Mercurial > repos > eschen42 > mqppep_anova
diff workflow/ppenrich_suite_wf.ga @ 0:c1403d18c189 draft
"planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit bb6c941be50db4c0719efdeaa904d7cb7aa1d182"
| author | eschen42 |
|---|---|
| date | Mon, 07 Mar 2022 19:05:01 +0000 |
| parents | |
| children | d728198f1ba5 |
line wrap: on
line diff
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/workflow/ppenrich_suite_wf.ga Mon Mar 07 19:05:01 2022 +0000 @@ -0,0 +1,653 @@ +{ + "a_galaxy_workflow": "true", + "annotation": "phoshpoproteomic enrichment data pre-processing and ANOVA", + "creator": [ + { + "class": "Person", + "identifier": "0000-0002-2882-0508", + "name": "Art Eschenlauer" + } + ], + "format-version": "0.1", + "license": "MIT", + "name": "ppenrich_suite_wf", + "steps": { + "0": { + "annotation": "The Phospho (STY)Sites.txt file produced by MaxQuant (found in the txt folder).", + "content_id": null, + "errors": null, + "id": 0, + "input_connections": {}, + "inputs": [ + { + "description": "The Phospho (STY)Sites.txt file produced by MaxQuant (found in the txt folder).", + "name": "Phospho (STY)Sites.txt" + } + ], + "label": "Phospho (STY)Sites.txt", + "name": "Input dataset", + "outputs": [], + "position": { + "bottom": 257.06666564941406, + "height": 81.39999389648438, + "left": 339.95001220703125, + "right": 539.9500122070312, + "top": 175.6666717529297, + "width": 200, + "x": 339.95001220703125, + "y": 175.6666717529297 + }, + "tool_id": null, + "tool_state": "{\"optional\": false, \"format\": [\"tabular\"], \"tag\": null}", + "tool_version": null, + "type": "data_input", + "uuid": "002d55e6-29a5-426d-9248-70ec33424b15", + "workflow_outputs": [] + }, + "1": { + "annotation": "FASTA file of all human canonical isoforms, derived from Swiss-Prot (e.g., merge of https://ftp.uniprot.org/pub/databases/uniprot/current_release/knowledgebase/complete/uniprot_sprot_varsplic.fasta.gz and https://ftp.uniprot.org/pub/databases/uniprot/current_release/knowledgebase/complete/uniprot_sprot.fasta.gz)", + "content_id": null, + "errors": null, + "id": 1, + "input_connections": {}, + "inputs": [ + { + "description": "FASTA file of all human canonical isoforms, derived from Swiss-Prot (e.g., merge of https://ftp.uniprot.org/pub/databases/uniprot/current_release/knowledgebase/complete/uniprot_sprot_varsplic.fasta.gz and https://ftp.uniprot.org/pub/databases/uniprot/current_release/knowledgebase/complete/uniprot_sprot.fasta.gz)", + "name": "SwissProt_Human_Canonical_Isoform.fasta" + } + ], + "label": "SwissProt_Human_Canonical_Isoform.fasta", + "name": "Input dataset", + "outputs": [], + "position": { + "bottom": 411.4666748046875, + "height": 101.79998779296875, + "left": 379.95001220703125, + "right": 579.9500122070312, + "top": 309.66668701171875, + "width": 200, + "x": 379.95001220703125, + "y": 309.66668701171875 + }, + "tool_id": null, + "tool_state": "{\"optional\": false, \"format\": [\"fasta\"], \"tag\": null}", + "tool_version": null, + "type": "data_input", + "uuid": "8f079dcc-1843-47cd-b4dc-1830e4466430", + "workflow_outputs": [] + }, + "2": { + "annotation": "Derived from https://networkin.info/download/networkin_human_predictions_3.1.tsv.xz (which is free for non-commercial use - for required