diff --git a/workflows/proteomics/clinicalmp/clinicalmp-discovery/.dockstore.yml b/workflows/proteomics/clinicalmp/clinicalmp-discovery/.dockstore.yml new file mode 100644 index 000000000..1fe74f851 --- /dev/null +++ b/workflows/proteomics/clinicalmp/clinicalmp-discovery/.dockstore.yml @@ -0,0 +1,11 @@ +version: 1.2 +workflows: +- name: main + subclass: Galaxy + publish: true + primaryDescriptorPath: /iwc-clinicalmp-discovery-workflow.ga + testParameterFiles: + - /iwc-clinicalmp-discovery-workflow-tests.yml + authors: + - name: Subina Mehta + orcid: 0000-0001-9818-0537 diff --git a/workflows/proteomics/clinicalmp/clinicalmp-discovery/CHANGELOG.md b/workflows/proteomics/clinicalmp/clinicalmp-discovery/CHANGELOG.md new file mode 100644 index 000000000..8ec28ce1e --- /dev/null +++ b/workflows/proteomics/clinicalmp/clinicalmp-discovery/CHANGELOG.md @@ -0,0 +1,4 @@ +# Changelog + +## [0.1] 2024-11-18 +First release. diff --git a/workflows/proteomics/clinicalmp/clinicalmp-discovery/README.md b/workflows/proteomics/clinicalmp/clinicalmp-discovery/README.md new file mode 100644 index 000000000..000ac21e4 --- /dev/null +++ b/workflows/proteomics/clinicalmp/clinicalmp-discovery/README.md @@ -0,0 +1,25 @@ +# Clinical Metaproteomics 2: Discovery + +Discovery in clinical metaproteomics is greatly enhanced by using a well-curated database, particularly one generated with the **MetaNovo tool**. This tool creates a manageable and streamlined database by identifying proteins relevant to the dataset, reducing the complexity of downstream analysis. For optimal results, the MetaNovo-generated database can be merged with reviewed proteins from **Human SwissProt** and known contaminants from the **cRAP (common Repository of Adventitious Proteins)** database, resulting in a compact yet comprehensive database of approximately 21,200 protein sequences. This refined database serves as the foundation for peptide identification, where mass spectrometry (MS) data is matched against the database to identify relevant peptides efficiently and accurately. By reducing redundancy and focusing on clinically relevant sequences, this approach improves the discovery of biomarkers and key protein insights, allowing researchers to extract meaningful biological information with reduced noise and false positives. This streamlined process is particularly valuable in clinical studies, where precision and relevance are critical for advancing diagnostics and therapeutic research. + +In this current workflow, we perform Discovery using the SearchGUI and MaxQuant tools. A GTN has been developed for this workflow. +[https://training.galaxyproject.org/training-material/topics/proteomics/tutorials/clinical-mp-2-discovery/tutorial.html](https://training.galaxyproject.org/training-material/topics/proteomics/tutorials/clinical-mp-2-discovery/tutorial.html) + +## Inputs dataset + +- `MSMS datasets` in RAW dataset collection +- `Databases for discovery` in Fasta (protein sequences for database searching) +- `Experimental-Design Discovery MaxQuant` in Tabular Format + +## Inputs values + +For MaxQuant and SearchGUI/PeptideShaker +- Peptide Length +- Variable modifications +- Labeled element + + +## Processing + +- extract microbial proteins and peptides using text formating tools +- Grouping duplicates using the Group tool diff --git a/workflows/proteomics/clinicalmp/clinicalmp-discovery/iwc-clinicalmp-discovery-workflow-tests.yml b/workflows/proteomics/clinicalmp/clinicalmp-discovery/iwc-clinicalmp-discovery-workflow-tests.yml new file mode 100644 index 000000000..f9c55dacf --- /dev/null +++ b/workflows/proteomics/clinicalmp/clinicalmp-discovery/iwc-clinicalmp-discovery-workflow-tests.yml @@ -0,0 +1,24 @@ +- doc: Test outline for iwc-clinicalmp-discovery-workflow + job: + Human UniProt Microbial Proteins from MetaNovo and cRAP: + class: File + location: https://zenodo.org/records/10720030/files/Human_UniProt_Microbial_Proteins_(from_MetaNovo)_and_cRAP.fasta + filetype: fasta + Experimental Design Discovery MaxQuant: + class: File + path: test-data/Experimental Design Discovery MaxQuant.tabular + filetype: tabular + Tandem Mass Spectrometry MSMS files: + class: Collection + collection_type: list + elements: + - class: File + identifier: PTRC_Skubitz_Plex2_F10_9Aug19_Rage_Rep-19-06-08.raw + location: https://zenodo.org/records/14182981/files/PTRC_Skubitz_Plex2_F10_9Aug19_Rage_Rep-19-06-08.raw + outputs: + SGPS MQ Peptides: + asserts: + - has_n_columns: + n: 1 + - has_text: + text: "AAFPNVTAMNITTNNGK" diff --git a/workflows/proteomics/clinicalmp/clinicalmp-discovery/iwc-clinicalmp-discovery-workflow.ga b/workflows/proteomics/clinicalmp/clinicalmp-discovery/iwc-clinicalmp-discovery-workflow.ga new file mode 100644 index 000000000..c7ada0e47 --- /dev/null +++ b/workflows/proteomics/clinicalmp/clinicalmp-discovery/iwc-clinicalmp-discovery-workflow.ga @@ -0,0 +1,1345 @@ +{ + "a_galaxy_workflow": "true", + "annotation": "Workflow for clinical metaproteomics database searching", + "comments": [], + "creator": [ + { + "class": "Organization", + "identifier": "0000-0001-9818-0537", + "name": "Subina Mehta" + } + ], + "format-version": "0.1", + "license": "CC-BY-4.0", + "name": "Clinical Metaproteomics Discovery Workflow", + "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" + }, + "steps": { + "0": { + "annotation": "", + "content_id": null, + "errors": null, + "id": 0, + "input_connections": {}, + "inputs": [ + { + "description": "Adding decoys to MetaNovo Human SwissProt cRAP to improve FDR", + "name": "Human UniProt Microbial Proteins from MetaNovo and cRAP" + } + ], + "label": "Human UniProt Microbial Proteins from MetaNovo and cRAP", + "name": "Input dataset", + "outputs": [], + "position": { + "left": 249.51593017578125, + "top": 272.60801696777344 + }, + "tool_id": null, + "tool_state": "{\"optional\": false, \"format\": [\"fasta\"], \"tag\": null}", + "tool_version": null, + "type": "data_input", + "uuid": "c0c1c1cf-e899-4b8e-b1b1-6a4f24d87ad1", + "when": null, + "workflow_outputs": [] + }, + "1": { + "annotation": "identification