From 049395a656bec1e4e991516a02bef4d79071e016 Mon Sep 17 00:00:00 2001 From: Clea Siguret Date: Tue, 10 Dec 2024 11:39:23 +0100 Subject: [PATCH 1/6] Init metaproteomics-gtn --- .../metaproteomics-gtn/.dockstore.yml | 19 + .../metaproteomics-gtn/CHANGELOG.md | 4 + .../proteomics/metaproteomics-gtn/README.md | 6 + .../metaproteomics_gtn_wf-tests.yml | 60 ++ .../metaproteomics_gtn_wf.ga | 724 ++++++++++++++++++ 5 files changed, 813 insertions(+) create mode 100644 workflows/proteomics/metaproteomics-gtn/.dockstore.yml create mode 100644 workflows/proteomics/metaproteomics-gtn/CHANGELOG.md create mode 100644 workflows/proteomics/metaproteomics-gtn/README.md create mode 100644 workflows/proteomics/metaproteomics-gtn/metaproteomics_gtn_wf-tests.yml create mode 100644 workflows/proteomics/metaproteomics-gtn/metaproteomics_gtn_wf.ga diff --git a/workflows/proteomics/metaproteomics-gtn/.dockstore.yml b/workflows/proteomics/metaproteomics-gtn/.dockstore.yml new file mode 100644 index 000000000..3f2a7c71b --- /dev/null +++ b/workflows/proteomics/metaproteomics-gtn/.dockstore.yml @@ -0,0 +1,19 @@ +version: 1.2 +workflows: +- name: main + subclass: Galaxy + publish: true + primaryDescriptorPath: /metaproteomics_gtn_wf.ga + testParameterFiles: + - /metaproteomics_gtn_wf-tests.yml + authors: + - name: Timothy Griffin + orcid: 0000-0001-6801-2559 + - name: Pratik Jagtap + orcid: 0000-0003-0984-0973 + - name: James Johnson + identifier: https://github.com/jj-umn + - name: Clemens Blank + orcid: 0000-0002-1726-2256 + - name: Subina Mehta + orcid: 0000-0001-9818-0537 diff --git a/workflows/proteomics/metaproteomics-gtn/CHANGELOG.md b/workflows/proteomics/metaproteomics-gtn/CHANGELOG.md new file mode 100644 index 000000000..7f923112e --- /dev/null +++ b/workflows/proteomics/metaproteomics-gtn/CHANGELOG.md @@ -0,0 +1,4 @@ +# Changelog + +## [0.1] 2024-12-10 +First release. \ No newline at end of file diff --git a/workflows/proteomics/metaproteomics-gtn/README.md b/workflows/proteomics/metaproteomics-gtn/README.md new file mode 100644 index 000000000..cf16feba2 --- /dev/null +++ b/workflows/proteomics/metaproteomics-gtn/README.md @@ -0,0 +1,6 @@ +# MetaProteomics Tutorial +In this metaproteomics worflow, we will identify expressed proteins from a complex bacterial community sample. For this MS/MS data will be matched to peptide sequences provided through a FASTA file. + +Metaproteomics is the large-scale characterization of the entire protein complement of environmental microbiota at a given point in time. It has the potential to unravel the mechanistic details of microbial interactions with the host / environment by analyzing the functional dynamics of the microbiome. + +More background on this workflow can be found in the [Metaproteomics tutorial](https://galaxyproject.github.io/training-material//topics/proteomics/tutorials/metaproteomics/tutorial.html) \ No newline at end of file diff --git a/workflows/proteomics/metaproteomics-gtn/metaproteomics_gtn_wf-tests.yml b/workflows/proteomics/metaproteomics-gtn/metaproteomics_gtn_wf-tests.yml new file mode 100644 index 000000000..81d34529e --- /dev/null +++ b/workflows/proteomics/metaproteomics-gtn/metaproteomics_gtn_wf-tests.yml @@ -0,0 +1,60 @@ +- doc: Test outline for metaproteomics_gtn_wf.ga + job: + Sixgill generated protein FASTA File: + class: File + path: https://zenodo.org/records/839701/files/FASTA_Bering_Strait_Trimmed_metapeptides_cRAP.fasta + filetype: fasta + Dataset collection of MGF files: + class: Collection + collection_type: list + elements: + - class: File + identifier: 2016_Jan_12_QE2_45.mgf + location: https://zenodo.org/records/839701/files/2016_Jan_12_QE2_45.mgf + - class: File + identifier: 2016_Jan_12_QE2_46.mgf + location: https://zenodo.org/records/839701/files/2016_Jan_12_QE2_46.mgf + - class: File + identifier: 2016_Jan_12_QE2_47.mgf + location: https://zenodo.org/records/839701/files/2016_Jan_12_QE2_47.mgf + Gene Ontology Terms (Selected): + class: File + path: https://zenodo.org/records/839701/files/Gene_Ontology_Terms.tabular + filetype: tabular + outputs: + 'Peptide Shaker on input dataset(s): PSM report': + asserts: + has_text: + text: "AAs Before" + Query Tabular output: + asserts: + has_text: + text: "AADGHTMHFDVITGEK" + 'Unipept on selected peptides: pept2prot output': + asserts: + has_text: + text: "#peptide" + Taxonomy table: + asserts: + has_text: + text: "superkingdom" + GO terms: + asserts: + has_text: + text: "GO:" + Combined table of all genera, PSMs and peptides: + asserts: + has_text: + text: "PSMs" + GO Biological Processes: + asserts: + has_text: + text: "translation" + GO Cellular Localizations: + asserts: + has_text: + text: "cytoplasm" + GO Molecular Functions: + asserts: + has_text: + text: "ATP binding" diff --git a/workflows/proteomics/metaproteomics-gtn/metaproteomics_gtn_wf.ga b/workflows/proteomics/metaproteomics-gtn/metaproteomics_gtn_wf.ga new file mode 100644 index 000000000..25600d129 --- /dev/null +++ b/workflows/proteomics/metaproteomics-gtn/metaproteomics_gtn_wf.ga @@ -0,0 +1,724 @@ +{ + "a_galaxy_workflow": "true", + "annotation": "This workflow identifies expressed proteins from a complex bacterial community sample. For this, MS/MS data will be matched to peptide sequences provided through a FASTA file.\n", + "comments": [], + "creator": [ + { + "class": "Person", + "identifier": "https://orcid.org/0000-0001-6801-2559", + "name": "Timothy Griffin" + }, + { + "class": "Person", + "identifier": "https://orcid.org/0000-0003-0984-0973", + "name": "Pratik Jagtap" + }, + { + "class": "Person", + "identifier": "https://github.com/jj-umn", + "name": "James Johnson" + }, + { + "class": "Person", + "identifier": "https://orcid.org/0000-0002-1726-2256", + "name": "Clemens Blank" + }, + { + "class": "Person", + "identifier": "https://orcid.org/0000-0001-9818-0537", + "name": "Subina Mehta" + } + ], + "format-version": "0.1", + "license": "MIT", + "release": "0.1", + "name": "Metaproteomics workflow", + "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": "FASTA file consisting of trimmed peptides, given as a protein database input for Search GUI", + "content_id": null, + "errors": null, + "id": 0, + "input_connections": {}, + "inputs": [ + { + "description": "FASTA file consisting of trimmed peptides, given as a protein database input for Search GUI", + "name": "Sixgill generated protein FASTA File" + } + ], + "label": "Sixgill generated protein FASTA File", + "name": "Input dataset", + "outputs": [], + "position": { + "left": 0, + "top": 0.5937504090177583 + }, + "tool_id": null, + "tool_state": "{\"optional\": false, \"tag\": null}", + "tool_version": null, + "type": "data_input", + "uuid": "4c5ba166-09de-4e95-b193-8cddb52d93fb", + "when": null, + "workflow_outputs": [] + }, + "1": { + "annotation": "Collection of MS/MS spectral summary files", + "content_id": null, + "errors": null, + "id": 1, + "input_connections": {}, + "inputs": [ + { + "description": "Collection of MS/MS spectral summary files", + "name": "Dataset collection of MGF files" + } + ], + "label": "Dataset collection of MGF files", + "name": "Input dataset collection", + "outputs": [], + "position": { + "left": 2.84375, + "top": 159.53125 + }, + "tool_id": null, + "tool_state": "{\"optional\": false, \"tag\": null, \"collection_type\": \"list\"}", + "tool_version": null, + "type": "data_collection_input", + "uuid": "a68cee17-c1cd-4bd2-9a28-1d12e5aecefe", + "when": null, + "workflow_outputs": [] + }, + "2": { + "annotation": "List of Gene Ontology terms including biological processes, molecular functions and cellular components", + "content_id": null, + "errors": null, + "id": 2, + "input_connections": {}, + "inputs": [ + { + "description": "List of Gene Ontology terms including biological processes, molecular functions and cellular components", + "name": "Gene Ontology Terms (Selected)" + } + ], + "label": "Gene Ontology Terms (Selected)", + "name": "Input dataset", + "outputs": [], + "position": { + "left": 1209.3117556405728, + "top": 0 + }, + "tool_id": null, + "tool_state": "{\"optional\": false, \"tag\": null}", + "tool_version": null, + "type": "data_input", + "uuid": "09a667d2-66e9-4f41-947d-0000a1fbb88b", + "when": null, + "workflow_outputs": [] + }, + "3": { + "annotation": "Matches MS/MS peaks to peptide sequences", + "content_id": "toolshed.g2.bx.psu.edu/repos/galaxyp/peptideshaker/search_gui/3.3.10.1", + "errors": null, + "id": 3, + "input_connections": { + "input_database": { + "id": 0, + "output_name": "output" + }, + "peak_lists": { + "id": 1, + "output_name": "output" + } + }, + "inputs": [], + "label": "Search GUI", + "name": "Search GUI", + "outputs": [ + { + "name": "searchgui_results", + "type": "searchgui_archive" + } + ], + "position": { + "left": 228.84373957916367, + "top": 14.484374745319764 + }, + "post_job_actions": {}, + "tool_id": "toolshed.g2.bx.psu.edu/repos/galaxyp/peptideshaker/search_gui/3.3.10.1", + "tool_shed_repository": { + "changeset_revision": "7fdd9119cc4f", + "name": "peptideshaker", + "owner": "galaxyp", + "tool_shed": "toolshed.g2.bx.psu.edu" + }, + "tool_state": "{\"advanced_options\": {\"searchgui_advanced\": {\"searchgui_advanced_selector\": \"basic\", \"__current_case__\": 0}, \"xtandem\": {\"xtandem_advanced\": \"yes\", \"__current_case__\": 1, \"xtandem_npeaks\": \"50\", \"xtandem_min_peaks\": \"15\", \"xtandem_min_frag_mz\": \"200\", \"xtandem_min_prec_mass\": \"200\", \"xtandem_noise_suppr\": true, \"xtandem_dynamic_range\": \"100\", \"xtandem_quick_acetyl\": false, \"xtandem_quick_pyro\": false, \"xtandem_stp_bias\": false, \"xtandem_evalue\": \"100.0\", \"xtandem_output_proteins\": false, \"xtandem_output_sequences\": false, \"xtandem_output_spectra\": true, \"xtandem_refine\": {\"xtandem_refine_selector\": \"no\", \"__current_case__\": 0}}, \"omssa\": {\"omssa_advanced\": \"no\", \"__current_case__\": 0}, \"msgf\": {\"msgf_advanced\": \"no\", \"__current_case__\": 0}, \"ms_amanda\": {\"ms_amanda_advanced\": \"no\", \"__current_case__\": 0}, \"tide\": {\"tide_advanced\": \"no\", \"__current_case__\": 0}, \"myrimatch\": {\"myrimatch_advanced\": \"no\", \"__current_case__\": 0}, \"comet\": {\"comet_advanced\": \"no\", \"__current_case__\": 0}, \"directtag\": {\"directtag_advanced\": \"no\", \"__current_case__\": 0}, \"novor\": {\"novor_advanced\": \"no\", \"__current_case__\": 0}}, \"input_database\": {\"__class__\": \"ConnectedValue\"}, \"peak_lists\": {\"__class__\": \"ConnectedValue\"}, \"precursor_options\": {\"precursor_ion_tol_units\": \"1\", \"precursor_ion_tol\": \"10.0\", \"fragment_tol_units\": \"0\", \"fragment_tol\": \"0.2\", \"min_charge\": \"2\", \"max_charge\": \"6\", \"forward_ion\": \"b\", \"reverse_ion\": \"y\", \"min_isotope\": \"0\", \"max_isotope\": \"1\"}, \"protein_database_options\": {\"create_decoy\": true, \"use_gene_mapping\": false, \"update_gene_mapping\": false}, \"protein_digest_options\": {\"digestion\": {\"cleavage\": \"0\", \"__current_case__\": 0, \"digests\": [{\"__index__\": 0, \"enzyme\": \"Trypsin\", \"missed_cleavages\": \"2\"}]}}, \"protein_modification_options\": {\"fixed_modifications\": [\"Carbamidomethylation of C\"], \"variable_modifications\": [\"Oxidation of M\"]}, \"search_engines_options\": {\"engines\": [\"X!Tandem\"]}, \"__page__\": null, \"__rerun_remap_job_id__\": null}", + "tool_version": "3.3.10.1", + "type": "tool", + "uuid": "050f3ea1-0f60-4f88-9a17-d8d328f15bb5", + "when": null, + "workflow_outputs": [ + { + "label": "Search GUI on input dataset(s)", + "output_name": "searchgui_results", + "uuid": "115e42ab-4f6c-4664-b399-c8c3a54e9b6f" + } + ] + }, + "4": { + "annotation": "Post-processing tool for Search GUI output", + "content_id": "toolshed.g2.bx.psu.edu/repos/galaxyp/peptideshaker/peptide_shaker/1.16.36.3", + "errors": null, + "id": 