citation, see https://networkin.info/)", + "content_id": null, + "errors": null, + "id": 2, + "input_connections": {}, + "inputs": [ + { + "description": "Derived from https://networkin.info/download/networkin_human_predictions_3.1.tsv.xz (which is free for non-commercial use - for required citation, see https://networkin.info/)", + "name": "NetworKIN_cutoffscore2.0.tabular" + } + ], + "label": "NetworKIN_cutoffscore2.0.tabular", + "name": "Input dataset", + "outputs": [], + "position": { + "bottom": 573.4666748046875, + "height": 101.79998779296875, + "left": 418.95001220703125, + "right": 618.9500122070312, + "top": 471.66668701171875, + "width": 200, + "x": 418.95001220703125, + "y": 471.66668701171875 + }, + "tool_id": null, + "tool_state": "{\"optional\": false, \"format\": [\"tabular\"], \"tag\": null}", + "tool_version": null, + "type": "data_input", + "uuid": "dc894a94-97a3-40ff-811e-01b30d498478", + "workflow_outputs": [] + }, + "3": { + "annotation": "Derived from http://hprd.org/serine_motifs, http://hprd.org/tyrosine_motifs, and http://pegasus.biochem.mpg.de/phosida/help/motifs.aspx", + "content_id": null, + "errors": null, + "id": 3, + "input_connections": {}, + "inputs": [ + { + "description": "Derived from http://hprd.org/serine_motifs, http://hprd.org/tyrosine_motifs, and http://pegasus.biochem.mpg.de/phosida/help/motifs.aspx", + "name": "pSTY_Motifs.tabular" + } + ], + "label": "pSTY_Motifs.tabular", + "name": "Input dataset", + "outputs": [], + "position": { + "bottom": 726.0666809082031, + "height": 81.39999389648438, + "left": 459.95001220703125, + "right": 659.9500122070312, + "top": 644.6666870117188, + "width": 200, + "x": 459.95001220703125, + "y": 644.6666870117188 + }, + "tool_id": null, + "tool_state": "{\"optional\": false, \"format\": [\"tabular\"], \"tag\": null}", + "tool_version": null, + "type": "data_input", + "uuid": "6fc936ad-0b52-484f-a051-73c1776fdeb0", + "workflow_outputs": [] + }, + "4": { + "annotation": "Derived from Kinase_Substrate_Dataset.gz found at https://www.phosphosite.org/staticDownloads (free for non-commercial use - see that link for citation.)", + "content_id": null, + "errors": null, + "id": 4, + "input_connections": {}, + "inputs": [ + { + "description": "Derived from Kinase_Substrate_Dataset.gz found at https://www.phosphosite.org/staticDownloads (free for non-commercial use - see that link for citation.)", + "name": "PSP_Kinase_Substrate_Dataset.tabular" + } + ], + "label": "PSP_Kinase_Substrate_Dataset.tabular", + "name": "Input dataset", + "outputs": [], + "position": { + "bottom": 894.4666748046875, + "height": 101.79998779296875, + "left": 503.95001220703125, + "right": 703.9500122070312, + "top": 792.6666870117188, + "width": 200, + "x": 503.95001220703125, + "y": 792.6666870117188 + }, + "tool_id": null, + "tool_state": "{\"optional\": false, \"format\": [\"tabular\"], \"tag\": null}", + "tool_version": null, + "type": "data_input", + "uuid": "22b77482-2339-4b45-8fc6-d39f7175131b", + "workflow_outputs": [] + }, + "5": { + "annotation": "Derived from Regulatory_sites.gz found at https://www.phosphosite.org/staticDownloads (free for non-commercial use - see that link for citation.)", + "content_id": null, + "errors": null, + "id": 