parameters for SGPS", + "content_id": "toolshed.g2.bx.psu.edu/repos/galaxyp/peptideshaker/ident_params/4.0.41+galaxy1", + "errors": null, + "id": 1, + "input_connections": {}, + "inputs": [], + "label": "IdentificationParameters:PAR file", + "name": "Identification Parameters", + "outputs": [ + { + "name": "Identification_Parameters_File", + "type": "json" + } + ], + "position": { + "left": 814.9930419921875, + "top": 0 + }, + "post_job_actions": { + "RenameDatasetActionIdentification_Parameters_File": { + "action_arguments": { + "newname": "Identification Parameters (PAR)" + }, + "action_type": "RenameDatasetAction", + "output_name": "Identification_Parameters_File" + } + }, + "tool_id": "toolshed.g2.bx.psu.edu/repos/galaxyp/peptideshaker/ident_params/4.0.41+galaxy1", + "tool_shed_repository": { + "changeset_revision": "3ec27b4cee7c", + "name": "peptideshaker", + "owner": "galaxyp", + "tool_shed": "toolshed.g2.bx.psu.edu" + }, + "tool_state": "{\"advanced_options\": {\"spectrum_annotation_options\": {\"annotation_level\": \"0.75\", \"annotation_mz_tolerance\": \"0.5\", \"annotation_high_resolution\": true}, \"sequence_matching_options\": {\"sequence_matching_type\": \"2\", \"sequence_matching_x\": \"0.25\", \"sequence_matching_enzymatic_tags\": false, \"sequence_matching_max_ptms_per_tag\": \"3\", \"sequence_matching_min_amino_acid_score\": \"30\", \"sequence_matching_min_tag_length\": \"3\"}, \"import_filters_options\": {\"min_peptide_length\": \"8\", \"max_peptide_length\": \"30\", \"max_precursor_error\": \"10.0\", \"max_precursor_error_type\": \"1\", \"missed_cleavages_min\": null, \"missed_cleavages_max\": null, \"exclude_unknown_ptms\": true}, \"ptm_localization_options\": {\"ptm_score\": {\"ptm_score_selector\": \"1\", \"__current_case__\": 0, \"score_neutral_losses\": false, \"ptm_threshold\": \"95.0\"}, \"ptm_sequence_matching_type\": \"1\", \"ptm_alignment\": true}, \"gene_annotation_options\": {\"use_gene_mapping\": false, \"update_gene_mapping\": false}, \"protein_inference_options\": {\"simplify_protein_groups_conditional\": {\"simplify_protein_groups_selector\": \"yes\", \"__current_case__\": 1, \"simplify_protein_groups_evidence\": true, \"simplify_protein_groups_confidence\": true, \"simplify_protein_groups_confidence_threshold\": \"0.05\", \"simplify_protein_groups_enzymaticity\": true, \"simplify_protein_groups_variant\": true}, \"simplify_protein_pi_modifications\": true}, \"validation_levels_options\": {\"protein_fdr\": \"1.0\", \"peptide_fdr\": \"1.0\", \"psm_fdr\": \"1.0\"}, \"fraction_analysis_options\": {\"protein_fraction_mw_confidence\": \"95.0\"}, \"database_processing_options\": {\"decoy_conditional\": {\"create_decoy_selector\": \"yes\", \"__current_case__\": 1, \"decoy_tag\": \"_REVERSED\", \"decoy_type\": \"1\"}, \"decoy_file_tag\": \"_concatenated_target_decoy\"}}, \"searchengines_options\": {\"xtandem\": {\"xtandem_advanced\": \"no\", \"__current_case__\": 0}, \"myrimatch\": {\"myrimatch_advanced\": \"no\", \"__current_case__\": 0}, \"msgf\": {\"msgf_advanced\": \"no\", \"__current_case__\": 0}, \"ms_amanda\": {\"ms_amanda_advanced\": \"no\", \"__current_case__\": 0}, \"omssa\": {\"omssa_advanced\": \"no\", \"__current_case__\": 0}, \"comet\": {\"comet_advanced\": \"no\", \"__current_case__\": 0}, \"tide\": {\"tide_advanced\": \"no\", \"__current_case__\": 0}, \"directtag\": {\"directtag_advanced\": \"no\", \"__current_case__\": 0}, \"metamorpheus\": {\"metamorpheus_advanced\": \"no\", \"__current_case__\": 0}, \"novor\": {\"novor_advanced\": \"no\", \"__current_case__\": 0}, \"pepnovo\": {\"pepnovo_advanced\": \"no\", \"__current_case__\": 0}, \"pnovo\": {\"pnovo_advanced\": \"no\", \"__current_case__\": 0}}, \"spectrum_matching_options\": {\"fixed_modifications\": [\"Carbamidomethylation of C\", \"TMT 11-plex of K+4\", \"TMT 11-plex of peptide N-term\"], \"variable_modifications\": [\"Oxidation of M\"], \"digestion\": {\"cleavage\": \"0\", \"__current_case__\": 0, \"digests\": [{\"__index__\": 0, \"enzyme\": \"Trypsin\", \"missed_cleavages\": \"2\", \"specificity\": \"0\"}]}, \"precursor_ion_tol_units\": \"1\", \"precursor_ion_tol\": \"10.0\", \"fragment_tol_units\": \"0\", \"fragment_tol\": \"0.6\", \"min_charge\": \"2\", \"max_charge\": \"6\", \"forward_ion\": \"b\", \"reverse_ion\": \"y\", \"min_isotope\": \"0\", \"max_isotope\": \"1\"}, \"__page__\": null, \"__rerun_remap_job_id__\": null}", + "tool_version": "4.0.41+galaxy1", + "type": "tool", + "uuid": "abaf5892-7976-4526-9cf6-a0c96b9222ea", + "when": null, + "workflow_outputs": [] + }, + "2": { + "annotation": "Input Raw files", + "content_id": null, + "errors": null, + "id": 2, + "input_connections": {}, + "inputs": [ + { + "description": "Input Raw files", + "name": "Tandem Mass Spectrometry MSMS files" + } + ], + "label": "Tandem Mass Spectrometry MSMS files", + "name": "Input dataset collection", + "outputs": [], + "position": { + "left": 0, + "top": 833.7075958251953 + }, + "tool_id": null, + "tool_state": "{\"optional\": false, \"format\": [\"thermo.raw\"], \"tag\": null, \"collection_type\": \"list\"}", + "tool_version": null, + "type": "data_collection_input", + "uuid": "c0f85358-244a-4254-ac94-e920a6cdbe39", + "when": null, + "workflow_outputs": [] + }, + "3": { + "annotation": "", + "content_id": "toolshed.g2.bx.psu.edu/repos/galaxyp/dbbuilder/dbbuilder/0.3.4", + "errors": null, + "id": 3, + "input_connections": {}, + "inputs": [], + "label": "Human SwissProt", + "name": "Protein Database Downloader", + "outputs": [ + { + "name": "output_database", + "type": "fasta" + } + ], + "position": { + "left": 634.640625488066, + "top": 607.9116168878928 + }, + "post_job_actions": { + "RenameDatasetActionoutput_database": { + "action_arguments": { + "newname": "Human SwissProt" + }, + "action_type": "RenameDatasetAction", + "output_name": "output_database" + } + }, + "tool_id": "toolshed.g2.bx.psu.edu/repos/galaxyp/dbbuilder/dbbuilder/0.3.4", + "tool_shed_repository": { + "changeset_revision": "983bf725dfc2", + "name": "dbbuilder", + "owner": "galaxyp", + "tool_shed": "toolshed.g2.bx.psu.edu" + }, + "tool_state": "{\"source\": {\"from\": \"uniprot\", \"__current_case__\": 