4, + "input_connections": { + "searchgui_input": { + "id": 3, + "output_name": "searchgui_results" + } + }, + "inputs": [], + "label": null, + "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": 312.9375055367535, + "top": 272.4207633135564 + }, + "post_job_actions": { + "HideDatasetActionoutput_peptides": { + "action_arguments": {}, + "action_type": "HideDatasetAction", + "output_name": "output_peptides" + }, + "HideDatasetActionoutput_proteins": { + "action_arguments": {}, + "action_type": "HideDatasetAction", + "output_name": "output_proteins" + } + }, + "tool_id": "toolshed.g2.bx.psu.edu/repos/galaxyp/peptideshaker/peptide_shaker/1.16.36.3", + "tool_shed_repository": { + "changeset_revision": "7fdd9119cc4f", + "name": "peptideshaker", + "owner": "galaxyp", + "tool_shed": "toolshed.g2.bx.psu.edu" + }, + "tool_state": "{\"contact_options\": {\"contact_options_selector\": \"no\", \"__current_case__\": 0}, \"exporting_options\": {\"mzidentml_conditional\": {\"mzidentml_creation\": true, \"__current_case__\": 0, \"include_sequences\": false}, \"zip_conditional\": {\"zip_output_boolean\": false, \"__current_case__\": 0, \"export_cps\": false}, \"output_reports\": [\"3\", \"6\", \"9\", \"0\"]}, \"filtering_options\": {\"filtering_options_selector\": \"yes\", \"__current_case__\": 1, \"min_peptide_length\": \"6\", \"max_peptide_length\": \"30\", \"max_precursor_error\": \"10.0\", \"max_precursor_error_type\": \"0\", \"exclude_unknown_ptms\": true}, \"processing_options\": {\"processing_options_selector\": \"no\", \"__current_case__\": 0}, \"searchgui_input\": {\"__class__\": \"ConnectedValue\"}, \"__page__\": null, \"__rerun_remap_job_id__\": null}", + "tool_version": "1.16.36.3", + "type": "tool", + "uuid": "c74f9b66-8ba2-4c99-8560-570bb082ffc5", + "when": null, + "workflow_outputs": [ + { + "label": "Certificate of analysis", + "output_name": "output_certificate", + "uuid": "65559b47-4b7f-45e7-8743-e568346c602a" + }, + { + "label": "Peptide Shaker on input dataset(s): mzidentML file", + "output_name": "mzidentML", + "uuid": "d144ed43-b930-41f2-a492-fb1c1823d9b7" + }, + { + "label": "Peptide Shaker on input dataset(s): PSM report", + "output_name": "output_psm", + "uuid": "040bfa41-e7c2-405f-b3ff-a4ff1a7b1899" + } + ] + }, + "5": { + "annotation": "Generates a list of peptide sequences from the PSM report", + "content_id": "toolshed.g2.bx.psu.edu/repos/iuc/query_tabular/query_tabular/3.0.0", + "errors": null, + "id": 5, + "input_connections": { + "tables_0|table": { + "id": 4, + "output_name": "output_psm" + } + }, + "inputs": [ + { + "description": "runtime parameter for tool Query Tabular", + "name": "add_to_database" + } + ], + "label": "Query Tabular Select Peptides", + "name": "Query Tabular", + "outputs": [ + { + "name": "output", + "type": "tabular" + } + ], + "position": { + "left": 646.875, + "top": 140.671875 + }, + "post_job_actions": { + "HideDatasetActionsqlitedb": { + "action_arguments": {}, + "action_type": "HideDatasetAction", + "output_name": "sqlitedb" + } + }, + "tool_id": "toolshed.g2.bx.psu.edu/repos/iuc/query_tabular/query_tabular/3.0.0", + "tool_shed_repository": { + "changeset_revision": "33d61c89fb8d", + "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\": \"no\", \"__current_case__\": 1}, \"save_db\": false, \"sqlquery\": \"SELECT distinct sequence \\nFROM psm \\nWHERE confidence >= 95 \\nORDER BY sequence\", \"tables\": [{\"__index__\": 0, \"table\": {\"__class__\": \"ConnectedValue\"}, \"input_opts\": {\"linefilters\": [{\"__index__\": 0, \"filter\": {\"filter_type\": \"regex\", \"__current_case__\": 6, \"regex_pattern\": \"^\\\\d\", \"regex_action\": \"include_match\"}}]}, \"tbl_opts\": {\"table_name\": \"psm\", \"column_names_from_first_line\": false, \"col_names\": \"id,,sequence,,,,,,,,,,,,,,,,,,,,confidence,validation\", \"load_named_columns\": true, \"pkey_autoincr\": \"\", \"indexes\": []}}], \"workdb\": \"workdb.sqlite\", \"__page__\": null, \"__rerun_remap_job_id__\": null}", + "tool_version": "3.0.0", + "type": "tool", + "uuid": "48b2b26c-90c2-4474-858b-4823e25ffb0b", + "when": null, + "workflow_outputs": [ + { + "label": "Query Tabular output", + "output_name": "output", + "uuid": "17ba215c-9efa-4b7c-bf8f-8404a36bfaea" + } + ] + }, + "6": { + "annotation": "Matches the list of peptides with the correlated Gene Ontology terms", + "content_id": "toolshed.g2.bx.psu.edu/repos/galaxyp/unipept/unipept/4.3.0", + "errors": null, + "id": 6, + "input_connections": { + "peptide_src|input_tsv": { + "id": 5, + "output_name": "output" + } + }, + "inputs": [ + { + "description": "runtime parameter for tool Unipept", + "name": "peptide_src" + } + ], + "label": "Unipept pept2prot", + "name": "Unipept", + "outputs": [ + { + "name": "output_tsv", + "type": "tabular" + } + ], + "position": { + "left": 915.5001115978775, + "top": 37.078122777010826 + }, + "post_job_actions": {}, + "tool_id": "toolshed.g2.bx.psu.edu/repos/galaxyp/unipept/unipept/4.3.0", + "tool_shed_repository": { + "changeset_revision": "9aaa46d45472", + "name": "unipept", + "owner": "galaxyp", + "tool_shed": "toolshed.g2.bx.psu.edu" + }, + "tool_state": "{\"peptide_src\": {\"fmt\": \"tabular\", \"__current_case__\": 1, \"input_tsv\": {\"__class__\": \"ConnectedValue\"}, \"column\": \"1\"}, \"selected_outputs\": \"tsv\", \"strict\": false, \"unipept\": {\"api\": \"pept2prot\", \"__current_case__\": 2, \"equate_il\": true, \"extra\": true}, \"__page__\": null, \"__rerun_remap_job_id__\": null}", + "tool_version": "4.3.0", + "type": "tool", + "uuid": "57678873-6623-4ac0-9b86-697fa4246c11", + "when": null, + "workflow_outputs": [ + { + "label": "Unipept on selected peptides: pept2prot output", + "output_name": "output_tsv", + "uuid": "2fb042a4-8497-40d5-94d2-2ad47d04ab52" + } + ] + }, + "7": { + "annotation": "Returns the taxonomic lowest common ancestor for each peptide", + "content_id": "toolshed.g2.bx.psu.edu/repos/galaxyp/unipept/unipept/4.3.0", + "errors": null, + "id": 7, + "input_connections": { + "peptide_src|input_tsv": { + "id": 5, + "output_name": "output" + } + }, + "inputs": [ + { + "description": "runtime parameter for tool Unipept", + "name": "peptide_src" + } + ], + "label": "Unipept lca", + "name": "Unipept", + "outputs": [ + { + "name": "output_json", + "type": "d3_hierarchy" + }, + { + "name": "output_tsv", + "type": "tabular" + } + ], + "position": { + "left": 912.359375, + "top": 281.984375 + }, + "post_job_actions": {}, + "tool_id": "toolshed.g2.bx.psu.edu/repos/galaxyp/unipept/unipept/4.3.0", + "tool_shed_repository": { + "changeset_revision": "9aaa46d45472", + "name": "unipept", + "owner": "galaxyp", + "tool_shed": "toolshed.g2.bx.psu.edu" + }, + "tool_state": "{\"peptide_src\": {\"fmt\": \"tabular\", \"__current_case__\": 1, \"input_tsv\": {\"__class__\": \"ConnectedValue\"}, \"column\": \"1\"}, \"selected_outputs\": [\"tsv\", \"json\", \"ec_json\"], \"strict\": false, \"unipept\": {\"api\": \"pept2lca\", \"__current_case__\": 0, \"equate_il\": false, \"extra\": false, \"names\": true, \"allfields\": false}, \"__page__\": null, \"__rerun_remap_job_id__\": null}", + "tool_version": "4.3.0", + "type": "tool", + "uuid": "98103c15-f03d-4a06-b16a-2187fc31cab4", + "when": null, + "workflow_outputs": [ + { + "label": "JSON taxonomy tree", + "output_name": "output_json", + "uuid": "6cb3ba22-5fb6-42cb-94ec-12697ed06377" + }, + { + "label": "Taxonomy table", + "output_name": "output_tsv", + "uuid": "80ba446f-06bc-49f0-ae46-44fab0b2d10f" + } + ] + }, + "8": { + "annotation": "", + "content_id": "toolshed.g2.bx.psu.edu/repos/iuc/query_tabular/query_tabular/3.0.0", + "errors": null, + "id": 8, + "input_connections": { + "tables_0|table": { + "id": 2, + "output_name": "output" + }, + "tables_1|table": { + "id": 6, + "output_name": "output_tsv" + }, + "tables_2|table": { + "id": 6, + "output_name": "output_tsv" + }, + "tables_3|table": { + "id": 4, + "output_name": "output_psm" + } + }, + "inputs": [ + { + "description": "runtime parameter for tool Query Tabular", + "name": "add_to_database" + } + ], + "label": "Go Pop2Prot DB", + "name": "Query Tabular", + "outputs": [ + { + "name": "sqlitedb", + "type": "sqlite" + }, + { + "name": "output", + "type": "tabular" + } + ], + "position": { + "left": 922.890625, + "top": 546.59375 + }, + "post_job_actions": { + "RenameDatasetActionoutput": { + "action_arguments": { + "newname": "Peptides and PSMs" + }, + "action_type": "RenameDatasetAction", + "output_name": "output" + } + }, + "tool_id": "toolshed.g2.bx.psu.edu/repos/iuc/query_tabular/query_tabular/3.0.0", + "tool_shed_repository": { + "changeset_revision": "33d61c89fb8d", + "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\": \"35\"}, \"save_db\": true, \"sqlquery\": \"SELECT sequence as \\\"peptide\\\", count(id) as \\\"PSMs\\\"\\nFROM bering_psms\\nWHERE confidence >= 95\\nGROUP BY sequence\\nORDER BY sequence\\n\", \"tables\": [{\"__index__\": 0, \"table\": {\"__class__\": \"ConnectedValue\"}, \"input_opts\": {\"linefilters\": [{\"__index__\": 0, \"filter\": {\"filter_type\": \"skip\", \"__current_case__\": 0, \"skip_lines\": \"1\"}}]}, \"tbl_opts\": {\"table_name\": \"go\", \"column_names_from_first_line\": false, \"col_names\": \"aspect,go_id,description\", \"load_named_columns\": false, \"pkey_autoincr\": \"\", \"indexes\": [{\"__index__\": 0, \"unique\": false, \"index_columns\": \"aspect,go_id\"}]}}, {\"__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}}]}, \"tbl_opts\": {\"table_name\": \"bering_prot\", \"column_names_from_first_line\": false, \"col_names\": \"id,peptide,uniprot_id,taxon_id,taxon_name,ec_references,go_references,refseq_ids,refseq_protein_ids,insdc_ids,insdc_protein_ids\", \"load_named_columns\": false, \"pkey_autoincr\": \"\", \"indexes\": [{\"__index__\": 0, \"unique\": false, \"index_columns\": \"id,peptide\"}]}}, {\"__index__\": 2, \"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\": \"select_columns\", \"__current_case__\": 7, \"columns\": \"1,7\"}}, {\"__index__\": 3, \"filter\": {\"filter_type\": \"normalize\", \"__current_case__\": 9, \"columns\": \"2\", \"separator\": \" \"}}]}, \"tbl_opts\": {\"table_name\": \"bering_prot_go\", \"column_names_from_first_line\": false, \"col_names\": \"id,go_reference\", \"load_named_columns\": false, \"pkey_autoincr\": \"\", \"indexes\": [{\"__index__\": 0, \"unique\": false, \"index_columns\": \"go_reference,id\"}]}}, {\"__index__\": 3, \"table\": {\"__class__\": \"ConnectedValue\"}, \"input_opts\": {\"linefilters\": [{\"__index__\": 0, \"filter\": {\"filter_type\": \"regex\", \"__current_case__\": 6, \"regex_pattern\": \"^\\\\d\", \"regex_action\": \"include_match\"}}, {\"__index__\": 1, \"filter\": {\"filter_type\": \"select_columns\", \"__current_case__\": 7, \"columns\": \"1,3,23,24\"}}]}, \"tbl_opts\": {\"table_name\": \"bering_psms\", \"column_names_from_first_line\": false, \"col_names\": \"id,sequence,confidence,validation\", \"load_named_columns\": true, \"pkey_autoincr\": \"\", \"indexes\": [{\"__index__\": 0, \"unique\": false, \"index_columns\": \"sequence,id\"}]}}], \"workdb\": \"workdb.sqlite\", \"__page__\": null, \"__rerun_remap_job_id__\": null}", + "tool_version": "3.0.0", + "type": "tool", + "uuid": "684e9a81-02fe-421e-bcb3-14ec4697a2fc", + "when": null, + "workflow_outputs": [ + { + "label": "GO terms", + "output_name": "output", + "uuid": "29cfb124-bbfd-4a44-b3a8-684eab72d546" + }, + { + "label": "GO terms database in SQLite format", + "output_name": "sqlitedb", + "uuid": "61d4830c-4ec9-4b38-b586-2acdd540b16a" + } + ] + }, + "9": { + "annotation": "Combines all genera, PSMs and peptides into a single database", + "content_id": "toolshed.g2.bx.psu.edu/repos/iuc/query_tabular/query_tabular/3.0.0", + "errors": null, + "id": 