5, + "input_connections": {}, + "inputs": [ + { + "description": "Derived from Regulatory_sites.gz found at https://www.phosphosite.org/staticDownloads (free for non-commercial use - see that link for citation.)", + "name": "PSP_Regulatory_sites.tabular" + } + ], + "label": "PSP_Regulatory_sites.tabular", + "name": "Input dataset", + "outputs": [], + "position": { + "bottom": 1041.0666809082031, + "height": 81.39999389648438, + "left": 535.9500122070312, + "right": 735.9500122070312, + "top": 959.6666870117188, + "width": 200, + "x": 535.9500122070312, + "y": 959.6666870117188 + }, + "tool_id": null, + "tool_state": "{\"optional\": false, \"format\": [\"tabular\"], \"tag\": null}", + "tool_version": null, + "type": "data_input", + "uuid": "3d97a902-1408-403c-b82e-ddb6ca6a7d47", + "workflow_outputs": [] + }, + "6": { + "annotation": "List of alpha cutoff values for significance testing; text file having no header and a single line for each cutoff value.", + "content_id": null, + "errors": null, + "id": 6, + "input_connections": {}, + "inputs": [ + { + "description": "List of alpha cutoff values for significance testing; text file having no header and a single line for each cutoff value.", + "name": "alpha_levels.tabular" + } + ], + "label": "alpha_levels.tabular", + "name": "Input dataset", + "outputs": [], + "position": { + "bottom": 1210.5666198730469, + "height": 81.39999389648438, + "left": 562.9500122070312, + "right": 762.9500122070312, + "top": 1129.1666259765625, + "width": 200, + "x": 562.9500122070312, + "y": 1129.1666259765625 + }, + "tool_id": null, + "tool_state": "{\"optional\": false, \"format\": [\"tabular\"], \"tag\": null}", + "tool_version": null, + "type": "data_input", + "uuid": "7b5eab97-7dad-4b0e-81eb-22aac39dd5b6", + "workflow_outputs": [] + }, + "7": { + "annotation": "", + "content_id": "mqppep_preproc", + "errors": null, + "id": 7, + "input_connections": { + "networkin": { + "id": 2, + "output_name": "output" + }, + "p_sty_motifs": { + "id": 3, + "output_name": "output" + }, + "phosphoSites": { + "id": 0, + "output_name": "output" + }, + "protein_fasta": { + "id": 1, + "output_name": "output" + }, + "psp_kinase_substrate": { + "id": 4, + "output_name": "output" + }, + "psp_regulatory_sites": { + "id": 5, + "output_name": "output" + } + }, + "inputs": [], + "label": null, + "name": "MaxQuant Phosphopeptide Preprocessing", + "outputs": [ + { + "name": "phosphoPepIntensities", + "type": "tabular" + }, + { + "name": "enrichGraph", + "type": "pdf" + }, + { + "name": "locProbCutoffGraph", + "type": "pdf" + }, + { + "name": "enrichGraph_svg", + "type": "svg" + }, + { + "name": "locProbCutoffGraph_svg", + "type": "svg" + }, + { + "name": "filteredData_tabular", + "type": "tabular" + }, + { + "name": "quantData_tabular", + "type": "tabular" + }, + { + "name": "mapped_phophopeptides", + "type": "tabular" + }, + { + "name": "melted_phophopeptide_map", + "type": "tabular" + }, + { + "name": "mqppep_output_sqlite", + "type": "sqlite" + }, + { + "name": "preproc_tab", + "type": "tabular" + }, + { + "name": "preproc_csv", + "type": "csv" + }, + { + "name": "preproc_sqlite", + "type": "sqlite" + } + ], + "position": { + "bottom": 1186.6000366210938, + "height": 812.933349609375, + "left": 