0, \"taxon\": \"9606\", \"taxon_id\": null, \"reviewed\": \"reviewed:true\", \"set\": \"keyword:KW-1185\", \"include_isoform\": false}, \"__page__\": null, \"__rerun_remap_job_id__\": null}", + "tool_version": "0.3.4", + "type": "tool", + "uuid": "5b0de886-9f18-4dd2-8e81-4b29467e727a", + "when": null, + "workflow_outputs": [ + { + "label": "Human SwissProt", + "output_name": "output_database", + "uuid": "335f3fe6-c7fb-4fd6-b04e-9f5afb3fe5a6" + } + ] + }, + "4": { + "annotation": "", + "content_id": "toolshed.g2.bx.psu.edu/repos/galaxyp/dbbuilder/dbbuilder/0.3.4", + "errors": null, + "id": 4, + "input_connections": {}, + "inputs": [], + "label": "Contaminants", + "name": "Protein Database Downloader", + "outputs": [ + { + "name": "output_database", + "type": "fasta" + } + ], + "position": { + "left": 631.7343839163847, + "top": 789.1078163439809 + }, + "post_job_actions": {}, + "tool_id": "toolshed.g2.bx.psu.edu/repos/galaxyp/dbbuilder/dbbuilder/0.3.4", + "tool_shed_repository": { + "changeset_revision": "983bf725dfc2", + "name": "dbbuilder", + "owner": "galaxyp", + "tool_shed": "toolshed.g2.bx.psu.edu" + }, + "tool_state": "{\"source\": {\"from\": \"cRAP\", \"__current_case__\": 1}, \"__page__\": null, \"__rerun_remap_job_id__\": null}", + "tool_version": "0.3.4", + "type": "tool", + "uuid": "6f0be889-015d-4be0-a997-dd63e18344eb", + "when": null, + "workflow_outputs": [] + }, + "5": { + "annotation": "File for experimental design containing Name, Fraction, Experiment, and PTM, where the name refers to the dataset filename, with each dataset listed on a separate line.", + "content_id": null, + "errors": null, + "id": 5, + "input_connections": {}, + "inputs": [ + { + "description": "Experimental Design manually created for MaxQuant", + "name": "Experimental Design Discovery MaxQuant" + } + ], + "label": "Experimental Design Discovery MaxQuant", + "name": "Input dataset", + "outputs": [], + "position": { + "left": 872.66015625, + "top": 1088.484375 + }, + "tool_id": null, + "tool_state": "{\"optional\": false, \"tag\": null}", + "tool_version": null, + "type": "data_input", + "uuid": "9652a70a-de8c-4966-b7cf-121f1b9f0b54", + "when": null, + "workflow_outputs": [] + }, + "6": { + "annotation": "", + "content_id": "toolshed.g2.bx.psu.edu/repos/galaxyp/peptideshaker/fasta_cli/4.0.41+galaxy1", + "errors": null, + "id": 6, + "input_connections": { + "input_database": { + "id": 0, + "output_name": "output" + } + }, + "inputs": [], + "label": "FastaCLI_ MetaNovo Human SwissProt cRAP with decoys", + "name": "FastaCLI", + "outputs": [ + { + "name": "input_database_concatenated_target_decoy", + "type": "fasta" + } + ], + "position": { + "left": 873.1780375305545, + "top": 286.53022010497557 + }, + "post_job_actions": { + "RenameDatasetActioninput_database_concatenated_target_decoy": { + "action_arguments": { + "newname": "FastaCLI_ MetaNovo Human SwissProt cRAP with decoys" + }, + "action_type": "RenameDatasetAction", + "output_name": "input_database_concatenated_target_decoy" + } + }, + "tool_id": "toolshed.g2.bx.psu.edu/repos/galaxyp/peptideshaker/fasta_cli/4.0.41+galaxy1", + "tool_shed_repository": { + "changeset_revision": "3ec27b4cee7c", + "name": "peptideshaker", + "owner": "galaxyp", + "tool_shed": "toolshed.g2.bx.psu.edu" + }, + "tool_state": "{\"database_processing_options\": {\"decoy_tag\": \"_REVERSED\", \"decoy_type\": \"2\", \"decoy_file_tag\": \"_concatenated_target_decoy\"}, \"input_database\": {\"__class__\": \"ConnectedValue\"}, \"__page__\": null, \"__rerun_remap_job_id__\": null}", + "tool_version": "4.0.41+galaxy1", + "type": "tool", + "uuid": "7a0729f9-8827-4202-a20e-48e103efc502", + "when": null, + "workflow_outputs": [] + }, + "7": { + "annotation": "", + "content_id": "toolshed.g2.bx.psu.edu/repos/galaxyp/msconvert/msconvert/3.0.20287.2", + "errors": null, + "id": 7, + "input_connections": { + "input": { + "id": 2, + "output_name": "output" + } + }, + "inputs": [], + "label": null, + "name": "msconvert", + "outputs": [ + { + "name": "output", + "type": "mzml" + } + ], + "position": { + "left": 213.25472010132836, + "top": 454.38506518621944 + }, + "post_job_actions": {}, + "tool_id": "toolshed.g2.bx.psu.edu/repos/galaxyp/msconvert/msconvert/3.0.20287.2", + "tool_shed_repository": { + "changeset_revision": "6153e8ada1ee", + "name": "msconvert", + "owner": "galaxyp", + "tool_shed": "toolshed.g2.bx.psu.edu" + }, + "tool_state": "{\"data_processing\": {\"peak_picking\": {\"pick_peaks\": true, \"__current_case__\": 1, \"pick_peaks_ms_levels\": \"1-\", \"pick_peaks_algorithm\": \"vendor\"}, \"precursor_refinement\": {\"use_mzrefinement\": false, \"__current_case__\": 0}, \"charge_state_calculation\": {\"charge_state_calculation_method\": \"false\", \"__current_case__\": 0}, \"thresholds\": [], \"filter_mz_windows\": {\"do_mzwindow_filter\": false, \"__current_case__\": 0}, \"etd_filtering\": {\"do_etd_filtering\": false, \"__current_case__\": 0}, \"ms2denoise\": {\"denoise\": false, \"__current_case__\": 1}, \"ms2deisotope\": false, \"demultiplex\": {\"demultiplex_on\": false, \"__current_case__\": 1}}, \"filtering\": {\"activation\": \"false\", \"indices\": [], \"scan_numbers\": [], \"strip_it\": false, \"filter_ms_levels\": {\"do_ms_level_filter\": false, \"__current_case__\": 0}, \"polarity\": \"false\", \"analyzer\": \"false\"}, \"general_options\": {\"combineIonMobilitySpectra\": false, \"scan_summing\": {\"do_scan_summing\": false, \"__current_case__\": 0}, \"simAsSpectra\": false, \"srmAsSpectra\": false, \"acceptZeroLengthSpectra\": false, \"ignoreUnknownInstrumentError\": false, \"multi_run_output\": {\"do_multi_run_output\": false, \"__current_case__\": 