9, + "input_connections": { + "tables_0|table": { + "id": 4, + "output_name": "output_psm" + }, + "tables_1|table": { + "id": 7, + "output_name": "output_tsv" + } + }, + "inputs": [ + { + "description": "runtime parameter for tool Query Tabular", + "name": "add_to_database" + } + ], + "label": "Genera | PSMs | Peptides", + "name": "Query Tabular", + "outputs": [ + { + "name": "output", + "type": "tabular" + } + ], + "position": { + "left": 914.1249399474883, + "top": 986.578160827765 + }, + "post_job_actions": { + "HideDatasetActionsqlitedb": { + "action_arguments": {}, + "action_type": "HideDatasetAction", + "output_name": "sqlitedb" + } + }, + "tool_id": "toolshed.g2.bx.psu.edu/repos/iuc/query_tabular/query_tabular/3.0.0", + "tool_shed_repository": { + "changeset_revision": "33d61c89fb8d", + "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\": \"35\"}, \"save_db\": false, \"sqlquery\": \"SELECT lca.genus,count(psm.sequence) as \\\"PSMs\\\",count(distinct psm.sequence) as \\\"DISTINCT PEPTIDES\\\" \\nFROM psm LEFT JOIN lca ON psm.sequence = lca.peptide \\nWHERE confidence >= 95 \\nGROUP BY lca.genus \\nORDER BY PSMs desc, 'DISTINCT PEPTIDES' desc\", \"tables\": [{\"__index__\": 0, \"table\": {\"__class__\": \"ConnectedValue\"}, \"input_opts\": {\"linefilters\": [{\"__index__\": 0, \"filter\": {\"filter_type\": \"regex\", \"__current_case__\": 6, \"regex_pattern\": \"^\\\\d\", \"regex_action\": \"include_match\"}}]}, \"tbl_opts\": {\"table_name\": \"psm\", \"column_names_from_first_line\": false, \"col_names\": \",,sequence,,,,,,,,,,,,,,,,,,,,confidence,validation\", \"load_named_columns\": true, \"pkey_autoincr\": \"\", \"indexes\": []}}, {\"__index__\": 1, \"table\": {\"__class__\": \"ConnectedValue\"}, \"input_opts\": {\"linefilters\": [{\"__index__\": 0, \"filter\": {\"filter_type\": \"regex\", \"__current_case__\": 6, \"regex_pattern\": \"#peptide\", \"regex_action\": \"exclude_match\"}}]}, \"tbl_opts\": {\"table_name\": \"lca\", \"column_names_from_first_line\": false, \"col_names\": \"peptide,,,,,,,,,,,,,,,,,,,,,genus\", \"load_named_columns\": true, \"pkey_autoincr\": \"\", \"indexes\": []}}], \"workdb\": \"workdb.sqlite\", \"__page__\": null, \"__rerun_remap_job_id__\": null}", + "tool_version": "3.0.0", + "type": "tool", + "uuid": "5a0f0694-71d9-4f2f-8e1b-77b684f9033f", + "when": null, + "workflow_outputs": [ + { + "label": "Combined table of all genera, PSMs and peptides", + "output_name": "output", + "uuid": "010131bc-ce84-4238-baec-3eac7dacd6a0" + } + ] + }, + "10": { + "annotation": "", + "content_id": "toolshed.g2.bx.psu.edu/repos/iuc/sqlite_to_tabular/sqlite_to_tabular/2.0.0", + "errors": null, + "id": 10, + "input_connections": { + "sqlitedb": { + "id": 8, + "output_name": "sqlitedb" + } + }, + "inputs": [], + "label": "GO Terms: Biological Processes", + "name": "SQLite to tabular", + "outputs": [ + { + "name": "query_results", + "type": "tabular" + } + ], + "position": { + "left": 1529.4054698421558, + "top": 108.10937290594494 + }, + "post_job_actions": { + "RenameDatasetActionquery_results": { + "action_arguments": { + "newname": "GO Terms: Biological Processes" + }, + "action_type": "RenameDatasetAction", + "output_name": "query_results" + } + }, + "tool_id": "toolshed.g2.bx.psu.edu/repos/iuc/sqlite_to_tabular/sqlite_to_tabular/2.0.0", + "tool_shed_repository": { + "changeset_revision": "b722161a845a", + "name": "sqlite_to_tabular", + "owner": "iuc", + "tool_shed": "toolshed.g2.bx.psu.edu" + }, + "tool_state": "{\"query_result\": {\"header\": \"yes\", \"__current_case__\": 0, \"header_prefix\": \"35\"}, \"sqlitedb\": {\"__class__\": \"ConnectedValue\"}, \"sqlquery\": \"SELECT go.description, \\ncount(distinct bering_psms.sequence) as \\\"bering_peptides\\\", count(distinct bering_psms.id) as \\\"bering_psms\\\" \\nFROM go JOIN bering_prot_go ON go.go_id = bering_prot_go.go_reference JOIN bering_prot on bering_prot_go.id = bering_prot.id JOIN bering_psms ON bering_prot.peptide = bering_psms.sequence\\nWHERE go.aspect = 'biological_process'\\nGROUP BY go.description\\nORDER BY bering_peptides desc,bering_psms desc\", \"__page__\": null, \"__rerun_remap_job_id__\": null}", + "tool_version": "2.0.0", + "type": "tool", + "uuid": "05a5928a-fd97-4c4a-af60-b99cf4dd04a1", + "when": null, + "workflow_outputs": [ + { + "label": "GO Biological Processes", + "output_name": "query_results", + "uuid": "89730292-7595-4b95-bed9-c8f11953c9d7" + } + ] + }, + "11": { + "annotation": "", + "content_id": "toolshed.g2.bx.psu.edu/repos/iuc/sqlite_to_tabular/sqlite_to_tabular/2.0.0", + "errors": null, + "id": 11, + "input_connections": { + "sqlitedb": { + "id": 8, + "output_name": "sqlitedb" + } + }, + "inputs": [], + "label": "GO Terms: Cellular Localization", + "name": "SQLite to tabular", + "outputs": [ + { + "name": "query_results", + "type": "tabular" + } + ], + "position": { + "left": 1542.390636968383, + "top": 408.18861741916913 + }, + "post_job_actions": { + "RenameDatasetActionquery_results": { + "action_arguments": { + "newname": "GO Terms: Cellular Localization" + }, + "action_type": "RenameDatasetAction", + "output_name": "query_results" + } + }, + "tool_id": "toolshed.g2.bx.psu.edu/repos/iuc/sqlite_to_tabular/sqlite_to_tabular/2.0.0", + "tool_shed_repository": { + "changeset_revision": "b722161a845a", + "name": "sqlite_to_tabular", + "owner": "iuc", + "tool_shed": "toolshed.g2.bx.psu.edu" + }, + "tool_state": "{\"query_result\": {\"header\": \"yes\", \"__current_case__\": 0, \"header_prefix\": \"35\"}, \"sqlitedb\": {\"__class__\": \"ConnectedValue\"}, \"sqlquery\": \"SELECT go.description, \\ncount(distinct bering_psms.sequence) as \\\"bering_peptides\\\", count(distinct bering_psms.id) as \\\"bering_psms\\\" \\nFROM go JOIN bering_prot_go ON go.go_id = bering_prot_go.go_reference JOIN bering_prot on bering_prot_go.id = bering_prot.id JOIN bering_psms ON bering_prot.peptide = bering_psms.sequence\\nWHERE go.aspect = 'cellular_component'\\nGROUP BY go.description\\nORDER BY bering_peptides desc,bering_psms desc\", \"__page__\": null, \"__rerun_remap_job_id__\": null}", + "tool_version": "2.0.0", + "type": "tool", + "uuid": "87355427-5567-4695-88c3-ca64703b1ce4", + "when": null, + "workflow_outputs": [ + { + "label": "GO Cellular Localizations", + "output_name": "query_results", + "uuid": "2e8a071a-da5c-4260-9591-aac88362cf4e" + } + ] + }, + "12": { + "annotation": "", + "content_id": "toolshed.g2.bx.psu.edu/repos/iuc/sqlite_to_tabular/sqlite_to_tabular/2.0.0", + "errors": null, + "id": 12, + "input_connections": { + "sqlitedb": { + "id": 8, + "output_name": "sqlitedb" + } + }, + "inputs": [], + "label": "GO Terms: Molecular Functions", + "name": "SQLite to tabular", + "outputs": [ + { + "name": "query_results", + "type": "tabular" + } + ], + "position": { + "left": 1775.4054698421558, + "top": 195.10937290594495 + }, + "post_job_actions": { + "RenameDatasetActionquery_results": { + "action_arguments": { + "newname": "GO Terms: Molecular Functions" + }, + "action_type": "RenameDatasetAction", + "output_name": "query_results" + } + }, + "tool_id": "toolshed.g2.bx.psu.edu/repos/iuc/sqlite_to_tabular/sqlite_to_tabular/2.0.0", + "tool_shed_repository": { + "changeset_revision": "b722161a845a", + "name": "sqlite_to_tabular", + "owner": "iuc", + "tool_shed": "toolshed.g2.bx.psu.edu" + }, + "tool_state": "{\"query_result\": {\"header\": \"yes\", \"__current_case__\": 0, \"header_prefix\": \"35\"}, \"sqlitedb\": {\"__class__\": \"ConnectedValue\"}, \"sqlquery\": \"SELECT go.description, \\ncount(distinct bering_psms.sequence) as \\\"bering_peptides\\\", count(distinct bering_psms.id) as \\\"bering_psms\\\" \\nFROM go JOIN bering_prot_go ON go.go_id = bering_prot_go.go_reference JOIN bering_prot on bering_prot_go.id = bering_prot.id JOIN bering_psms ON bering_prot.peptide = bering_psms.sequence\\nWHERE go.aspect = 'molecular_function'\\nGROUP BY go.description\\nORDER BY bering_peptides desc,bering_psms desc\", \"__page__\": null, \"__rerun_remap_job_id__\": null}", + "tool_version": "2.0.0", + "type": "tool", + "uuid": "2a397c66-3da4-4cbe-a186-2adaaea9c39e", + "when": null, + "workflow_outputs": [ + { + "label": "GO Molecular Functions", + "output_name": "query_results", + "uuid": "f6fb7920-4385-4452-b0ea-6bb0bf7770fe" + } + ] + } + }, + "tags": [ + "name:metaproteomics", + "name:galaxyp", + "name:massspectrometry", + "name:microgalaxy" + ], + "uuid": "a0cfa0a6-bd97-48c0-aa30-7bcf546ffd3d", + "version": 40 +} \ No newline at end of file From 8f0e4a9baa7396295bdfd69ae62fb699911f5470 Mon Sep 17 00:00:00 2001 From: Clea Siguret Date: Tue, 10 Dec 2024 15:12:24 +0100 Subject: [PATCH 2/6] init metaquantome-function workflow --- .../metaquantome-function/.dockstore.yml | 21 + .../metaquantome-function/CHANGELOG.md | 4 + .../metaquantome-function/README.md | 4 + .../metaquantome_function_wf-tests.yml | 47 ++ .../metaquantome_function_wf.ga | 636 ++++++++++++++++++ 5 files changed, 712 insertions(+) create mode 100644 workflows/proteomics/metaquantome-function/.dockstore.yml create mode 100644 workflows/proteomics/metaquantome-function/CHANGELOG.md create mode 100644 workflows/proteomics/metaquantome-function/README.md create mode 100644 workflows/proteomics/metaquantome-function/metaquantome_function_wf-tests.yml create mode 100644 workflows/proteomics/metaquantome-function/metaquantome_function_wf.ga diff --git a/workflows/proteomics/metaquantome-function/.dockstore.yml b/workflows/proteomics/metaquantome-function/.dockstore.yml new file mode 100644 index 000000000..82dd73fda --- /dev/null +++ b/workflows/proteomics/metaquantome-function/.dockstore.yml @@ -0,0 +1,21 @@ +version: 1.2 +workflows: +- name: main + subclass: Galaxy + publish: true + primaryDescriptorPath: /metaquantome_function_wf.ga + testParameterFiles: + - /metaquantome_function_wf-tests.yml + authors: + - name: Subina Mehta + orcid: 0000-0001-9818-0537 + - name: Timothy J. Griffin + orcid: 0000-0001-6801-2559 + - name: Pratik Jagtap + orcid: 0000-0003-0984-0973 + - name: Emma Leith + alternateName: emmaleith + - name: Marie Crane + alternateName: mariecrane + - name: Praveen Kumar + alternateName: pravs3683 diff --git a/workflows/proteomics/metaquantome-function/CHANGELOG.md b/workflows/proteomics/metaquantome-function/CHANGELOG.md new file mode 100644 index 000000000..7f923112e --- /dev/null +++ b/workflows/proteomics/metaquantome-function/CHANGELOG.md @@ -0,0 +1,4 @@ +# Changelog + +## [0.1] 2024-12-10 +First release. \ No newline at end of file diff --git a/workflows/proteomics/metaquantome-function/README.md b/workflows/proteomics/metaquantome-function/README.md new file mode 100644 index 000000000..622ebad63 --- /dev/null +++ b/workflows/proteomics/metaquantome-function/README.md @@ -0,0 +1,4 @@ +# metaQuantome 2: Function +metaQuantome software suite Easterly et al. 2019 was developed by the Team for quantitative and statistical analysis of metaproteomics data. For taxonomic and functional expression analysis within the microbial community, metaQuantome leverages peptide-level quantitative information to generate visual outputs for data interpretation. It also generates outputs that help in understanding the taxonomic contribution to a selected function as well as functions expressed by selected taxonomic group. + +More background on this workflow can be found in the [metaQuantome 2: Function tutorial](https://training.galaxyproject.org/training-material/topics/proteomics/tutorials/metaquantome-function/tutorial.html) \ No newline at end of file diff --git a/workflows/proteomics/metaquantome-function/metaquantome_function_wf-tests.yml b/workflows/proteomics/metaquantome-function/metaquantome_function_wf-tests.yml new file mode 