [PATCH 09/54] Update workflows/proteomics/clinicalmp/clinicalmp-database-generation/iwc-clinicalmp-database-generation-tests.yml Co-authored-by: Marius van den Beek --- .../iwc-clinicalmp-database-generation-tests.yml | 14 +++++++------- 1 file changed, 7 insertions(+), 7 deletions(-) diff --git a/workflows/proteomics/clinicalmp/clinicalmp-database-generation/iwc-clinicalmp-database-generation-tests.yml b/workflows/proteomics/clinicalmp/clinicalmp-database-generation/iwc-clinicalmp-database-generation-tests.yml index 92a24a04f..dc99db6ca 100644 --- a/workflows/proteomics/clinicalmp/clinicalmp-database-generation/iwc-clinicalmp-database-generation-tests.yml +++ b/workflows/proteomics/clinicalmp/clinicalmp-database-generation/iwc-clinicalmp-database-generation-tests.yml @@ -2,15 +2,15 @@ job: HUMAN-SwissProt-Protein-Database: class: File - path: https://zenodo.org/records/14181725/files/HUMAN-SwissProt-Protein-Database.fasta + location: https://zenodo.org/records/14181725/files/HUMAN-SwissProt-Protein-Database.fasta filetype: fasta Species_UniProt_FASTA: class: File - path: https://zenodo.org/records/14181725/files/Species_UniProt_FASTA.fasta + location: https://zenodo.org/records/14181725/files/Species_UniProt_FASTA.fasta filetype: fasta Contaminants(cRAP)-Protein-Database: class: File - path: https://zenodo.org/records/14181725/files/Contaminants(cRAP)-Protein-Database.fasta + location: https://zenodo.org/records/14181725/files/Contaminants(cRAP)-Protein-Database.fasta filetype: fasta Input-MGF-files: class: Collection @@ -18,16 +18,16 @@ elements: - class: File identifier: PTRC_Skubitz_Plex2_F15_9Aug19_Rage_Rep-19-06-08.mgf - path: https://zenodo.org/records/14181725/files/PTRC_Skubitz_Plex2_F15_9Aug19_Rage_Rep-19-06-08.mgf + location: https://zenodo.org/records/14181725/files/PTRC_Skubitz_Plex2_F15_9Aug19_Rage_Rep-19-06-08.mgf - class: File identifier: PTRC_Skubitz_Plex2_F13_9Aug19_Rage_Rep-19-06-08.mgf - path: https://zenodo.org/records/14181725/files/PTRC_Skubitz_Plex2_F13_9Aug19_Rage_Rep-19-06-08.mgf + location: https://zenodo.org/records/14181725/files/PTRC_Skubitz_Plex2_F13_9Aug19_Rage_Rep-19-06-08.mgf - class: File identifier: PTRC_Skubitz_Plex2_F11_9Aug19_Rage_Rep-19-06-08.mgf - path: https://zenodo.org/records/14181725/files/PTRC_Skubitz_Plex2_F11_9Aug19_Rage_Rep-19-06-08.mgf + location: https://zenodo.org/records/14181725/files/PTRC_Skubitz_Plex2_F11_9Aug19_Rage_Rep-19-06-08.mgf - class: File identifier: PTRC_Skubitz_Plex2_F10_9Aug19_Rage_Rep-19-06-08.mgf - path: https://zenodo.org/records/14181725/files/PTRC_Skubitz_Plex2_F10_9Aug19_Rage_Rep-19-06-08.mgf + location: https://zenodo.org/records/14181725/files/PTRC_Skubitz_Plex2_F10_9Aug19_Rage_Rep-19-06-08.mgf outputs: Human-UniProt-Microbial-Proteins-cRAP-for-MetaNovo: asserts: From 99d8ab0cd70e4b57a378b5a38c8c1e354eb3ac90 Mon Sep 17 00:00:00 2001 From: Subina Mehta Date: Tue, 19 Nov 2024 11:21:33 -0500 Subject: [PATCH 10/54] Update iwc-clinicalmp-database-generation.ga --- .../iwc-clinicalmp-database-generation.ga | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/workflows/proteomics/clinicalmp/clinicalmp-database-generation/iwc-clinicalmp-database-generation.ga b/workflows/proteomics/clinicalmp/clinicalmp-database-generation/iwc-clinicalmp-database-generation.ga index ad3ceda98..0cc564301 100644 --- a/workflows/proteomics/clinicalmp/clinicalmp-database-generation/iwc-clinicalmp-database-generation.ga +++ b/workflows/proteomics/clinicalmp/clinicalmp-database-generation/iwc-clinicalmp-database-generation.ga @@ -1,6 +1,6 @@ { "a_galaxy_workflow": "true", - "annotation": "Generating a customized database for clinical metaproteomics", + "annotation": "The workflow begins with the Database Generation process. The Galaxy-P team has developed a workflow that collects protein sequences from known disease-causing microorganisms to build a comprehensive database. This extensive database is then refined into a smaller, more relevant dataset using the Metanovo tool.", "comments": [], "creator": [ { From a2a7954ed5cca3f054a076b5c63541c07e29c86e Mon Sep 17 00:00:00 2001 From: Subina Mehta Date: Tue, 19 Nov 2024 11:22:47 -0500 Subject: [PATCH 11/54] Update iwc-clinicalmp-database-generation-tests.yml --- .../iwc-clinicalmp-database-generation-tests.yml | 14 +++++++------- 1 file changed, 7 insertions(+), 7 deletions(-) diff --git a/workflows/proteomics/clinicalmp/clinicalmp-database-generation/iwc-clinicalmp-database-generation-tests.yml b/workflows/proteomics/clinicalmp/clinicalmp-database-generation/iwc-clinicalmp-database-generation-tests.yml index dc99db6ca..e39300816 100644 --- a/workflows/proteomics/clinicalmp/clinicalmp-database-generation/iwc-clinicalmp-database-generation-tests.yml +++ b/workflows/proteomics/clinicalmp/clinicalmp-database-generation/iwc-clinicalmp-database-generation-tests.yml @@ -1,6 +1,6 @@ - doc: Test outline for iwc-clinicalmp-database-generation job: - HUMAN-SwissProt-Protein-Database: + HUMAN SwissProt-Protein Database: class: File location: https://zenodo.org/records/14181725/files/HUMAN-SwissProt-Protein-Database.fasta filetype: fasta @@ -8,11 +8,11 @@ class: File location: https://zenodo.org/records/14181725/files/Species_UniProt_FASTA.fasta filetype: fasta - Contaminants(cRAP)-Protein-Database: + Contaminants(cRAP) Protein Database: class: File location: https://zenodo.org/records/14181725/files/Contaminants(cRAP)-Protein-Database.fasta filetype: fasta - Input-MGF-files: + Input MGF files: class: Collection collection_type: list elements: @@ -29,19 +29,19 @@ identifier: PTRC_Skubitz_Plex2_F10_9Aug19_Rage_Rep-19-06-08.mgf location: https://zenodo.org/records/14181725/files/PTRC_Skubitz_Plex2_F10_9Aug19_Rage_Rep-19-06-08.mgf outputs: - Human-UniProt-Microbial-Proteins-cRAP-for-MetaNovo: + Human UniProt Microbial Proteins cRAP for MetaNovo: asserts: has_text: text: ">sp" - Metanovo-Compact-database: + Metanovo Compact database: asserts: has_text: text: ">sp" - CSV-database: + CSV database: asserts: has_text: text: " index Accession File ID Length Organism PeptideCount Peptides Record SAF PTRC_Skubitz_Plex2_F10_9Aug19_Rage_Rep-19-06-08 SAF PTRC_Skubitz_Plex2_F11_9Aug19_Rage_Rep-19-06-08 SAF PTRC_Skubitz_Plex2_F13_9Aug19_Rage_Rep-19-06-08 SAF PTRC_Skubitz_Plex2_F15_9Aug19_Rage_Rep-19-06-08 Sample PTRC_Skubitz_Plex2_F10_9Aug19_Rage_Rep-19-06-08 (msms) Sample PTRC_Skubitz_Plex2_F11_9Aug19_Rage_Rep-19-06-08 (msms) Sample PTRC_Skubitz_Plex2_F13_9Aug19_Rage_Rep-19-06-08 (msms) Sample PTRC_Skubitz_Plex2_F15_9Aug19_Rage_Rep-19-06-08 (msms) ScanCount Scans NSAF PTRC_Skubitz_Plex2_F10_9Aug19_Rage_Rep-19-06-08 NSAF PTRC_Skubitz_Plex2_F11_9Aug19_Rage_Rep-19-06-08 NSAF PTRC_Skubitz_Plex2_F13_9Aug19_Rage_Rep-19-06-08 NSAF PTRC_Skubitz_Plex2_F15_9Aug19_Rage_Rep-19-06-08 Summed_NSAF Protein_Prob Organism_Prob MSMS_Percent Combined_Prob" - Human-UniProt-Microbial-Proteins-(from-MetaNovo)+cRAP: + Human UniProt-Microbial-Proteins (from MetaNovo) cRAP: asserts: has_text: text: ">sp" From 0ce051a8edd3eea7d9c766355893968d364a89a0 Mon Sep 17 00:00:00 2001 From: Subina Mehta Date: Tue, 19 Nov 2024 11:23:09 -0500 Subject: [PATCH 12/54] Update iwc-clinicalmp-database-generation-tests.yml --- .../iwc-clinicalmp-database-generation-tests.yml | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/workflows/proteomics/clinicalmp/clinicalmp-database-generation/iwc-clinicalmp-database-generation-tests.yml b/workflows/proteomics/clinicalmp/clinicalmp-database-generation/iwc-clinicalmp-database-generation-tests.yml index e39300816..9b98c5323 100644 --- a/workflows/proteomics/clinicalmp/clinicalmp-database-generation/iwc-clinicalmp-database-generation-tests.yml +++ b/workflows/proteomics/clinicalmp/clinicalmp-database-generation/iwc-clinicalmp-database-generation-tests.yml @@ -1,10 +1,10 @@ - doc: Test outline for iwc-clinicalmp-database-generation job: - HUMAN SwissProt-Protein Database: + HUMAN SwissProt Protein Database: class: File location: https://zenodo.org/records/14181725/files/HUMAN-SwissProt-Protein-Database.fasta filetype: fasta - Species_UniProt_FASTA: + Species UniProt FASTA: class: File location: https://zenodo.org/records/14181725/files/Species_UniProt_FASTA.fasta filetype: fasta @@ -41,7 +41,7 @@ asserts: has_text: text: " index Accession File ID Length Organism PeptideCount Peptides Record SAF PTRC_Skubitz_Plex2_F10_9Aug19_Rage_Rep-19-06-08 SAF PTRC_Skubitz_Plex2_F11_9Aug19_Rage_Rep-19-06-08 SAF PTRC_Skubitz_Plex2_F13_9Aug19_Rage_Rep-19-06-08 SAF PTRC_Skubitz_Plex2_F15_9Aug19_Rage_Rep-19-06-08 Sample PTRC_Skubitz_Plex2_F10_9Aug19_Rage_Rep-19-06-08 (msms) Sample PTRC_Skubitz_Plex2_F11_9Aug19_Rage_Rep-19-06-08 (msms) Sample PTRC_Skubitz_Plex2_F13_9Aug19_Rage_Rep-19-06-08 (msms) Sample PTRC_Skubitz_Plex2_F15_9Aug19_Rage_Rep-19-06-08 (msms) ScanCount Scans NSAF PTRC_Skubitz_Plex2_F10_9Aug19_Rage_Rep-19-06-08 NSAF PTRC_Skubitz_Plex2_F11_9Aug19_Rage_Rep-19-06-08 NSAF PTRC_Skubitz_Plex2_F13_9Aug19_Rage_Rep-19-06-08 NSAF PTRC_Skubitz_Plex2_F15_9Aug19_Rage_Rep-19-06-08 Summed_NSAF Protein_Prob Organism_Prob MSMS_Percent Combined_Prob" - Human UniProt-Microbial-Proteins (from MetaNovo) cRAP: + Human UniProt Microbial-Proteins (from MetaNovo) cRAP: asserts: has_text: text: ">sp" From 6dcc2a37d9e4aedc4a1b481169020f2bbe92b340 Mon Sep 17 00:00:00 2001 From: Subina Mehta Date: Tue, 19 Nov 2024 11:26:05 -0500 Subject: [PATCH 13/54] Update iwc-clinicalmp-database-generation.ga --- .../iwc-clinicalmp-database-generation.ga | 32 +++++++++---------- 1 file changed, 16 insertions(+), 16 deletions(-) diff --git a/workflows/proteomics/clinicalmp/clinicalmp-database-generation/iwc-clinicalmp-database-generation.ga b/workflows/proteomics/clinicalmp/clinicalmp-database-generation/iwc-clinicalmp-database-generation.ga index 0cc564301..ddda043ef 100644 --- a/workflows/proteomics/clinicalmp/clinicalmp-database-generation/iwc-clinicalmp-database-generation.ga +++ b/workflows/proteomics/clinicalmp/clinicalmp-database-generation/iwc-clinicalmp-database-generation.ga @@ -26,10 +26,10 @@ "inputs": [ { "description": "HUMAN SwissProt Protein Database", - "name": "HUMAN-SwissProt-Protein-Database" + "name": "HUMAN SwissProt Protein Database" } ], - "label": "HUMAN-SwissProt-Protein-Database", + "label": "HUMAN SwissProt Protein Database", "name": "Input dataset", "outputs": [], "position": { @@ -53,10 +53,10 @@ "inputs": [ { "description": "Input MGF files (Dataset Collection)", - "name": "Input-MGF-files" + "name": "Input MGF files" } ], - "label": "Input-MGF-files", + "label": "Input MGF files", "name": "Input dataset collection", "outputs": [], "position": { @@ -80,10 +80,10 @@ "inputs": [ { "description": "FASTA database List of Species", - "name": "Species_UniProt_FASTA" + "name": "Species UniProt FASTA" } ], - "label": "Species_UniProt_FASTA", + "label": "Species UniProt FASTA", "name": "Input dataset", "outputs": [], "position": { @@ -107,10 +107,10 @@ "inputs": [ { "description": "Contaminants (cRAP) Protein