From e592be3235016fb787bf86f146533eb8a4f1920d Mon Sep 17 00:00:00 2001 From: diana chJ <122611454+dianichj@users.noreply.github.com> Date: Mon, 4 Nov 2024 14:56:31 +0100 Subject: [PATCH] Update pseudo-bulk_edgeR.ga Editions for better automatisation of workflow. User contrast_file input not needed anymore. --- .../pseudo-bulk_edgeR.ga | 285 +++++++++++------- 1 file changed, 169 insertions(+), 116 deletions(-) diff --git a/workflows/scRNAseq/pseudobulk-worflow-decoupler-edger/pseudo-bulk_edgeR.ga b/workflows/scRNAseq/pseudobulk-worflow-decoupler-edger/pseudo-bulk_edgeR.ga index c581952a8..eb9bb57d3 100644 --- a/workflows/scRNAseq/pseudobulk-worflow-decoupler-edger/pseudo-bulk_edgeR.ga +++ b/workflows/scRNAseq/pseudobulk-worflow-decoupler-edger/pseudo-bulk_edgeR.ga @@ -21,7 +21,6 @@ ], "format-version": "0.1", "license": "CC-BY-4.0", - "release": "0.1", "name": "pseudo-bulk_edgeR", "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" @@ -43,8 +42,8 @@ "name": "Input dataset", "outputs": [], "position": { - "left": 1.299886068362639, - "top": 516.1706375133249 + "left": 0, + "top": 114.82675544995811 }, "tool_id": null, "tool_state": "{\"optional\": false, \"format\": [\"h5\", \"h5ad\"], \"tag\": \"\"}", @@ -70,8 +69,8 @@ "name": "Input parameter", "outputs": [], "position": { - "left": 0, - "top": 647.32421875 + "left": 60.495251676792236, + "top": 230.35374378726198 }, "tool_id": null, "tool_state": "{\"parameter_type\": \"text\", \"optional\": true}", @@ -79,7 +78,13 @@ "type": "parameter_input", "uuid": "b765c928-15de-4a9b-8bf2-96f9a9a5cdba", "when": null, - "workflow_outputs": [] + "workflow_outputs": [ + { + "label": null, + "output_name": "output", + "uuid": "c70d7068-d535-430f-ba40-199bbfed605c" + } + ] }, "2": { "annotation": "Typically, the column in obs that you want to use for comparisons later (the main contrast field) should be specified here. This column will also be used for plotting the pseudo-bulk samples, showing the number of counts and cells.", @@ -97,8 +102,8 @@ "name": "Input parameter", "outputs": [], "position": { - "left": 7.383289960141873, - "top": 751.7249615417315 + "left": 123.70374778716867, + "top": 341.8746744746166 }, "tool_id": null, "tool_state": "{\"parameter_type\": \"text\", \"optional\": false}", @@ -106,7 +111,13 @@ "type": "parameter_input", "uuid": "fa4b1127-560a-4ce5-8ae7-65b1cbd466f1", "when": null, - "workflow_outputs": [] + "workflow_outputs": [ + { + "label": null, + "output_name": "output", + "uuid": "9b6c5134-f9fb-413a-8a65-62ca29401dd9" + } + ] }, "3": { "annotation": "The field used to create the pseudo-bulk replicates is typically a combination of multiple Obs fields merged together.", @@ -124,8 +135,8 @@ "name": "Input parameter", "outputs": [], "position": { - "left": 10.529437950525221, - "top": 861.5770833419796 + "left": 151.20372670956235, + "top": 465.91578876790373 }, "tool_id": null, "tool_state": "{\"parameter_type\": \"text\", \"optional\": false}", @@ -133,7 +144,13 @@ "type": "parameter_input", "uuid": "5daa239e-1acc-4730-993d-d7a62ae30575", "when": null, - "workflow_outputs": [] + "workflow_outputs": [ + { + "label": null, + "output_name": "output", + "uuid": "e6d9cb6d-1128-4bd1-bb7e-e8d0d4dd11f6" + } + ] }, "4": { "annotation": "Name of the layer containing your raw (non-normalized) counts.", @@ -151,8 +168,8 @@ "name": "Input parameter", "outputs": [], "position": { - "left": 9.002804977774513, - "top": 