100644 index 000000000..33c57ddf0 --- /dev/null +++ b/workflows/proteomics/metaquantome-function/metaquantome_function_wf-tests.yml @@ -0,0 +1,47 @@ +- doc: Test outline for metaquantome_function_wf.ga + job: + Functional file: + class: File + path: https://zenodo.org/records/4110725/files/Function-File.tabular + filetype: tabular + Intensity file: + class: File + path: https://zenodo.org/records/4110725/files/Intensity-File.tabular + filetype: tabular + outputs: + Samples metaQuantome file: + asserts: + has_text: + text: "colnames" + metaQuantome expand file: + asserts: + has_text: + text: "mitochondrial" + metaQuantome filtered file: + asserts: + has_text: + text: "ribosomal" + metaQuantome stats file: + asserts: + has_text: + text: "GO:0000015" + Bar plot data for sample T2: + asserts: + has_text: + text: "binding" + Bar plot data for sample T4: + asserts: + has_text: + text: "catalytic activity" + Bar plot data for sample T7: + asserts: + has_text: + text: "binding" + Volcano plot data for T7 and T2: + asserts: + has_text: + text: "ion binding" + Volcano plot data for T4 and T2: + asserts: + has_text: + text: "ribosomal" diff --git a/workflows/proteomics/metaquantome-function/metaquantome_function_wf.ga b/workflows/proteomics/metaquantome-function/metaquantome_function_wf.ga new file mode 100644 index 000000000..6cf68f002 --- /dev/null +++ b/workflows/proteomics/metaquantome-function/metaquantome_function_wf.ga @@ -0,0 +1,636 @@ +{ + "a_galaxy_workflow": "true", + "annotation": "metaquantome-function", + "comments": [], + "creator": [ + { + "class": "Person", + "identifier": "0000-0001-9818-0537 ", + "name": "Subina Mehta" + }, + { + "class": "Person", + "identifier": "0000-0001-6801-2559 ", + "name": "Timothy J. Griffin" + }, + { + "class": "Person", + "identifier": "0000-0003-0984-0973 ", + "name": "Pratik Jagtap" + }, + { + "alternateName": "emmaleith", + "class": "Person", + "name": "Emma Leith" + }, + { + "alternateName": "mariecrane", + "class": "Person", + "name": "Marie Crane" + }, + { + "alternateName": "pravs3683", + "class": "Person", + "name": "Praveen Kumar" + } + ], + "format-version": "0.1", + "license": "MIT", + "release": "0.1", + "name": "metaquantome-function-worklow", + "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": "toolshed.g2.bx.psu.edu/repos/galaxyp/metaquantome_db/metaquantome_db/2.0.2+galaxy0", + "errors": null, + "id": 0, + "input_connections": {}, + "inputs": [], + "label": null, + "name": "metaQuantome: database", + "outputs": [ + { + "name": "outfile", + "type": "tar" + } + ], + "position": { + "left": 0, + "top": 164.1260045776367 + }, + "post_job_actions": {}, + "tool_id": "toolshed.g2.bx.psu.edu/repos/galaxyp/metaquantome_db/metaquantome_db/2.0.2+galaxy0", + "tool_shed_repository": { + "changeset_revision": "e63db1aa82ee", + "name": "metaquantome_db", + "owner": "galaxyp", + "tool_shed": "toolshed.g2.bx.psu.edu" + }, + "tool_state": "{\"__input_ext\": \"data\", \"chromInfo\": \"/opt/galaxy/tool-data/shared/ucsc/chrom/?.len\", \"databases\": [\"ncbi\", \"go\", \"ec\"], \"__page__\": null, \"__rerun_remap_job_id__\": null}", + "tool_version": "2.0.2+galaxy0", + "type": "tool", + "uuid": "1ae509c1-52ea-4fef-ad4f-bcc3b836ed08", + "when": null, + "workflow_outputs": [ + { + "label": "metaQuantome databases archive File", + "output_name": "outfile", + "uuid": "2c90e06b-9d2a-40c5-bedd-c50c88c47d01" + } + ] + }, + "1": { + "annotation": "", + "content_id": "toolshed.g2.bx.psu.edu/repos/galaxyp/metaquantome_sample/metaquantome_sample/2.0.2+galaxy0", + "errors": null, + "id": 1, + "input_connections": {}, + "inputs": [], + "label": null, + "name": "metaQuantome: create samples file", + "outputs": [ + { + "name": "samples_file", + "type": "tabular" + } + ], + "position": { + "left": 6.015625, + "top": 310.1728795776367 + }, + "post_job_actions": {}, + "tool_id": "toolshed.g2.bx.psu.edu/repos/galaxyp/metaquantome_sample/metaquantome_sample/2.0.2+galaxy0", + "tool_shed_repository": { + "changeset_revision": "06f6826d380c", + "name": "metaquantome_sample", + "owner": "galaxyp", + "tool_shed": "toolshed.g2.bx.psu.edu" + }, + "tool_state": "{\"samps_args\": {\"samps_src\": \"build\", \"__current_case__\": 0, \"samps\": [{\"__index__\": 0, \"group_name\": \"T2\", \"col_names\": \"T2_A1,T2_B1\"}, {\"__index__\": 1, \"group_name\": \"T4\", \"col_names\": \"T4A_1,T4B_1\"}, {\"__index__\": 2, \"group_name\": \"T7\", \"col_names\": \"T7A_1,T7B_1\"}]}, \"__page__\": null, \"__rerun_remap_job_id__\": null}", + "tool_version": "2.0.2+galaxy0", + "type": "tool", + "uuid": "7c62b58f-170d-4b7b-ae26-eadb97517c6b", + "when": null, + "workflow_outputs": [ + { + "label": "Samples metaQuantome file", + "output_name": "samples_file", + "uuid": "3b201825-9901-4688-97b7-b1fa6541f718" + } + ] + }, + "2": { + "annotation": "Functional metaQuantome file", + "content_id": null, + "errors": null, + "id": 2, + "input_connections": {}, + "inputs": [ + { + "description": "Functional metaQuantome file", + "name": "Functional file" + } + ], + "label": "Functional file", + "name": "Input dataset", + "outputs": [], + "position": { + "left": 17.46875, + "top": 484.7510045776367 + }, + "tool_id": null, + "tool_state": "{\"optional\": false, \"tag\": null}", + "tool_version": null, + "type": "data_input", + "uuid": "a1af3031-e681-4f18-9ac0-3771627a4cea", + "when": null, + "workflow_outputs": [] + }, + "3": { + "annotation": "Intensity metaQuantome file", + "content_id": null, + "errors": null, + "id": 3, + "input_connections": {}, + "inputs": [ + { + "description": "Intensity metaQuantome file", + "name": "Intensity file" + } + ], + "label": "Intensity file", + "name": "Input dataset", + "outputs": [], + "position": { + "left": 11.484375, + "top": 601.7510045776368 + }, + "tool_id": null, + "tool_state": "{\"optional\": false, \"tag\": null}", + "tool_version": null, + "type": "data_input", + "uuid": "a8674794-94ea-4a5d-9a1d-dde5cf99587e", + "when": null, + "workflow_outputs": [] + }, + "4": { + "annotation": "", + "content_id": "toolshed.g2.bx.psu.edu/repos/galaxyp/metaquantome_expand/metaquantome_expand/2.0.2+galaxy0", + "errors": null, + "id": 4, + "input_connections": { + "db_tar": { + "id": 0, + "output_name": "outfile" + }, + "int_file": { + "id": 3, + "output_name": "output" + }, + "mode_args|func_file": { + "id": 2, + "output_name": "output" + }, + "samps": { + "id": 1, + "output_name": "samples_file" + } + }, + "inputs": [ + { + "description": "runtime parameter for tool metaQuantome: expand", + "name": "mode_args" + } + ], + "label": null, + "name": "metaQuantome: expand", + "outputs": [ + { + "name": "outfile", + "type": "tabular" + } + ], + "position": { + "left": 333.03125, + "top": 20.141629577636714 + }, + "post_job_actions": {}, + "tool_id": "toolshed.g2.bx.psu.edu/repos/galaxyp/metaquantome_expand/metaquantome_expand/2.0.2+galaxy0", + "tool_shed_repository": { + "changeset_revision": "767c1d761aaf", + "name": "metaquantome_expand", + "owner": "galaxyp", + "tool_shed": "toolshed.g2.bx.psu.edu" + }, + "tool_state": "{\"db_tar\": {\"__class__\": \"ConnectedValue\"}, \"int_file\": {\"__class__\": \"ConnectedValue\"}, \"mode_args\": {\"mode\": \"f\", \"__current_case__\": 0, \"func_file\": {\"__class__\": \"ConnectedValue\"}, \"pep_colname_func\": \"peptide\", \"ontology_args\": {\"ontology\": \"go\", \"__current_case__\": 0, \"slim_down\": false}, \"func_colname\": \"go_term\"}, \"pep_colname_int\": \"peptide\", \"samps\": {\"__class__\": \"ConnectedValue\"}, \"__page__\": null, \"__rerun_remap_job_id__\": null}", + "tool_version": "2.0.2+galaxy0", + "type": "tool", + "uuid": "ecc42284-276c-4102-b607-fb1fe888fe01", + "when": null, + "workflow_outputs": [ + { + "label": "metaQuantome expand file", + "output_name": "outfile", + "uuid": "dabf0b50-c135-4aec-be39-300e1027f6f5" + } + ] + }, + "5": { + "annotation": "", + "content_id": "toolshed.g2.bx.psu.edu/repos/galaxyp/metaquantome_filter/metaquantome_filter/2.0.2+galaxy0", + "errors": null, + "id": 5, + "input_connections": { + "expand_file": { + "id": 4, + "output_name": "outfile" + }, + "samps": { + "id": 1, + "output_name": "samples_file" + } + }, + "inputs": [], + "label": null, + "name": "metaQuantome: filter", + "outputs": [ + { + "name": "outfile", + "type": "tabular" + } + ], + "position": { + "left": 332.03125, + "top": 514.1572545776368 + }, + "post_job_actions": {}, + "tool_id": "toolshed.g2.bx.psu.edu/repos/galaxyp/metaquantome_filter/metaquantome_filter/2.0.2+galaxy0", + "tool_shed_repository": { + "changeset_revision": "35cc7ca0bdc7", + "name": "metaquantome_filter", + "owner": "galaxyp", + "tool_shed": "toolshed.g2.bx.psu.edu" + }, + "tool_state": "{\"__input_ext\": \"tabular\", \"chromInfo\": \"/opt/galaxy/tool-data/shared/ucsc/chrom/?.len\", \"expand_file\": {\"__class__\": \"ConnectedValue\"}, \"min_child_nsamp\": \"1\", \"min_children_non_leaf\": \"2\", \"min_pep_nsamp\": \"1\", \"min_peptides\": \"1\", \"mode_args\": {\"mode\": \"f\", \"__current_case__\": 0, \"ontology_args\": {\"ontology\": \"go\", \"__current_case__\": 0, \"slim_down\": false}}, \"qthreshold\": \"2\", \"samps\": {\"__class__\": \"ConnectedValue\"}, \"__page__\": null, \"__rerun_remap_job_id__\": null}", + "tool_version": "2.0.2+galaxy0", + "type": "tool", + "uuid": "ea520b67-0287-45b9-896e-5e98dfc6e206", + "when": null, + "workflow_outputs": [ + { + "label": "metaQuantome filtered file", + "output_name": "outfile", + "uuid": "5dda4a02-284f-46b9-a77a-a038e004e8c6" + } + ] + }, + "6": { + "annotation": "", + "content_id": "toolshed.g2.bx.psu.edu/repos/galaxyp/metaquantome_stat/metaquantome_stat/2.0.2+galaxy0", + "errors": null, + "id": 6, + "input_connections": { + "file": { + "id": 5, + "output_name": "outfile" + }, + "samps": { + "id": 1, + "output_name": "samples_file" + } + }, + "inputs": [], + "label": null, + "name": "metaQuantome: stat", + "outputs": [ + { + "name": "outfile", + "type": "tabular" + } + ], + "position": { + "left": 636.0333251953125, + "top": 139.1666717529297 + }, + "post_job_actions": {}, + "tool_id": "toolshed.g2.bx.psu.edu/repos/galaxyp/metaquantome_stat/metaquantome_stat/2.0.2+galaxy0", + "tool_shed_repository": { + "changeset_revision": "b9d453dca8d3", + "name": "metaquantome_stat", + "owner": "galaxyp", + "tool_shed": "toolshed.g2.bx.psu.edu" + }, + "tool_state": "{\"control_group\": \"T2\", \"file\": {\"__class__\": \"ConnectedValue\"}, \"mode_args\": {\"mode\": \"f\", \"__current_case__\": 0, \"ontology_args\": {\"ontology\": \"go\", \"__current_case__\": 0, \"slim_down\": false}}, \"paired\": true, \"parametric\": \"True\", \"samps\": {\"__class__\": \"ConnectedValue\"}, \"__page__\": null, \"__rerun_remap_job_id__\": null}", + "tool_version": "2.0.2+galaxy0", + "type": "tool", + "uuid": "2c6fbe47-92f7-4664-aca7-f3b2e704ad18", + "when": null, + "workflow_outputs": [ + { + "label": "metaQuantome stats file", + "output_name": "outfile", + "uuid": "da280c5f-241d-4c16-9dc2-15afe48ccd9c" + } + ] + }, + "7": { + "annotation": "", + "content_id": "toolshed.g2.bx.psu.edu/repos/galaxyp/metaquantome_viz/metaquantome_viz/2.0.2+galaxy0", + "errors": null, + "id": 7, + "input_connections": { + "infile": { + "id": 6, + "output_name": "outfile" + }, + "samps": { + "id": 6, + "output_name": "outfile" + } + }, + "inputs": [], + "label": "T2-Bar-Plot", + "name": "metaQuantome: visualize", + "outputs": [ + { + "name": "wrapped_outfile", + "type": "html" + }, + { + "name": "plotdata", + "type": "tabular" + } + ], + "position": { + "left": 960, + "top": 0.0 + }, + "post_job_actions": {}, + "tool_id": "toolshed.g2.bx.psu.edu/repos/galaxyp/metaquantome_viz/metaquantome_viz/2.0.2+galaxy0", + "tool_shed_repository": { + "changeset_revision": "8bd7734309f6", + "name": "metaquantome_viz", + "owner": "galaxyp", + "tool_shed": "toolshed.g2.bx.psu.edu" + }, + "tool_state": "{\"height\": null, \"infile\": {\"__class__\": \"ConnectedValue\"}, \"mode_args\": {\"mode\": \"f\", \"__current_case__\": 