945.4500122070312, + "right": 1145.4500122070312, + "top": 373.66668701171875, + "width": 200, + "x": 945.4500122070312, + "y": 373.66668701171875 + }, + "post_job_actions": { + "RenameDatasetActionenrichGraph": { + "action_arguments": { + "newname": "#{phosphoSites}.enrichGraph_pdf" + }, + "action_type": "RenameDatasetAction", + "output_name": "enrichGraph" + }, + "RenameDatasetActionenrichGraph_svg": { + "action_arguments": { + "newname": "#{phosphoSites}.enrichGraph_svg" + }, + "action_type": "RenameDatasetAction", + "output_name": "enrichGraph_svg" + }, + "RenameDatasetActionfilteredData_tabular": { + "action_arguments": { + "newname": "#{phosphoSites}.filteredData" + }, + "action_type": "RenameDatasetAction", + "output_name": "filteredData_tabular" + }, + "RenameDatasetActionlocProbCutoffGraph": { + "action_arguments": { + "newname": "#{phosphoSites}.locProbCutoffGraph_pdf" + }, + "action_type": "RenameDatasetAction", + "output_name": "locProbCutoffGraph" + }, + "RenameDatasetActionlocProbCutoffGraph_svg": { + "action_arguments": { + "newname": "#{phosphoSites}.locProbCutoffGraph_svg" + }, + "action_type": "RenameDatasetAction", + "output_name": "locProbCutoffGraph_svg" + }, + "RenameDatasetActionmapped_phophopeptides": { + "action_arguments": { + "newname": "#{phosphoSites}.ppep_map" + }, + "action_type": "RenameDatasetAction", + "output_name": "mapped_phophopeptides" + }, + "RenameDatasetActionmelted_phophopeptide_map": { + "action_arguments": { + "newname": "#{phosphoSites}.melted" + }, + "action_type": "RenameDatasetAction", + "output_name": "melted_phophopeptide_map" + }, + "RenameDatasetActionmqppep_output_sqlite": { + "action_arguments": { + "newname": "#{phosphoSites}.ppep_mapping_sqlite" + }, + "action_type": "RenameDatasetAction", + "output_name": "mqppep_output_sqlite" + }, + "RenameDatasetActionphosphoPepIntensities": { + "action_arguments": { + "newname": "#{phosphoSites}.ppep_intensities" + }, + "action_type": "RenameDatasetAction", + "output_name": "phosphoPepIntensities" + }, + "RenameDatasetActionpreproc_csv": { + "action_arguments": { + "newname": "#{phosphoSites}.preproc_csv" + }, + "action_type": "RenameDatasetAction", + "output_name": "preproc_csv" + }, + "RenameDatasetActionpreproc_sqlite": { + "action_arguments": { + "newname": "#{phosphoSites}.preproc_sqlite" + }, + "action_type": "RenameDatasetAction", + "output_name": "preproc_sqlite" + }, + "RenameDatasetActionpreproc_tab": { + "action_arguments": { + "newname": "#{phosphoSites}.preproc_tab" + }, + "action_type": "RenameDatasetAction", + "output_name": "preproc_tab" + }, + "RenameDatasetActionquantData_tabular": { + "action_arguments": { + "newname": "#{phosphoSites}.quantData" + }, + "action_type": "RenameDatasetAction", + "output_name": "quantData_tabular" + } + }, + "tool_id": "mqppep_preproc", + "tool_state": "{\"collapseFunc\": \"sum\", \"enriched\": \"ST\", \"intervalCol\": \"1\", \"localProbCutoff\": \"0.75\", \"merge_function\": \"sum\", \"networkin\": {\"__class__\": \"ConnectedValue\"}, \"p_sty_motifs\": {\"__class__\": \"ConnectedValue\"}, \"phosphoCol\": \"^Number of Phospho [(]STY[)]$\", \"phosphoSites\": {\"__class__\": \"ConnectedValue\"}, \"phospho_type\": \"sty\", \"protein_fasta\": {\"__class__\": \"ConnectedValue\"}, \"psp_kinase_substrate\": {\"__class__\": \"ConnectedValue\"}, \"psp_regulatory_sites\": {\"__class__\": \"ConnectedValue\"}, \"species\": \"human\", \"startCol\": \"^Intensity[^_]\", \"__page__\": null, \"__rerun_remap_job_id__\": null}", + "tool_version": "0.1.0+galaxy0", + "type": "tool", + "uuid": "235b1a2e-ccc0-4c91-bb91-bbf4d272c870", + "workflow_outputs": [ + { + "label": "ppep_intensities", + "output_name": "phosphoPepIntensities", + "uuid": "92fd4e27-5d4b-4e9f-b3ad-6bdad53bb93d" + }, + { + "label": "enrichGraph_pdf", + "output_name": "enrichGraph", + "uuid": "4c1d5590-f8ba-421c-858c-4c026691b52e" + }, + { + "label": "locProbCutoffGraph_pdf", + "output_name": "locProbCutoffGraph", + "uuid": "66a79534-6372-4937-bcf2-8644be985eea" + }, + { + "label": "enrichGraph_svg", + "output_name": "enrichGraph_svg", + "uuid": "5e713d9c-1868-423b-be9a-25c0486e1472" + }, + { + "label": "locProbCutoffGraph_svg", + "output_name": "locProbCutoffGraph_svg", + "uuid": "4621ea21-ae90-4547-a68f-30dfc7857368" + }, + { + "label": "filteredData", + "output_name": "filteredData_tabular", + "uuid": "bb26d0fb-6f19-43c7-80ef-1cf81aa09ee8" + }, + { + "label": "quantData", + "output_name": "quantData_tabular", + "uuid": "20efe04f-2700-4af0-92c6-0830a42d8e75" + }, + { + "label": "ppep_map", + "output_name": "mapped_phophopeptides", + "uuid": "037e2b97-8fc8-436d-bcc3-af5ee685b752" + }, + { + "label": "melted_phosphopeptide_map", + "output_name": "melted_phophopeptide_map", + "uuid": "c3e5de84-2659-45eb-81a6-edef6037d8aa" + }, + { + "label": "ppep_mapping_sqlite", + "output_name": "mqppep_output_sqlite", + "uuid": "a1a4f827-1f1f-4175-ae51-c238f9e1f248" + }, + { + "label": "preproc_tab", + "output_name": "preproc_tab", + "uuid": "b22b4b56-9395-4f6d-945e-0089e8897069" + }, + { + "label": "preproc_csv", + "output_name": "preproc_csv", + "uuid": "54be90f9-1158-4686-af42-43d021088300" + }, + { + "label": "preproc_sqlite", + "output_name": "preproc_sqlite", + "uuid": "33663f9c-b718-4bdd-acc9-087c76bea678" + } + ] + }, + "8": { + "annotation": "Perform ANOVA. For imputing missing values, use median of non-missing values from the same treatment group.", + "content_id": "mqppep_anova", + "errors": null, + "id": 8, + "input_connections": { + "alpha_file": { + "id": 6, + "output_name": "output" + }, + "input_file": { + "id": 7, + "output_name": "preproc_tab" + } + }, + "inputs": [], + "label": "MaxQuant Phosphopeptide ANOVA group-median imputed", + "name": "MaxQuant Phosphopeptide ANOVA", + "outputs": [ + { + "name": "imputed_data_file", + "type": "tabular" + }, + { + "name": "report_file", + "type": "html" + } + ], + "position": { + "bottom": 1488.0999603271484, + "height": 254.93333435058594, + "left": 1202.949951171875, + "right": 1402.949951171875, + "top": 1233.1666259765625, + "width": 200, + "x": 1202.949951171875, + "y": 1233.1666259765625 + }, + "post_job_actions": { + "RenameDatasetActionimputed_data_file": { + "action_arguments": { + "newname": "#{input_file}.intensities_group-mean-imputed_QN_LT" + }, + "action_type": "RenameDatasetAction", + "output_name": "imputed_data_file" + }, + "RenameDatasetActionreport_file": { + "action_arguments": { + "newname": "#{input_file}.intensities_group-mean-imputed_report (download/unzip to view)" + }, + "action_type": "RenameDatasetAction", + "output_name": "report_file" + } + }, + "tool_id": "mqppep_anova", + "tool_state": "{\"alpha_file\": {\"__class__\": \"ConnectedValue\"}, \"first_data_column\": \"Intensity\", \"imputation\": {\"imputation_method\": \"group-median\", \"__current_case__\": 0}, \"input_file\": {\"__class__\": \"ConnectedValue\"}, \"sample_grouping_regex\": \"(\\\\d+)\", \"sample_names_regex\": \"\\\\.