31:T725,chart = { const width = 700; const height = 700; const min_node_size = 3; const links = graph.links.map(d => Object.create(d)); const nodes = graph.nodes.map(d => Object.create(d)); const simulation = d3.forceSimulation(nodes) .force("link", d3.forceLink(links).id(d => d.id)) .force("charge", d3.forceManyBody()) .force("x", d3.forceX()) .force("y", d3.forceY()); const svg = d3.create("svg") .attr("viewBox", [-width / 2, -height / 2, width, height]); svg.append ("defs").append ("marker").attr ('id', 'arrowhead') .attr ('orient', 'auto') .attr ('markerWidth', '2') .attr ('markerHeight', '4') .attr ('refX', '0.1') .attr ('refY', '2') .append ("path").attr ("d",'M0,0 V4 L2,2 Z'); const fill_me = (d)=> { if (d.SNP.indexOf ('417') >= 0) return 'firebrick'; return 'lightgrey'; } const link = svg.append("g") .attr("stroke", "#999") .attr("stroke-opacity", 0.6) .selectAll("line") .data(links) .join("line").attr ("marker-start",'url(#arrowhead)') .attr("stroke-width", 1); const sizef = (d)=>Math.max (min_node_size, Math.sqrt (d.F)* 50); const node = svg.append("g") .attr("stroke", "#666") .attr("stroke-width", 1.5) .selectAll("circle") .data(nodes) .join("circle") .attr("r", sizef) .attr ("fill", fill_me) .call(drag(simulation)); node.append("title") .text(d => d.SNP + " (" + d.F + ")"); simulation.on("tick", () => { link .attr("x1", d => d.source.x) .attr("y1", d => d.source.y) .attr("x2", d => d.target.x) .attr("y2", d => d.target.y); node .attr("cx", d => d.x) .attr("cy", d => d.y); }); invalidation.then(() => simulation.stop()); return svg.node(); }32:T63f,vegalite ({ "hconcat" : [{ "width": 400,"height": 400, "data": { "values": _.map (linkage_by_mutationOmicron) }, "transform" : [ {"calculate" : "datum.OR>1?datum.OR:1/datum.OR", "as" : "OR2"} ], "selection": { "view": {"type": "interval", "bind": "scales"} }, "mark": "circle", "encoding": { "y": { "field": "SNP1", "type": "nominal", "scale" : {"domain" : sorterOmicron}, "axis" : {"labelFontSize" : 14, title : ""} }, "x": { "field": "SNP2", "type": "nominal", "scale" : {"domain" : sorterOmicron}, "axis" : {"labelFontSize" : 14, title : ""} }, "size": {"field": "OR2","type": "quantitative", "legend" : {"orient" : "top", "title" : "OR"}}, "color": {"condition": {"test": "datum['OR'] < 1", "value": "steelblue"}, "value": "firebrick"} }}, { "width": 40,"height": 400, "data": { "values": _.map (linkage_by_mutationOmicron) }, "selection": { "view": {"type": "interval", "bind": "scales"} }, "mark": "circle", "encoding": { "y": { "field": "SNP1", "type": "nominal", "scale" : {"domain" : sorterOmicron}, "axis" : {"labelFontSize" : 0, title : ""} }, "size": {"field": "f1","type": "quantitative", "title" : "Global Frequency", "legend" : {"orient" : "right"}, "scale" : {"type": "log"}}, "color": {"value": "black"} }} ], "resolve": {"scale": {"size": "independent"}} }) 33:T9d3,linkage_by_mutation_generator = (filter)=> { let by_pair = {}; let included_codes = new Set(); _.each (haplotype_data.codes, (c,i)=> { //let tr = translate_ambiguous_codon (c[1]); if (filter (c)) { included_codes.add (i); } }); let haplo_with_mut = {}; let mc = haplotype_data.codes.length; let hc = haplotype_data.haplotypes.length; _.each (haplotype_data.haplotypes, (h)=> { const hl = h[0].length; for (let i = 0; i < hl; i++) { haplo_with_mut[h[0][i]] = 1 + ( haplo_with_mut[h[0][i]] ? haplo_with_mut[h[0][i]] : 0); for (let j = i+1; j < hl; j ++) { if (included_codes.has (h[0][i]) && included_codes.has (h[0][j])) { let code = h[0][i]*mc + h[0][j]; if (code in by_pair) { by_pair[code] += 1;//h[1]; } else { by_pair[code] = 1;//h[1]; } code = h[0][j]*mc + h[0][i]; if (code in by_pair) { by_pair[code] += 1;//h[1]; } else { by_pair[code] = 1;//h[1]; } } } } }); let total = hc; _.each (by_pair, (count, code)=> { code = +code; let c2 = code % mc; let c1 = (code-c2) / mc; //let N1 = haplotype_data.codes[c1][2]; //let N2 = haplotype_data.codes[c2][2]; let N1 = haplo_with_mut[c1]; let N2 = haplo_with_mut[c2]; //'AA' : (x)=>html`${x[0]}` //let aa_pair = haplotype_data.codes[c1][0].replace ("/", ":") by_pair[code] = _.extend (pair_frequency (N1, N2, count, total), {"SNP1" : haplotype_data.codes[c1][0] + ":" +haplotype_data.codes[c1][1] +"/" + translate_ambiguous_codon(haplotype_data.codes[c1][1]), "SNP2" : haplotype_data.codes[c2][0] + ":" + haplotype_data.codes[c2][1] + "/" + translate_ambiguous_codon(haplotype_data.codes[c2][1])}); by_pair[code] = _.extend (by_pair[code], {'N00' : total - N1 - N2 + count, 'N10' : N1 - count, 'N01' : N2 - count, 'N11' : count}); by_pair[code]['p'] = twoByTwo (by_pair[code]['N00'], by_pair[code]['N10'], by_pair[code]['N01'], by_pair[code]['N11']); by_pair[code]['OR'] = (by_pair[code]['N11']/(by_pair[code]['N01'] + by_pair[code]['N11'])) / (by_pair[code]['N10'] / (by_pair[code]['N00'] + by_pair[code]['N10'])); }); return by_pair; }34:[] 2f:{"title":"Haplotypes and mutational background profiles in SARS-CoV-2 enabled by data from ","cells":[{"id":0,"value":"md`# Haplotypes and mutational background profiles in SARS-CoV-2 enabled by data from $\"gisaid-logo\"$
`","pinned":false,"hidden":false,"mode":"ojs"},{"id":1137,"value":"For a given gene in the SARS-CoV-2 genome, view codon mutations found in at least **${haplotype_data[\"min-count\"]}** sequences, how many unique haplotypes for that gene they occur in, and what are the haplotypes that contain the mutation.\n\nUsing data from **${haplotype_data[\"N\"]}** sequences, comprising **${haplotype_data.M}** unique codon mutations passing frequency threshold, and **${haplotype_data[\"haplotypes\"].length}** haplotypes.\n\n[Download .json data](https://github.com/spond/SARS-CoV-2-variation/tree/master/haplotypes)","pinned":false,"hidden":false,"mode":"md"},{"id":1192,"value":"viewof segment = select ({\n options : [\"3C\",\"E\",\"ENDORNASE\",\"EXONUCLEASE\",\"HELICASE\",\"LEADER\",\"METHYLTRANSFERASE\",\"M\",\"N\",\"NSP10\",\"NSP2\",\"NSP3\",\"NSP4\",\"NSP6\",\"NSP7\",\"NSP8\",\"NSP9\",\"ORF3A\",\"ORF6\",\"ORF7A\",\"ORF8\",\"RDRP\",\"S\"],\n description: \"Select a gene/segment to view\",\n value: \"S\"\n})","pinned":false,"hidden":false,"mode":"ojs"},{"id":1576,"value":"md`**Figure 1.** Descriptive statistics on mutations and haplotypes.`","pinned":false,"hidden":false,"mode":"ojs"},{"id":1581,"value":"vegalite ({\n \"data\": { \"values\": mutation_table_data},\n \"mark\": {\"type\" : \"circle\", \"tooltip\" : {\"content\" : \"data\"}, \"opacity\" : 0.5},\n \"width\" : \"400\",\n \"height\" : \"400\",\n \"encoding\": {\n \"x\": {\n \"field\": \"frac_seq\",\n \"type\" : \"quantitative\",\n \"scale\" : {\"type\" : \"pow\", \"exponent\" : 1/3, \"domain\" : [0,1]},\n \"axis\": {\"titleColor\": \"black\", \"grid\" : false, \"titleFontSize\" : 14, \"title\" : \"Fraction of sequences with mutation\"}\n },\n \"y\": {\n \"field\": \"frac_haplo\",\n \"type\" : \"quantitative\",\n \"scale\" : {\"type\" : \"pow\", \"exponent\" : 1/3, \"domain\" : [0,1]},\n \"axis\": {\"titleColor\": \"black\", \"grid\" : false, \"titleFontSize\" : 