0, \"runIndexSet\": \"0\"}}, \"input\": {\"__class__\": \"ConnectedValue\"}, \"license_agreement\": true, \"output_type\": \"mgf\", \"settings\": {\"mz_encoding\": \"64\", \"intensity_encoding\": \"32\", \"binary_compression\": \"zlib\", \"gzip_compression\": false}, \"__page__\": null, \"__rerun_remap_job_id__\": null}", + "tool_version": "3.0.20287.2", + "type": "tool", + "uuid": "83018642-2850-4df8-b328-ee1e8bdc8fcb", + "when": null, + "workflow_outputs": [] + }, + "8": { + "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": 8, + "input_connections": { + "batchmode|input_fastas_0|input_fasta": { + "id": 3, + "output_name": "output_database" + }, + "batchmode|input_fastas_1|input_fasta": { + "id": 4, + "output_name": "output_database" + } + }, + "inputs": [], + "label": "Human SwissProt+cRAP", + "name": "FASTA Merge Files and Filter Unique Sequences", + "outputs": [ + { + "name": "output", + "type": "fasta" + } + ], + "position": { + "left": 902.4973253039605, + "top": 577.0886700391638 + }, + "post_job_actions": { + "RenameDatasetActionoutput": { + "action_arguments": { + "newname": "Human SwissProt+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": "{\"accession_parser\": \"^>([^ ]+).*$\", \"batchmode\": {\"processmode\": \"individual\", \"__current_case__\": 0, \"input_fastas\": [{\"__index__\": 0, \"input_fasta\": {\"__class__\": \"ConnectedValue\"}}, {\"__index__\": 1, \"input_fasta\": {\"__class__\": \"ConnectedValue\"}}]}, \"uniqueness_criterion\": \"sequence\", \"__page__\": null, \"__rerun_remap_job_id__\": null}", + "tool_version": "1.2.0", + "type": "tool", + "uuid": "a35c2efa-70f2-41e8-bc46-cb2a245fdf57", + "when": null, + "workflow_outputs": [ + { + "label": "Human SwissProt+cRAP", + "output_name": "output", + "uuid": "2f14902f-b005-4c08-b6d1-6d7ee0b4b199" + } + ] + }, + "9": { + "annotation": "", + "content_id": "toolshed.g2.bx.psu.edu/repos/galaxyp/maxquant/maxquant/2.0.3.0+galaxy0", + "errors": null, + "id": 9, + "input_connections": { + "input_opts|fasta_files": { + "id": 0, + "output_name": "output" + }, + "paramGroups_0|files": { + "id": 2, + "output_name": "output" + }, + "search_opts|template": { + "id": 5, + "output_name": "output" + } + }, + "inputs": [ + { + "description": "runtime parameter for tool MaxQuant", + "name": "input_opts" + }, + { + "description": "runtime parameter for tool MaxQuant", + "name": "search_opts" + } + ], + "label": null, + "name": "MaxQuant", + "outputs": [ + { + "name": "proteinGroups", + "type": "tabular" + }, + { + "name": "mqpar", + "type": "xml" + }, + { + "name": "peptides", + "type": "tabular" + }, + { + "name": "msms", + "type": "tabular" + }, + { + "name": "msmsScans", + "type": "tabular" + }, + { + "name": "summary", + "type": "tabular" + }, + { + "name": "log", + "type": "txt" + }, + { + "name": "config", + "type": "txt" + } + ], + "position": { + "left": 1389.0771241398825, + "top": 778.3294605307798 + }, + "post_job_actions": { + "TagDatasetActionpeptides": { + "action_arguments": { + "tags": "#MQ_Peptides" + }, + "action_type": "TagDatasetAction", + "output_name": "peptides" + }, + "TagDatasetActionproteinGroups": { + "action_arguments": { + "tags": "#MQ_ProteinGroups" + }, + "action_type": "TagDatasetAction", + "output_name": "proteinGroups" + } + }, + "tool_id": "toolshed.g2.bx.psu.edu/repos/galaxyp/maxquant/maxquant/2.0.3.0+galaxy0", + "tool_shed_repository": { + "changeset_revision": "9c52362ae7bb", + "name": "maxquant", + "owner": "galaxyp", + "tool_shed": "toolshed.g2.bx.psu.edu" + }, + "tool_state": "{\"input_opts\": {\"ftype\": \".thermo.raw\", \"fasta_files\": {\"__class__\": \"ConnectedValue\"}, \"identifier_parse_rule\": \">([^\\\\s]*)\", \"description_parse_rule\": \">(.*)\"}, \"output_opts\": {\"dry_run\": false, \"output\": [\"proteinGroups\", \"mqpar\", \"peptides\", \"msms\", \"msmsScans\", \"summary\", \"log\", \"config\"]}, \"paramGroups\": [{\"__index__\": 0, \"files\": {\"__class__\": \"ConnectedValue\"}, \"maxMissedCleavages\": \"2\", \"fixedModifications\": [\"Carbamidomethyl (C)\"], \"variableModifications\": [\"Oxidation (M)\"], \"enzymes\": [\"Trypsin/P\"], \"digestion_mode\": \"0\", \"quant_method\": {\"select_quant_method\": \"reporter_ion_ms2\", \"__current_case__\": 3, \"iso_labels\": {\"labeling\": \"tmt11plex\", \"__current_case__\": 4}, \"filter_by_pif\": {\"filter_pif\": \"True\", \"__current_case__\": 0, \"reporter_pif\": \"0.75\"}}}], \"protein_quant\": {\"peptides_for_quantification\": \"1\", \"only_unmod_prot\": {\"unmod_prot\": \"True\", \"__current_case__\": 0, \"mods_used_prot_quant\": [\"Oxidation (M)\"], \"discard_unmod_cpart_peptides\": true}, \"lfq_opts\": {\"separateLfq\": false, \"lfqStabilizeLargeRatios\": true, \"lfqRequireMsms\": true, \"do_ibaq\": {\"ibaq\": \"False\", \"__current_case__\": 1}, \"advancedSiteIntensities\": true}}, \"qc\": {\"do_it\": \"false\", \"__current_case__\": 1}, \"search_opts\": {\"template\": {\"__class__\": \"ConnectedValue\"}, \"min_peptide_len\": \"8\", \"max_peptide_mass\": \"4600\", \"min_unique_pep\": \"0\", \"calc_peak_properties\": false, \"mbr\": {\"match_between_runs\": \"True\", \"__current_case__\": 1, \"matching_time_window\": \"0.7\", \"matching_ion_mobility_window\": \"0.05\", \"alignment_time_window\": \"20\", \"alignment_ion_mobility_window\": \"1\", \"match_unidentified_features\": false}, \"incl_contaminants\": false, \"decoy_mode\": \"revert\", \"psm_fdr\": \"0.01\", \"protein_fdr\": \"0.01\", \"min_pep_length\": \"8\", \"max_pep_length\": \"50\"}, \"__page__\": null, \"__rerun_remap_job_id__\": null}", + "tool_version": "2.0.3.0+galaxy0", + "type": "tool", + "uuid": "46c61a69-355c-44ac-9945-0e4d43f0b2ec", + "when": null, + "workflow_outputs": [] + }, + "10": { + "annotation": "", + "content_id": "toolshed.g2.bx.psu.edu/repos/galaxyp/peptideshaker/search_gui/4.0.41+galaxy1", + "errors": null, + "id": 10, + "input_connections": { + "input_fasta_file": { + "id": 6, + "output_name": "input_database_concatenated_target_decoy" + }, + "input_parameters_file": { + "id": 1, + "output_name": "Identification_Parameters_File" + }, + "peak_lists_files": { + "id": 7, + "output_name": "output" + } + }, + "inputs": [], + "label": null, + "name": "Search