Database", - "name": "Contaminants(cRAP)-Protein-Database" + "name": "Contaminants(cRAP) Protein-Database" } ], - "label": "Contaminants(cRAP)-Protein-Database", + "label": "Contaminants(cRAP) Protein Database", "name": "Input dataset", "outputs": [], "position": { @@ -145,7 +145,7 @@ } }, "inputs": [], - "label": "Human-UniProt-Microbial-Proteins-cRAP-for-MetaNovo", + "label": "Human UniProt Microbial Proteins cRAP for MetaNovo", "name": "FASTA Merge Files and Filter Unique Sequences", "outputs": [ { @@ -167,7 +167,7 @@ }, "RenameDatasetActionoutput": { "action_arguments": { - "newname": "Human-UniProt-Microbial-Proteins-cRAP-for-MetaNovo" + "newname": "Human UniProt Microbial Proteins cRAP for MetaNovo" }, "action_type": "RenameDatasetAction", "output_name": "output" @@ -187,7 +187,7 @@ "when": null, "workflow_outputs": [ { - "label": "Human-UniProt-Microbial-Proteins-cRAP-for-MetaNovo", + "label": "Human UniProt Microbial Proteins cRAP for MetaNovo", "output_name": "output", "uuid": "9e590019-6897-4b0e-bc63-ef0599a48578" } @@ -233,14 +233,14 @@ "post_job_actions": { "RenameDatasetActionoutput_csv": { "action_arguments": { - "newname": "CSV-database" + "newname": "CSV database" }, "action_type": "RenameDatasetAction", "output_name": "output_csv" }, "RenameDatasetActionoutput_fasta": { "action_arguments": { - "newname": "Metanovo-Compact-database" + "newname": "Metanovo Compact database" }, "action_type": "RenameDatasetAction", "output_name": "output_fasta" @@ -260,12 +260,12 @@ "when": null, "workflow_outputs": [ { - "label": "CSV-database", + "label": "CSV database", "output_name": "output_csv", "uuid": "d7208cb6-a907-4a8b-b8b7-cf44c103d14a" }, { - "label": "Metanovo-Compact-database", + "label": "Metanovo Compact database", "output_name": "output_fasta", "uuid": "da55e450-b86a-46a0-bc92-f602e8e8242a" } @@ -333,7 +333,7 @@ "when": null, "workflow_outputs": [ { - "label": "Human-UniProt-Microbial-Proteins-(from-MetaNovo)+cRAP", + "label": "Human UniProt Microbial Proteins (from-MetaNovo) cRAP", "output_name": "output", "uuid": "cf10a376-8dce-44f1-b473-028444968f9e" } From 35b19e9c9584c28e912581916471e1eda06e9e08 Mon Sep 17 00:00:00 2001 From: Subina Mehta Date: Tue, 19 Nov 2024 11:26:41 -0500 Subject: [PATCH 14/54] Update iwc-clinicalmp-database-generation.ga --- .../iwc-clinicalmp-database-generation.ga | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/workflows/proteomics/clinicalmp/clinicalmp-database-generation/iwc-clinicalmp-database-generation.ga b/workflows/proteomics/clinicalmp/clinicalmp-database-generation/iwc-clinicalmp-database-generation.ga index ddda043ef..ed0e5d15d 100644 --- a/workflows/proteomics/clinicalmp/clinicalmp-database-generation/iwc-clinicalmp-database-generation.ga +++ b/workflows/proteomics/clinicalmp/clinicalmp-database-generation/iwc-clinicalmp-database-generation.ga @@ -107,7 +107,7 @@ "inputs": [ { "description": "Contaminants (cRAP) Protein Database", - "name": "Contaminants(cRAP) Protein-Database" + "name": "Contaminants(cRAP) Protein Database" } ], "label": "Contaminants(cRAP) Protein Database", From 3c28cf25d6f73f3534f5b7def1932ba3d6957d9e Mon Sep 17 00:00:00 2001 From: Subina Mehta Date: Tue, 19 Nov 2024 11:51:04 -0500 Subject: [PATCH 15/54] Update iwc-clinicalmp-database-generation.ga --- .../iwc-clinicalmp-database-generation.ga | 53 +++++++++---------- 1 file changed, 26 insertions(+), 27 deletions(-) diff --git a/workflows/proteomics/clinicalmp/clinicalmp-database-generation/iwc-clinicalmp-database-generation.ga b/workflows/proteomics/clinicalmp/clinicalmp-database-generation/iwc-clinicalmp-database-generation.ga index ed0e5d15d..a4ea85f92 100644 --- a/workflows/proteomics/clinicalmp/clinicalmp-database-generation/iwc-clinicalmp-database-generation.ga +++ b/workflows/proteomics/clinicalmp/clinicalmp-database-generation/iwc-clinicalmp-database-generation.ga @@ -11,8 +11,7 @@ ], "format-version": "0.1", "license": "CC-BY-4.0", - "release": "0.1", - "name": "Generate a Clinical Metaproteomics Database", + "name": "iwc-clinicalmp-database-generation ", "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" }, @@ -26,10 +25,10 @@ "inputs": [ { "description": "HUMAN SwissProt Protein Database", - "name": "HUMAN SwissProt Protein Database" + "name": "HUMAN-SwissProt-Protein-Database" } ], - "label": "HUMAN SwissProt Protein Database", + "label": "HUMAN-SwissProt-Protein-Database", "name": "Input dataset", "outputs": [], "position": { @@ -80,10 +79,10 @@ "inputs": [ { "description": "FASTA database List of Species", - "name": "Species UniProt FASTA" + "name": "Species_UniProt_FASTA" } ], - "label": "Species UniProt FASTA", + "label": "Species_UniProt_FASTA", "name": "Input dataset", "outputs": [], "position": { @@ -99,18 +98,18 @@ "workflow_outputs": [] }, "3": { - "annotation": "Contaminants (cRAP) Protein Database", + "annotation": "Contaminants (cRAP) Protein Database ", "content_id": null, "errors": null, "id": 3, "input_connections": {}, "inputs": [ { - "description": "Contaminants (cRAP) Protein Database", - "name": "Contaminants(cRAP) Protein Database" + "description": "Contaminants (cRAP) Protein Database ", + "name": "Contaminants(cRAP)-Protein-Database " } ], - "label": "Contaminants(cRAP) Protein Database", + "label": "Contaminants(cRAP)-Protein-Database ", "name": "Input dataset", "outputs": [], "position": { @@ -126,7 +125,7 @@ "workflow_outputs": [] }, "4": { - "annotation": "Fasta-merge", + "annotation": "", "content_id": "toolshed.g2.bx.psu.edu/repos/galaxyp/fasta_merge_files_and_filter_unique_sequences/fasta_merge_files_and_filter_unique_sequences/1.2.0", "errors": null, "id": 4, @@ -145,7 +144,7 @@ } }, "inputs": [], - "label": "Human UniProt Microbial Proteins cRAP for MetaNovo", + "label": "Human-UniProt-Microbial-Proteins-cRAP-for-MetaNovo", "name": "FASTA Merge Files and Filter Unique Sequences", "outputs": [ { @@ -189,7 +188,7 @@ { "label": "Human UniProt Microbial Proteins cRAP for MetaNovo", "output_name": "output", - "uuid": "9e590019-6897-4b0e-bc63-ef0599a48578" + "uuid": "fbc778a5-f931-4b0c-b641-7782abfb4351" } ] }, @@ -233,7 +232,7 @@ "post_job_actions": { "RenameDatasetActionoutput_csv": { "action_arguments": { - "newname": "CSV database" + "newname": "CSV-database" }, "action_type": "RenameDatasetAction", "output_name": "output_csv" @@ -259,20 +258,20 @@ "uuid": "07d51088-eb68-4ffd-b505-7228a21de93c", "when": null, "workflow_outputs": [ - { - "label": "CSV database", - "output_name": "output_csv", - "uuid": "d7208cb6-a907-4a8b-b8b7-cf44c103d14a" - }, { "label": "Metanovo Compact database", "output_name": "output_fasta", - "uuid": "da55e450-b86a-46a0-bc92-f602e8e8242a" + "uuid": "02940034-f0fe-4151-acd0-c6982e77b717" + }, + { + "label": "CSV-database", + "output_name": "output_csv", + "uuid": "d7208cb6-a907-4a8b-b8b7-cf44c103d14a" } ] }, "6": { - "annotation": "Merge-all-FASTA", + "annotation": "Merge all FASTA", "content_id": "toolshed.g2.bx.psu.edu/repos/galaxyp/fasta_merge_files_and_filter_unique_sequences/fasta_merge_files_and_filter_unique_sequences/1.2.0", "errors": null, "id": 6, @@ -291,7 +290,7 @@ } }, "inputs": [], - "label": "Merge-all-FASTA", + "label": "Merge all FASTA", "name": "FASTA Merge Files and Filter Unique Sequences", "outputs": [ { @@ -313,7 +312,7 @@ }, "RenameDatasetActionoutput": { "action_arguments": { - "newname": "Human-UniProt-Microbial-Proteins-(from-MetaNovo)+cRAP" + "newname": "Human UniProt Microbial Proteins (from MetaNovo) cRAP " }, "action_type": "RenameDatasetAction", "output_name": "output" @@ -333,9 +332,9 @@ "when": null, "workflow_outputs": [ { - "label": "Human UniProt Microbial Proteins (from-MetaNovo) cRAP", + "label": "Human UniProt Microbial Proteins (from MetaNovo) cRAP ", "output_name": "output", - "uuid": "cf10a376-8dce-44f1-b473-028444968f9e" + "uuid": "e3f490ef-1307-4892-bab1-6085cf8194ae" } ] } @@ -343,6 +342,6 @@ "tags": [ "name:clinicalMP" ], - "uuid": "9f8a8ec3-fc1f-4470-824a-9eb69d61e20e", - "version": 8 + "uuid": "758f86d1-b81e-438d-9666-bc7dc31b4627", + "version": 10 } From 14f5ddd0db8a5eaf1a3d9fb6d053a296b57ae978 Mon Sep 17 00:00:00 2001 From: Subina Mehta Date: Tue, 19 Nov 2024 11:53:29 -0500 Subject: [PATCH 16/54] Update iwc-clinicalmp-database-generation-tests.yml --- .../iwc-clinicalmp-database-generation-tests.yml | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/workflows/proteomics/clinicalmp/clinicalmp-database-generation/iwc-clinicalmp-database-generation-tests.yml b/workflows/proteomics/clinicalmp/clinicalmp-database-generation/iwc-clinicalmp-database-generation-tests.yml index 9b98c5323..7c7ed7f2b 100644 --- a/workflows/proteomics/clinicalmp/clinicalmp-database-generation/iwc-clinicalmp-database-generation-tests.yml +++ b/workflows/proteomics/clinicalmp/clinicalmp-database-generation/iwc-clinicalmp-database-generation-tests.yml @@ -1,14 +1,14 @@ - doc: Test outline for iwc-clinicalmp-database-generation job: - HUMAN SwissProt Protein Database: + HUMAN-SwissProt-Protein-Database: class: File location: https://zenodo.org/records/14181725/files/HUMAN-SwissProt-Protein-Database.fasta filetype: fasta - Species UniProt FASTA: + Species_UniProt_FASTA: class: File location: https://zenodo.org/records/14181725/files/Species_UniProt_FASTA.fasta filetype: fasta - Contaminants(cRAP) Protein Database: + Contaminants(cRAP)-Protein-Database: class: File location: https://zenodo.org/records/14181725/files/Contaminants(cRAP)-Protein-Database.fasta filetype: fasta @@ -37,7 +37,7 @@ asserts: has_text: text: ">sp" - CSV database: + CSV-database: asserts: has_text: text: " index Accession File ID Length Organism PeptideCount Peptides Record SAF PTRC_Skubitz_Plex2_F10_9Aug19_Rage_Rep-19-06-08 SAF PTRC_Skubitz_Plex2_F11_9Aug19_Rage_Rep-19-06-08 SAF PTRC_Skubitz_Plex2_F13_9Aug19_Rage_Rep-19-06-08 SAF PTRC_Skubitz_Plex2_F15_9Aug19_Rage_Rep-19-06-08 Sample PTRC_Skubitz_Plex2_F10_9Aug19_Rage_Rep-19-06-08 (msms) Sample PTRC_Skubitz_Plex2_F11_9Aug19_Rage_Rep-19-06-08 (msms) Sample PTRC_Skubitz_Plex2_F13_9Aug19_Rage_Rep-19-06-08 (msms) Sample PTRC_Skubitz_Plex2_F15_9Aug19_Rage_Rep-19-06-08 (msms) ScanCount Scans NSAF PTRC_Skubitz_Plex2_F10_9Aug19_Rage_Rep-19-06-08 NSAF PTRC_Skubitz_Plex2_F11_9Aug19_Rage_Rep-19-06-08 NSAF PTRC_Skubitz_Plex2_F13_9Aug19_Rage_Rep-19-06-08 NSAF PTRC_Skubitz_Plex2_F15_9Aug19_Rage_Rep-19-06-08 Summed_NSAF Protein_Prob Organism_Prob MSMS_Percent Combined_Prob" From 406e331d72549e26a6321686a1bc8e78d3c90206 Mon Sep 17 00:00:00 2001 From: Subina Mehta Date: Tue, 19 Nov 2024 13:44:50 -0500 Subject: [PATCH 17/54] Update iwc-clinicalmp-database-generation.ga --- .../iwc-clinicalmp-database-generation.ga | 1 + 1 file changed, 1 insertion(+) diff --git a/workflows/proteomics/clinicalmp/clinicalmp-database-generation/iwc-clinicalmp-database-generation.ga b/workflows/proteomics/clinicalmp/clinicalmp-database-generation/iwc-clinicalmp-database-generation.ga index a4ea85f92..ef24ccec1 100644 --- a/workflows/proteomics/clinicalmp/clinicalmp-database-generation/iwc-clinicalmp-database-generation.ga +++ b/workflows/proteomics/clinicalmp/clinicalmp-database-generation/iwc-clinicalmp-database-generation.ga @@ -12,6 +12,7 @@ "format-version": "0.1", "license": "CC-BY-4.0", "name": "iwc-clinicalmp-database-generation ", + "release": "0.1", "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" }, From e43526b71f208358f011bad25701b467ab47f2c5 Mon Sep 17 00:00:00 2001 From: Subina Mehta Date: Tue, 19 Nov 2024 13:49:48 -0500 Subject: [PATCH 18/54] Update iwc-clinicalmp-database-generation.ga --- .../iwc-clinicalmp-database-generation.ga | 14 +++++++------- 1 file changed, 7 insertions(+), 7 deletions(-) diff --git a/workflows/proteomics/clinicalmp/clinicalmp-database-generation/iwc-clinicalmp-database-generation.ga b/workflows/proteomics/clinicalmp/clinicalmp-database-generation/iwc-clinicalmp-database-generation.ga index ef24ccec1..3e489ca8f 100644 --- a/workflows/proteomics/clinicalmp/clinicalmp-database-generation/iwc-clinicalmp-database-generation.ga +++ b/workflows/proteomics/clinicalmp/clinicalmp-database-generation/iwc-clinicalmp-database-generation.ga @@ -18,14 +18,14 @@ }, "steps": { "0": { - "annotation": "HUMAN SwissProt Protein Database", + "annotation": "HUMAN-SwissProt-Protein-Database", "content_id": null, "errors": null, "id": 0, "input_connections": {}, "inputs": [ { - "description": "HUMAN SwissProt Protein Database", + "description": "HUMAN-SwissProt-Protein-Database", "name": "HUMAN-SwissProt-Protein-Database" } ], @@ -99,15 +99,15 @@ "workflow_outputs": [] }, "3": { - "annotation": "Contaminants (cRAP) Protein Database ", + "annotation": "Contaminants(cRAP)-Protein-Database", "content_id": null, "errors": null, "id": 3, "input_connections": {}, "inputs": [ { - "description": "Contaminants (cRAP) Protein Database ", - "name": "Contaminants(cRAP)-Protein-Database " + "description": "Contaminants(cRAP)-Protein-Database", + "name": "Contaminants(cRAP)-Protein-Database" } ], "label": "Contaminants(cRAP)-Protein-Database ", @@ -167,7 +167,7 @@ }, "RenameDatasetActionoutput": { "action_arguments": { - "newname": "Human UniProt Microbial Proteins cRAP for MetaNovo" + "newname": "Human-UniProt-Microbial-Proteins-cRAP-for-MetaNovo" }, "action_type": "RenameDatasetAction", "output_name": "output" @@ -187,7 +187,7 @@ "when": null, "workflow_outputs": [ { - "label": "Human UniProt Microbial Proteins cRAP for MetaNovo", + "label": "Human-UniProt-Microbial-Proteins-cRAP-for-MetaNovo", "output_name": "output", "uuid": "fbc778a5-f931-4b0c-b641-7782abfb4351" } From d8ad8dc1f6ab416a3ce527de103e54c7b236b2f6 Mon Sep 17 00:00:00 2001 From: Subina Mehta Date: Tue, 19 Nov 2024 15:45:20 -0500 Subject: [PATCH 19/54] Update iwc-clinicalmp-database-generation.ga --- .../iwc-clinicalmp-database-generation.ga | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/workflows/proteomics/clinicalmp/clinicalmp-database-generation/iwc-clinicalmp-database-generation.ga b/workflows/proteomics/clinicalmp/clinicalmp-database-generation/iwc-clinicalmp-database-generation.ga index 3e489ca8f..9f687429d 100644 --- a/workflows/proteomics/clinicalmp/clinicalmp-database-generation/iwc-clinicalmp-database-generation.ga +++ b/workflows/proteomics/clinicalmp/clinicalmp-database-generation/iwc-clinicalmp-database-generation.ga @@ -126,7 +126,7 @@ "workflow_outputs": [] }, "4": { - "annotation": "", + "annotation": "Merging FASTA files", "content_id": "toolshed.g2.bx.psu.edu/repos/galaxyp/fasta_merge_files_and_filter_unique_sequences/fasta_merge_files_and_filter_unique_sequences/1.2.0", "errors": null, "id": 4, From 9c135eaec54719e25362a2d43e429784efb11d94 Mon Sep 17 00:00:00 2001 From: Subina Mehta Date: Tue, 19 Nov 2024 15:51:04 -0500 Subject: [PATCH 20/54] Update iwc-clinicalmp-database-generation-tests.yml --- .../iwc-clinicalmp-database-generation-tests.yml | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/workflows/proteomics/clinicalmp/clinicalmp-database-generation/iwc-clinicalmp-database-generation-tests.yml b/workflows/proteomics/clinicalmp/clinicalmp-database-generation/iwc-clinicalmp-database-generation-tests.yml index 7c7ed7f2b..12adbb2b4 100644 --- a/workflows/proteomics/clinicalmp/clinicalmp-database-generation/iwc-clinicalmp-database-generation-tests.yml +++ b/workflows/proteomics/clinicalmp/clinicalmp-database-generation/iwc-clinicalmp-database-generation-tests.yml @@ -12,7 +12,7 @@ class: File location: https://zenodo.org/records/14181725/files/Contaminants(cRAP)-Protein-Database.fasta filetype: fasta - Input MGF files: + Input-MGF-files: class: Collection collection_type: list elements: From 3d677ddfb95d7b7b7734b5223a3c9b42a0a88450 Mon Sep 17 00:00:00 2001 From: Subina Mehta Date: Tue, 19 Nov 2024 15:52:31 -0500 Subject: [PATCH 21/54] Update iwc-clinicalmp-database-generation.ga --- .../iwc-clinicalmp-database-generation.ga | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/workflows/proteomics/clinicalmp/clinicalmp-database-generation/iwc-clinicalmp-database-generation.ga b/workflows/proteomics/clinicalmp/clinicalmp-database-generation/iwc-clinicalmp-database-generation.ga index 9f687429d..4767d9c28 100644 --- a/workflows/proteomics/clinicalmp/clinicalmp-database-generation/iwc-clinicalmp-database-generation.ga +++ b/workflows/proteomics/clinicalmp/clinicalmp-database-generation/iwc-clinicalmp-database-generation.ga @@ -53,7 +53,7 @@ "inputs": [ { "description": "Input MGF files (Dataset Collection)", - "name": "Input MGF files" + "name": "Input-MGF-files" } ], "label": "Input MGF files", From 299ec367d98572134857d9f6b77280e85e20d532 Mon Sep 17 00:00:00 2001 From: Subina Mehta Date: Tue, 19 Nov 2024 16:00:09 -0500 Subject: [PATCH 22/54] Update iwc-clinicalmp-database-generation-tests.yml --- .../iwc-clinicalmp-database-generation-tests.yml | 14 +++++++------- 1 file changed, 7 insertions(+), 7 deletions(-) diff --git a/workflows/proteomics/clinicalmp/clinicalmp-database-generation/iwc-clinicalmp-database-generation-tests.yml b/workflows/proteomics/clinicalmp/clinicalmp-database-generation/iwc-clinicalmp-database-generation-tests.yml index 12adbb2b4..f9ca6c260 100644 --- a/workflows/proteomics/clinicalmp/clinicalmp-database-generation/iwc-clinicalmp-database-generation-tests.yml +++ b/workflows/proteomics/clinicalmp/clinicalmp-database-generation/iwc-clinicalmp-database-generation-tests.yml @@ -2,15 +2,15 @@ job: HUMAN-SwissProt-Protein-Database: class: File - location: https://zenodo.org/records/14181725/files/HUMAN-SwissProt-Protein-Database.fasta + path: https://zenodo.org/records/14181725/files/HUMAN-SwissProt-Protein-Database.fasta filetype: fasta Species_UniProt_FASTA: class: File - location: https://zenodo.org/records/14181725/files/Species_UniProt_FASTA.fasta + path: https://zenodo.org/records/14181725/files/Species_UniProt_FASTA.fasta filetype: fasta Contaminants(cRAP)-Protein-Database: class: File - location: https://zenodo.org/records/14181725/files/Contaminants(cRAP)-Protein-Database.fasta + path: https://zenodo.org/records/14181725/files/Contaminants(cRAP)-Protein-Database.fasta filetype: fasta Input-MGF-files: class: Collection @@ -18,16 +18,16 @@ elements: - class: File identifier: PTRC_Skubitz_Plex2_F15_9Aug19_Rage_Rep-19-06-08.mgf - location: https://zenodo.org/records/14181725/files/PTRC_Skubitz_Plex2_F15_9Aug19_Rage_Rep-19-06-08.mgf + path: https://zenodo.org/records/14181725/files/PTRC_Skubitz_Plex2_F15_9Aug19_Rage_Rep-19-06-08.mgf - class: File identifier: PTRC_Skubitz_Plex2_F13_9Aug19_Rage_Rep-19-06-08.mgf - location: https://zenodo.org/records/14181725/files/PTRC_Skubitz_Plex2_F13_9Aug19_Rage_Rep-19-06-08.mgf + path: https://zenodo.org/records/14181725/files/PTRC_Skubitz_Plex2_F13_9Aug19_Rage_Rep-19-06-08.mgf - class: File identifier: PTRC_Skubitz_Plex2_F11_9Aug19_Rage_Rep-19-06-08.mgf - location: https://zenodo.org/records/14181725/files/PTRC_Skubitz_Plex2_F11_9Aug19_Rage_Rep-19-06-08.mgf + path: https://zenodo.org/records/14181725/files/PTRC_Skubitz_Plex2_F11_9Aug19_Rage_Rep-19-06-08.mgf - class: File identifier: PTRC_Skubitz_Plex2_F10_9Aug19_Rage_Rep-19-06-08.mgf - location: https://zenodo.org/records/14181725/files/PTRC_Skubitz_Plex2_F10_9Aug19_Rage_Rep-19-06-08.mgf + path: https://zenodo.org/records/14181725/files/PTRC_Skubitz_Plex2_F10_9Aug19_Rage_Rep-19-06-08.mgf outputs: Human UniProt Microbial Proteins cRAP for MetaNovo: asserts: From 4228825f970191a68538ce70fe756bfbf74dc684 Mon Sep 17 00:00:00 2001 From: Subina Mehta Date: Tue, 19 Nov 2024 16:18:54 -0500 Subject: [PATCH 23/54] Update iwc-clinicalmp-database-generation-tests.yml --- .../iwc-clinicalmp-database-generation-tests.yml | 14 +++++++------- 1 file changed, 7 insertions(+), 7 deletions(-) diff --git a/workflows/proteomics/clinicalmp/clinicalmp-database-generation/iwc-clinicalmp-database-generation-tests.yml b/workflows/proteomics/clinicalmp/clinicalmp-database-generation/iwc-clinicalmp-database-generation-tests.yml index f9ca6c260..12adbb2b4 100644 --- a/workflows/proteomics/clinicalmp/clinicalmp-database-generation/iwc-clinicalmp-database-generation-tests.yml +++ b/workflows/proteomics/clinicalmp/clinicalmp-database-generation/iwc-clinicalmp-database-generation-tests.yml @@ -2,15 +2,15 @@ job: HUMAN-SwissProt-Protein-Database: class: File - path: https://zenodo.org/records/14181725/files/HUMAN-SwissProt-Protein-Database.fasta + location: https://zenodo.org/records/14181725/files/HUMAN-SwissProt-Protein-Database.fasta filetype: fasta Species_UniProt_FASTA: class: File - path: https://zenodo.org/records/14181725/files/Species_UniProt_FASTA.fasta + location: https://zenodo.org/records/14181725/files/Species_UniProt_FASTA.fasta filetype: fasta Contaminants(cRAP)-Protein-Database: class: File - path: https://zenodo.org/records/14181725/files/Contaminants(cRAP)-Protein-Database.fasta + location: https://zenodo.org/records/14181725/files/Contaminants(cRAP)-Protein-Database.fasta filetype: fasta Input-MGF-files: class: Collection @@ -18,16 +18,16 @@ elements: - class: File identifier: PTRC_Skubitz_Plex2_F15_9Aug19_Rage_Rep-19-06-08.mgf - path: https://zenodo.org/records/14181725/files/PTRC_Skubitz_Plex2_F15_9Aug19_Rage_Rep-19-06-08.mgf + location: https://zenodo.org/records/14181725/files/PTRC_Skubitz_Plex2_F15_9Aug19_Rage_Rep-19-06-08.mgf - class: File identifier: PTRC_Skubitz_Plex2_F13_9Aug19_Rage_Rep-19-06-08.mgf - path: https://zenodo.org/records/14181725/files/PTRC_Skubitz_Plex2_F13_9Aug19_Rage_Rep-19-06-08.mgf + location: https://zenodo.org/records/14181725/files/PTRC_Skubitz_Plex2_F13_9Aug19_Rage_Rep-19-06-08.mgf - class: File identifier: PTRC_Skubitz_Plex2_F11_9Aug19_Rage_Rep-19-06-08.mgf - path: https://zenodo.org/records/14181725/files/PTRC_Skubitz_Plex2_F11_9Aug19_Rage_Rep-19-06-08.mgf + location: https://zenodo.org/records/14181725/files/PTRC_Skubitz_Plex2_F11_9Aug19_Rage_Rep-19-06-08.mgf - class: File identifier: PTRC_Skubitz_Plex2_F10_9Aug19_Rage_Rep-19-06-08.mgf - path: https://zenodo.org/records/14181725/files/PTRC_Skubitz_Plex2_F10_9Aug19_Rage_Rep-19-06-08.mgf + location: https://zenodo.org/records/14181725/files/PTRC_Skubitz_Plex2_F10_9Aug19_Rage_Rep-19-06-08.mgf outputs: Human UniProt Microbial Proteins cRAP for MetaNovo: asserts: From 6d684046091e52bd486462472b37d278537665e3 Mon Sep 17 00:00:00 2001 From: Subina Mehta Date: Tue, 19 Nov 2024 16:25:58 -0500 Subject: [PATCH 24/54] Update iwc-clinicalmp-database-generation.ga --- .../iwc-clinicalmp-database-generation.ga | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) diff --git a/workflows/proteomics/clinicalmp/clinicalmp-database-generation/iwc-clinicalmp-database-generation.ga b/workflows/proteomics/clinicalmp/clinicalmp-database-generation/iwc-clinicalmp-database-generation.ga index 4767d9c28..00b1fc65e 100644 --- a/workflows/proteomics/clinicalmp/clinicalmp-database-generation/iwc-clinicalmp-database-generation.ga +++ b/workflows/proteomics/clinicalmp/clinicalmp-database-generation/iwc-clinicalmp-database-generation.ga @@ -11,7 +11,7 @@ ], "format-version": "0.1", "license": "CC-BY-4.0", - "name": "iwc-clinicalmp-database-generation ", + "name": "iwc-clinicalmp-database-generation", "release": "0.1", "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" @@ -56,7 +56,7 @@ "name": "Input-MGF-files" } ], - "label": "Input MGF files", + "label": "Input-MGF-files", "name": "Input dataset collection", "outputs": [], "position": { @@ -110,7 +110,7 @@ "name": "Contaminants(cRAP)-Protein-Database" } ], - "label": "Contaminants(cRAP)-Protein-Database ", + "label": "Contaminants(cRAP)-Protein-Database", "name": "Input dataset", "outputs": [], "position": { @@ -313,7 +313,7 @@ }, "RenameDatasetActionoutput": { "action_arguments": { - "newname": "Human UniProt Microbial Proteins (from MetaNovo) cRAP " + "newname": "Human UniProt Microbial Proteins (from MetaNovo) cRAP" }, "action_type": "RenameDatasetAction", "output_name": "output" @@ -333,7 +333,7 @@ "when": null, "workflow_outputs": [ { - "label": "Human UniProt Microbial Proteins (from MetaNovo) cRAP ", + "label": "Human UniProt Microbial Proteins (from MetaNovo) cRAP", "output_name": "output", "uuid": "e3f490ef-1307-4892-bab1-6085cf8194ae" } From af152321477f4f3e4720cc0619efb2b08b41e606 Mon Sep 17 00:00:00 2001 From: Subina Mehta Date: Tue, 19 Nov 2024 20:30:22 -0500 Subject: [PATCH 25/54] Update README.md --- .../clinicalmp/clinicalmp-database-generation/README.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/workflows/proteomics/clinicalmp/clinicalmp-database-generation/README.md b/workflows/proteomics/clinicalmp/clinicalmp-database-generation/README.md index ac28a2fd3..c5a155a7c 100644 --- a/workflows/proteomics/clinicalmp/clinicalmp-database-generation/README.md +++ b/workflows/proteomics/clinicalmp/clinicalmp-database-generation/README.md @@ -4,7 +4,7 @@ Metaproteomics involves the large-scale identification and analysis of all prote To overcome this challenge, we developed a metaproteomics workflow using tandem mass spectrometry (MS/MS) and bioinformatics tools on the Galaxy platform. This workflow enables the characterization of metaproteomes in clinical samples. The first step in this workflow is the Database Generation process. The Galaxy-P team has created a workflow that compiles a large database by downloading protein sequences of known disease-causing microorganisms. From this extensive database, a compact, relevant database is then created using the Metanovo tool. -A GTN has been developed for this workflow. [https://training.galaxyproject.org/training-material/topics/proteomics/tutorials/clinical-mp-4-quantitation/tutorial.html](https://training.galaxyproject.org/training-material/topics/proteomics/tutorials/clinical-mp-1-database-generation/tutorial.html) +A GTN has been developed for this workflow. [https://training.galaxyproject.org/training-material/topics/proteomics/tutorials/clinical-mp-1-database-generation/tutorial.html](https://training.galaxyproject.org/training-material/topics/proteomics/tutorials/clinical-mp-1-database-generation/tutorial.html) ## Inputs dataset From 587c08c2eacb41751475b2b71128af92e3ae0992 Mon Sep 17 00:00:00 2001 From: Subina Mehta Date: Tue, 19 Nov 2024 21:41:20 -0500 Subject: [PATCH 26/54] Update iwc-clinicalmp-database-generation-tests.yml --- .../iwc-clinicalmp-database-generation-tests.yml | 14 +++++++------- 1 file changed, 7 insertions(+), 7 deletions(-) diff --git a/workflows/proteomics/clinicalmp/clinicalmp-database-generation/iwc-clinicalmp-database-generation-tests.yml b/workflows/proteomics/clinicalmp/clinicalmp-database-generation/iwc-clinicalmp-database-generation-tests.yml index 12adbb2b4..4f973ed16 100644 --- a/workflows/proteomics/clinicalmp/clinicalmp-database-generation/iwc-clinicalmp-database-generation-tests.yml +++ b/workflows/proteomics/clinicalmp/clinicalmp-database-generation/iwc-clinicalmp-database-generation-tests.yml @@ -2,15 +2,15 @@ job: HUMAN-SwissProt-Protein-Database: class: File - location: https://zenodo.org/records/14181725/files/HUMAN-SwissProt-Protein-Database.fasta + location: https://zenodo.org/records/14181725/files/HUMAN-SwissProt-Protein-Database.fasta?download=1 filetype: fasta Species_UniProt_FASTA: class: File - location: https://zenodo.org/records/14181725/files/Species_UniProt_FASTA.fasta + location: https://zenodo.org/records/14181725/files/Species_UniProt_FASTA.fasta?download=1 filetype: fasta Contaminants(cRAP)-Protein-Database: class: File - location: https://zenodo.org/records/14181725/files/Contaminants(cRAP)-Protein-Database.fasta + location: https://zenodo.org/records/14181725/files/Contaminants(cRAP)-Protein-Database.fasta?download=1 filetype: fasta Input-MGF-files: class: Collection @@ -18,16 +18,16 @@ elements: - class: File identifier: PTRC_Skubitz_Plex2_F15_9Aug19_Rage_Rep-19-06-08.mgf - location: https://zenodo.org/records/14181725/files/PTRC_Skubitz_Plex2_F15_9Aug19_Rage_Rep-19-06-08.mgf + location: https://zenodo.org/records/14181725/files/PTRC_Skubitz_Plex2_F10_9Aug19_Rage_Rep-19-06-08.mgf?download=1 - class: File identifier: PTRC_Skubitz_Plex2_F13_9Aug19_Rage_Rep-19-06-08.mgf - location: https://zenodo.org/records/14181725/files/PTRC_Skubitz_Plex2_F13_9Aug19_Rage_Rep-19-06-08.mgf + location: https://zenodo.org/records/14181725/files/PTRC_Skubitz_Plex2_F13_9Aug19_Rage_Rep-19-06-08.mgf?download=1 - class: File identifier: PTRC_Skubitz_Plex2_F11_9Aug19_Rage_Rep-19-06-08.mgf - location: https://zenodo.org/records/14181725/files/PTRC_Skubitz_Plex2_F11_9Aug19_Rage_Rep-19-06-08.mgf + location: https://zenodo.org/records/14181725/files/PTRC_Skubitz_Plex2_F11_9Aug19_Rage_Rep-19-06-08.mgf?download=1 - class: File identifier: PTRC_Skubitz_Plex2_F10_9Aug19_Rage_Rep-19-06-08.mgf - location: https://zenodo.org/records/14181725/files/PTRC_Skubitz_Plex2_F10_9Aug19_Rage_Rep-19-06-08.mgf + location: https://zenodo.org/records/14181725/files/PTRC_Skubitz_Plex2_F10_9Aug19_Rage_Rep-19-06-08.mgf?download=1 outputs: Human UniProt Microbial Proteins cRAP for MetaNovo: asserts: From fbac866bc13439a02d6aa7c097b6ea8a063d8fbf Mon Sep 17 00:00:00 2001 From: Subina Mehta Date: Tue, 19 Nov 2024 21:42:00 -0500 Subject: [PATCH 27/54] Update iwc-clinicalmp-database-generation-tests.yml --- .../iwc-clinicalmp-database-generation-tests.yml | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/workflows/proteomics/clinicalmp/clinicalmp-database-generation/iwc-clinicalmp-database-generation-tests.yml b/workflows/proteomics/clinicalmp/clinicalmp-database-generation/iwc-clinicalmp-database-generation-tests.yml index 4f973ed16..5b3db3712 100644 --- a/workflows/proteomics/clinicalmp/clinicalmp-database-generation/iwc-clinicalmp-database-generation-tests.yml +++ b/workflows/proteomics/clinicalmp/clinicalmp-database-generation/iwc-clinicalmp-database-generation-tests.yml @@ -18,7 +18,7 @@ elements: - class: File identifier: PTRC_Skubitz_Plex2_F15_9Aug19_Rage_Rep-19-06-08.mgf - location: https://zenodo.org/records/14181725/files/PTRC_Skubitz_Plex2_F10_9Aug19_Rage_Rep-19-06-08.mgf?download=1 + location: https://zenodo.org/records/14181725/files/PTRC_Skubitz_Plex2_F15_9Aug19_Rage_Rep-19-06-08.mgf?download=1 - class: File identifier: PTRC_Skubitz_Plex2_F13_9Aug19_Rage_Rep-19-06-08.mgf location: https://zenodo.org/records/14181725/files/PTRC_Skubitz_Plex2_F13_9Aug19_Rage_Rep-19-06-08.mgf?download=1 From 5499333dfd09397292dac6f84a2c45434a6bd828 Mon Sep 17 00:00:00 2001 From: Subina Mehta Date: Tue, 19 Nov 2024 22:07:34 -0500 Subject: [PATCH 28/54] Update iwc-clinicalmp-database-generation.ga --- .../iwc-clinicalmp-database-generation.ga | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/workflows/proteomics/clinicalmp/clinicalmp-database-generation/iwc-clinicalmp-database-generation.ga b/workflows/proteomics/clinicalmp/clinicalmp-database-generation/iwc-clinicalmp-database-generation.ga index 00b1fc65e..7489fea1b 100644 --- a/workflows/proteomics/clinicalmp/clinicalmp-database-generation/iwc-clinicalmp-database-generation.ga +++ b/workflows/proteomics/clinicalmp/clinicalmp-database-generation/iwc-clinicalmp-database-generation.ga @@ -45,14 +45,14 @@ "workflow_outputs": [] }, "1": { - "annotation": "Input MGF files (Dataset Collection)", + "annotation": "Input-MGF-files", "content_id": null, "errors": null, "id": 1, "input_connections": {}, "inputs": [ { - "description": "Input MGF files (Dataset Collection)", + "description": "Input-MGF-files", "name": "Input-MGF-files" } ], @@ -72,14 +72,14 @@ "workflow_outputs": [] }, "2": { - "annotation": "FASTA database List of Species", + "annotation": "Species_UniProt_FASTA", "content_id": null, "errors": null, "id": 2, "input_connections": {}, "inputs": [ { - "description": "FASTA database List of Species", + "description": "Species_UniProt_FASTA", "name": "Species_UniProt_FASTA" } ], From bbd8019421272b96dba9f8a0a2b695f3e418a03e Mon Sep 17 00:00:00 2001 From: Subina Mehta Date: Wed, 20 Nov 2024 09:29:03 -0500 Subject: [PATCH 29/54] Update workflows/proteomics/clinicalmp/clinicalmp-database-generation/iwc-clinicalmp-database-generation.ga Co-authored-by: Marius van den Beek --- .../iwc-clinicalmp-database-generation.ga | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/workflows/proteomics/clinicalmp/clinicalmp-database-generation/iwc-clinicalmp-database-generation.ga b/workflows/proteomics/clinicalmp/clinicalmp-database-generation/iwc-clinicalmp-database-generation.ga index 7489fea1b..5f732bcc8 100644 --- a/workflows/proteomics/clinicalmp/clinicalmp-database-generation/iwc-clinicalmp-database-generation.ga +++ b/workflows/proteomics/clinicalmp/clinicalmp-database-generation/iwc-clinicalmp-database-generation.ga @@ -11,7 +11,7 @@ ], "format-version": "0.1", "license": "CC-BY-4.0", - "name": "iwc-clinicalmp-database-generation", + "name": "Generate a Clinical Metaproteomics Database", "release": "0.1", "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" From aa55ecdb03b46a1e90f949b7736dc85ff0fedc51 Mon Sep 17 00:00:00 2001 From: Subina Mehta Date: Wed, 20 Nov 2024 09:30:20 -0500 Subject: [PATCH 30/54] Update