14, \"title\" : \"Fraction of haplotypes with mutation\"}\n },\n \"size\": {\"value\" : 64},\n \"color\" : {\"field\" : \"h/s\", \"type\" : \"quantitative\", \"scale\": {\"scheme\": \"category20b\"}}\n }\n}\n)","pinned":false,"hidden":false,"mode":"ojs"},{"id":1637,"value":"vegalite ({\n \"data\": { \"values\": haplo_table_data},\n \"mark\": {\"type\" : \"circle\", \"tooltip\" : {\"content\" : \"data\"}, \"opacity\" : 0.5},\n \"width\" : \"400\",\n \"height\" : \"400\",\n \"encoding\": {\n \"x\": {\n \"field\": \"length\",\n \"type\" : \"quantitative\",\n //\"scale\" : {\"type\" : \"pow\", \"exponent\" : 1/3},\n \"axis\": {\"titleColor\": \"black\", \"grid\" : false, \"titleFontSize\" : 14, \"title\" : \"Mutations in haplotype\"}\n },\n \"y\": {\n \"field\": \"frac\",\n \"type\" : \"quantitative\",\n \"scale\" : {\"type\" : \"pow\", \"exponent\" : 1/3},\n \"axis\": {\"titleColor\": \"black\", \"grid\" : false, \"titleFontSize\" : 14, \"title\" : \"Fraction of sequences with haplotypes\"}\n },\n \"size\": {\"value\" : 64},\n //\"color\" : {\"field\" : \"h/s\", \"type\" : \"quantitative\", \"scale\": {\"scheme\": \"category20b\"}}\n }\n}\n)","pinned":false,"hidden":false,"mode":"ojs"},{"id":1378,"value":"md`**Table 1.** Explore codon allelic variants.`","pinned":false,"hidden":false,"mode":"ojs"},{"id":1368,"value":"viewof wrangled = Wrangler(mutation_table_data)","pinned":false,"hidden":false,"mode":"ojs"},{"id":1685,"value":"md`**Table 2.** Mutations occuring at frequencies between 0.001 and 0.2, that are in linkage disequilibirum (r²≥ 0.7)`","pinned":false,"hidden":false,"mode":"ojs"},{"id":1691,"value":"Inputs.table (_.map (_.filter (linkage_by_mutation, (d)=>d.r2 >= 0.7 && (d.f1 <= 0.2 || d.f2 <= 0.2)), (d)=>_.pick (d, ['SNP1','SNP2','r2','f1','f2','f12','p'])))","pinned":false,"hidden":false,"mode":"ojs"},{"id":1735,"value":"md`**Table 3.** Mutations that are linked based on OR > 10 (or OR < 0.1, OR computed for the rates at which SNP1 occurs in the presence/absense of SNP2) and a significant χ² association test. Only subconsensus mutations are used`","pinned":false,"hidden":false,"mode":"ojs"},{"id":1829,"value":"viewof subset_pairs = Inputs.search(t2)","pinned":false,"hidden":false,"mode":"ojs"},{"id":1740,"value":"Inputs.table (subset_pairs, {'format' : { 'SNP2' : (x)=>html`${x}`}})","pinned":false,"hidden":false,"mode":"ojs"},{"id":1765,"value":"$31","pinned":false,"hidden":false,"mode":"ojs"},{"id":1880,"value":"$32","pinned":true,"hidden":false,"mode":"ojs"},{"id":5,"value":"md`### Libraries and data`","pinned":false,"hidden":false,"mode":"ojs"},{"id":9,"value":"d3 = require(\"d3@6\")","pinned":false,"hidden":false,"mode":"ojs"},{"id":1194,"value":"import {select} from \"@jashkenas/inputs\"","pinned":false,"hidden":false,"mode":"ojs"},{"id":1510,"value":"haplotype_data = {\n let raw_data = await d3.json (\"https://raw.githubusercontent.com/spond/SARS-CoV-2-variation/master/haplotypes/codons.