0, \"ontology\": \"go\", \"plot\": {\"plottype\": \"bar\", \"__current_case__\": 0, \"meancol\": \"T2_mean\", \"nterms\": \"5\", \"target_onto\": \"mf\", \"barcol\": \"2\"}}, \"samps\": {\"__class__\": \"ConnectedValue\"}, \"width\": null, \"__page__\": null, \"__rerun_remap_job_id__\": null}", + "tool_version": "2.0.2+galaxy0", + "type": "tool", + "uuid": "3fc0f0ad-f2e7-4425-be1c-11b6ea8fb2f5", + "when": null, + "workflow_outputs": [ + { + "label": "Bar plot data for sample T2", + "output_name": "plotdata", + "uuid": "37958e59-30ee-40af-a7e6-6543ab4d5cda" + }, + { + "label": "Wrapped outfile for sample T2", + "output_name": "wrapped_outfile", + "uuid": "689d104d-aa7a-46c3-b336-1995f587cf84" + } + ] + }, + "8": { + "annotation": "", + "content_id": "toolshed.g2.bx.psu.edu/repos/galaxyp/metaquantome_viz/metaquantome_viz/2.0.2+galaxy0", + "errors": null, + "id": 8, + "input_connections": { + "infile": { + "id": 6, + "output_name": "outfile" + }, + "samps": { + "id": 1, + "output_name": "samples_file" + } + }, + "inputs": [], + "label": "T4-Bar-Plot", + "name": "metaQuantome: visualize", + "outputs": [ + { + "name": "wrapped_outfile", + "type": "html" + }, + { + "name": "plotdata", + "type": "tabular" + } + ], + "position": { + "left": 976.490028561959, + "top": 329.75081678818736 + }, + "post_job_actions": {}, + "tool_id": "toolshed.g2.bx.psu.edu/repos/galaxyp/metaquantome_viz/metaquantome_viz/2.0.2+galaxy0", + "tool_shed_repository": { + "changeset_revision": "8bd7734309f6", + "name": "metaquantome_viz", + "owner": "galaxyp", + "tool_shed": "toolshed.g2.bx.psu.edu" + }, + "tool_state": "{\"height\": null, \"infile\": {\"__class__\": \"ConnectedValue\"}, \"mode_args\": {\"mode\": \"f\", \"__current_case__\": 0, \"ontology\": \"go\", \"plot\": {\"plottype\": \"bar\", \"__current_case__\": 0, \"meancol\": \"T4_mean\", \"nterms\": \"5\", \"target_onto\": \"mf\", \"barcol\": \"2\"}}, \"samps\": {\"__class__\": \"ConnectedValue\"}, \"width\": null, \"__page__\": null, \"__rerun_remap_job_id__\": null}", + "tool_version": "2.0.2+galaxy0", + "type": "tool", + "uuid": "0bc77e55-8872-47f4-a4b7-b19424daaaf4", + "when": null, + "workflow_outputs": [ + { + "label": "Bar plot data for sample T4", + "output_name": "plotdata", + "uuid": "0ed3f789-1d9a-446a-b23c-d8504fd65a90" + }, + { + "label": "Wrapped outfile for sample T4", + "output_name": "wrapped_outfile", + "uuid": "9dc116e1-fab5-4ef8-91e5-dc697ab54b50" + } + ] + }, + "9": { + "annotation": "", + "content_id": "toolshed.g2.bx.psu.edu/repos/galaxyp/metaquantome_viz/metaquantome_viz/2.0.2+galaxy0", + "errors": null, + "id": 9, + "input_connections": { + "infile": { + "id": 6, + "output_name": "outfile" + }, + "samps": { + "id": 1, + "output_name": "samples_file" + } + }, + "inputs": [], + "label": "T7-Bar-Plot", + "name": "metaQuantome: visualize", + "outputs": [ + { + "name": "wrapped_outfile", + "type": "html" + }, + { + "name": "plotdata", + "type": "tabular" + } + ], + "position": { + "left": 978.40625, + "top": 690.7353795776368 + }, + "post_job_actions": {}, + "tool_id": "toolshed.g2.bx.psu.edu/repos/galaxyp/metaquantome_viz/metaquantome_viz/2.0.2+galaxy0", + "tool_shed_repository": { + "changeset_revision": "8bd7734309f6", + "name": "metaquantome_viz", + "owner": "galaxyp", + "tool_shed": "toolshed.g2.bx.psu.edu" + }, + "tool_state": "{\"height\": null, \"infile\": {\"__class__\": \"ConnectedValue\"}, \"mode_args\": {\"mode\": \"f\", \"__current_case__\": 0, \"ontology\": \"go\", \"plot\": {\"plottype\": \"bar\", \"__current_case__\": 0, \"meancol\": \"T7_mean\", \"nterms\": \"5\", \"target_onto\": \"mf\", \"barcol\": \"2\"}}, \"samps\": {\"__class__\": \"ConnectedValue\"}, \"width\": null, \"__page__\": null, \"__rerun_remap_job_id__\": null}", + "tool_version": "2.0.2+galaxy0", + "type": "tool", + "uuid": "0d99230f-6eb0-4372-b9ba-ef3529daa483", + "when": null, + "workflow_outputs": [ + { + "label": "Bar plot data for sample T7", + "output_name": "plotdata", + "uuid": "374b2a2a-2f33-4197-9f97-bde4103a48f7" + }, + { + "label": "Wrapped outfile for sample T7", + "output_name": "wrapped_outfile", + "uuid": "c97bfa5e-5d25-4143-9c92-d55577b14cb1" + } + ] + }, + "10": { + "annotation": "", + "content_id": "toolshed.g2.bx.psu.edu/repos/galaxyp/metaquantome_viz/metaquantome_viz/2.0.2+galaxy0", + "errors": null, + "id": 10, + "input_connections": { + "infile": { + "id": 6, + "output_name": "outfile" + }, + "samps": { + "id": 1, + "output_name": "samples_file" + } + }, + "inputs": [], + "label": "T7-T2-Volcano-Plot", + "name": "metaQuantome: visualize", + "outputs": [ + { + "name": "wrapped_outfile", + "type": "html" + }, + { + "name": "plotdata", + "type": "tabular" + } + ], + "position": { + "left": 1330.040750288969, + "top": 210.9459581914276 + }, + "post_job_actions": {}, + "tool_id": "toolshed.g2.bx.psu.edu/repos/galaxyp/metaquantome_viz/metaquantome_viz/2.0.2+galaxy0", + "tool_shed_repository": { + "changeset_revision": "8bd7734309f6", + "name": "metaquantome_viz", + "owner": "galaxyp", + "tool_shed": "toolshed.g2.bx.psu.edu" + }, + "tool_state": "{\"height\": null, \"infile\": {\"__class__\": \"ConnectedValue\"}, \"mode_args\": {\"mode\": \"f\", \"__current_case__\": 0, \"ontology\": \"go\", \"plot\": {\"plottype\": \"volcano\", \"__current_case__\": 1, \"fc_name\": \"log2fc_T7_over_T2\", \"fc_corr_p\": \"corrected_p_T7_over_T2\", \"textannot\": \"id\", \"flip_fc\": false, \"gosplit\": true}}, \"samps\": {\"__class__\": \"ConnectedValue\"}, \"width\": null, \"__page__\": null, \"__rerun_remap_job_id__\": null}", + "tool_version": "2.0.2+galaxy0", + "type": "tool", + "uuid": "721c0ffa-e669-4dc0-92a3-bfd6e0c30e82", + "when": null, + "workflow_outputs": [ + { + "label": "Wrapped outfile for T7 and T2", + "output_name": "wrapped_outfile", + "uuid": "cfedaf7d-9b05-4071-bc1f-91a8cd819385" + }, + { + "label": "Volcano plot data for T7 and T2", + "output_name": "plotdata", + "uuid": "ef3bca7b-9045-401a-8b22-3e5b089ff52b" + } + ] + }, + "11": { + "annotation": "", + "content_id": "toolshed.g2.bx.psu.edu/repos/galaxyp/metaquantome_viz/metaquantome_viz/2.0.2+galaxy0", + "errors": null, + "id": 11, + "input_connections": { + "infile": { + "id": 6, + "output_name": "outfile" + }, + "samps": { + "id": 1, + "output_name": "samples_file" + } + }, + "inputs": [], + "label": "T4-T2-Volcano-Plot", + "name": "metaQuantome: visualize", + "outputs": [ + { + "name": "wrapped_outfile", + "type": "html" + }, + { + "name": "plotdata", + "type": "tabular" + } + ], + "position": { + "left": 1264.390625, + "top": 525.7041295776368 + }, + "post_job_actions": {}, + "tool_id": "toolshed.g2.bx.psu.edu/repos/galaxyp/metaquantome_viz/metaquantome_viz/2.0.2+galaxy0", + "tool_shed_repository": { + "changeset_revision": "8bd7734309f6", + "name": "metaquantome_viz", + "owner": "galaxyp", + "tool_shed": "toolshed.g2.bx.psu.edu" + }, + "tool_state": "{\"height\": null, \"infile\": {\"__class__\": \"ConnectedValue\"}, \"mode_args\": {\"mode\": \"f\", \"__current_case__\": 0, \"ontology\": \"go\", \"plot\": {\"plottype\": \"volcano\", \"__current_case__\": 1, \"fc_name\": \"log2fc_T4_over_T2\", \"fc_corr_p\": \"corrected_p_T4_over_T2\", \"textannot\": \"id\", \"flip_fc\": false, \"gosplit\": true}}, \"samps\": {\"__class__\": \"ConnectedValue\"}, \"width\": null, \"__page__\": null, \"__rerun_remap_job_id__\": null}", + "tool_version": "2.0.2+galaxy0", + "type": "tool", + "uuid": "e9d8930e-1110-4794-bc9d-bf307dc1b049", + "when": null, + "workflow_outputs": [ + { + "label": "Volcano plot data for T4 and T2", + "output_name": "plotdata", + "uuid": "109c1dec-29c9-476e-9e83-6c7ea6ac13db" + }, + { + "label": "Wrapped outfile for T4 and T2", + "output_name": "wrapped_outfile", + "uuid": "61ae75a5-e486-4063-8018-dde23894f6a7" + } + ] + } + }, + "tags": [ + "proteomics", + "name:microGalaxy" + ], + "uuid": "14b3407e-d303-4152-973b-2a2486e785c9", + "version": 3 +} \ No newline at end of file From 28ee074dc1be6c67c87a9428a3b764b63e2847cc Mon Sep 17 00:00:00 2001 From: Clea Siguret Date: Tue, 10 Dec 2024 15:18:04 +0100 Subject: [PATCH 3/6] clean repo --- .../metaproteomics-gtn/.dockstore.yml | 19 - .../metaproteomics-gtn/CHANGELOG.md | 4 - .../proteomics/metaproteomics-gtn/README.md | 6 - .../metaproteomics_gtn_wf-tests.yml | 60 -- .../metaproteomics_gtn_wf.ga | 724 ------------------ 5 files changed, 813 deletions(-) delete mode 100644 workflows/proteomics/metaproteomics-gtn/.dockstore.yml delete mode 100644 workflows/proteomics/metaproteomics-gtn/CHANGELOG.md delete mode 100644 workflows/proteomics/metaproteomics-gtn/README.md delete mode 100644 workflows/proteomics/metaproteomics-gtn/metaproteomics_gtn_wf-tests.yml delete mode 100644 workflows/proteomics/metaproteomics-gtn/metaproteomics_gtn_wf.ga diff --git a/workflows/proteomics/metaproteomics-gtn/.dockstore.yml b/workflows/proteomics/metaproteomics-gtn/.dockstore.yml deleted file mode 100644 index 3f2a7c71b..000000000 --- a/workflows/proteomics/metaproteomics-gtn/.dockstore.yml +++ /dev/null @@ -1,19 +0,0 @@ -version: 1.2 -workflows: -- name: main - subclass: Galaxy - publish: true - primaryDescriptorPath: /metaproteomics_gtn_wf.ga - testParameterFiles: - - /metaproteomics_gtn_wf-tests.yml - authors: - - name: Timothy Griffin - orcid: 0000-0001-6801-2559 - - name: Pratik Jagtap - orcid: 0000-0003-0984-0973 - - name: James Johnson - identifier: https://github.com/jj-umn - - name: Clemens Blank - orcid: 0000-0002-1726-2256 - - name: Subina Mehta - orcid: 0000-0001-9818-0537 diff --git a/workflows/proteomics/metaproteomics-gtn/CHANGELOG.md b/workflows/proteomics/metaproteomics-gtn/CHANGELOG.md deleted file mode 100644 index 7f923112e..000000000 --- a/workflows/proteomics/metaproteomics-gtn/CHANGELOG.md +++ /dev/null @@ -1,4 +0,0 @@ -# Changelog - -## [0.1] 2024-12-10 -First release. \ No newline at end of file diff --git a/workflows/proteomics/metaproteomics-gtn/README.md b/workflows/proteomics/metaproteomics-gtn/README.md deleted file mode 100644 index cf16feba2..000000000 --- a/workflows/proteomics/metaproteomics-gtn/README.md +++ /dev/null @@ -1,6 +0,0 @@ -# MetaProteomics Tutorial -In this metaproteomics worflow, we will identify expressed proteins from a complex bacterial community sample. For this MS/MS data will be matched to peptide sequences provided through a FASTA file. - -Metaproteomics is the large-scale characterization of the entire protein complement of environmental microbiota at a given point in time. It has the potential to unravel the mechanistic details of microbial interactions with the host / environment by analyzing the functional dynamics of the microbiome. - -More background on this workflow can be found in the [Metaproteomics tutorial](https://galaxyproject.github.io/training-material//topics/proteomics/tutorials/metaproteomics/tutorial.html) \ No newline at end of file diff --git a/workflows/proteomics/metaproteomics-gtn/metaproteomics_gtn_wf-tests.yml b/workflows/proteomics/metaproteomics-gtn/metaproteomics_gtn_wf-tests.yml deleted file mode 100644 index 81d34529e..000000000 --- a/workflows/proteomics/metaproteomics-gtn/metaproteomics_gtn_wf-tests.yml +++ /dev/null @@ -1,60 +0,0 @@ -- doc: Test outline for metaproteomics_gtn_wf.ga - job: - Sixgill generated protein FASTA File: - class: File - path: https://zenodo.org/records/839701/files/FASTA_Bering_Strait_Trimmed_metapeptides_cRAP.fasta - filetype: fasta - Dataset collection of MGF files: - class: Collection - collection_type: list - elements: - - class: File - identifier: 2016_Jan_12_QE2_45.mgf - location: https://zenodo.org/records/839701/files/2016_Jan_12_QE2_45.mgf - - class: File - identifier: 2016_Jan_12_QE2_46.mgf - location: https://zenodo.org/records/839701/files/2016_Jan_12_QE2_46.mgf - - class: File - identifier: 2016_Jan_12_QE2_47.mgf - location: https://zenodo.org/records/839701/files/2016_Jan_12_QE2_47.mgf - Gene Ontology Terms (Selected): - class: File - path: https://zenodo.org/records/839701/files/Gene_Ontology_Terms.tabular - filetype: tabular - outputs: - 'Peptide Shaker on input dataset(s): PSM report': - asserts: - has_text: - text: "AAs Before" - Query Tabular output: - asserts: - has_text: - text: "AADGHTMHFDVITGEK" - 'Unipept on selected peptides: pept2prot output': - asserts: - has_text: - text: "#peptide" - Taxonomy table: - asserts: - has_text: - text: "superkingdom" - GO terms: - asserts: - has_text: - text: "GO:" - Combined table of all genera, PSMs and peptides: - asserts: - has_text: - text: "PSMs" - GO Biological Processes: - asserts: - has_text: - text: "translation" - GO Cellular Localizations: - asserts: - has_text: - text: "cytoplasm" - GO Molecular Functions: - asserts: - has_text: - text: "ATP binding" diff --git a/workflows/proteomics/metaproteomics-gtn/metaproteomics_gtn_wf.ga b/workflows/proteomics/metaproteomics-gtn/metaproteomics_gtn_wf.ga deleted file mode 100644 index 25600d129..000000000 --- a/workflows/proteomics/metaproteomics-gtn/metaproteomics_gtn_wf.ga +++ /dev/null @@ -1,724 +0,0 @@ -{ - "a_galaxy_workflow": "true", - "annotation": "This workflow identifies expressed proteins from a complex bacterial community sample. For this, MS/MS data will be matched to peptide sequences provided through a FASTA file.