2f:T525,plot = { let FG_sortedData = _.sortBy(table_data, 'FG_pval'); let FG_E_sortedData = _.sortBy(table_data, 'FG_pval_E'); let BG_sortedData = _.sortBy(table_data, 'BG_pval'); let BG_E_sortedData = _.sortBy(table_data, 'BG_pval_E'); let DF_sortedData = _.sortBy(table_data, 'DF_pval'); let DF_E_sortedData = _.sortBy(table_data, 'DF_pval_E'); let cumulativeData = _.flatMap(FG_sortedData, (d, i) => [ { facet: "FG", x: d.FG_pval, xE: FG_E_sortedData[i].FG_pval_E, cumsum: i + 1 }, { facet: "BG", x: BG_sortedData[i].BG_pval, xE: BG_E_sortedData[i].BG_pval_E, cumsum: i + 1 }, { facet: "DF", x: DF_sortedData[i].DF_pval, xE: DF_E_sortedData[i].DF_pval_E, cumsum: i + 1 } ]); //return cumulativeData return Plot.plot({ y: { grid: true, domain: [0, 100] }, facet: { data: cumulativeData, x: "facet", scale: { sort: ["FG", "BG", "DF"] } }, marks: [ Plot.ruleY([0]), Plot.lineY(cumulativeData, {x: "x", y: "cumsum", facet: "include", stroke: "steelblue"}), Plot.areaY(cumulativeData, {x: "x", y: "cumsum", fillOpacity: 0.1, facet: "include"}), Plot.lineY(cumulativeData, {x: "xE", y: "cumsum", facet: "include", stroke: "red"}), Plot.areaY(cumulativeData, {x: "xE", y: "cumsum", fillOpacity: 0.3, facet: "include"}) ] }); }30:T422,get2x2 = (data, branches, pv, key1, key2)=> { let counts = [[0,0],[0,0]]; let busted = 'BUSTED_' + branches let busted_e = 'BUSTED-E_' + branches let p = pv || 0.05; key1 = key1 || "p"; key2 = key2 || "p_e"; _.each (data, (d)=> { counts [d[key1] <= p ? 1 : 0][d[key2] <= p ? 1 : 0] += 1; }); return [ {[busted] : 'No', [busted_e] : 'No', 'Count' : counts[0][0], 'p' : counts[0][0] / data.length * 100.}, {[busted] : 'Yes', [busted_e] : 'No', 'Count' : counts[1][0], 'p' : counts[1][0] / data.length * 100.}, {[busted] : 'No', [busted_e] : 'Yes', 'Count' : counts[0][1], 'p' : counts[0][1] / data.length * 100.}, {[busted] : 'Yes', [busted_e] : 'Yes', 'Count' : counts[1][1], 'p' : counts[1][1] / data.length * 100.}, {[busted] : 'Yes', [busted_e] : '*', 'Count' : counts[1][1] + counts[1][0], 'p' : (counts[1][1] + counts[1][0]) / data.length * 100.}, {[busted] : '*', [busted_e] : 'Yes', 'Count' : counts[0][1] + counts[1][1], 'p' : (counts[1][1] + counts[0][1]) / data.length * 100.}, ]; }31:Ta24,table_data = { function get_omegas(entry, MODEL, OMEGA) { let omegas = [ entry[MODEL]?.fits?.['Unconstrained model']?.['Rate Distributions']?.['Test']?.[0]?.[OMEGA], entry[MODEL]?.fits?.['Unconstrained model']?.['Rate Distributions']?.['Test']?.[1]?.[OMEGA], entry[MODEL]?.fits?.['Unconstrained model']?.['Rate Distributions']?.['Test']?.[2]?.[OMEGA] ]; if (MODEL.includes('-E')) { omegas.push(entry[MODEL]?.fits?.['Unconstrained model']?.['Rate Distributions']?.['Test']?.[3]?.[OMEGA]); } return omegas.join(','); } function getGeneNameByProtId(prot_id) { const result = ensembl_convert.find(obj => obj.prot_id === prot_id); return result ? result.gene_name : prot_id; } let res = _.map (filtered_res, (val, key)=> { if ('BUSTED-PH-E'in val && 'BUSTED-FG' in val && 'BUSTED-PH' in val){ return { "ID" : dataset != 'rodent_busted-phe.json' ? key: getGeneNameByProtId(key), "FG_pval_E" : val['BUSTED-PH-E']['FG p-val'], "FG_lrt_E" : val['BUSTED-PH-E']['FG LRT'], "BG_pval_E" : val['BUSTED-PH-E']['BG p-val'], "BG_lrt_E" : val['BUSTED-PH-E']['BG