(\\\\d+)[A-Z]$\", \"__page__\": null, \"__rerun_remap_job_id__\": null}", + "tool_version": "0.1.0+galaxy0", + "type": "tool", + "uuid": "2257286b-6f9a-45c1-90a3-bf5b972959d5", + "workflow_outputs": [ + { + "label": "intensities_group-mean-imputed_QN_LT", + "output_name": "imputed_data_file", + "uuid": "8e7317c6-95e9-4454-b4d7-31b4de6167a8" + }, + { + "label": "intensities_group-mean-imputed_report", + "output_name": "report_file", + "uuid": "dfe9b34e-1f3e-4971-8382-41178104e253" + } + ] + }, + "9": { + "annotation": "Perform ANOVA. For imputing missing values, create random values.", + "content_id": "mqppep_anova", + "errors": null, + "id": 9, + "input_connections": { + "alpha_file": { + "id": 6, + "output_name": "output" + }, + "input_file": { + "id": 7, + "output_name": "preproc_tab" + } + }, + "inputs": [], + "label": "MaxQuant Phosphopeptide ANOVA randomly imputed", + "name": "MaxQuant Phosphopeptide ANOVA", + "outputs": [ + { + "name": "imputed_data_file", + "type": "tabular" + }, + { + "name": "report_file", + "type": "html" + } + ], + "position": { + "bottom": 1325.0999603271484, + "height": 254.93333435058594, + "left": 1452.949951171875, + "right": 1652.949951171875, + "top": 1070.1666259765625, + "width": 200, + "x": 1452.949951171875, + "y": 1070.1666259765625 + }, + "post_job_actions": { + "RenameDatasetActionimputed_data_file": { + "action_arguments": { + "newname": "#{input_file}.intensities_randomly-imputed_QN_LT" + }, + "action_type": "RenameDatasetAction", + "output_name": "imputed_data_file" + }, + "RenameDatasetActionreport_file": { + "action_arguments": { + "newname": "#{input_file}.intensities_randomly-imputed_report (download/unzip to view)" + }, + "action_type": "RenameDatasetAction", + "output_name": "report_file" + } + }, + "tool_id": "mqppep_anova", + "tool_state": "{\"alpha_file\": {\"__class__\": \"ConnectedValue\"}, \"first_data_column\": \"Intensity\", \"imputation\": {\"imputation_method\": \"random\", \"__current_case__\": 3, \"meanPercentile\": \"1\", \"sdPercentile\": \"0.2\"}, \"input_file\": {\"__class__\": \"ConnectedValue\"}, \"sample_grouping_regex\": \"(\\\\d+)\", \"sample_names_regex\": \"\\\\.(\\\\d+)[A-Z]$\", \"__page__\": null, \"__rerun_remap_job_id__\": null}", + "tool_version": "0.1.0+galaxy0", + "type": "tool", + "uuid": "9516971c-8532-4797-8bf9-4655ff104dbd", + "workflow_outputs": [ + { + "label": "intensities_randomly-imputed_QN_LT", + "output_name": "imputed_data_file", + "uuid": "8ceda029-d5fd-4d75-a2b3-ac582bb137c3" + }, + { + "label": "intensities_randomly-imputed_report", + "output_name": "report_file", + "uuid": "84bedf25-c15b-4cc7-97e0-92f746e89f9c" + } + ] + } + }, + "tags": [ + "ppenrich" + ], + "uuid": "ac7bf2d1-89fe-4bf6-920a-d5508842d3f9", + "version": 7 +} \ No newline at end of file