iwc-clinicalmp-database-generation-tests.yml --- .../iwc-clinicalmp-database-generation-tests.yml | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/workflows/proteomics/clinicalmp/clinicalmp-database-generation/iwc-clinicalmp-database-generation-tests.yml b/workflows/proteomics/clinicalmp/clinicalmp-database-generation/iwc-clinicalmp-database-generation-tests.yml index 5b3db3712..7e63e4ba3 100644 --- a/workflows/proteomics/clinicalmp/clinicalmp-database-generation/iwc-clinicalmp-database-generation-tests.yml +++ b/workflows/proteomics/clinicalmp/clinicalmp-database-generation/iwc-clinicalmp-database-generation-tests.yml @@ -40,8 +40,8 @@ CSV-database: asserts: has_text: - text: " index Accession File ID Length Organism PeptideCount Peptides Record SAF PTRC_Skubitz_Plex2_F10_9Aug19_Rage_Rep-19-06-08 SAF PTRC_Skubitz_Plex2_F11_9Aug19_Rage_Rep-19-06-08 SAF PTRC_Skubitz_Plex2_F13_9Aug19_Rage_Rep-19-06-08 SAF PTRC_Skubitz_Plex2_F15_9Aug19_Rage_Rep-19-06-08 Sample PTRC_Skubitz_Plex2_F10_9Aug19_Rage_Rep-19-06-08 (msms) Sample PTRC_Skubitz_Plex2_F11_9Aug19_Rage_Rep-19-06-08 (msms) Sample PTRC_Skubitz_Plex2_F13_9Aug19_Rage_Rep-19-06-08 (msms) Sample PTRC_Skubitz_Plex2_F15_9Aug19_Rage_Rep-19-06-08 (msms) ScanCount Scans NSAF PTRC_Skubitz_Plex2_F10_9Aug19_Rage_Rep-19-06-08 NSAF PTRC_Skubitz_Plex2_F11_9Aug19_Rage_Rep-19-06-08 NSAF PTRC_Skubitz_Plex2_F13_9Aug19_Rage_Rep-19-06-08 NSAF PTRC_Skubitz_Plex2_F15_9Aug19_Rage_Rep-19-06-08 Summed_NSAF Protein_Prob Organism_Prob MSMS_Percent Combined_Prob" - Human UniProt Microbial-Proteins (from MetaNovo) cRAP: + text: "index Accession File ID Length Organism PeptideCount Peptides Record SAF PTRC_Skubitz_Plex2_F10_9Aug19_Rage_Rep-19-06-08 SAF PTRC_Skubitz_Plex2_F11_9Aug19_Rage_Rep-19-06-08 SAF PTRC_Skubitz_Plex2_F13_9Aug19_Rage_Rep-19-06-08 SAF PTRC_Skubitz_Plex2_F15_9Aug19_Rage_Rep-19-06-08 Sample PTRC_Skubitz_Plex2_F10_9Aug19_Rage_Rep-19-06-08 (msms) Sample PTRC_Skubitz_Plex2_F11_9Aug19_Rage_Rep-19-06-08 (msms) Sample PTRC_Skubitz_Plex2_F13_9Aug19_Rage_Rep-19-06-08 (msms) Sample PTRC_Skubitz_Plex2_F15_9Aug19_Rage_Rep-19-06-08 (msms) ScanCount Scans NSAF PTRC_Skubitz_Plex2_F10_9Aug19_Rage_Rep-19-06-08 NSAF PTRC_Skubitz_Plex2_F11_9Aug19_Rage_Rep-19-06-08 NSAF PTRC_Skubitz_Plex2_F13_9Aug19_Rage_Rep-19-06-08 NSAF PTRC_Skubitz_Plex2_F15_9Aug19_Rage_Rep-19-06-08 Summed_NSAF Protein_Prob Organism_Prob MSMS_Percent Combined_Prob" + Human UniProt Microbial Proteins (from MetaNovo) cRAP: asserts: has_text: text: ">sp" From 1fb0474f6914930f0f185a18fbd6804d72c1104f Mon Sep 17 00:00:00 2001 From: Subina Mehta Date: Wed, 20 Nov 2024 09:33:07 -0500 Subject: [PATCH 31/54] Update iwc-clinicalmp-database-generation-tests.yml --- .../iwc-clinicalmp-database-generation-tests.yml | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/workflows/proteomics/clinicalmp/clinicalmp-database-generation/iwc-clinicalmp-database-generation-tests.yml b/workflows/proteomics/clinicalmp/clinicalmp-database-generation/iwc-clinicalmp-database-generation-tests.yml index 7e63e4ba3..91ebae00b 100644 --- a/workflows/proteomics/clinicalmp/clinicalmp-database-generation/iwc-clinicalmp-database-generation-tests.yml +++ b/workflows/proteomics/clinicalmp/clinicalmp-database-generation/iwc-clinicalmp-database-generation-tests.yml @@ -37,7 +37,7 @@ asserts: has_text: text: ">sp" - CSV-database: + CSV database: asserts: has_text: text: "index Accession File ID Length Organism PeptideCount Peptides Record SAF PTRC_Skubitz_Plex2_F10_9Aug19_Rage_Rep-19-06-08 SAF PTRC_Skubitz_Plex2_F11_9Aug19_Rage_Rep-19-06-08 SAF PTRC_Skubitz_Plex2_F13_9Aug19_Rage_Rep-19-06-08 SAF PTRC_Skubitz_Plex2_F15_9Aug19_Rage_Rep-19-06-08 Sample PTRC_Skubitz_Plex2_F10_9Aug19_Rage_Rep-19-06-08 (msms) Sample PTRC_Skubitz_Plex2_F11_9Aug19_Rage_Rep-19-06-08 (msms) Sample PTRC_Skubitz_Plex2_F13_9Aug19_Rage_Rep-19-06-08 (msms) Sample PTRC_Skubitz_Plex2_F15_9Aug19_Rage_Rep-19-06-08 (msms) ScanCount Scans NSAF PTRC_Skubitz_Plex2_F10_9Aug19_Rage_Rep-19-06-08 NSAF PTRC_Skubitz_Plex2_F11_9Aug19_Rage_Rep-19-06-08 NSAF PTRC_Skubitz_Plex2_F13_9Aug19_Rage_Rep-19-06-08 NSAF PTRC_Skubitz_Plex2_F15_9Aug19_Rage_Rep-19-06-08 Summed_NSAF Protein_Prob Organism_Prob MSMS_Percent Combined_Prob" From da9efa5446a2a42a4be1e4bb3bc222654a28b533 Mon Sep 17 00:00:00 2001 From: Subina Mehta Date: Wed, 20 Nov 2024 09:33:23 -0500 Subject: [PATCH 32/54] Update iwc-clinicalmp-database-generation.ga --- .../iwc-clinicalmp-database-generation.ga | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) diff --git a/workflows/proteomics/clinicalmp/clinicalmp-database-generation/iwc-clinicalmp-database-generation.ga b/workflows/proteomics/clinicalmp/clinicalmp-database-generation/iwc-clinicalmp-database-generation.ga index 5f732bcc8..bad500a84 100644 --- a/workflows/proteomics/clinicalmp/clinicalmp-database-generation/iwc-clinicalmp-database-generation.ga +++ b/workflows/proteomics/clinicalmp/clinicalmp-database-generation/iwc-clinicalmp-database-generation.ga @@ -145,7 +145,7 @@ } }, "inputs": [], - "label": "Human-UniProt-Microbial-Proteins-cRAP-for-MetaNovo", + "label": "Human UniProt Microbial Proteins cRAP for MetaNovo", "name": "FASTA Merge Files and Filter Unique Sequences", "outputs": [ { @@ -167,7 +167,7 @@ }, "RenameDatasetActionoutput": { "action_arguments": { - "newname": "Human-UniProt-Microbial-Proteins-cRAP-for-MetaNovo" + "newname": "Human UniProt Microbial Proteins cRAP for MetaNovo" }, "action_type": "RenameDatasetAction", "output_name": "output" @@ -187,7 +187,7 @@ "when": null, "workflow_outputs": [ { - "label": "Human-UniProt-Microbial-Proteins-cRAP-for-MetaNovo", + "label": "Human UniProt Microbial Proteins cRAP for MetaNovo", "output_name": "output", "uuid": "fbc778a5-f931-4b0c-b641-7782abfb4351" } @@ -233,7 +233,7 @@ "post_job_actions": { "RenameDatasetActionoutput_csv": { "action_arguments": { - "newname": "CSV-database" + "newname": "CSV database" }, "action_type": "RenameDatasetAction", "output_name": "output_csv" @@ -265,7 +265,7 @@ "uuid": "02940034-f0fe-4151-acd0-c6982e77b717" }, { - "label": "CSV-database", + "label": "CSV database", "output_name": "output_csv", "uuid": "d7208cb6-a907-4a8b-b8b7-cf44c103d14a" } From 49018cf0de7b97a9ce19b4c3bda15439c68405e3 Mon Sep 17 00:00:00 2001 From: Subina Mehta Date: Wed, 20 Nov 2024 11:18:51 -0500 Subject: [PATCH 33/54] Update README.md --- .../clinicalmp/clinicalmp-database-generation/README.md | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/workflows/proteomics/clinicalmp/clinicalmp-database-generation/README.md b/workflows/proteomics/clinicalmp/clinicalmp-database-generation/README.md index c5a155a7c..1757facd9 100644 --- a/workflows/proteomics/clinicalmp/clinicalmp-database-generation/README.md +++ b/workflows/proteomics/clinicalmp/clinicalmp-database-generation/README.md @@ -8,11 +8,11 @@ A GTN has been developed for this workflow. [https://training.galaxyproject.org/ ## Inputs dataset -### Search Databases (FASTA) +### Search Databases (FASTA) from [Zenodo](https://zenodo.org/records/14181725) - `HUMAN_SwissProt_Protein_Database.fasta` - `Species_UniProt_FASTA.fasta` - `Contaminants_(cRAP)_Protein_Database.fasta` -### MSMS files +### MSMS files download from [Zenodo](https://zenodo.org/records/14181725) - `PTRC_Skubitz_Plex2_F10_9Aug19_Rage_Rep-19-06-08.mgf` - `PTRC_Skubitz_Plex2_F11_9Aug19_Rage_Rep-19-06-08.mgf` - `PTRC_Skubitz_Plex2_F13_9Aug19_Rage_Rep-19-06-08.mgf` From b00b8145fa86a340aab703897255afb608b035f5 Mon Sep 17 00:00:00 2001 From: Subina Mehta Date: Wed, 20 Nov 2024 11:22:03 -0500 Subject: [PATCH 34/54] Update iwc-clinicalmp-database-generation-tests.yml --- .../iwc-clinicalmp-database-generation-tests.yml | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/workflows/proteomics/clinicalmp/clinicalmp-database-generation/iwc-clinicalmp-database-generation-tests.yml b/workflows/proteomics/clinicalmp/clinicalmp-database-generation/iwc-clinicalmp-database-generation-tests.yml index 91ebae00b..66e3006a5 100644 --- a/workflows/proteomics/clinicalmp/clinicalmp-database-generation/iwc-clinicalmp-database-generation-tests.yml +++ b/workflows/proteomics/clinicalmp/clinicalmp-database-generation/iwc-clinicalmp-database-generation-tests.yml @@ -32,11 +32,11 @@ Human UniProt Microbial Proteins cRAP for MetaNovo: asserts: has_text: - text: ">sp" + text: ">" Metanovo Compact database: asserts: has_text: - text: ">sp" + text: ">" CSV database: asserts: has_text: @@ -44,5 +44,5 @@ Human UniProt Microbial Proteins (from MetaNovo) cRAP: asserts: has_text: - text: ">sp" + text: ">" From ec6b0b5bf471aeebd9d7b7789dae2156f19748a9 Mon Sep 17 00:00:00 2001 From: Subina Mehta Date: Wed, 20 Nov 2024 12:41:49 -0500 Subject: [PATCH 35/54] Update iwc-clinicalmp-database-generation-tests.yml --- .../iwc-clinicalmp-database-generation-tests.yml | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/workflows/proteomics/clinicalmp/clinicalmp-database-generation/iwc-clinicalmp-database-generation-tests.yml b/workflows/proteomics/clinicalmp/clinicalmp-database-generation/iwc-clinicalmp-database-generation-tests.yml index 66e3006a5..2d3b5daa1 100644 --- a/workflows/proteomics/clinicalmp/clinicalmp-database-generation/iwc-clinicalmp-database-generation-tests.yml +++ b/workflows/proteomics/clinicalmp/clinicalmp-database-generation/iwc-clinicalmp-database-generation-tests.yml @@ -40,7 +40,7 @@ CSV database: asserts: has_text: - text: "index Accession File ID Length Organism PeptideCount Peptides Record SAF PTRC_Skubitz_Plex2_F10_9Aug19_Rage_Rep-19-06-08 SAF PTRC_Skubitz_Plex2_F11_9Aug19_Rage_Rep-19-06-08 SAF PTRC_Skubitz_Plex2_F13_9Aug19_Rage_Rep-19-06-08 SAF PTRC_Skubitz_Plex2_F15_9Aug19_Rage_Rep-19-06-08 Sample PTRC_Skubitz_Plex2_F10_9Aug19_Rage_Rep-19-06-08 (msms) Sample PTRC_Skubitz_Plex2_F11_9Aug19_Rage_Rep-19-06-08 (msms) Sample PTRC_Skubitz_Plex2_F13_9Aug19_Rage_Rep-19-06-08 (msms) Sample PTRC_Skubitz_Plex2_F15_9Aug19_Rage_Rep-19-06-08 (msms) ScanCount Scans NSAF PTRC_Skubitz_Plex2_F10_9Aug19_Rage_Rep-19-06-08 NSAF PTRC_Skubitz_Plex2_F11_9Aug19_Rage_Rep-19-06-08 NSAF PTRC_Skubitz_Plex2_F13_9Aug19_Rage_Rep-19-06-08 NSAF PTRC_Skubitz_Plex2_F15_9Aug19_Rage_Rep-19-06-08 Summed_NSAF Protein_Prob Organism_Prob MSMS_Percent Combined_Prob" + text: " index Accession File ID Length Organism PeptideCount Peptides Record SAF PTRC_Skubitz_Plex2_F10_9Aug19_Rage_Rep-19-06-08 SAF PTRC_Skubitz_Plex2_F11_9Aug19_Rage_Rep-19-06-08 SAF PTRC_Skubitz_Plex2_F13_9Aug19_Rage_Rep-19-06-08 SAF PTRC_Skubitz_Plex2_F15_9Aug19_Rage_Rep-19-06-08 Sample PTRC_Skubitz_Plex2_F10_9Aug19_Rage_Rep-19-06-08 (msms) Sample PTRC_Skubitz_Plex2_F11_9Aug19_Rage_Rep-19-06-08 (msms) Sample PTRC_Skubitz_Plex2_F13_9Aug19_Rage_Rep-19-06-08 (msms) Sample PTRC_Skubitz_Plex2_F15_9Aug19_Rage_Rep-19-06-08 (msms) ScanCount Scans NSAF PTRC_Skubitz_Plex2_F10_9Aug19_Rage_Rep-19-06-08 NSAF PTRC_Skubitz_Plex2_F11_9Aug19_Rage_Rep-19-06-08 NSAF PTRC_Skubitz_Plex2_F13_9Aug19_Rage_Rep-19-06-08 NSAF PTRC_Skubitz_Plex2_F15_9Aug19_Rage_Rep-19-06-08 Summed_NSAF