LRT'], "DF_pval_E" : val['BUSTED-PH-E']['DF p-val'], "DF_lrt_E" : val['BUSTED-PH-E']['DF LRT'], "FG_pval" : val['BUSTED-PH']['FG p-val'], "FG_lrt" : val['BUSTED-PH']['FG LRT'], "BG_pval" : val['BUSTED-PH']['BG p-val'], "BG_lrt" : val['BUSTED-PH']['BG LRT'], "DF_pval" : val['BUSTED-PH']['DF p-val'], "DF_lrt" : val['BUSTED-PH']['DF LRT'], 'BUSTED-FG omegas' : get_omegas(val, 'BUSTED-FG', 'omega'), 'BUSTED-BG omegas' : get_omegas(val, 'BUSTED-BG', 'omega'), 'BUSTED-BOTH omegas' : get_omegas(val, 'BUSTED-BOTH', 'omega'), 'BUSTED-FG-E omegas' : get_omegas(val, 'BUSTED-FG-E', 'omega'), 'BUSTED-BG-E omegas' : get_omegas(val, 'BUSTED-BG-E', 'omega'), 'BUSTED-BOTH-E omegas' : get_omegas(val, 'BUSTED-BOTH-E', 'omega'), 'BUSTED-FG proportions' : get_omegas(val, 'BUSTED-FG', 'proportion'), 'BUSTED-BG proportions' : get_omegas(val, 'BUSTED-BG', 'proportion'), 'BUSTED-BOTH proportions' : get_omegas(val, 'BUSTED-BOTH', 'proportion'), 'BUSTED-FG-E proportions' : get_omegas(val, 'BUSTED-FG-E', 'proportion'), 'BUSTED-BG-E proportions' : get_omegas(val, 'BUSTED-BG-E', 'proportion'), 'BUSTED-BOTH-E proportions' : get_omegas(val, 'BUSTED-BOTH-E', 'proportion'), }; } else { return NaN } //else return NaN }) let res_filter = _.filter(res, item => !Number.isNaN(item)) return res_filter }32:[{"id":"93f1ee59c0f6ae3943eb0a6ab8a16f3a7001ce61336196e41c9730b9286b9775d6347c120ebb84bcea69b3f26714542a1e21e45dbbb89eabdf3c2cd530bb15f9","href":"https://static.observableusercontent.com/files/93f1ee59c0f6ae3943eb0a6ab8a16f3a7001ce61336196e41c9730b9286b9775d6347c120ebb84bcea69b3f26714542a1e21e45dbbb89eabdf3c2cd530bb15f9","name":"all_genes.csv","type":"text/csv","lastModified":1738250533109.767,"size":5538521}] 2d:{"title":"BUSTED-PHE: neutral simulations from BUSTED-E","cells":[{"id":0,"value":"# BUSTED-PHE: neutral simulations from BUSTED-E ","pinned":false,"hidden":false,"mode":"md"},{"id":420,"value":"viewof dataset = Inputs.select([...new Set(_.map(result_json, (val, key)=> key.split('_')[0]))], {value: \"adh\", label: \"Choose a simulated dataset\"})","pinned":false,"hidden":false,"mode":"ojs"},{"id":734,"value":"viewof simulated_vals = Inputs.select([...new Set(_.map(result_json, (val, key)=> key.split('_')[1]))], {value: \"omega-10-weight-0.05\", label: \"Choose simulated values\"})","pinned":false,"hidden":false,"mode":"ojs"},{"id":52,"value":"viewof search = Inputs.search(table_data)","pinned":false,"hidden":false,"mode":"ojs"},{"id":55,"value":"table1 = Inputs.table(search, {\n rows : 15\n})","pinned":false,"hidden":false,"mode":"ojs"},{"id":904,"value":"### Cumulative count of selected dataset","pinned":false,"hidden":false,"mode":"md"},{"id":776,"value":" vegalite ({\n \"data\" : {\"values\" : table_data},\n \"columns\" : 3,\n \"hconcat\" : _.map ([[\"FG_pval\", \"p (test for positive selection in FG)\"],[\"BG_pval\", \"p (test for positive selection in BG)\"],[\"DF_pval\", \"p (test for difference between FG and BG)\"]], (d)=> {return {\n \"transform\": [{\n \"sort\": [{\"field\": d[0]}],\n \"window\": [{\"op\": \"count\", \"field\": \"count\", \"as\": \"Cumulative Count (no E)\"}],\n \"frame\": [null, 0],\n }],\n \"mark\": {\"type\" : \"area\", \"line\" : true, \"opacity\" : 0.25},\n \"encoding\": {\n \"x\": {\n \"field\": d[0],\n \"type\": \"quantitative\",\n \"title\" : d[1]\n },\n \"y\": {\n \"field\": \"Cumulative Count (no E)\",\n \"type\": \"quantitative\",\n //\"scale\": {\"domain\": [0, 100]}\n },\n }\n}})}); ","pinned":false,"hidden":false,"mode":"ojs"},{"id":803,"value":" vegalite ({\n \"data\" : {\"values\" : table_data},\n \"columns\" : 3,\n \"hconcat\" : _.map ([[\"FG_pval_E\", \"p (test for positive selection in FG)\"],[\"BG_pval_E\", \"p (test for positive selection in BG)\"],[\"DF_pval_E\", \"p (test for difference between FG and BG)\"]], (d)=> {return {\n \"transform\": [{\n \"sort\": [{\"field\": d[0]}],\n \"window\": [{\"op\": \"count\", \"field\": \"count\", \"as\": \"Cumulative Count (with E)\"}],\n \"frame\": [null, 0],\n }],\n \"mark\": {\"type\" : \"area\", \"line\" : true, \"opacity\" : 0.25},\n \"encoding\": {\n \"x\": {\n \"field\": d[0],\n \"type\": \"quantitative\",\n \"title\" : d[1]\n },\n \"y\": {\n \"field\": \"Cumulative Count (with E)\",\n \"type\": \"quantitative\",\n //\"scale\": {\"domain\": [0, 100]}\n },\n }\n}})}); \n","pinned":false,"hidden":false,"mode":"ojs"},{"id":925,"value":"$2f","pinned":true,"hidden":false,"mode":"ojs"},{"id":500,"value":"## Looking at genes with phenotype-specific positive selection (FG significant, BG no selection, significant difference)","pinned":false,"hidden":false,"mode":"md"},{"id":518,"value":"Inputs.table(pheno_specific_data)","pinned":false,"hidden":false,"mode":"ojs"},{"id":505,"value":"pheno_specific_data = {\n let tests = ['_E', '']\n return _.map (tests, (test)=> {\n return {\n 'Test' : test === '_E' ? 'With error correction' : 'No error correction' ,\n 'Pos Sel in FG (C1**)' : _.filter (table_data, (d)=>d['FG_pval' + test] <= 0.05 ).length,\n 'Pos Sel in BG (C*1*)' : _.filter (table_data, (d)=>d['BG_pval' + test] <= 0.05 ).length,\n 'Sig DF (C**1)' : _.filter (table_data, (d)=>d['DF_pval' + test] <= 0.05 ).length,\n 'C101' : _.filter (table_data, (d)=>d['FG_pval' + test] <= 0.05 && d['BG_pval' + test] <= 0.05 && d['DF_pval' + test] <=0.05).length,\n 'C1*1' : _.filter (table_data, (d)=>d['FG_pval' + test] <= 0.05 && d['DF_pval' + test] <=0.05).length, \n };\n });\n\n}","pinned":false,"hidden":false,"mode":"ojs"},{"id":215,"value":"### Results for selected gene","pinned":false,"hidden":false,"mode":"md"},{"id":209,"value":"---","pinned":false,"hidden":false,"mode":"md"},{"id":361,"value":"$30","pinned":false,"hidden":false,"mode":"ojs"},{"id":8,"value":"$31","pinned":false,"hidden":false,"mode":"ojs"},{"id":5,"value":"result_json = await d3.json (\"https://data.hyphy.org/web/busted-ph/wrapper/combined_sims.json\");","pinned":false,"hidden":false,"mode":"ojs"},{"id":713,"value":"filtered_res = Object.fromEntries(\n Object.entries(result_json).filter(([key, val]) => key.includes(dataset) && key.includes(simulated_vals))\n);","pinned":false,"hidden":false,"mode":"ojs"},{"id":71,"value":"pvcut = 0.05","pinned":false,"hidden":false,"mode":"ojs"},{"id":462,"value":"ensembl_convert = FileAttachment(\"all_genes.csv\").csv()","pinned":false,"hidden":false,"mode":"ojs"},{"id":778,"value":"vegalite = require(\"@observablehq/vega-lite@0.0\")","pinned":false,"hidden":false,"mode":"ojs"}],"files":"$W32","stdlib":"1","titling":"auto"}