GUI", + "outputs": [ + { + "name": "searchgui_results", + "type": "searchgui_archive" + } + ], + "position": { + "left": 1136.7332639974097, + "top": 127.37631486278212 + }, + "post_job_actions": { + "TagDatasetActionsearchgui_results": { + "action_arguments": { + "tags": "#SGPS" + }, + "action_type": "TagDatasetAction", + "output_name": "searchgui_results" + } + }, + "tool_id": "toolshed.g2.bx.psu.edu/repos/galaxyp/peptideshaker/search_gui/4.0.41+galaxy1", + "tool_shed_repository": { + "changeset_revision": "3ec27b4cee7c", + "name": "peptideshaker", + "owner": "galaxyp", + "tool_shed": "toolshed.g2.bx.psu.edu" + }, + "tool_state": "{\"input_fasta_file\": {\"__class__\": \"ConnectedValue\"}, \"input_parameters_file\": {\"__class__\": \"ConnectedValue\"}, \"peak_lists_files\": {\"__class__\": \"ConnectedValue\"}, \"search_engines_options\": {\"engines\": [\"X!Tandem\", \"MSGF\"]}, \"searchgui_advanced\": {\"searchgui_advanced_selector\": \"basic\", \"__current_case__\": 0}, \"__page__\": null, \"__rerun_remap_job_id__\": null}", + "tool_version": "4.0.41+galaxy1", + "type": "tool", + "uuid": "58cf1b78-91c0-4726-8697-df2504d14611", + "when": null, + "workflow_outputs": [] + }, + "11": { + "annotation": "", + "content_id": "toolshed.g2.bx.psu.edu/repos/devteam/fasta_to_tabular/fasta2tab/1.1.0", + "errors": null, + "id": 11, + "input_connections": { + "input": { + "id": 8, + "output_name": "output" + } + }, + "inputs": [], + "label": "FASTA to Tabular", + "name": "FASTA-to-Tabular", + "outputs": [ + { + "name": "output", + "type": "tabular" + } + ], + "position": { + "left": 1164.015625, + "top": 614.1015625 + }, + "post_job_actions": {}, + "tool_id": "toolshed.g2.bx.psu.edu/repos/devteam/fasta_to_tabular/fasta2tab/1.1.0", + "tool_shed_repository": { + "changeset_revision": "7e801ab2b70e", + "name": "fasta_to_tabular", + "owner": "devteam", + "tool_shed": "toolshed.g2.bx.psu.edu" + }, + "tool_state": "{\"descr_columns\": \"1\", \"input\": {\"__class__\": \"ConnectedValue\"}, \"keep_first\": \"0\", \"__page__\": null, \"__rerun_remap_job_id__\": null}", + "tool_version": "1.1.0", + "type": "tool", + "uuid": "9a63693a-1b5b-4160-99da-4636a09f3fed", + "when": null, + "workflow_outputs": [] + }, + "12": { + "annotation": "", + "content_id": "Grep1", + "errors": null, + "id": 12, + "input_connections": { + "input": { + "id": 9, + "output_name": "peptides" + } + }, + "inputs": [], + "label": "Select microbial peptides MQ", + "name": "Select", + "outputs": [ + { + "name": "out_file1", + "type": "input" + } + ], + "position": { + "left": 1644.109353292642, + "top": 809.7786537420372 + }, + "post_job_actions": { + "RenameDatasetActionout_file1": { + "action_arguments": { + "newname": "Select microbial peptides MQ" + }, + "action_type": "RenameDatasetAction", + "output_name": "out_file1" + } + }, + "tool_id": "Grep1", + "tool_state": "{\"input\": {\"__class__\": \"ConnectedValue\"}, \"invert\": \"-v\", \"keep_header\": true, \"pattern\": \"(_HUMAN)|(_REVERSED)|(CON)|(con)\", \"__page__\": null, \"__rerun_remap_job_id__\": null}", + "tool_version": "1.0.4", + "type": "tool", + "uuid": "cb9b81ce-c86e-4b07-ba18-3d1deddeded5", + "when": null, + "workflow_outputs": [ + { + "label": "Select microbial peptides MQ", + "output_name": "out_file1", + "uuid": "aff2fb3d-58d3-4d1d-bfa2-8b68f14ec0a0" + } + ] + }, + "13": { + "annotation": "", + "content_id": "toolshed.g2.bx.psu.edu/repos/galaxyp/peptideshaker/peptide_shaker/2.0.33+galaxy1", + "errors": null, + "id": 13, + "input_connections": { + "searchgui_input": { + "id": 10, + "output_name": "searchgui_results" + } + }, + "inputs": [ + { + "description": "runtime parameter for tool Peptide Shaker", + "name": "optional_main_parameters" + }, + { + "description": "runtime parameter for tool Peptide Shaker", + "name": "optional_main_parameters" + }, + { + "description": "runtime parameter for tool Peptide Shaker", + "name": "optional_main_parameters" + } + ], + "label": "Peptide Shaker", + "name": "Peptide Shaker", + "outputs": [ + { + "name": "mzidentML", + "type": "mzid" + }, + { + "name": "output_certificate", + "type": "txt" + }, + { + "name": "output_psm", + "type": "tabular" + }, + { + "name": "output_peptides", + "type": "tabular" + }, + { + "name": "output_proteins", + "type": "tabular" + } + ], + "position": { + "left": 1376.546875, + "top": 136.69921875 + }, + "post_job_actions": { + "TagDatasetActionoutput_peptides": { + "action_arguments": { + "tags": "#PS_Peptides" + }, + "action_type": "TagDatasetAction", + "output_name": "output_peptides" + }, + "TagDatasetActionoutput_psm": { + "action_arguments": { + "tags": "#PS_PSM" + }, + "action_type": "TagDatasetAction", + "output_name": "output_psm" + } + }, + "tool_id": "toolshed.g2.bx.psu.edu/repos/galaxyp/peptideshaker/peptide_shaker/2.0.33+galaxy1", + "tool_shed_repository": { + "changeset_revision": "a6ff76e057fd", + "name": "peptideshaker", + "owner": "galaxyp", + "tool_shed": "toolshed.g2.bx.psu.edu" + }, + "tool_state": "{\"exporting_options\": {\"zip_conditional\": {\"zip_output_boolean\": false, \"__current_case__\": 0, \"export_psdb\": false}, \"mzidentml_conditional\": {\"mzidentml_creation\": true, \"__current_case__\": 0, \"include_sequences\": false, \"contact_options\": {\"contact_options_selector\": \"no\", \"__current_case__\": 0}}, \"followup_conditional\": {\"followup_conditional_selector\": \"no\", \"__current_case__\": 0}, \"output_reports\": [\"3\", \"6\", \"9\", \"0\"]}, \"optional_main_parameters\": {\"input_optional_identification_parameters\": {\"__class__\": \"RuntimeValue\"}, \"input_fasta_file\": {\"__class__\": \"RuntimeValue\"}, \"input_optional_spectrum_files\": {\"__class__\": \"RuntimeValue\"}}, \"searchgui_input\": {\"__class__\": \"ConnectedValue\"}, \"__page__\": null, \"__rerun_remap_job_id__\": null}", + "tool_version": "2.0.33+galaxy1", + "type": "tool", + "uuid": "d8293305-e003-4c82-9085-a6a6e27563f3", + "when": null, + "workflow_outputs": [] + }, + "14": { + "annotation": "", + "content_id": "toolshed.g2.bx.psu.edu/repos/iuc/filter_tabular/filter_tabular/3.3.0", + "errors": null, + "id": 