\n", - "comments": [], - "creator": [ - { - "class": "Person", - "identifier": "https://orcid.org/0000-0001-6801-2559", - "name": "Timothy Griffin" - }, - { - "class": "Person", - "identifier": "https://orcid.org/0000-0003-0984-0973", - "name": "Pratik Jagtap" - }, - { - "class": "Person", - "identifier": "https://github.com/jj-umn", - "name": "James Johnson" - }, - { - "class": "Person", - "identifier": "https://orcid.org/0000-0002-1726-2256", - "name": "Clemens Blank" - }, - { - "class": "Person", - "identifier": "https://orcid.org/0000-0001-9818-0537", - "name": "Subina Mehta" - } - ], - "format-version": "0.1", - "license": "MIT", - "release": "0.1", - "name": "Metaproteomics workflow", - "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": "FASTA file consisting of trimmed peptides, given as a protein database input for Search GUI", - "content_id": null, - "errors": null, - "id": 0, - "input_connections": {}, - "inputs": [ - { - "description": "FASTA file consisting of trimmed peptides, given as a protein database input for Search GUI", - "name": "Sixgill generated protein FASTA File" - } - ], - "label": "Sixgill generated protein FASTA File", - "name": "Input dataset", - "outputs": [], - "position": { - "left": 0, - "top": 0.5937504090177583 - }, - "tool_id": null, - "tool_state": "{\"optional\": false, \"tag\": null}", - "tool_version": null, - "type": "data_input", - "uuid": "4c5ba166-09de-4e95-b193-8cddb52d93fb", - "when": null, - "workflow_outputs": [] - }, - "1": { - "annotation": "Collection of MS/MS spectral summary files", - "content_id": null, - "errors": null, - "id": 1, - "input_connections": {}, - "inputs": [ - { - "description": "Collection of MS/MS spectral summary files", - "name": "Dataset collection of MGF files" - } - ], - "label": "Dataset collection of MGF files", - "name": "Input dataset collection", - "outputs": [], - "position": { - "left": 2.84375, - "top": 159.53125 - }, - "tool_id": null, - "tool_state": "{\"optional\": false, \"tag\": null, \"collection_type\": \"list\"}", - "tool_version": null, - "type": "data_collection_input", - "uuid": "a68cee17-c1cd-4bd2-9a28-1d12e5aecefe", - "when": null, - "workflow_outputs": [] - }, - "2": { - "annotation": "List of Gene Ontology terms including biological processes, molecular functions and cellular components", - "content_id": null, - "errors": null, - "id": 2, - "input_connections": {}, - "inputs": [ - { - "description": "List of Gene Ontology terms including biological processes, molecular functions and cellular components", - "name": "Gene Ontology Terms (Selected)" - } - ], - "label": "Gene Ontology Terms (Selected)", - "name": "Input dataset", - "outputs": [], - "position": { - "left": 1209.3117556405728, - "top": 0 - }, - "tool_id": null, - "tool_state": "{\"optional\": false, \"tag\": null}", - "tool_version": null, - "type": "data_input", - "uuid": "09a667d2-66e9-4f41-947d-0000a1fbb88b", - "when": null, - "workflow_outputs": [] - }, - "3": { - "annotation": "Matches MS/MS peaks to peptide sequences", - "content_id": "toolshed.g2.bx.psu.edu/repos/galaxyp/peptideshaker/search_gui/3.3.10.1", - "errors": null, - "id": 3, - "input_connections": { - "input_database": { - "id": 0, - "output_name": "output" - }, - "peak_lists": { - "id": 1, - "output_name": "output" - } - }, - "inputs": [], - "label": "Search GUI", - "name": "Search GUI", - "outputs": [ - { - "name": "searchgui_results", - "type": "searchgui_archive" - } - ], - "position": { - "left": 228.84373957916367, - "top": 14.484374745319764 - }, - "post_job_actions": {}, - "tool_id": "toolshed.g2.bx.psu.edu/repos/galaxyp/peptideshaker/search_gui/3.3.10.1", - "tool_shed_repository": { - "changeset_revision": "7fdd9119cc4f", - "name": "peptideshaker", - "owner": "galaxyp", - "tool_shed": "toolshed.g2.bx.psu.edu" - }, - "tool_state": "{\"advanced_options\": {\"searchgui_advanced\": {\"searchgui_advanced_selector\": \"basic\", \"__current_case__\": 0}, \"xtandem\": {\"xtandem_advanced\": \"yes\", \"__current_case__\": 1, \"xtandem_npeaks\": \"50\", \"xtandem_min_peaks\": \"15\", \"xtandem_min_frag_mz\": \"200\", \"xtandem_min_prec_mass\": \"200\", \"xtandem_noise_suppr\": true, \"xtandem_dynamic_range\": \"100\", \"xtandem_quick_acetyl\": false, \"xtandem_quick_pyro\": false, \"xtandem_stp_bias\": false, \"xtandem_evalue\": \"100.0\", \"xtandem_output_proteins\": false, \"xtandem_output_sequences\": false, \"xtandem_output_spectra\": true, \"xtandem_refine\": {\"xtandem_refine_selector\": \"no\", \"__current_case__\": 0}}, \"omssa\": {\"omssa_advanced\": \"no\", \"__current_case__\": 0}, \"msgf\": {\"msgf_advanced\": \"no\", \"__current_case__\": 0}, \"ms_amanda\": {\"ms_amanda_advanced\": \"no\", \"__current_case__\": 0}, \"tide\": {\"tide_advanced\": \"no\", \"__current_case__\": 0}, \"myrimatch\": {\"myrimatch_advanced\": \"no\", \"__current_case__\": 0}, \"comet\": {\"comet_advanced\": \"no\", \"__current_case__\": 0}, \"directtag\": {\"directtag_advanced\": \"no\", \"__current_case__\": 0}, \"novor\": {\"novor_advanced\": \"no\", \"__current_case__\": 0}}, \"input_database\": {\"__class__\": \"ConnectedValue\"}, \"peak_lists\": {\"__class__\": \"ConnectedValue\"}, \"precursor_options\": {\"precursor_ion_tol_units\": \"1\", \"precursor_ion_tol\": \"10.0\", \"fragment_tol_units\": \"0\", \"fragment_tol\": \"0.2\", \"min_charge\": \"2\", \"max_charge\": \"6\", \"forward_ion\": \"b\", \"reverse_ion\": \"y\", \"min_isotope\": \"0\", \"max_isotope\": \"1\"}, \"protein_database_options\": {\"create_decoy\": true, \"use_gene_mapping\": false, \"update_gene_mapping\": false}, \"protein_digest_options\": {\"digestion\": {\"cleavage\": \"0\", \"__current_case__\": 0, \"digests\": [{\"__index__\": 0, \"enzyme\": \"Trypsin\", \"missed_cleavages\": \"2\"}]}}, \"protein_modification_options\": {\"fixed_modifications\": [\"Carbamidomethylation of C\"], \"variable_modifications\": [\"Oxidation of M\"]}, \"search_engines_options\": {\"engines\": [\"X!Tandem\"]}, \"__page__\": null, \"__rerun_remap_job_id__\": null}", - "tool_version": "3.3.10.1", - "type": "tool", - "uuid": "050f3ea1-0f60-4f88-9a17-d8d328f15bb5", - "when": null, - "workflow_outputs": [ - { - "label": "Search GUI on input dataset(s)", - "output_name": "searchgui_results", - "uuid": "115e42ab-4f6c-4664-b399-c8c3a54e9b6f" - } - ] - }, - "4": { - "annotation": "Post-processing tool for Search GUI output", - "content_id": "toolshed.g2.bx.psu.edu/repos/galaxyp/peptideshaker/peptide_shaker/1.16.36.3", - "errors": null, - "id": 4, - "input_connections": { - "searchgui_input": { - "id": 3, - "output_name": "searchgui_results" - } - }, - "inputs": [], - "label": null, - "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": 312.9375055367535, - "top": 272.4207633135564 - }, - "post_job_actions": { - "HideDatasetActionoutput_peptides": { - "action_arguments": {}, - "action_type": "HideDatasetAction", - "output_name": "output_peptides" - }, - "HideDatasetActionoutput_proteins": { - "action_arguments": {}, - "action_type": "HideDatasetAction", - "output_name": "output_proteins" - } - }, - "tool_id": "toolshed.g2.bx.psu.edu/repos/galaxyp/peptideshaker/peptide_shaker/1.16.36.3", - "tool_shed_repository": { - "changeset_revision": "7fdd9119cc4f", - "name": "peptideshaker", - "owner": "galaxyp", - "tool_shed": "toolshed.g2.bx.psu.edu" - }, - "tool_state": "{\"contact_options\": {\"contact_options_selector\": \"no\", \"__current_case__\": 0}, \"exporting_options\": {\"mzidentml_conditional\": {\"mzidentml_creation\": true, \"__current_case__\": 0, \"include_sequences\": false}, \"zip_conditional\": {\"zip_output_boolean\": false, \"__current_case__\": 0, \"export_cps\": false}, \"output_reports\": [\"3\", \"6\", \"9\", \"0\"]}, \"filtering_options\": {\"filtering_options_selector\": \"yes\", \"__current_case__\": 1, \"min_peptide_length\": \"6\", \"max_peptide_length\": \"30\", \"max_precursor_error\": \"10.0\", \"max_precursor_error_type\": \"0\", \"exclude_unknown_ptms\": true}, \"processing_options\": {\"processing_options_selector\": \"no\", \"__current_case__\": 0}, \"searchgui_input\": {\"__class__\": \"ConnectedValue\"}, \"__page__\": null, \"__rerun_remap_job_id__\": null}", - "tool_version": "1.16.36.3", - "type": "tool", - "uuid": "c74f9b66-8ba2-4c99-8560-570bb082ffc5", - "when": null, - "workflow_outputs": [ - { - "label": "Certificate of analysis", - "output_name": "output_certificate", - "uuid": "65559b47-4b7f-45e7-8743-e568346c602a" - }, - { - "label": "Peptide Shaker on input dataset(s): mzidentML file", - "output_name": "mzidentML", - "uuid": "d144ed43-b930-41f2-a492-fb1c1823d9b7" - }, - { - "label": "Peptide Shaker on input dataset(s): PSM report", - "output_name": "output_psm", - "uuid": "040bfa41-e7c2-405f-b3ff-a4ff1a7b1899" - } - ] - }, - "5": { - "annotation": "Generates a list of peptide sequences from the PSM report", - "content_id": "toolshed.g2.bx.psu.edu/repos/iuc/query_tabular/query_tabular/3.0.0", - "errors": null, - "id": 5, - "input_connections": { - "tables_0|table": { - "id": 4, - "output_name": "output_psm" - } - }, - "inputs": [ - { - "description": "runtime parameter for tool Query Tabular", - "name": "add_to_database" - } - ], - "label": "Query Tabular Select Peptides", - "name": "Query Tabular", - "outputs": [ - { - "name": "output", - "type": "tabular" - } - ], - "position": { - "left": 646.875, - "top": 140.671875 - }, - "post_job_actions": { - "HideDatasetActionsqlitedb": { - "action_arguments": {}, - "action_type": "HideDatasetAction", - "output_name": "sqlitedb" - } - }, - "tool_id": "toolshed.g2.bx.psu.edu/repos/iuc/query_tabular/query_tabular/3.0.0", - "tool_shed_repository": { - "changeset_revision": "33d61c89fb8d", - "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\": \"no\", \"__current_case__\": 1}, \"save_db\": false, \"sqlquery\": \"SELECT distinct sequence \\nFROM psm \\nWHERE confidence >= 95 \\nORDER BY sequence\", \"tables\": [{\"__index__\": 0, \"table\": {\"__class__\": \"ConnectedValue\"}, \"input_opts\": {\"linefilters\": [{\"__index__\": 