Protein_Prob Organism_Prob MSMS_Percent Combined_Prob" Human UniProt Microbial Proteins (from MetaNovo) cRAP: asserts: has_text: From ddefa079198d88fa9c0c2ca40a0b080eb75b22e1 Mon Sep 17 00:00:00 2001 From: Subina Mehta Date: Wed, 20 Nov 2024 14:22:22 -0500 Subject: [PATCH 36/54] Update README.md --- .../clinicalmp/clinicalmp-database-generation/README.md | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/workflows/proteomics/clinicalmp/clinicalmp-database-generation/README.md b/workflows/proteomics/clinicalmp/clinicalmp-database-generation/README.md index 1757facd9..de38cabf8 100644 --- a/workflows/proteomics/clinicalmp/clinicalmp-database-generation/README.md +++ b/workflows/proteomics/clinicalmp/clinicalmp-database-generation/README.md @@ -9,9 +9,9 @@ A GTN has been developed for this workflow. [https://training.galaxyproject.org/ ## Inputs dataset ### Search Databases (FASTA) from [Zenodo](https://zenodo.org/records/14181725) -- `HUMAN_SwissProt_Protein_Database.fasta` -- `Species_UniProt_FASTA.fasta` -- `Contaminants_(cRAP)_Protein_Database.fasta` +- `HUMAN SwissProt Protein_Database.fasta` +- `Species UniProt FASTA.fasta` +- `Contaminants (cRAP) Protein Database.fasta` ### MSMS files download from [Zenodo](https://zenodo.org/records/14181725) - `PTRC_Skubitz_Plex2_F10_9Aug19_Rage_Rep-19-06-08.mgf` - `PTRC_Skubitz_Plex2_F11_9Aug19_Rage_Rep-19-06-08.mgf` From 16404bcb46536888c9a94799e6dd59ac1991606a Mon Sep 17 00:00:00 2001 From: Subina Mehta Date: Wed, 20 Nov 2024 14:25:37 -0500 Subject: [PATCH 37/54] Update iwc-clinicalmp-database-generation-tests.yml --- .../iwc-clinicalmp-database-generation-tests.yml | 1 + 1 file changed, 1 insertion(+) diff --git a/workflows/proteomics/clinicalmp/clinicalmp-database-generation/iwc-clinicalmp-database-generation-tests.yml b/workflows/proteomics/clinicalmp/clinicalmp-database-generation/iwc-clinicalmp-database-generation-tests.yml index 2d3b5daa1..91351062b 100644 --- a/workflows/proteomics/clinicalmp/clinicalmp-database-generation/iwc-clinicalmp-database-generation-tests.yml +++ b/workflows/proteomics/clinicalmp/clinicalmp-database-generation/iwc-clinicalmp-database-generation-tests.yml @@ -41,6 +41,7 @@ asserts: has_text: text: " index Accession File ID Length Organism PeptideCount Peptides Record SAF PTRC_Skubitz_Plex2_F10_9Aug19_Rage_Rep-19-06-08 SAF PTRC_Skubitz_Plex2_F11_9Aug19_Rage_Rep-19-06-08 SAF PTRC_Skubitz_Plex2_F13_9Aug19_Rage_Rep-19-06-08 SAF PTRC_Skubitz_Plex2_F15_9Aug19_Rage_Rep-19-06-08 Sample PTRC_Skubitz_Plex2_F10_9Aug19_Rage_Rep-19-06-08 (msms) Sample PTRC_Skubitz_Plex2_F11_9Aug19_Rage_Rep-19-06-08 (msms) Sample PTRC_Skubitz_Plex2_F13_9Aug19_Rage_Rep-19-06-08 (msms) Sample PTRC_Skubitz_Plex2_F15_9Aug19_Rage_Rep-19-06-08 (msms) ScanCount Scans NSAF PTRC_Skubitz_Plex2_F10_9Aug19_Rage_Rep-19-06-08 NSAF PTRC_Skubitz_Plex2_F11_9Aug19_Rage_Rep-19-06-08 NSAF PTRC_Skubitz_Plex2_F13_9Aug19_Rage_Rep-19-06-08 NSAF PTRC_Skubitz_Plex2_F15_9Aug19_Rage_Rep-19-06-08 Summed_NSAF Protein_Prob Organism_Prob MSMS_Percent Combined_Prob" + Human UniProt Microbial Proteins (from MetaNovo) cRAP: asserts: has_text: From b11b56269b380dd535a994c7c906c5342736c8c2 Mon Sep 17 00:00:00 2001 From: Subina Mehta Date: Wed, 20 Nov 2024 14:30:50 -0500 Subject: [PATCH 38/54] Update iwc-clinicalmp-database-generation-tests.yml --- ...c-clinicalmp-database-generation-tests.yml | 22 +++++++++++++------ 1 file changed, 15 insertions(+), 7 deletions(-) diff --git a/workflows/proteomics/clinicalmp/clinicalmp-database-generation/iwc-clinicalmp-database-generation-tests.yml b/workflows/proteomics/clinicalmp/clinicalmp-database-generation/iwc-clinicalmp-database-generation-tests.yml index 91351062b..eba3a454b 100644 --- a/workflows/proteomics/clinicalmp/clinicalmp-database-generation/iwc-clinicalmp-database-generation-tests.yml +++ b/workflows/proteomics/clinicalmp/clinicalmp-database-generation/iwc-clinicalmp-database-generation-tests.yml @@ -33,17 +33,25 @@ asserts: has_text: text: ">" + has_text: + text: "^[A-Za-z]+$" + not_empty: true Metanovo Compact database: asserts: has_text: text: ">" - CSV database: - asserts: - has_text: - text: " index Accession File ID Length Organism PeptideCount Peptides Record SAF PTRC_Skubitz_Plex2_F10_9Aug19_Rage_Rep-19-06-08 SAF PTRC_Skubitz_Plex2_F11_9Aug19_Rage_Rep-19-06-08 SAF PTRC_Skubitz_Plex2_F13_9Aug19_Rage_Rep-19-06-08 SAF PTRC_Skubitz_Plex2_F15_9Aug19_Rage_Rep-19-06-08 Sample PTRC_Skubitz_Plex2_F10_9Aug19_Rage_Rep-19-06-08 (msms) Sample PTRC_Skubitz_Plex2_F11_9Aug19_Rage_Rep-19-06-08 (msms) Sample PTRC_Skubitz_Plex2_F13_9Aug19_Rage_Rep-19-06-08 (msms) Sample PTRC_Skubitz_Plex2_F15_9Aug19_Rage_Rep-19-06-08 (msms) ScanCount Scans NSAF PTRC_Skubitz_Plex2_F10_9Aug19_Rage_Rep-19-06-08 NSAF PTRC_Skubitz_Plex2_F11_9Aug19_Rage_Rep-19-06-08 NSAF PTRC_Skubitz_Plex2_F13_9Aug19_Rage_Rep-19-06-08 NSAF PTRC_Skubitz_Plex2_F15_9Aug19_Rage_Rep-19-06-08 Summed_NSAF Protein_Prob Organism_Prob MSMS_Percent Combined_Prob" - + has_text: + text: "^[A-Za-z]+$" + not_empty: true + CSV database: + asserts: + has_text: + text: "^\\d+\\t[A-Za-z0-9]+\\t[A-Za-z0-9]+\\t\\d+" Human UniProt Microbial Proteins (from MetaNovo) cRAP: asserts: - has_text: - text: ">" + has_text: + text: ">" + has_text: + text: "^[A-Za-z]+$" + not_empty: true From 950291ae0adb10b1b39fa6c1dcee26191fa67d14 Mon Sep 17 00:00:00 2001 From: Subina Mehta Date: Wed, 20 Nov 2024 14:42:23 -0500 Subject: [PATCH 39/54] Update iwc-clinicalmp-database-generation-tests.yml --- .../iwc-clinicalmp-database-generation-tests.yml | 14 ++++---------- 1 file changed, 4 insertions(+), 10 deletions(-) diff --git a/workflows/proteomics/clinicalmp/clinicalmp-database-generation/iwc-clinicalmp-database-generation-tests.yml b/workflows/proteomics/clinicalmp/clinicalmp-database-generation/iwc-clinicalmp-database-generation-tests.yml index eba3a454b..5c6a7efb2 100644 --- a/workflows/proteomics/clinicalmp/clinicalmp-database-generation/iwc-clinicalmp-database-generation-tests.yml +++ b/workflows/proteomics/clinicalmp/clinicalmp-database-generation/iwc-clinicalmp-database-generation-tests.yml @@ -32,26 +32,20 @@ Human UniProt Microbial Proteins cRAP for MetaNovo: asserts: has_text: - text: ">" - has_text: - text: "^[A-Za-z]+$" + text: ">sp|" not_empty: true Metanovo Compact database: asserts: has_text: - text: ">" - has_text: - text: "^[A-Za-z]+$" + text: ">tr|" not_empty: true CSV database: asserts: has_text: - text: "^\\d+\\t[A-Za-z0-9]+\\t[A-Za-z0-9]+\\t\\d+" + text: "index" Human UniProt Microbial Proteins (from MetaNovo) cRAP: asserts: has_text: - text: ">" - has_text: - text: "^[A-Za-z]+$" + text: ">sp|" not_empty: true From c25bf3f09e0d5e91fdb37a140157a2678fa6317e Mon Sep 17 00:00:00 2001 From: Subina Mehta Date: Wed, 20 Nov 2024 15:07:21 -0500 Subject: [PATCH 40/54] Update iwc-clinicalmp-database-generation-tests.yml --- .../iwc-clinicalmp-database-generation-tests.yml | 14 ++++++-------- 1 file changed, 6 insertions(+), 8 deletions(-) diff --git a/workflows/proteomics/clinicalmp/clinicalmp-database-generation/iwc-clinicalmp-database-generation-tests.yml b/workflows/proteomics/clinicalmp/clinicalmp-database-generation/iwc-clinicalmp-database-generation-tests.yml index 5c6a7efb2..08cfa6f03 100644 --- a/workflows/proteomics/clinicalmp/clinicalmp-database-generation/iwc-clinicalmp-database-generation-tests.yml +++ b/workflows/proteomics/clinicalmp/clinicalmp-database-generation/iwc-clinicalmp-database-generation-tests.yml @@ -32,20 +32,18 @@ Human UniProt Microbial Proteins cRAP for MetaNovo: asserts: has_text: - text: ">sp|" - not_empty: true + text: ">sp" Metanovo Compact database: asserts: has_text: - text: ">tr|" - not_empty: true + text: ">tr" CSV database: asserts: has_text: - text: "index" + text: " index" Human UniProt Microbial Proteins (from MetaNovo) cRAP: asserts: - has_text: - text: ">sp|" - not_empty: true + has_text: + text: ">sp" + From 3bf3bf94ed8ba060eac3cf2128db2b2bb0077f71 Mon Sep 17 00:00:00 2001 From: Subina Mehta Date: Wed, 20 Nov 2024 15:13:09 -0500 Subject: [PATCH 41/54] Update iwc-clinicalmp-database-generation-tests.yml --- .../iwc-clinicalmp-database-generation-tests.yml | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/workflows/proteomics/clinicalmp/clinicalmp-database-generation/iwc-clinicalmp-database-generation-tests.yml b/workflows/proteomics/clinicalmp/clinicalmp-database-generation/iwc-clinicalmp-database-generation-tests.yml index 08cfa6f03..4c95d13fa 100644 --- a/workflows/proteomics/clinicalmp/clinicalmp-database-generation/iwc-clinicalmp-database-generation-tests.yml +++ b/workflows/proteomics/clinicalmp/clinicalmp-database-generation/iwc-clinicalmp-database-generation-tests.yml @@ -32,18 +32,18 @@ Human UniProt Microbial Proteins cRAP for MetaNovo: asserts: has_text: - text: ">sp" + text: ">" Metanovo Compact database: asserts: has_text: - text: ">tr" + text: ">" CSV database: asserts: has_text: - text: " index" + text: " index Accession File ID Length Organism PeptideCount Peptides Record SAF PTRC_Skubitz_Plex2_F10_9Aug19_Rage_Rep-19-06-08 SAF PTRC_Skubitz_Plex2_F11_9Aug19_Rage_Rep-19-06-08 SAF PTRC_Skubitz_Plex2_F13_9Aug19_Rage_Rep-19-06-08 SAF PTRC_Skubitz_Plex2_F15_9Aug19_Rage_Rep-19-06-08 Sample PTRC_Skubitz_Plex2_F10_9Aug19_Rage_Rep-19-06-08 (msms) Sample PTRC_Skubitz_Plex2_F11_9Aug19_Rage_Rep-19-06-08 (msms) Sample PTRC_Skubitz_Plex2_F13_9Aug19_Rage_Rep-19-06-08 (msms) Sample PTRC_Skubitz_Plex2_F15_9Aug19_Rage_Rep-19-06-08 (msms) ScanCount Scans NSAF PTRC_Skubitz_Plex2_F10_9Aug19_Rage_Rep-19-06-08 NSAF PTRC_Skubitz_Plex2_F11_9Aug19_Rage_Rep-19-06-08 NSAF PTRC_Skubitz_Plex2_F13_9Aug19_Rage_Rep-19-06-08 NSAF PTRC_Skubitz_Plex2_F15_9Aug19_Rage_Rep-19-06-08 Summed_NSAF Protein_Prob Organism_Prob MSMS_Percent Combined_Prob" Human UniProt Microbial Proteins (from MetaNovo) cRAP: asserts: has_text: - text: ">sp" + text: ">" From 85dafeb16e84e0bed8806ee568422afff51ea4ba Mon Sep 17 00:00:00 2001 From: Subina Mehta Date: Wed, 20 Nov 2024 15:47:52 -0500 Subject: [PATCH 42/54] Update iwc-clinicalmp-database-generation-tests.yml --- .../iwc-clinicalmp-database-generation-tests.yml | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/workflows/proteomics/clinicalmp/clinicalmp-database-generation/iwc-clinicalmp-database-generation-tests.yml b/workflows/proteomics/clinicalmp/clinicalmp-database-generation/iwc-clinicalmp-database-generation-tests.yml index 4c95d13fa..f4eba6d42 100644 --- a/workflows/proteomics/clinicalmp/clinicalmp-database-generation/iwc-clinicalmp-database-generation-tests.yml +++ b/workflows/proteomics/clinicalmp/clinicalmp-database-generation/iwc-clinicalmp-database-generation-tests.yml @@ -40,7 +40,7 @@ CSV database: asserts: has_text: - text: " index Accession File ID Length Organism PeptideCount Peptides Record SAF PTRC_Skubitz_Plex2_F10_9Aug19_Rage_Rep-19-06-08 SAF PTRC_Skubitz_Plex2_F11_9Aug19_Rage_Rep-19-06-08 SAF PTRC_Skubitz_Plex2_F13_9Aug19_Rage_Rep-19-06-08 SAF PTRC_Skubitz_Plex2_F15_9Aug19_Rage_Rep-19-06-08 Sample