14, + "input_connections": { + "input": { + "id": 11, + "output_name": "output" + } + }, + "inputs": [], + "label": "Filtering Accesions", + "name": "Filter Tabular", + "outputs": [ + { + "name": "output", + "type": "tabular" + } + ], + "position": { + "left": 1909.4926854592713, + "top": 567.042966564121 + }, + "post_job_actions": { + "RenameDatasetActionoutput": { + "action_arguments": { + "newname": "Filtering Accessions" + }, + "action_type": "RenameDatasetAction", + "output_name": "output" + } + }, + "tool_id": "toolshed.g2.bx.psu.edu/repos/iuc/filter_tabular/filter_tabular/3.3.0", + "tool_shed_repository": { + "changeset_revision": "557ec8d7087d", + "name": "filter_tabular", + "owner": "iuc", + "tool_shed": "toolshed.g2.bx.psu.edu" + }, + "tool_state": "{\"comment_char\": true, \"input\": {\"__class__\": \"ConnectedValue\"}, \"linefilters\": [{\"__index__\": 0, \"filter\": {\"filter_type\": \"select_columns\", \"__current_case__\": 9, \"columns\": \"1\"}}, {\"__index__\": 1, \"filter\": {\"filter_type\": \"replace\", \"__current_case__\": 11, \"column\": \"1\", \"regex_pattern\": \"^[^|]+[|]([^| ]+).*$\", \"regex_replace\": \"\\\\1\", \"add\": null}}], \"__page__\": null, \"__rerun_remap_job_id__\": null}", + "tool_version": "3.3.0", + "type": "tool", + "uuid": "e42dd88c-5e82-400e-810f-cb34746ce438", + "when": null, + "workflow_outputs": [ + { + "label": "Filtering Accessions", + "output_name": "output", + "uuid": "94f1a6b8-0f60-4ffc-ab90-31ba68d37cdc" + } + ] + }, + "15": { + "annotation": "", + "content_id": "Cut1", + "errors": null, + "id": 15, + "input_connections": { + "input": { + "id": 12, + "output_name": "out_file1" + } + }, + "inputs": [], + "label": "MQ Peptide Sequences", + "name": "Cut", + "outputs": [ + { + "name": "out_file1", + "type": "tabular" + } + ], + "position": { + "left": 1902.578125, + "top": 824.57421875 + }, + "post_job_actions": { + "RenameDatasetActionout_file1": { + "action_arguments": { + "newname": "MQ Peptide Sequences" + }, + "action_type": "RenameDatasetAction", + "output_name": "out_file1" + } + }, + "tool_id": "Cut1", + "tool_state": "{\"columnList\": \"c1\", \"delimiter\": \"T\", \"input\": {\"__class__\": \"ConnectedValue\"}, \"__page__\": null, \"__rerun_remap_job_id__\": null}", + "tool_version": "1.0.2", + "type": "tool", + "uuid": "d182a597-2b4f-4f60-bd76-e6cea6f9f610", + "when": null, + "workflow_outputs": [ + { + "label": "MQ Peptide Sequences", + "output_name": "out_file1", + "uuid": "26146545-0adf-43cd-a407-3981a64e2b8a" + } + ] + }, + "16": { + "annotation": "", + "content_id": "Grep1", + "errors": null, + "id": 16, + "input_connections": { + "input": { + "id": 13, + "output_name": "output_peptides" + } + }, + "inputs": [], + "label": "Select microbial peptides SGPS", + "name": "Select", + "outputs": [ + { + "name": "out_file1", + "type": "input" + } + ], + "position": { + "left": 1624.6171875, + "top": 133.078125 + }, + "post_job_actions": { + "RenameDatasetActionout_file1": { + "action_arguments": { + "newname": "Select microbial peptides SGPS" + }, + "action_type": "RenameDatasetAction", + "output_name": "out_file1" + } + }, + "tool_id": "Grep1", + "tool_state": "{\"input\": {\"__class__\": \"ConnectedValue\"}, \"invert\": \"-v\", \"keep_header\": true, \"pattern\": \"(_HUMAN)|(_REVERSED)|(CON)|(con)\", \"__page__\": null, \"__rerun_remap_job_id__\": null}", + "tool_version": "1.0.4", + "type": "tool", + "uuid": "088c67e2-5680-45ac-8fc6-58107304378b", + "when": null, + "workflow_outputs": [ + { + "label": "Select microbial peptides SGPS", + "output_name": "out_file1", + "uuid": "98fa521e-5f10-41f8-bbb0-0c37e36c7db8" + } + ] + }, + "17": { + "annotation": "", + "content_id": "Grep1", + "errors": null, + "id": 17, + "input_connections": { + "input": { + "id": 13, + "output_name": "output_psm" + } + }, + "inputs": [], + "label": "Select microbial PSMs SGPS", + "name": "Select", + "outputs": [ + { + "name": "out_file1", + "type": "input" + } + ], + "position": { + "left": 1633.46875, + "top": 337.29296875 + }, + "post_job_actions": { + "RenameDatasetActionout_file1": { + "action_arguments": { + "newname": "Select microbial PSMs SGPS" + }, + "action_type": "RenameDatasetAction", + "output_name": "out_file1" + } + }, + "tool_id": "Grep1", + "tool_state": "{\"input\": {\"__class__\": \"ConnectedValue\"}, \"invert\": \"-v\", \"keep_header\": true, \"pattern\": \"(_HUMAN)|(_REVERSED)|(CON)|(con)\", \"__page__\": null, \"__rerun_remap_job_id__\": null}", + "tool_version": "1.0.4", + "type": "tool", + "uuid": "77835fcd-c645-48fa-bfe2-2519cebdf93c", + "when": null, + "workflow_outputs": [ + { + "label": "Select microbial PSMs SGPS", + "output_name": "out_file1", + "uuid": "2d8e7875-144c-4cb8-8278-37156df85c6e" + } + ] + }, + "18": { + "annotation": "", + "content_id": "Remove beginning1", + "errors": null, + "id": 18, + "input_connections": { + "input": { + "id": 15, + "output_name": "out_file1" + } + }, + "inputs": [], + "label": "Remove beginning from MQ Peptides", + "name": "Remove beginning", + "outputs": [ + { + "name": "out_file1", + "type": "input" + } + ], + "position": { + "left": 2433.9375, + "top": 727.6328125 + }, + "post_job_actions": { + "RenameDatasetActionout_file1": { + "action_arguments": { + "newname": "Header removed MQ Peptides" + }, + "action_type": "RenameDatasetAction", + "output_name": "out_file1" + } + }, + "tool_id": "Remove beginning1", + "tool_state": "{\"input\": {\"__class__\": \"ConnectedValue\"}, \"num_lines\": \"1\", \"__page__\": null, \"__rerun_remap_job_id__\": null}", + "tool_version": "1.0.0", + "type": "tool", + "uuid": "3eb21bbd-483c-4685-b3e8-1feec0354c47", + "when": null, + "workflow_outputs": [ + { + "label": "Header removed MQ Peptides", + "output_name": "out_file1", + "uuid": "a31d9c7f-5c8a-462a-a114-f2d9201d7f78" + } + ] + }, + "19": { + "annotation": "", + "content_id": "Filter1", + "errors": null, + "id": 