986.7809696988667 + "left": 198.40796524172788, + "top": 596.2242453471495 }, "tool_id": null, "tool_state": "{\"parameter_type\": \"text\", \"optional\": false}", @@ -160,7 +177,13 @@ "type": "parameter_input", "uuid": "e2b06f23-4090-4014-b194-9afcd48e3905", "when": null, - "workflow_outputs": [] + "workflow_outputs": [ + { + "label": null, + "output_name": "output", + "uuid": "ed10dd0c-7c42-4c37-a2ec-788b25900c69" + } + ] }, "5": { "annotation": "The fields from Obs to be provided to EdgeR as factors. The first field should represent the main contrast for comparisons, while the subsequent fields will be used as covariates.", @@ -178,8 +201,8 @@ "name": "Input parameter", "outputs": [], "position": { - "left": 19.748813513029425, - "top": 1113.5786527382497 + "left": 223.45860152251703, + "top": 713.2366686237074 }, "tool_id": null, "tool_state": "{\"parameter_type\": \"text\", \"optional\": false}", @@ -187,94 +210,85 @@ "type": "parameter_input", "uuid": "d7f40c82-930a-45d4-8392-ecd071162040", "when": null, - "workflow_outputs": [] + "workflow_outputs": [ + { + "label": null, + "output_name": "output", + "uuid": "b3885b84-8cf3-47ce-9e57-51890d8f6aa8" + } + ] }, "6": { - "annotation": "Specify the name of the column containing your gene symbols. For example: gene_symbol, gene_name, x, etc.", + "annotation": "Example 1: ~ 0 + Factor_1\n(Use this formula when you only want to account for one factor, Factor_1).\n\nExample 2 (With covariate adjustment): ~ 0 + Factor_1 + Factor_2\n(Use this formula if you need to adjust for additional factors, such as Factor_2, which serves as a covariate).\n\nNote: Ensure that all factors (e.g., Factor_1, Factor_2) included in the formula are defined in your factor file.", "content_id": null, "errors": null, "id": 6, "input_connections": {}, "inputs": [ { - "description": "Specify the name of the column containing your gene symbols. For example: gene_symbol, gene_name, x, etc.", - "name": "Gene symbol column" + "description": "Example 1: ~ 0 + Factor_1\n(Use this formula when you only want to account for one factor, Factor_1).\n\nExample 2 (With covariate adjustment): ~ 0 + Factor_1 + Factor_2\n(Use this formula if you need to adjust for additional factors, such as Factor_2, which serves as a covariate).\n\nNote: Ensure that all factors (e.g., Factor_1, Factor_2) included in the formula are defined in your factor file.", + "name": "Formula" } ], - "label": "Gene symbol column", + "label": "Formula", "name": "Input parameter", "outputs": [], "position": { - "left": 1140.710055348184, - "top": 640.9960493841977 + "left": 1084.8910833860734, + "top": 839.4664158173962 }, "tool_id": null, "tool_state": "{\"parameter_type\": \"text\", \"optional\": false}", "tool_version": null, "type": "parameter_input", - "uuid": "e22b8666-3c73-41e2-8d3d-e6a8f4e2ba62", + "uuid": "71d2cf0a-7eaa-41fc-9ffd-f0ffbdbf9657", "when": null, - "workflow_outputs": [] + "workflow_outputs": [ + { + "label": null, + "output_name": "output", + "uuid": "e1911fda-16a7-4f48-8a17-5d9f4bd635ee" + } + ] }, "7": { - "annotation": "Example 1: ~ 0 + Factor_1\n(Use this formula when you only want to account for one factor, Factor_1).\n\nExample 2 (With covariate adjustment): ~ 0 + Factor_1 + Factor_2\n(Use this formula if you need to adjust for additional factors, such as Factor_2, which serves as a covariate).