PTRC_Skubitz_Plex2_F10_9Aug19_Rage_Rep-19-06-08 (msms) Sample PTRC_Skubitz_Plex2_F11_9Aug19_Rage_Rep-19-06-08 (msms) Sample PTRC_Skubitz_Plex2_F13_9Aug19_Rage_Rep-19-06-08 (msms) Sample PTRC_Skubitz_Plex2_F15_9Aug19_Rage_Rep-19-06-08 (msms) ScanCount Scans NSAF PTRC_Skubitz_Plex2_F10_9Aug19_Rage_Rep-19-06-08 NSAF PTRC_Skubitz_Plex2_F11_9Aug19_Rage_Rep-19-06-08 NSAF PTRC_Skubitz_Plex2_F13_9Aug19_Rage_Rep-19-06-08 NSAF PTRC_Skubitz_Plex2_F15_9Aug19_Rage_Rep-19-06-08 Summed_NSAF Protein_Prob Organism_Prob MSMS_Percent Combined_Prob" + text: " index Accession" Human UniProt Microbial Proteins (from MetaNovo) cRAP: asserts: has_text: From 7792b1fef9525dffdd11692810269ba316f746ab Mon Sep 17 00:00:00 2001 From: Subina Mehta Date: Wed, 20 Nov 2024 18:41:16 -0500 Subject: [PATCH 43/54] Update iwc-clinicalmp-database-generation-tests.yml --- .../iwc-clinicalmp-database-generation-tests.yml | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/workflows/proteomics/clinicalmp/clinicalmp-database-generation/iwc-clinicalmp-database-generation-tests.yml b/workflows/proteomics/clinicalmp/clinicalmp-database-generation/iwc-clinicalmp-database-generation-tests.yml index f4eba6d42..8b1058b12 100644 --- a/workflows/proteomics/clinicalmp/clinicalmp-database-generation/iwc-clinicalmp-database-generation-tests.yml +++ b/workflows/proteomics/clinicalmp/clinicalmp-database-generation/iwc-clinicalmp-database-generation-tests.yml @@ -32,11 +32,11 @@ Human UniProt Microbial Proteins cRAP for MetaNovo: asserts: has_text: - text: ">" + text: ">sp" Metanovo Compact database: asserts: has_text: - text: ">" + text: ">sp" CSV database: asserts: has_text: @@ -44,6 +44,6 @@ Human UniProt Microbial Proteins (from MetaNovo) cRAP: asserts: has_text: - text: ">" + text: ">sp" From 780b66ace20d4d84c95ca47234867fa85d703931 Mon Sep 17 00:00:00 2001 From: Subina Mehta Date: Wed, 20 Nov 2024 18:48:30 -0500 Subject: [PATCH 44/54] Update iwc-clinicalmp-database-generation-tests.yml edited asserts --- ...wc-clinicalmp-database-generation-tests.yml | 18 +++++++++--------- 1 file changed, 9 insertions(+), 9 deletions(-) diff --git a/workflows/proteomics/clinicalmp/clinicalmp-database-generation/iwc-clinicalmp-database-generation-tests.yml b/workflows/proteomics/clinicalmp/clinicalmp-database-generation/iwc-clinicalmp-database-generation-tests.yml index 8b1058b12..4f65a05de 100644 --- a/workflows/proteomics/clinicalmp/clinicalmp-database-generation/iwc-clinicalmp-database-generation-tests.yml +++ b/workflows/proteomics/clinicalmp/clinicalmp-database-generation/iwc-clinicalmp-database-generation-tests.yml @@ -31,19 +31,19 @@ outputs: Human UniProt Microbial Proteins cRAP for MetaNovo: asserts: - has_text: - text: ">sp" + - that: has_text + text: ">sp" Metanovo Compact database: asserts: - has_text: - text: ">sp" + - that: has_text + text: ">sp" CSV database: asserts: - has_text: - text: " index Accession" + - that: has_text + text: " index Accession" Human UniProt Microbial Proteins (from MetaNovo) cRAP: - asserts: - has_text: - text: ">sp" + asserts: + - that: has_text + text: ">sp" From 82590ba31897d0ef334b81dabadbdd4ca55bb007 Mon Sep 17 00:00:00 2001 From: Subina Mehta Date: Wed, 20 Nov 2024 18:57:56 -0500 Subject: [PATCH 45/54] Update iwc-clinicalmp-database-generation-tests.yml --- .../iwc-clinicalmp-database-generation-tests.yml | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/workflows/proteomics/clinicalmp/clinicalmp-database-generation/iwc-clinicalmp-database-generation-tests.yml b/workflows/proteomics/clinicalmp/clinicalmp-database-generation/iwc-clinicalmp-database-generation-tests.yml index 4f65a05de..438a29d07 100644 --- a/workflows/proteomics/clinicalmp/clinicalmp-database-generation/iwc-clinicalmp-database-generation-tests.yml +++ b/workflows/proteomics/clinicalmp/clinicalmp-database-generation/iwc-clinicalmp-database-generation-tests.yml @@ -32,11 +32,11 @@ Human UniProt Microbial Proteins cRAP for MetaNovo: asserts: - that: has_text - text: ">sp" + text: ">sp|" Metanovo Compact database: asserts: - that: has_text - text: ">sp" + text: ">sp|" CSV database: asserts: - that: has_text @@ -44,6 +44,6 @@ Human UniProt Microbial Proteins (from MetaNovo) cRAP: asserts: - that: has_text - text: ">sp" + text: ">sp|" From b103b9064bfee6191ff6a1708ec601450d775dbf Mon Sep 17 00:00:00 2001 From: Subina Mehta Date: Wed, 20 Nov 2024 19:03:03 -0500 Subject: [PATCH 46/54] Update iwc-clinicalmp-database-generation-tests.yml --- ...c-clinicalmp-database-generation-tests.yml | 52 +++++++++---------- 1 file changed, 25 insertions(+), 27 deletions(-) diff --git a/workflows/proteomics/clinicalmp/clinicalmp-database-generation/iwc-clinicalmp-database-generation-tests.yml b/workflows/proteomics/clinicalmp/clinicalmp-database-generation/iwc-clinicalmp-database-generation-tests.yml index 438a29d07..3ab57853a 100644 --- a/workflows/proteomics/clinicalmp/clinicalmp-database-generation/iwc-clinicalmp-database-generation-tests.yml +++ b/workflows/proteomics/clinicalmp/clinicalmp-database-generation/iwc-clinicalmp-database-generation-tests.yml @@ -8,7 +8,7 @@ class: File location: https://zenodo.org/records/14181725/files/Species_UniProt_FASTA.fasta?download=1 filetype: fasta - Contaminants(cRAP)-Protein-Database: + Contaminants-cRAP-Protein-Database: class: File location: https://zenodo.org/records/14181725/files/Contaminants(cRAP)-Protein-Database.fasta?download=1 filetype: fasta @@ -16,34 +16,32 @@ class: Collection collection_type: list elements: - - class: File - identifier: PTRC_Skubitz_Plex2_F15_9Aug19_Rage_Rep-19-06-08.mgf - location: https://zenodo.org/records/14181725/files/PTRC_Skubitz_Plex2_F15_9Aug19_Rage_Rep-19-06-08.mgf?download=1 - - class: File - identifier: PTRC_Skubitz_Plex2_F13_9Aug19_Rage_Rep-19-06-08.mgf - location: https://zenodo.org/records/14181725/files/PTRC_Skubitz_Plex2_F13_9Aug19_Rage_Rep-19-06-08.mgf?download=1 - - class: File - identifier: PTRC_Skubitz_Plex2_F11_9Aug19_Rage_Rep-19-06-08.mgf - location: https://zenodo.org/records/14181725/files/PTRC_Skubitz_Plex2_F11_9Aug19_Rage_Rep-19-06-08.mgf?download=1 - - class: File - identifier: PTRC_Skubitz_Plex2_F10_9Aug19_Rage_Rep-19-06-08.mgf - location: https://zenodo.org/records/14181725/files/PTRC_Skubitz_Plex2_F10_9Aug19_Rage_Rep-19-06-08.mgf?download=1 + - class: File + identifier: PTRC_Skubitz_Plex2_F15_9Aug19_Rage_Rep-19-06-08.mgf + location: https://zenodo.org/records/14181725/files/PTRC_Skubitz_Plex2_F15_9Aug19_Rage_Rep-19-06-08.mgf?download=1 + - class: File + identifier: PTRC_Skubitz_Plex2_F13_9Aug19_Rage_Rep-19-06-08.mgf + location: https://zenodo.org/records/14181725/files/PTRC_Skubitz_Plex2_F13_9Aug19_Rage_Rep-19-06-08.mgf?download=1 + - class: File + identifier: PTRC_Skubitz_Plex2_F11_9Aug19_Rage_Rep-19-06-08.mgf + location: https://zenodo.org/records/14181725/files/PTRC_Skubitz_Plex2_F11_9Aug19_Rage_Rep-19-06-08.mgf?download=1 + - class: File + identifier: PTRC_Skubitz_Plex2_F10_9Aug19_Rage_Rep-19-06-08.mgf + location: https://zenodo.org/records/14181725/files/PTRC_Skubitz_Plex2_F10_9Aug19_Rage_Rep-19-06-08.mgf?download=1 outputs: - Human UniProt Microbial Proteins cRAP for MetaNovo: + Human-UniProt-Microbial-Proteins-cRAP-for-MetaNovo: asserts: - - that: has_text - text: ">sp|" - Metanovo Compact database: + - that: has_text + text: ">sp|" + Metanovo-Compact-database: asserts: - - that: has_text - text: ">sp|" - CSV database: + - that: has_text + text: ">sp|" + CSV-database: asserts: - - that: has_text - text: " index Accession" - Human UniProt Microbial Proteins (from MetaNovo) cRAP: + - that: has_text + text: "index Accession" + Human-UniProt-Microbial-Proteins-from-MetaNovo-cRAP: asserts: - - that: has_text - text: ">sp|" - - + - that: has_text + text: ">sp|" From 5f9aaacc4a9018e3ab027bcded549aa60c332a42 Mon Sep 17 00:00:00 2001 From: Subina Mehta Date: Wed, 20 Nov 2024 19:08:43 -0500 Subject: [PATCH 47/54] Update iwc-clinicalmp-database-generation-tests.yml --- .../iwc-clinicalmp-database-generation-tests.yml | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/workflows/proteomics/clinicalmp/clinicalmp-database-generation/iwc-clinicalmp-database-generation-tests.yml b/workflows/proteomics/clinicalmp/clinicalmp-database-generation/iwc-clinicalmp-database-generation-tests.yml index 3ab57853a..ec1cf46c2 100644 --- a/workflows/proteomics/clinicalmp/clinicalmp-database-generation/iwc-clinicalmp-database-generation-tests.yml +++ b/workflows/proteomics/clinicalmp/clinicalmp-database-generation/iwc-clinicalmp-database-generation-tests.yml @@ -29,19 +29,19 @@ identifier: PTRC_Skubitz_Plex2_F10_9Aug19_Rage_Rep-19-06-08.mgf location: https://zenodo.org/records/14181725/files/PTRC_Skubitz_Plex2_F10_9Aug19_Rage_Rep-19-06-08.mgf?download=1 outputs: - Human-UniProt-Microbial-Proteins-cRAP-for-MetaNovo: + Human UniProt Microbial Proteins cRAP for MetaNovo: asserts: - that: has_text text: ">sp|" - Metanovo-Compact-database: + Metanovo Compact database: asserts: - that: has_text text: ">sp|" - CSV-database: + CSV database: asserts: - that: has_text text: "index Accession" - Human-UniProt-Microbial-Proteins-from-MetaNovo-cRAP: + Human UniProt Microbial Proteins from MetaNovo cRAP: asserts: - that: has_text text: ">sp|" From 15f2bf07abc9b6bc22328c14d753e77e7944e8cd Mon Sep 17 00:00:00 2001 From: Subina Mehta Date: Wed, 20 Nov 2024 19:14:28 -0500 Subject: [PATCH 48/54] Update iwc-clinicalmp-database-generation.ga --- .../iwc-clinicalmp-database-generation.ga | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/workflows/proteomics/clinicalmp/clinicalmp-database-generation/iwc-clinicalmp-database-generation.ga b/workflows/proteomics/clinicalmp/clinicalmp-database-generation/iwc-clinicalmp-database-generation.ga index bad500a84..4db7d5f18 100644 --- a/workflows/proteomics/clinicalmp/clinicalmp-database-generation/iwc-clinicalmp-database-generation.ga +++ b/workflows/proteomics/clinicalmp/clinicalmp-database-generation/iwc-clinicalmp-database-generation.ga @@ -313,7 +313,7 @@ }, "RenameDatasetActionoutput": { "action_arguments": { - "newname": "Human UniProt Microbial Proteins (from MetaNovo) cRAP" + "newname": "Human UniProt Microbial Proteins from MetaNovo cRAP" }, "action_type": "RenameDatasetAction", "output_name": "output" @@ -333,7 +333,7 @@ "when": null, "workflow_outputs": [ { - "label": "Human UniProt Microbial Proteins (from MetaNovo) cRAP", + "label": "Human UniProt Microbial Proteins from MetaNovo cRAP", "output_name": "output", "uuid": "e3f490ef-1307-4892-bab1-6085cf8194ae" } From dd34a9b3e99eddfcfea8b7a6f7d1ce9e5e0cd6c1 Mon Sep 17 00:00:00 2001 From: Subina Mehta Date: Wed, 20 Nov 2024 19:16:04 -0500 Subject: [PATCH 49/54] Update iwc-clinicalmp-database-generation.ga --- .../iwc-clinicalmp-database-generation.ga | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/workflows/proteomics/clinicalmp/clinicalmp-database-generation/iwc-clinicalmp-database-generation.ga b/workflows/proteomics/clinicalmp/clinicalmp-database-generation/iwc-clinicalmp-database-generation.ga