19, + "input_connections": { + "input": { + "id": 16, + "output_name": "out_file1" + } + }, + "inputs": [], + "label": "Filter confident microbial Peptides", + "name": "Filter", + "outputs": [ + { + "name": "out_file1", + "type": "input" + } + ], + "position": { + "left": 1882.4063928456353, + "top": 138.52877496551775 + }, + "post_job_actions": { + "RenameDatasetActionout_file1": { + "action_arguments": { + "newname": "Filter confident microbial Peptides" + }, + "action_type": "RenameDatasetAction", + "output_name": "out_file1" + } + }, + "tool_id": "Filter1", + "tool_state": "{\"cond\": \"c17=='Confident'\", \"header_lines\": \"1\", \"input\": {\"__class__\": \"ConnectedValue\"}, \"__page__\": null, \"__rerun_remap_job_id__\": null}", + "tool_version": "1.1.1", + "type": "tool", + "uuid": "a2763f6c-4bb4-4637-b9a5-4319b8176e57", + "when": null, + "workflow_outputs": [ + { + "label": "Filter confident microbial Peptides", + "output_name": "out_file1", + "uuid": "bd070980-580f-4e1c-ba87-0e7bf097c4b9" + } + ] + }, + "20": { + "annotation": "", + "content_id": "Filter1", + "errors": null, + "id": 20, + "input_connections": { + "input": { + "id": 17, + "output_name": "out_file1" + } + }, + "inputs": [], + "label": "Filter confident microbial PSMs", + "name": "Filter", + "outputs": [ + { + "name": "out_file1", + "type": "input" + } + ], + "position": { + "left": 1892.8281925994486, + "top": 347.30488486357063 + }, + "post_job_actions": { + "RenameDatasetActionout_file1": { + "action_arguments": { + "newname": "Filter confident microbial PSMs" + }, + "action_type": "RenameDatasetAction", + "output_name": "out_file1" + } + }, + "tool_id": "Filter1", + "tool_state": "{\"cond\": \"c24=='Confident'\", \"header_lines\": \"1\", \"input\": {\"__class__\": \"ConnectedValue\"}, \"__page__\": null, \"__rerun_remap_job_id__\": null}", + "tool_version": "1.1.1", + "type": "tool", + "uuid": "2986ffd8-f797-4bdd-ba33-e3383bb3cbd1", + "when": null, + "workflow_outputs": [ + { + "label": "Filter confident microbial PSMs", + "output_name": "out_file1", + "uuid": "902234ac-5870-40fb-8b9b-2baf6e7a5786" + } + ] + }, + "21": { + "annotation": "", + "content_id": "Grouping1", + "errors": null, + "id": 21, + "input_connections": { + "input1": { + "id": 18, + "output_name": "out_file1" + } + }, + "inputs": [], + "label": "MQ Distinct Peptides", + "name": "Group", + "outputs": [ + { + "name": "out_file1", + "type": "tabular" + } + ], + "position": { + "left": 2692.1307728764114, + "top": 524.4947117996797 + }, + "post_job_actions": { + "RenameDatasetActionout_file1": { + "action_arguments": { + "newname": "MQ Distinct Peptides" + }, + "action_type": "RenameDatasetAction", + "output_name": "out_file1" + } + }, + "tool_id": "Grouping1", + "tool_state": "{\"groupcol\": \"1\", \"ignorecase\": false, \"ignorelines\": null, \"input1\": {\"__class__\": \"ConnectedValue\"}, \"operations\": [], \"__page__\": null, \"__rerun_remap_job_id__\": null}", + "tool_version": "2.1.4", + "type": "tool", + "uuid": "eadd5e67-4653-4895-bd99-d7ec8e8514f7", + "when": null, + "workflow_outputs": [ + { + "label": "MQ Distinct Peptides", + "output_name": "out_file1", + "uuid": "635bd0b8-42da-4605-a7b5-c914f8628917" + } + ] + }, + "22": { + "annotation": "", + "content_id": "toolshed.g2.bx.psu.edu/repos/iuc/query_tabular/query_tabular/3.3.0", + "errors": null, + "id": 22, + "input_connections": { + "tables_0|table": { + "id": 20, + "output_name": "out_file1" + }, + "tables_1|table": { + "id": 20, + "output_name": "out_file1" + }, + "tables_2|table": { + "id": 14, + "output_name": "output" + } + }, + "inputs": [ + { + "description": "runtime parameter for tool Query Tabular", + "name": "add_to_database" + } + ], + "label": "Extracting peptides SGPS from PSM", + "name": "Query Tabular", + "outputs": [ + { + "name": "output", + "type": "tabular" + } + ], + "position": { + "left": 2171.984360939529, + "top": 230.6947040667832 + }, + "post_job_actions": { + "RenameDatasetActionoutput": { + "action_arguments": { + "newname": "Extracting peptides SGPS from PSM" + }, + "action_type": "RenameDatasetAction", + "output_name": "output" + } + }, + "tool_id": "toolshed.g2.bx.psu.edu/repos/iuc/query_tabular/query_tabular/3.3.0", + "tool_shed_repository": { + "changeset_revision": "cf34c344508d", + "name": "query_tabular", + "owner": "iuc", + "tool_shed": "toolshed.g2.bx.psu.edu" + }, + "tool_state": "{\"add_to_database\": {\"withdb\": {\"__class__\": \"RuntimeValue\"}}, \"addqueries\": {\"queries\": []}, \"modify_database\": {\"sql_stmts\": []}, \"query_result\": {\"header\": \"yes\", \"__current_case__\": 0, \"header_prefix\": null}, \"save_db\": false, \"sqlquery\": \"SELECT id,Proteins,Sequence\\nFROM psms \\nWHERE psms.ln NOT IN\\n(SELECT distinct prots.ln\\nFROM prots JOIN Uniprot ON prots.prot = Uniprot.prot)\\nORDER BY psms.ln\", \"tables\": [{\"__index__\": 0, \"table\": {\"__class__\": \"ConnectedValue\"}, \"input_opts\": {\"linefilters\": [{\"__index__\": 0, \"filter\": {\"filter_type\": \"skip\", \"__current_case__\": 0, \"skip_lines\": \"1\"}}, {\"__index__\": 1, \"filter\": {\"filter_type\": \"prepend_line_num\", \"__current_case__\": 2}}]}, \"tbl_opts\": {\"table_name\": \"psms\", \"column_names_from_first_line\": false, \"col_names\": \"ln,id,Proteins,Sequence\", \"load_named_columns\": true, \"pkey_autoincr\": \"\", \"indexes\": [{\"__index__\": 0, \"unique\": false, \"index_columns\": \"ln\"}]}}, {\"__index__\": 1, \"table\": {\"__class__\": \"ConnectedValue\"}, \"input_opts\": {\"linefilters\": [{\"__index__\": 0, \"filter\": {\"filter_type\": \"skip\", \"__current_case__\": 0, \"skip_lines\": \"1\"}}, {\"__index__\": 1, \"filter\": {\"filter_type\": \"prepend_line_num\", \"__current_case__\": 2}}, {\"__index__\": 2, \"filter\": {\"filter_type\": \"normalize\", \"__current_case__\": 12, \"columns\": \"3\", \"separator\": \",\"}}]}, \"tbl_opts\": {\"table_name\": \"prots\", \"column_names_from_first_line\": false, \"col_names\": \"ln,id,prot\", \"load_named_columns\": true, \"pkey_autoincr\": \"\", \"indexes\": [{\"__index__\": 