0, \"filter\": {\"filter_type\": \"regex\", \"__current_case__\": 6, \"regex_pattern\": \"^\\\\d\", \"regex_action\": \"include_match\"}}]}, \"tbl_opts\": {\"table_name\": \"psm\", \"column_names_from_first_line\": false, \"col_names\": \"id,,sequence,,,,,,,,,,,,,,,,,,,,confidence,validation\", \"load_named_columns\": true, \"pkey_autoincr\": \"\", \"indexes\": []}}], \"workdb\": \"workdb.sqlite\", \"__page__\": null, \"__rerun_remap_job_id__\": null}", - "tool_version": "3.0.0", - "type": "tool", - "uuid": "48b2b26c-90c2-4474-858b-4823e25ffb0b", - "when": null, - "workflow_outputs": [ - { - "label": "Query Tabular output", - "output_name": "output", - "uuid": "17ba215c-9efa-4b7c-bf8f-8404a36bfaea" - } - ] - }, - "6": { - "annotation": "Matches the list of peptides with the correlated Gene Ontology terms", - "content_id": "toolshed.g2.bx.psu.edu/repos/galaxyp/unipept/unipept/4.3.0", - "errors": null, - "id": 6, - "input_connections": { - "peptide_src|input_tsv": { - "id": 5, - "output_name": "output" - } - }, - "inputs": [ - { - "description": "runtime parameter for tool Unipept", - "name": "peptide_src" - } - ], - "label": "Unipept pept2prot", - "name": "Unipept", - "outputs": [ - { - "name": "output_tsv", - "type": "tabular" - } - ], - "position": { - "left": 915.5001115978775, - "top": 37.078122777010826 - }, - "post_job_actions": {}, - "tool_id": "toolshed.g2.bx.psu.edu/repos/galaxyp/unipept/unipept/4.3.0", - "tool_shed_repository": { - "changeset_revision": "9aaa46d45472", - "name": "unipept", - "owner": "galaxyp", - "tool_shed": "toolshed.g2.bx.psu.edu" - }, - "tool_state": "{\"peptide_src\": {\"fmt\": \"tabular\", \"__current_case__\": 1, \"input_tsv\": {\"__class__\": \"ConnectedValue\"}, \"column\": \"1\"}, \"selected_outputs\": \"tsv\", \"strict\": false, \"unipept\": {\"api\": \"pept2prot\", \"__current_case__\": 2, \"equate_il\": true, \"extra\": true}, \"__page__\": null, \"__rerun_remap_job_id__\": null}", - "tool_version": "4.3.0", - "type": "tool", - "uuid": "57678873-6623-4ac0-9b86-697fa4246c11", - "when": null, - "workflow_outputs": [ - { - "label": "Unipept on selected peptides: pept2prot output", - "output_name": "output_tsv", - "uuid": "2fb042a4-8497-40d5-94d2-2ad47d04ab52" - } - ] - }, - "7": { - "annotation": "Returns the taxonomic lowest common ancestor for each peptide", - "content_id": "toolshed.g2.bx.psu.edu/repos/galaxyp/unipept/unipept/4.3.0", - "errors": null, - "id": 7, - "input_connections": { - "peptide_src|input_tsv": { - "id": 5, - "output_name": "output" - } - }, - "inputs": [ - { - "description": "runtime parameter for tool Unipept", - "name": "peptide_src" - } - ], - "label": "Unipept lca", - "name": "Unipept", - "outputs": [ - { - "name": "output_json", - "type": "d3_hierarchy" - }, - { - "name": "output_tsv", - "type": "tabular" - } - ], - "position": { - "left": 912.359375, - "top": 281.984375 - }, - "post_job_actions": {}, - "tool_id": "toolshed.g2.bx.psu.edu/repos/galaxyp/unipept/unipept/4.3.0", - "tool_shed_repository": { - "changeset_revision": "9aaa46d45472", - "name": "unipept", - "owner": "galaxyp", - "tool_shed": "toolshed.g2.bx.psu.edu" - }, - "tool_state": "{\"peptide_src\": {\"fmt\": \"tabular\", \"__current_case__\": 1, \"input_tsv\": {\"__class__\": \"ConnectedValue\"}, \"column\": \"1\"}, \"selected_outputs\": [\"tsv\", \"json\", \"ec_json\"], \"strict\": false, \"unipept\": {\"api\": \"pept2lca\", \"__current_case__\": 0, \"equate_il\": false, \"extra\": false, \"names\": true, \"allfields\": false}, \"__page__\": null, \"__rerun_remap_job_id__\": null}", - "tool_version": "4.3.0", - "type": "tool", - "uuid": "98103c15-f03d-4a06-b16a-2187fc31cab4", - "when": null, - "workflow_outputs": [ - { - "label": "JSON taxonomy tree", - "output_name": "output_json", - "uuid": "6cb3ba22-5fb6-42cb-94ec-12697ed06377" - }, - { - "label": "Taxonomy table", - "output_name": "output_tsv", - "uuid": "80ba446f-06bc-49f0-ae46-44fab0b2d10f" - } - ] - }, - "8": { - "annotation": "", - "content_id": "toolshed.g2.bx.psu.edu/repos/iuc/query_tabular/query_tabular/3.0.0", - "errors": null, - "id": 8, - "input_connections": { - "tables_0|table": { - "id": 2, - "output_name": "output" - }, - "tables_1|table": { - "id": 6, - "output_name": "output_tsv" - }, - "tables_2|table": { - "id": 6, - "output_name": "output_tsv" - }, - "tables_3|table": { - "id": 4, - "output_name": "output_psm" - } - }, - "inputs": [ - { - "description": "runtime parameter for tool Query Tabular", - "name": "add_to_database" - } - ], - "label": "Go Pop2Prot DB", - "name": "Query Tabular", - "outputs": [ - { - "name": "sqlitedb", - "type": "sqlite" - }, - { - "name": "output", - "type": "tabular" - } - ], - "position": { - "left": 922.890625, - "top": 546.59375 - }, - "post_job_actions": { - "RenameDatasetActionoutput": { - "action_arguments": { - "newname": "Peptides and PSMs" - }, - "action_type": "RenameDatasetAction", - "output_name": "output" - } - }, - "tool_id": "toolshed.g2.bx.psu.edu/repos/iuc/query_tabular/query_tabular/3.0.0", - "tool_shed_repository": { - "changeset_revision": "33d61c89fb8d", - "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\": \"35\"}, \"save_db\": true, \"sqlquery\": \"SELECT sequence as \\\"peptide\\\", count(id) as \\\"PSMs\\\"\\nFROM bering_psms\\nWHERE confidence >= 95\\nGROUP BY sequence\\nORDER BY sequence\\n\", \"tables\": [{\"__index__\": 0, \"table\": {\"__class__\": \"ConnectedValue\"}, \"input_opts\": {\"linefilters\": [{\"__index__\": 0, \"filter\": {\"filter_type\": \"skip\", \"__current_case__\": 0, \"skip_lines\": \"1\"}}]}, \"tbl_opts\": {\"table_name\": \"go\", \"column_names_from_first_line\": false, \"col_names\": \"aspect,go_id,description\", \"load_named_columns\": false, \"pkey_autoincr\": \"\", \"indexes\": [{\"__index__\": 0, \"unique\": false, \"index_columns\": \"aspect,go_id\"}]}}, {\"__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}}]}, \"tbl_opts\": {\"table_name\": \"bering_prot\", \"column_names_from_first_line\": false, \"col_names\": \"id,peptide,uniprot_id,taxon_id,taxon_name,ec_references,go_references,refseq_ids,refseq_protein_ids,insdc_ids,insdc_protein_ids\", \"load_named_columns\": false, \"pkey_autoincr\": \"\", \"indexes\": [{\"__index__\": 0, \"unique\": false, \"index_columns\": \"id,peptide\"}]}}, {\"__index__\": 2, \"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\": \"select_columns\", \"__current_case__\": 7, \"columns\": \"1,7\"}}, {\"__index__\": 3, \"filter\": {\"filter_type\": \"normalize\", \"__current_case__\": 9, \"columns\": \"2\", \"separator\": \" \"}}]}, \"tbl_opts\": {\"table_name\": \"bering_prot_go\", \"column_names_from_first_line\": false, \"col_names\": \"id,go_reference\", \"load_named_columns\": false, \"pkey_autoincr\": \"\", \"indexes\": [{\"__index__\": 0, \"unique\": false, \"index_columns\": \"go_reference,id\"}]}}, {\"__index__\": 3, \"table\": {\"__class__\": \"ConnectedValue\"}, \"input_opts\": {\"linefilters\": [{\"__index__\": 0, \"filter\": {\"filter_type\": \"regex\", \"__current_case__\": 6, \"regex_pattern\": \"^\\\\d\", \"regex_action\": \"include_match\"}}, {\"__index__\": 1, \"filter\": {\"filter_type\": \"select_columns\", \"__current_case__\": 7, \"columns\": \"1,3,23,24\"}}]}, \"tbl_opts\": {\"table_name\": \"bering_psms\", \"column_names_from_first_line\": false, \"col_names\": \"id,sequence,confidence,validation\", \"load_named_columns\": true, \"pkey_autoincr\": \"\", \"indexes\": [{\"__index__\": 0, \"unique\": false, \"index_columns\": \"sequence,id\"}]}}], \"workdb\": \"workdb.sqlite\", \"__page__\": null, \"__rerun_remap_job_id__\": null}", - "tool_version": "3.0.0", - "type": "tool", - "uuid": "684e9a81-02fe-421e-bcb3-14ec4697a2fc", - "when": null, - "workflow_outputs": [ - { - "label": "GO terms", - "output_name": "output", - "uuid": "29cfb124-bbfd-4a44-b3a8-684eab72d546" - }, - { - "label": "GO terms database in SQLite format", - "output_name": "sqlitedb", - "uuid": "61d4830c-4ec9-4b38-b586-2acdd540b16a" - } - ] - }, - "9": { - "annotation": "Combines all genera, PSMs and peptides into a single database", - "content_id": "toolshed.g2.bx.psu.edu/repos/iuc/query_tabular/query_tabular/3.0.0", - "errors": null, - "id": 9, - "input_connections": { - "tables_0|table": { - "id": 4, - "output_name": "output_psm" - }, - "tables_1|table": { - "id": 7, - "output_name": "output_tsv" - } - }, - "inputs": [ - { - "description": "runtime parameter for tool Query Tabular", - "name": "add_to_database" - } - ], - "label": "Genera | PSMs | Peptides", - "name": "Query Tabular", - "outputs": [ - { - "name": "output", - "type": "tabular" - } - ], - "position": { - "left": 914.1249399474883, - "top": 986.578160827765 - }, - "post_job_actions": { - "HideDatasetActionsqlitedb": { - "action_arguments": {}, - "action_type": "HideDatasetAction", - "output_name": "sqlitedb" - } - }, - "tool_id": "toolshed.g2.bx.psu.edu/repos/iuc/query_tabular/query_tabular/3.0.0", - "tool_shed_repository": { - "changeset_revision": "33d61c89fb8d", - "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\": \"35\"}, \"save_db\": false, \"sqlquery\": \"SELECT lca.genus,count(psm.sequence) as \\\"PSMs\\\",count(distinct psm.sequence) as \\\"DISTINCT PEPTIDES\\\" \\nFROM psm LEFT JOIN lca ON psm.sequence = lca.peptide \\nWHERE confidence >= 95 \\nGROUP BY lca.genus \\nORDER BY PSMs desc, 'DISTINCT PEPTIDES' desc\", \"tables\": [{\"__index__\": 0, \"table\": {\"__class__\": \"ConnectedValue\"}, \"input_opts\": {\"linefilters\": [{\"__index__\": 0, \"filter\": {\"filter_type\": \"regex\", \"__current_case__\": 6, \"regex_pattern\": \"^\\\\d\", \"regex_action\": \"include_match\"}}]}, \"tbl_opts\": {\"table_name\": \"psm\", \"column_names_from_first_line\": false, \"col_names\": \",,sequence,,,,,,,,,,,,,,,,,,,,confidence,validation\", \"load_named_columns\": true, \"pkey_autoincr\": \"\", \"indexes\": []}}, {\"__index__\": 1, \"table\": {\"__class__\": \"ConnectedValue\"}, \"input_opts\": {\"linefilters\": [{\"__index__\": 0, \"filter\": {\"filter_type\": \"regex\", \"__current_case__\": 6, \"regex_pattern\": \"#peptide\", \"regex_action\": \"exclude_match\"}}]}, \"tbl_opts\": {\"table_name\": \"lca\", \"column_names_from_first_line\": false, \"col_names\": \"peptide,,,,,,,,,,,,,,,,,,,,,genus\", \"load_named_columns\": true, \"pkey_autoincr\": \"\", \"indexes\": []}}], \"workdb\": \"workdb.sqlite\", \"__page__\": null, \"__rerun_remap_job_id__\": null}", - "tool_version": "3.0.0", - "type": "tool", - "uuid": "5a0f0694-71d9-4f2f-8e1b-77b684f9033f", - "when": null, - "workflow_outputs": [ - { - "label": "Combined table of all genera, PSMs and peptides", - "output_name": "output", - "uuid": "010131bc-ce84-4238-baec-3eac7dacd6a0" - } - ] - }, - "10": { - "annotation": "", - "content_id": "toolshed.g2.bx.psu.edu/repos/iuc/sqlite_to_tabular/sqlite_to_tabular/2.0.0", - "errors": null, - "id": 10, - "input_connections": { - "sqlitedb": { - "id": 8, - "output_name": "sqlitedb" - } - }, - "inputs": [], - "label": "GO Terms: Biological Processes", - "name": "SQLite to tabular", - "outputs": [ - { - "name": "query_results", - "type": "tabular" - } - ], - "position": { - "left": 1529.4054698421558, - "top": 108.10937290594494 - }, - "post_job_actions": { - "RenameDatasetActionquery_results": { - "action_arguments": { - "newname": "GO Terms: Biological Processes" - }, - "action_type": "RenameDatasetAction", - "output_name": "query_results" - } - }, - "tool_id": "toolshed.g2.bx.psu.edu/repos/iuc/sqlite_to_tabular/sqlite_to_tabular/2.0.0", - "tool_shed_repository": { - "changeset_revision": "b722161a845a", - "name": "sqlite_to_tabular", - "owner": "iuc", - "tool_shed": "toolshed.g2.bx.psu.edu" - }, - "tool_state": "{\"query_result\": {\"header\": \"yes\", \"__current_case__\": 