index 4db7d5f18..778b2c6ec 100644 --- a/workflows/proteomics/clinicalmp/clinicalmp-database-generation/iwc-clinicalmp-database-generation.ga +++ b/workflows/proteomics/clinicalmp/clinicalmp-database-generation/iwc-clinicalmp-database-generation.ga @@ -106,11 +106,11 @@ "input_connections": {}, "inputs": [ { - "description": "Contaminants(cRAP)-Protein-Database", - "name": "Contaminants(cRAP)-Protein-Database" + "description": "Contaminants-cRAP-Protein-Database", + "name": "Contaminants-cRAP-Protein-Database" } ], - "label": "Contaminants(cRAP)-Protein-Database", + "label": "Contaminants-cRAP-Protein-Database", "name": "Input dataset", "outputs": [], "position": { From cd5b76ecf7433538499f0188d898f04789851299 Mon Sep 17 00:00:00 2001 From: Subina Mehta Date: Thu, 21 Nov 2024 09:51:13 -0500 Subject: [PATCH 50/54] Update iwc-clinicalmp-database-generation.ga --- .../iwc-clinicalmp-database-generation.ga | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/workflows/proteomics/clinicalmp/clinicalmp-database-generation/iwc-clinicalmp-database-generation.ga b/workflows/proteomics/clinicalmp/clinicalmp-database-generation/iwc-clinicalmp-database-generation.ga index 778b2c6ec..0ca4414cf 100644 --- a/workflows/proteomics/clinicalmp/clinicalmp-database-generation/iwc-clinicalmp-database-generation.ga +++ b/workflows/proteomics/clinicalmp/clinicalmp-database-generation/iwc-clinicalmp-database-generation.ga @@ -99,7 +99,7 @@ "workflow_outputs": [] }, "3": { - "annotation": "Contaminants(cRAP)-Protein-Database", + "annotation": "Contaminants-cRAP-Protein-Database", "content_id": null, "errors": null, "id": 3, From 3f4a97f544aaa966b3c21bc446072307d48baa1b Mon Sep 17 00:00:00 2001 From: mvdbeek Date: Thu, 21 Nov 2024 16:32:55 +0100 Subject: [PATCH 51/54] Update input and output labels --- .../clinicalmp-database-generation/README.md | 2 +- ...c-clinicalmp-database-generation-tests.yml | 10 +++--- .../iwc-clinicalmp-database-generation.ga | 36 +++++++++---------- 3 files changed, 24 insertions(+), 24 deletions(-) diff --git a/workflows/proteomics/clinicalmp/clinicalmp-database-generation/README.md b/workflows/proteomics/clinicalmp/clinicalmp-database-generation/README.md index de38cabf8..c607be07b 100644 --- a/workflows/proteomics/clinicalmp/clinicalmp-database-generation/README.md +++ b/workflows/proteomics/clinicalmp/clinicalmp-database-generation/README.md @@ -10,7 +10,7 @@ A GTN has been developed for this workflow. [https://training.galaxyproject.org/ ### Search Databases (FASTA) from [Zenodo](https://zenodo.org/records/14181725) - `HUMAN SwissProt Protein_Database.fasta` -- `Species UniProt FASTA.fasta` +- `Species UniProt Protein Database FASTA.fasta` - `Contaminants (cRAP) Protein Database.fasta` ### MSMS files download from [Zenodo](https://zenodo.org/records/14181725) - `PTRC_Skubitz_Plex2_F10_9Aug19_Rage_Rep-19-06-08.mgf` diff --git a/workflows/proteomics/clinicalmp/clinicalmp-database-generation/iwc-clinicalmp-database-generation-tests.yml b/workflows/proteomics/clinicalmp/clinicalmp-database-generation/iwc-clinicalmp-database-generation-tests.yml index ec1cf46c2..2b485cddd 100644 --- a/workflows/proteomics/clinicalmp/clinicalmp-database-generation/iwc-clinicalmp-database-generation-tests.yml +++ b/workflows/proteomics/clinicalmp/clinicalmp-database-generation/iwc-clinicalmp-database-generation-tests.yml @@ -1,18 +1,18 @@ - doc: Test outline for iwc-clinicalmp-database-generation job: - HUMAN-SwissProt-Protein-Database: + Human SwissProt Protein Database: class: File location: https://zenodo.org/records/14181725/files/HUMAN-SwissProt-Protein-Database.fasta?download=1 filetype: fasta - Species_UniProt_FASTA: + Species UniProt Protein Database: class: File location: https://zenodo.org/records/14181725/files/Species_UniProt_FASTA.fasta?download=1 filetype: fasta - Contaminants-cRAP-Protein-Database: + Contaminants cRAP Protein Database: class: File location: https://zenodo.org/records/14181725/files/Contaminants(cRAP)-Protein-Database.fasta?download=1 filetype: fasta - Input-MGF-files: + Tandem Mass Spectrometry (MS/MS) datasets: class: Collection collection_type: list elements: @@ -37,7 +37,7 @@ asserts: - that: has_text text: ">sp|" - CSV database: + Metanovo Compact CSV database: asserts: - that: has_text text: "index Accession" diff --git a/workflows/proteomics/clinicalmp/clinicalmp-database-generation/iwc-clinicalmp-database-generation.ga b/workflows/proteomics/clinicalmp/clinicalmp-database-generation/iwc-clinicalmp-database-generation.ga index 0ca4414cf..bbe7e3a9f 100644 --- a/workflows/proteomics/clinicalmp/clinicalmp-database-generation/iwc-clinicalmp-database-generation.ga +++ b/workflows/proteomics/clinicalmp/clinicalmp-database-generation/iwc-clinicalmp-database-generation.ga @@ -18,18 +18,18 @@ }, "steps": { "0": { - "annotation": "HUMAN-SwissProt-Protein-Database", + "annotation": "Human SwissProt Protein Database", "content_id": null, "errors": null, "id": 0, "input_connections": {}, "inputs": [ { - "description": "HUMAN-SwissProt-Protein-Database", - "name": "HUMAN-SwissProt-Protein-Database" + "description": "Human SwissProt Protein Database", + "name": "Human SwissProt Protein Database" } ], - "label": "HUMAN-SwissProt-Protein-Database", + "label": "Human SwissProt Protein Database", "name": "Input dataset", "outputs": [], "position": { @@ -45,18 +45,18 @@ "workflow_outputs": [] }, "1": { - "annotation": "Input-MGF-files", + "annotation": "Tandem Mass Spectrometry (MS/MS) datasets", "content_id": null, "errors": null, "id": 1, "input_connections": {}, "inputs": [ { - "description": "Input-MGF-files", - "name": "Input-MGF-files" + "description": "Tandem Mass Spectrometry (MS/MS) datasets", + "name": "Tandem Mass Spectrometry (MS/MS) datasets" } ], - "label": "Input-MGF-files", + "label": "Tandem Mass Spectrometry (MS/MS) datasets", "name": "Input dataset collection", "outputs": [], "position": { @@ -72,18 +72,18 @@ "workflow_outputs": [] }, "2": { - "annotation": "Species_UniProt_FASTA", + "annotation": "Species UniProt Protein Database", "content_id": null, "errors": null, "id": 2, "input_connections": {}, "inputs": [ { - "description": "Species_UniProt_FASTA", - "name": "Species_UniProt_FASTA" + "description": "Species UniProt Protein Database", + "name": "Species UniProt Protein Database" } ], - "label": "Species_UniProt_FASTA", + "label": "Species UniProt Protein Database", "name": "Input dataset", "outputs": [], "position": { @@ -99,18 +99,18 @@ "workflow_outputs": [] }, "3": { - "annotation": "Contaminants-cRAP-Protein-Database", + "annotation": "Contaminants cRAP Protein Database", "content_id": null, "errors": null, "id": 3, "input_connections": {}, "inputs": [ { - "description": "Contaminants-cRAP-Protein-Database", - "name": "Contaminants-cRAP-Protein-Database" + "description": "Contaminants cRAP Protein Database", + "name": "Contaminants cRAP Protein Database" } ], - "label": "Contaminants-cRAP-Protein-Database", + "label": "Contaminants cRAP Protein Database", "name": "Input dataset", "outputs": [], "position": { @@ -233,7 +233,7 @@ "post_job_actions": { "RenameDatasetActionoutput_csv": { "action_arguments": { - "newname": "CSV database" + "newname": "Metanovo Compact CSV database" }, "action_type": "RenameDatasetAction", "output_name": "output_csv" @@ -265,7 +265,7 @@ "uuid": "02940034-f0fe-4151-acd0-c6982e77b717" }, { - "label": "CSV database", + "label": "Metanovo Compact CSV database", "output_name": "output_csv", "uuid": "d7208cb6-a907-4a8b-b8b7-cf44c103d14a" } From 8d08ad6544a1f70b56d764de1ff49d8fc7a735b4 Mon Sep 17 00:00:00 2001 From: Subina Mehta Date: Thu, 21 Nov 2024 13:56:37 -0500 Subject: [PATCH 52/54] Update iwc-clinicalmp-database-generation-tests.yml --- .../iwc-clinicalmp-database-generation-tests.yml | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/workflows/proteomics/clinicalmp/clinicalmp-database-generation/iwc-clinicalmp-database-generation-tests.yml b/workflows/proteomics/clinicalmp/clinicalmp-database-generation/iwc-clinicalmp-database-generation-tests.yml index 2b485cddd..937b61191 100644 --- a/workflows/proteomics/clinicalmp/clinicalmp-database-generation/iwc-clinicalmp-database-generation-tests.yml +++ b/workflows/proteomics/clinicalmp/clinicalmp-database-generation/iwc-clinicalmp-database-generation-tests.yml @@ -40,7 +40,7 @@ Metanovo Compact CSV database: asserts: - that: has_text - text: "index Accession" + text: "index" Human UniProt Microbial Proteins from MetaNovo cRAP: asserts: - that: has_text From c2ee714903ccaf55c7bb43ec99cdd961cd38cff5 Mon Sep 17 00:00:00 2001 From: Marius van den Beek Date: Fri, 22 Nov 2024 10:48:19 +0100 Subject: [PATCH 53/54] Add missing newline --- .../clinicalmp/clinicalmp-database-generation/README.md | 1 + 1 file changed, 1 insertion(+) diff --git a/workflows/proteomics/clinicalmp/clinicalmp-database-generation/README.md b/workflows/proteomics/clinicalmp/clinicalmp-database-generation/README.md index c607be07b..470a9d89f 100644 --- a/workflows/proteomics/clinicalmp/clinicalmp-database-generation/README.md +++ b/workflows/proteomics/clinicalmp/clinicalmp-database-generation/README.md @@ -12,6 +12,7 @@ A GTN has been developed for this workflow. [https://training.galaxyproject.org/ - `HUMAN SwissProt Protein_Database.fasta` - `Species UniProt Protein Database FASTA.fasta` - `Contaminants (cRAP) Protein Database.fasta` + ### MSMS files download from [Zenodo](https://zenodo.org/records/14181725) - `PTRC_Skubitz_Plex2_F10_9Aug19_Rage_Rep-19-06-08.mgf` - `PTRC_Skubitz_Plex2_F11_9Aug19_Rage_Rep-19-06-08.mgf` From 5382c4d907ddef7d07fd5873107c0349343ffa9b Mon Sep 17 00:00:00 2001 From: Marius van den Beek Date: Fri, 22 Nov 2024 11:23:13 +0100 Subject: [PATCH 54/54] Remove email notification --- .../iwc-clinicalmp-database-generation.ga | 14 -------------- 1 file changed, 14 deletions(-) diff --git a/workflows/proteomics/clinicalmp/clinicalmp-database-generation/iwc-clinicalmp-database-generation.ga b/workflows/proteomics/clinicalmp/clinicalmp-database-generation/iwc-clinicalmp-database-generation.ga index bbe7e3a9f..038e046ef 100644 --- a/workflows/proteomics/clinicalmp/clinicalmp-database-generation/iwc-clinicalmp-database-generation.ga +++ b/workflows/proteomics/clinicalmp/clinicalmp-database-generation/iwc-clinicalmp-database-generation.ga @@ -158,13 +158,6 @@ "top": 137.68359736327898 }, "post_job_actions": { - "EmailActionoutput": { - "action_arguments": { - "host": "usegalaxy.eu" - }, - "action_type": "EmailAction", - "output_name": "output" - }, "RenameDatasetActionoutput": { "action_arguments": { "newname": "Human UniProt Microbial Proteins cRAP for MetaNovo" @@ -304,13 +297,6 @@ "top": 322.62533209947645 }, "post_job_actions": { - "EmailActionoutput": { - "action_arguments": { - "host": "usegalaxy.eu" - }, - "action_type": "EmailAction", - "output_name": "output" - }, "RenameDatasetActionoutput": { "action_arguments": { "newname": "Human UniProt Microbial Proteins from MetaNovo cRAP"