0, \"unique\": true, \"index_columns\": \"prot,ln\"}]}}, {\"__index__\": 2, \"table\": {\"__class__\": \"ConnectedValue\"}, \"input_opts\": {\"linefilters\": []}, \"tbl_opts\": {\"table_name\": \"Uniprot\", \"column_names_from_first_line\": false, \"col_names\": \"prot\", \"load_named_columns\": false, \"pkey_autoincr\": \"\", \"indexes\": [{\"__index__\": 0, \"unique\": false, \"index_columns\": \"prot\"}]}}], \"workdb\": \"workdb.sqlite\", \"__page__\": null, \"__rerun_remap_job_id__\": null}", + "tool_version": "3.3.0", + "type": "tool", + "uuid": "6727a48b-5576-4fd9-a8d6-b998c2f25e65", + "when": null, + "workflow_outputs": [ + { + "label": "Extracting peptides SGPS from PSM", + "output_name": "output", + "uuid": "5ea51c53-b7f1-447c-8b15-6ae3b89c2246" + } + ] + }, + "23": { + "annotation": "", + "content_id": "Cut1", + "errors": null, + "id": 23, + "input_connections": { + "input": { + "id": 22, + "output_name": "output" + } + }, + "inputs": [], + "label": "Cut Peptide column", + "name": "Cut", + "outputs": [ + { + "name": "out_file1", + "type": "tabular" + } + ], + "position": { + "left": 2429, + "top": 320.03125 + }, + "post_job_actions": { + "RenameDatasetActionout_file1": { + "action_arguments": { + "newname": "SGPS Peptides" + }, + "action_type": "RenameDatasetAction", + "output_name": "out_file1" + } + }, + "tool_id": "Cut1", + "tool_state": "{\"columnList\": \"c3\", \"delimiter\": \"T\", \"input\": {\"__class__\": \"ConnectedValue\"}, \"__page__\": null, \"__rerun_remap_job_id__\": null}", + "tool_version": "1.0.2", + "type": "tool", + "uuid": "079cee20-8cf1-417e-9ede-9e8d3e4157e1", + "when": null, + "workflow_outputs": [ + { + "label": "SGPS Peptides", + "output_name": "out_file1", + "uuid": "6d45c71b-64ef-4786-a89d-ee43c27ee969" + } + ] + }, + "24": { + "annotation": "", + "content_id": "Grouping1", + "errors": null, + "id": 24, + "input_connections": { + "input1": { + "id": 23, + "output_name": "out_file1" + } + }, + "inputs": [], + "label": "SGPS Distinct Peptides", + "name": "Group", + "outputs": [ + { + "name": "out_file1", + "type": "tabular" + } + ], + "position": { + "left": 2692.21992119554, + "top": 329.70161173161625 + }, + "post_job_actions": { + "RenameDatasetActionout_file1": { + "action_arguments": { + "newname": "SGPS Distinct Peptides" + }, + "action_type": "RenameDatasetAction", + "output_name": "out_file1" + } + }, + "tool_id": "Grouping1", + "tool_state": "{\"groupcol\": \"1\", \"ignorecase\": false, \"ignorelines\": null, \"input1\": {\"__class__\": \"ConnectedValue\"}, \"operations\": [], \"__page__\": null, \"__rerun_remap_job_id__\": null}", + "tool_version": "2.1.4", + "type": "tool", + "uuid": "17433c88-5d56-453f-9371-dc2943eecac2", + "when": null, + "workflow_outputs": [ + { + "label": "SGPS Distinct Peptides", + "output_name": "out_file1", + "uuid": "1eea0b81-8c35-4351-bbf3-2941561e4fcf" + } + ] + }, + "25": { + "annotation": "", + "content_id": "toolshed.g2.bx.psu.edu/repos/bgruening/text_processing/tp_cat/0.1.1", + "errors": null, + "id": 25, + "input_connections": { + "inputs": [ + { + "id": 21, + "output_name": "out_file1" + }, + { + "id": 24, + "output_name": "out_file1" + } + ] + }, + "inputs": [], + "label": "SGPS MQ Peptides", + "name": "Concatenate datasets", + "outputs": [ + { + "name": "out_file1", + "type": "input" + } + ], + "position": { + "left": 3005.427930624518, + "top": 411.55050647320707 + }, + "post_job_actions": { + "RenameDatasetActionout_file1": { + "action_arguments": { + "newname": "SGPS MQ Peptides" + }, + "action_type": "RenameDatasetAction", + "output_name": "out_file1" + } + }, + "tool_id": "toolshed.g2.bx.psu.edu/repos/bgruening/text_processing/tp_cat/0.1.1", + "tool_shed_repository": { + "changeset_revision": "d698c222f354", + "name": "text_processing", + "owner": "bgruening", + "tool_shed": "toolshed.g2.bx.psu.edu" + }, + "tool_state": "{\"inputs\": {\"__class__\": \"ConnectedValue\"}, \"queries\": [], \"__page__\": null, \"__rerun_remap_job_id__\": null}", + "tool_version": "0.1.1", + "type": "tool", + "uuid": "967a29c5-8ef9-45de-918a-f99e3f9a058f", + "when": null, + "workflow_outputs": [ + { + "label": "SGPS MQ Peptides", + "output_name": "out_file1", + "uuid": "df2db225-d108-4337-a684-dbca973da64e" + } + ] + }, + "26": { + "annotation": "", + "content_id": "Grouping1", + "errors": null, + "id": 26, + "input_connections": { + "input1": { + "id": 25, + "output_name": "out_file1" + } + }, + "inputs": [], + "label": "Distinct Peptides", + "name": "Group", + "outputs": [ + { + "name": "out_file1", + "type": "tabular" + } + ], + "position": { + "left": 3283.015625, + "top": 419.21875 + }, + "post_job_actions": { + "RenameDatasetActionout_file1": { + "action_arguments": { + "newname": "Distinct Peptides" + }, + "action_type": "RenameDatasetAction", + "output_name": "out_file1" + } + }, + "tool_id": "Grouping1", + "tool_state": "{\"groupcol\": \"1\", \"ignorecase\": false, \"ignorelines\": null, \"input1\": {\"__class__\": \"ConnectedValue\"}, \"operations\": [], \"__page__\": null, \"__rerun_remap_job_id__\": null}", + "tool_version": "2.1.4", + "type": "tool", + "uuid": "b5462dd0-3af9-41d4-a011-65d4244525a9", + "when": null, + "workflow_outputs": [ + { + "label": "Distinct Peptides", + "output_name": "out_file1", + "uuid": "c283b145-a685-49c4-8787-6e2e70f262b4" + } + ] + } + }, + "tags": [ + "name:clinicalMP" + ], + "uuid": "94138387-134e-4622-96a9-fdaee428ee1b", + "version": 2 +} diff --git a/workflows/proteomics/clinicalmp/clinicalmp-discovery/test-data/Experimental Design Discovery MaxQuant.tabular b/workflows/proteomics/clinicalmp/clinicalmp-discovery/test-data/Experimental Design Discovery MaxQuant.tabular new file mode 100644 index 000000000..92f9fa3a8 --- /dev/null +++ b/workflows/proteomics/clinicalmp/clinicalmp-discovery/test-data/Experimental Design Discovery MaxQuant.tabular @@ -0,0 +1,2 @@ +Name Fraction Experiment PTM +PTRC_Skubitz_Plex2_F10_9Aug19_Rage_Rep-19-06-08.raw 1 1 FALSE \ No newline at end of file