\n\nNote: Ensure that all factors (e.g., Factor_1, Factor_2) included in the formula are defined in your factor file.", + "annotation": "Specify the name of the column containing your gene symbols. For example: gene_symbol, gene_name, x, etc.", "content_id": null, "errors": null, "id": 7, "input_connections": {}, "inputs": [ { - "description": "Example 1: ~ 0 + Factor_1\n(Use this formula when you only want to account for one factor, Factor_1).\n\nExample 2 (With covariate adjustment): ~ 0 + Factor_1 + Factor_2\n(Use this formula if you need to adjust for additional factors, such as Factor_2, which serves as a covariate).\n\nNote: Ensure that all factors (e.g., Factor_1, Factor_2) included in the formula are defined in your factor file.", - "name": "Formula" + "description": "Specify the name of the column containing your gene symbols. For example: gene_symbol, gene_name, x, etc.", + "name": "Gene symbol column" } ], - "label": "Formula", + "label": "Gene symbol column", "name": "Input parameter", "outputs": [], "position": { - "left": 995.3732100945864, - "top": 1273.76953125 + "left": 1357.37679290235, + "top": 445.59148543814814 }, "tool_id": null, "tool_state": "{\"parameter_type\": \"text\", \"optional\": false}", "tool_version": null, "type": "parameter_input", - "uuid": "71d2cf0a-7eaa-41fc-9ffd-f0ffbdbf9657", + "uuid": "e22b8666-3c73-41e2-8d3d-e6a8f4e2ba62", "when": null, - "workflow_outputs": [] - }, - "8": { - "annotation": "File with one contrast per line. Each contrast should be a combination of factor name and value, such as FactorA.ValueX - FactorA.ValueY", - "content_id": null, - "errors": null, - "id": 8, - "input_connections": {}, - "inputs": [ + "workflow_outputs": [ { - "description": "File with one contrast per line. Each contrast should be a combination of factor name and value, such as FactorA.ValueX - FactorA.ValueY", - "name": "contrasts_files" + "label": null, + "output_name": "output", + "uuid": "7b3c4345-840d-4305-97ec-20ffe71a3a36" } - ], - "label": "contrasts_files", - "name": "Input dataset", - "outputs": [], - "position": { - "left": 996.953160069549, - "top": 1362.6562035835825 - }, - "tool_id": null, - "tool_state": "{\"optional\": false, \"format\": [\"txt\", \"tabular\"], \"tag\": \"\"}", - "tool_version": null, - "type": "data_input", - "uuid": "6506a188-624d-4607-813e-e89fa063e318", - "when": null, - "workflow_outputs": [] + ] }, - "9": { + "8": { "annotation": "", "content_id": "toolshed.g2.bx.psu.edu/repos/ebi-gxa/decoupler_pseudobulk/decoupler_pseudobulk/1.4.0+galaxy5", "errors": null, - "id": 9, + "id": 8, "input_connections": { "adata_obs_fields_to_merge": { "id": 1, @@ -331,8 +345,8 @@ } ], "position": { - "left": 385.0194442492359, - "top": 850.2148583687383 + "left": 516.0467803847828, + "top": 418.1072761184286 }, "post_job_actions": { "DeleteIntermediatesActioncount_matrix": { @@ -381,14 +395,14 @@ } ] }, - "10": { + "9": { "annotation": "", "content_id": "toolshed.g2.bx.psu.edu/repos/bgruening/text_processing/tp_replace_in_line/9.3+galaxy1", "errors": null, - "id": 10, + "id": 9, "input_connections": { "infile": { - "id": 9, + "id": 8, "output_name": "count_matrix" } }, @@ -402,8 +416,8 @@ } ], "position": { - "left": 688.1746137411936, - "top": 716.864770683492 + "left": 817.694628152607, + "top": 326.31168881503567 }, "post_job_actions": { "DeleteIntermediatesActionoutfile": { @@ -438,14 +452,14 @@ "when": null, "workflow_outputs": [] }, - "11": { + "10": { "annotation": "", "content_id": "toolshed.g2.bx.psu.edu/repos/bgruening/text_processing/tp_replace_in_line/9.3+galaxy1", "errors": null, - "id": 11, + "id": 10, "input_connections": { "infile": { - "id": 9, + "id": 8, "output_name": "samples_metadata" } }, @@ -459,8 +473,8 @@ } ], "position": { - "left": 688.4911915852701, - "top": 882.8932432784438 + "left": 818.0112059966837, + "top": 492.3401614099875 }, "post_job_actions": { "DeleteIntermediatesActionoutfile": { @@ -495,14 +509,14 @@ "when": null, "workflow_outputs": [] }, - "12": { - "annotation": "This columns offend EdgeR and DESeq2.", + "11": { + "annotation": "A column that may affect EdgeR and DESeq2.", "content_id": "toolshed.g2.bx.psu.edu/repos/iuc/column_remove_by_header/column_remove_by_header/1.0", "errors": null, - "id": 12, + "id": 11, "input_connections": { "input_tabular": { - "id": 9, + "id": 8, "output_name": "genes_metadata" } }, @@ -516,8 +530,8 @@ } ], "position": { - "left": 694.3886167394281, - "top": 1069.883945552724 + "left": 834.6675907510573, + "top": 728.5754761171477 }, "post_job_actions": { "HideDatasetActionoutput_tabular": { @@ -547,19 +561,19 @@ "when": null, "workflow_outputs": [] }, - "13": { + "12": { "annotation": "", "content_id": "toolshed.g2.bx.psu.edu/repos/bgruening/text_processing/tp_replace_in_column/9.3+galaxy1", "errors": null, - "id": 13, + "id": 12, "input_connections": { "infile": { - "id": 11, + "id": 10, "output_name": "outfile" } }, "inputs": [], - "label": "Sanitise first factor for leading digits", + "label": "Sanitize first factor for leading digits", "name": "Replace Text", "outputs": [ { @@ -568,8 +582,8 @@ } ], "position": { - "left": 942.8842589893927, - "top": 1022.3450832446107 + "left": 1073.6410833860734, + "top": 630.5406345673962 }, "post_job_actions": { "HideDatasetActionoutfile": { @@ -592,6 +606,50 @@ "when": null, "workflow_outputs": [] }, + "13": { + "annotation": "", + "content_id": "toolshed.g2.bx.psu.edu/repos/bgruening/text_processing/tp_awk_tool/9.3+galaxy1", + "errors": null, + "id": 13, + "input_connections": { + "infile": { + "id": 12, + "output_name": "outfile" + } + }, + "inputs": [ + { + "description": "runtime parameter for tool Text reformatting", + "name": "infile" + } + ], + "label": null, + "name": "Text reformatting", + "outputs": [ + { + "name": "outfile", + "type": "input" + } + ], + "position": { + "left": 1364.7928022139954, + "top": 910.5816068561169 + }, + "post_job_actions": {}, + "tool_id": "toolshed.g2.bx.psu.edu/repos/bgruening/text_processing/tp_awk_tool/9.3+galaxy1", + "tool_shed_repository": { + "changeset_revision": "86755160afbf", + "name": "text_processing", + "owner": "bgruening", + "tool_shed": "toolshed.g2.bx.psu.edu" + }, + "tool_state": "{\"code\": \"BEGIN { print \\\"header\\\" } NR > 1 { if (!seen[$2]++) words[++count]=$2 } END { for (i=1; i<=count; i++) for (j=i+1; j<=count; j++) print words[i]\\\"-\\\"words[j] }\", \"infile\": {\"__class__\": \"RuntimeValue\"}, \"__page__\": null, \"__rerun_remap_job_id__\": null}", + "tool_version": "9.3+galaxy1", + "type": "tool", + "uuid": "5701bab4-15b7-401a-9689-c127d17e5bdf", + "when": null, + "workflow_outputs": [] + }, "14": { "annotation": "", "content_id": "toolshed.g2.bx.psu.edu/repos/iuc/edger/edger/3.36.0+galaxy5", @@ -599,23 +657,23 @@ "id": 14, "input_connections": { "anno|geneanno": { - "id": 12, + "id": 11, "output_name": "output_tabular" }, "contrasts|cinfo": { - "id": 