0, \"header_prefix\": \"35\"}, \"sqlitedb\": {\"__class__\": \"ConnectedValue\"}, \"sqlquery\": \"SELECT go.description, \\ncount(distinct bering_psms.sequence) as \\\"bering_peptides\\\", count(distinct bering_psms.id) as \\\"bering_psms\\\" \\nFROM go JOIN bering_prot_go ON go.go_id = bering_prot_go.go_reference JOIN bering_prot on bering_prot_go.id = bering_prot.id JOIN bering_psms ON bering_prot.peptide = bering_psms.sequence\\nWHERE go.aspect = 'biological_process'\\nGROUP BY go.description\\nORDER BY bering_peptides desc,bering_psms desc\", \"__page__\": null, \"__rerun_remap_job_id__\": null}", - "tool_version": "2.0.0", - "type": "tool", - "uuid": "05a5928a-fd97-4c4a-af60-b99cf4dd04a1", - "when": null, - "workflow_outputs": [ - { - "label": "GO Biological Processes", - "output_name": "query_results", - "uuid": "89730292-7595-4b95-bed9-c8f11953c9d7" - } - ] - }, - "11": { - "annotation": "", - "content_id": "toolshed.g2.bx.psu.edu/repos/iuc/sqlite_to_tabular/sqlite_to_tabular/2.0.0", - "errors": null, - "id": 11, - "input_connections": { - "sqlitedb": { - "id": 8, - "output_name": "sqlitedb" - } - }, - "inputs": [], - "label": "GO Terms: Cellular Localization", - "name": "SQLite to tabular", - "outputs": [ - { - "name": "query_results", - "type": "tabular" - } - ], - "position": { - "left": 1542.390636968383, - "top": 408.18861741916913 - }, - "post_job_actions": { - "RenameDatasetActionquery_results": { - "action_arguments": { - "newname": "GO Terms: Cellular Localization" - }, - "action_type": "RenameDatasetAction", - "output_name": "query_results" - } - }, - "tool_id": "toolshed.g2.bx.psu.edu/repos/iuc/sqlite_to_tabular/sqlite_to_tabular/2.0.0", - "tool_shed_repository": { - "changeset_revision": "b722161a845a", - "name": "sqlite_to_tabular", - "owner": "iuc", - "tool_shed": "toolshed.g2.bx.psu.edu" - }, - "tool_state": "{\"query_result\": {\"header\": \"yes\", \"__current_case__\": 0, \"header_prefix\": \"35\"}, \"sqlitedb\": {\"__class__\": \"ConnectedValue\"}, \"sqlquery\": \"SELECT go.description, \\ncount(distinct bering_psms.sequence) as \\\"bering_peptides\\\", count(distinct bering_psms.id) as \\\"bering_psms\\\" \\nFROM go JOIN bering_prot_go ON go.go_id = bering_prot_go.go_reference JOIN bering_prot on bering_prot_go.id = bering_prot.id JOIN bering_psms ON bering_prot.peptide = bering_psms.sequence\\nWHERE go.aspect = 'cellular_component'\\nGROUP BY go.description\\nORDER BY bering_peptides desc,bering_psms desc\", \"__page__\": null, \"__rerun_remap_job_id__\": null}", - "tool_version": "2.0.0", - "type": "tool", - "uuid": "87355427-5567-4695-88c3-ca64703b1ce4", - "when": null, - "workflow_outputs": [ - { - "label": "GO Cellular Localizations", - "output_name": "query_results", - "uuid": "2e8a071a-da5c-4260-9591-aac88362cf4e" - } - ] - }, - "12": { - "annotation": "", - "content_id": "toolshed.g2.bx.psu.edu/repos/iuc/sqlite_to_tabular/sqlite_to_tabular/2.0.0", - "errors": null, - "id": 12, - "input_connections": { - "sqlitedb": { - "id": 8, - "output_name": "sqlitedb" - } - }, - "inputs": [], - "label": "GO Terms: Molecular Functions", - "name": "SQLite to tabular", - "outputs": [ - { - "name": "query_results", - "type": "tabular" - } - ], - "position": { - "left": 1775.4054698421558, - "top": 195.10937290594495 - }, - "post_job_actions": { - "RenameDatasetActionquery_results": { - "action_arguments": { - "newname": "GO Terms: Molecular Functions" - }, - "action_type": "RenameDatasetAction", - "output_name": "query_results" - } - }, - "tool_id": "toolshed.g2.bx.psu.edu/repos/iuc/sqlite_to_tabular/sqlite_to_tabular/2.0.0", - "tool_shed_repository": { - "changeset_revision": "b722161a845a", - "name": "sqlite_to_tabular", - "owner": "iuc", - "tool_shed": "toolshed.g2.bx.psu.edu" - }, - "tool_state": "{\"query_result\": {\"header\": \"yes\", \"__current_case__\": 0, \"header_prefix\": \"35\"}, \"sqlitedb\": {\"__class__\": \"ConnectedValue\"}, \"sqlquery\": \"SELECT go.description, \\ncount(distinct bering_psms.sequence) as \\\"bering_peptides\\\", count(distinct bering_psms.id) as \\\"bering_psms\\\" \\nFROM go JOIN bering_prot_go ON go.go_id = bering_prot_go.go_reference JOIN bering_prot on bering_prot_go.id = bering_prot.id JOIN bering_psms ON bering_prot.peptide = bering_psms.sequence\\nWHERE go.aspect = 'molecular_function'\\nGROUP BY go.description\\nORDER BY bering_peptides desc,bering_psms desc\", \"__page__\": null, \"__rerun_remap_job_id__\": null}", - "tool_version": "2.0.0", - "type": "tool", - "uuid": "2a397c66-3da4-4cbe-a186-2adaaea9c39e", - "when": null, - "workflow_outputs": [ - { - "label": "GO Molecular Functions", - "output_name": "query_results", - "uuid": "f6fb7920-4385-4452-b0ea-6bb0bf7770fe" - } - ] - } - }, - "tags": [ - "name:metaproteomics", - "name:galaxyp", - "name:massspectrometry", - "name:microgalaxy" - ], - "uuid": "a0cfa0a6-bd97-48c0-aa30-7bcf546ffd3d", - "version": 40 -} \ No newline at end of file From cce125b12214d6be1d59884db5febfa399fbab8e Mon Sep 17 00:00:00 2001 From: meltemktn <63255967+meltemktn@users.noreply.github.com> Date: Thu, 12 Dec 2024 23:43:05 +0300 Subject: [PATCH 4/6] Update workflows/proteomics/metaquantome-function/metaquantome_function_wf.ga Co-authored-by: Wolfgang Maier --- .../metaquantome-function/metaquantome_function_wf.ga | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/workflows/proteomics/metaquantome-function/metaquantome_function_wf.ga b/workflows/proteomics/metaquantome-function/metaquantome_function_wf.ga index 6cf68f002..57472e5f9 100644 --- a/workflows/proteomics/metaquantome-function/metaquantome_function_wf.ga +++ b/workflows/proteomics/metaquantome-function/metaquantome_function_wf.ga @@ -37,7 +37,7 @@ "format-version": "0.1", "license": "MIT", "release": "0.1", - "name": "metaquantome-function-worklow", + "name": "metaquantome-function-workflow", "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 1cd390797b9470af2974a5345f695d69a6aafbdf Mon Sep 17 00:00:00 2001 From: meltemktn <63255967+meltemktn@users.noreply.github.com> Date: Fri, 13 Dec 2024 11:58:47 +0300 Subject: [PATCH 5/6] Update README.md WF steps outlined --- workflows/proteomics/metaquantome-function/README.md | 10 +++++++--- 1 file changed, 7 insertions(+), 3 deletions(-) diff --git a/workflows/proteomics/metaquantome-function/README.md b/workflows/proteomics/metaquantome-function/README.md index 622ebad63..d1128f7cd 100644 --- a/workflows/proteomics/metaquantome-function/README.md +++ b/workflows/proteomics/metaquantome-function/README.md @@ -1,4 +1,8 @@ -# metaQuantome 2: Function -metaQuantome software suite Easterly et al. 2019 was developed by the Team for quantitative and statistical analysis of metaproteomics data. For taxonomic and functional expression analysis within the microbial community, metaQuantome leverages peptide-level quantitative information to generate visual outputs for data interpretation. It also generates outputs that help in understanding the taxonomic contribution to a selected function as well as functions expressed by selected taxonomic group. +# Creating plots using metaQuantome 2: Functional enrichment analysis and clustering -More background on this workflow can be found in the [metaQuantome 2: Function tutorial](https://training.galaxyproject.org/training-material/topics/proteomics/tutorials/metaquantome-function/tutorial.html) \ No newline at end of file +metaQuantome software suite (Easterly et al. 2019) was developed by the Team for quantitative and statistical analysis of metaproteomics data. For taxonomic and functional expression analysis within the microbial community, metaQuantome leverages peptide-level quantitative information to generate visual outputs for data interpretation. It also generates outputs that help in understanding the taxonomic contribution to a selected function as well as functions expressed by selected taxonomic group. + +This workflow uses a function file, an intensity file and the metaQuantome databases (NCBI Taxonomy, GO term and ENZYME database) as inputs. Four modules of the metaQuantome suite are used: **expand**,**filter**, **stat** and **visualize**. After the experimental conditions and samples are manually specified, the **expand** module analyzes differentially expressed functions in the samples using the metaQuantome databases to correlate the information in the input files with GO terms, taxa and enzyme classifications. The output file and the manually specified samples are then used in the **filter** module where the expanded terms are filtered to those that are representative of the data according to the user-specified sample parameters. Finally, the **stat** module performs a functional analysis of the filtered data on multiple conditions. The tabular output file is then used as input in the **visualize** module to generate a bar plot and a volcano plot. Users can also generate a PCA plot and a heatmap for cluster analysis. + + +More background on this workflow can be found in the [metaQuantome 2: Function tutorial](https://training.galaxyproject.org/training-material/topics/proteomics/tutorials/metaquantome-function/tutorial.html) From 06581d710d96fa823fc489af22cfbbafbfc4a63e Mon Sep 17 00:00:00 2001 From: meltemktn <63255967+meltemktn@users.noreply.github.com> Date: Fri, 13 Dec 2024 12:30:11 +0300 Subject: [PATCH 6/6] Update README.md --- workflows/proteomics/metaquantome-function/README.md | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/workflows/proteomics/metaquantome-function/README.md b/workflows/proteomics/metaquantome-function/README.md index d1128f7cd..6e22c496f 100644 --- a/workflows/proteomics/metaquantome-function/README.md +++ b/workflows/proteomics/metaquantome-function/README.md @@ -1,8 +1,9 @@ -# Creating plots using metaQuantome 2: Functional enrichment analysis and clustering +# Creating plots using metaQuantome: Functional enrichment analysis and clustering metaQuantome software suite (Easterly et al. 2019) was developed by the Team for quantitative and statistical analysis of metaproteomics data. For taxonomic and functional expression analysis within the microbial community, metaQuantome leverages peptide-level quantitative information to generate visual outputs for data interpretation. It also generates outputs that help in understanding the taxonomic contribution to a selected function as well as functions expressed by selected taxonomic group. This workflow uses a function file, an intensity file and the metaQuantome databases (NCBI Taxonomy, GO term and ENZYME database) as inputs. Four modules of the metaQuantome suite are used: **expand**,**filter**, **stat** and **visualize**. After the experimental conditions and samples are manually specified, the **expand** module analyzes differentially expressed functions in the samples using the metaQuantome databases to correlate the information in the input files with GO terms, taxa and enzyme classifications. The output file and the manually specified samples are then used in the **filter** module where the expanded terms are filtered to those that are representative of the data according to the user-specified sample parameters. Finally, the **stat** module performs a functional analysis of the filtered data on multiple conditions. The tabular output file is then used as input in the **visualize** module to generate a bar plot and a volcano plot. Users can also generate a PCA plot and a heatmap for cluster analysis. +***Note:*** The **expand** module of the metaQuantome suite is run in "Functional analysis" mode in this workflow. More background on this workflow can be found in the [metaQuantome 2: Function tutorial](https://training.galaxyproject.org/training-material/topics/proteomics/tutorials/metaquantome-function/tutorial.html)