8, - "output_name": "output" + "id": 13, + "output_name": "outfile" }, "formula": { - "id": 7, + "id": 6, "output_name": "output" }, "input|counts": { - "id": 10, + "id": 9, "output_name": "outfile" }, "input|fact|finfo": { - "id": 13, + "id": 12, "output_name": "outfile" } }, @@ -646,8 +704,8 @@ } ], "position": { - "left": 1333.9860916368436, - "top": 1075.1709496390679 + "left": 1623.5448063037918, + "top": 655.3696689453593 }, "post_job_actions": {}, "tool_id": "toolshed.g2.bx.psu.edu/repos/iuc/edger/edger/3.36.0+galaxy5", @@ -696,8 +754,8 @@ } ], "position": { - "left": 1469.7602879692938, - "top": 372.90924868740876 + "left": 1855.0434149796085, + "top": 281.6915885082918 }, "post_job_actions": { "HideDatasetActionoutput": { @@ -727,7 +785,7 @@ "id": 16, "input_connections": { "headers_0|name": { - "id": 6, + "id": 7, "output_name": "output" }, "input_tabular": { @@ -735,12 +793,7 @@ "output_name": "outTables" } }, - "inputs": [ - { - "description": "runtime parameter for tool Remove columns", - "name": "input_tabular" - } - ], + "inputs": [], "label": "Select gene symbols, logFC, PValue and FDR", "name": "Remove columns", "outputs": [ @@ -750,8 +803,8 @@ } ], "position": { - "left": 1676.8387926808718, - "top": 527.0458386379028 + "left": 1940.8759531861979, + "top": 513.5126602860244 }, "post_job_actions": {}, "tool_id": "toolshed.g2.bx.psu.edu/repos/iuc/column_remove_by_header/column_remove_by_header/1.0", @@ -761,7 +814,7 @@ "owner": "iuc", "tool_shed": "toolshed.g2.bx.psu.edu" }, - "tool_state": "{\"headers\": [{\"__index__\": 0, \"name\": {\"__class__\": \"ConnectedValue\"}}, {\"__index__\": 1, \"name\": \"logFC\"}, {\"__index__\": 2, \"name\": \"PValue\"}, {\"__index__\": 3, \"name\": \"FDR\"}], \"input_tabular\": {\"__class__\": \"RuntimeValue\"}, \"keep_columns\": true, \"strip_characters\": \"#\", \"__page__\": null, \"__rerun_remap_job_id__\": null}", + "tool_state": "{\"headers\": [{\"__index__\": 0, \"name\": {\"__class__\": \"ConnectedValue\"}}, {\"__index__\": 1, \"name\": \"logFC\"}, {\"__index__\": 2, \"name\": \"PValue\"}, {\"__index__\": 3, \"name\": \"FDR\"}], \"input_tabular\": {\"__class__\": \"ConnectedValue\"}, \"keep_columns\": true, \"strip_characters\": \"#\", \"__page__\": null, \"__rerun_remap_job_id__\": null}", "tool_version": "1.0", "type": "tool", "uuid": "9935a582-7775-4706-be28-720224f5ba9e", @@ -795,8 +848,8 @@ } ], "position": { - "left": 1736.4192938751548, - "top": 238.42686256263465 + "left": 2097.058869383114, + "top": 160.46839568505237 }, "post_job_actions": { "HideDatasetActionoutfile": { @@ -845,8 +898,8 @@ } ], "position": { - "left": 2006.4343450573622, - "top": 148.05037289296598 + "left": 2376.5570395203194, + "top": 0 }, "post_job_actions": { "HideDatasetActionlist_output_txt": { @@ -890,8 +943,8 @@ } ], "position": { - "left": 2242.840767653825, - "top": 0 + "left": 2601.5947847657694, + "top": 142.72866520857775 }, "post_job_actions": { "HideDatasetActiontext_param": { @@ -938,8 +991,8 @@ } ], "position": { - "left": 2461.98898332815, - "top": 223.8346304244149 + "left": 2858.6197555934036, + "top": 367.5558994050945 }, "post_job_actions": {}, "tool_id": "toolshed.g2.bx.psu.edu/repos/iuc/volcanoplot/volcanoplot/0.0.6", @@ -964,6 +1017,6 @@ } }, "tags": [], - "uuid": "f91cd317-1c52-43be-baaf-3365de3ba45a", - "version": 24 -} \ No newline at end of file + "uuid": "e4e4055c-7e3f-4014-a8e6-343199fd9b01", + "version": 31 +}