\"+segment+\".json\");\n raw_data.M = 0;\n _.each (raw_data.codes, (c,i)=> {\n if (c.length > 2) {\n c.push (c[2]/raw_data.N);\n c.push (c[3]/raw_data.haplotypes.length);\n raw_data.M ++;\n }\n });\n \n \n return raw_data;\n}","pinned":false,"hidden":false,"mode":"ojs"},{"id":1549,"value":"viewable_muts = _.map (mutation_table_data)","pinned":false,"hidden":false,"mode":"ojs"},{"id":1533,"value":"mutation_table_data = {\n let mt = _.sortBy (_.filter (haplotype_data.codes, (d)=>d.length > 2), (d)=>-d[5]);\n return _.map (mt, (d,i)=> {\n return {\n 'Site' : d[0],\n 'AV' : d[1],\n 'AA(AV)': translate_ambiguous_codon (d[1]),\n 'seq' : d[2],\n 'haplo' : d[3],\n 'frac_seq' : d[4],\n 'frac_haplo' : d[5],\n 'h/s' : d[5]/d[4],\n 'haplo_rank' : i+1\n };\n });\n}","pinned":false,"hidden":false,"mode":"ojs"},{"id":1625,"value":"haplo_table_data = {\n let mt = _.filter (haplotype_data.haplotypes, (d)=>d[0].length < 50);\n return _.map (mt, (d,i)=> {\n return {\n 'rank' : i+1,\n 'length' : d[0].length,\n 'count': d[1],\n 'frac' : d[1]/haplotype_data.N\n };\n });\n}","pinned":false,"hidden":false,"mode":"ojs"},{"id":1841,"value":"omicron_mutations = new Set ([\"S/67V\",\"S/95I\",\"S/142D\",\"S/212I\",\"S/339D\",\"S/371L\",\"S/373P\",\"S/375F\",\"S/417N\",\"S/440K\",\"S/446S\",\"S/477N\",\"S/478K\",\"S/484A\",\"S/493R\",\"S/496S\",\"S/498R\",\"S/501Y\",\"S/505H\",\"S/547K\",\"S/614G\",\"S/655Y\",\"S/679K\",\"S/681H\",\"S/764K\",\"S/796Y\",\"S/856K\",\"S/954H\",\"S/969K\",\"S/981F\"])","pinned":false,"hidden":false,"mode":"ojs"},{"id":1845,"value":"$33","pinned":false,"hidden":false,"mode":"ojs"},{"id":1853,"value":"filterFreq = (c)=> {\n let tr = translate_ambiguous_codon (c[1]);\n if (c[4] >= 0.001 && tr.length == 1 && tr != '?') return true;\n return false;\n}","pinned":false,"hidden":false,"mode":"ojs"},{"id":1859,"value":"filterFreqOmicron = (c)=> {\n let tr = translate_ambiguous_codon (c[1]);\n if (omicron_mutations.has (c[0]+tr)) return true;\n return false;\n}","pinned":false,"hidden":false,"mode":"ojs"},{"id":1890,"value":"pairwiseP = _.map (linkage_by_mutationOmicron)","pinned":false,"hidden":false,"mode":"ojs"},{"id":1864,"value":"linkage_by_mutationOmicron = linkage_by_mutation_generator (filterFreqOmicron)","pinned":false,"hidden":false,"mode":"ojs"},{"id":1895,"value":"sorterOmicron = _.sortBy (_.uniq(_.map (linkage_by_mutationOmicron, (d)=>d.SNP1)), (d)=>+d.split (\":\")[0].split (\"/\")[1])","pinned":false,"hidden":false,"mode":"ojs"},{"id":1658,"value":"linkage_by_mutation = linkage_by_mutation_generator (filterFreq)","pinned":false,"hidden":false,"mode":"ojs"},{"id":12,"value":"vegalite = require (\"vega-embed\")","pinned":false,"hidden":false,"mode":"ojs"},{"id":15,"value":"_ = require (\"lodash\")","pinned":false,"hidden":false,"mode":"ojs"},{"id":22,"value":"import {gene_coordinates} from \"@spond/revised-sars-cov-2-analytics-page\"","pinned":false,"hidden":false,"mode":"ojs"},{"id":1365,"value":"import {Wrangler, op} from \"@observablehq/data-wrangler\"","pinned":false,"hidden":false,"mode":"ojs"},{"id":692,"value":"site_equiv = _.groupBy (_.toPairs (jsonCodonLookup), (d)=>d[1])","pinned":false,"hidden":false,"mode":"ojs"},{"id":49,"value":"import {jsonCodonLookup} from \"@spond/sars_cov_2_sites\"","pinned":false,"hidden":false,"mode":"ojs"},{"id":58,"value":"import {multiAutoSelect} from \"@spond/untitled/3\"","pinned":false,"hidden":false,"mode":"ojs"},{"id":1402,"value":"pad_array = (arr)=>_.map (arr, (d)=>\"Site \" + d.toUpperCase())","pinned":false,"hidden":false,"mode":"ojs"},{"id":1477,"value":"selectable_sites = _.keys(jsonCodonLookup)","pinned":false,"hidden":false,"mode":"ojs"},{"id":1259,"value":"nucToCodons = _.chain (_.toPairs (jsonCodonLookup)).groupBy ((d)=>d[1]).mapValues ((d)=>_.map (d, (c)=>c[0])).value()","pinned":false,"hidden":false,"mode":"ojs"},{"id":596,"value":"parseSiteList = (site_list) => {\n let labels = {};\n site_list = _.map (site_list, (d)=>d.split (\"/\"));\n \n let sites = new Set (_.map (site_list, (d)=>{\n if (+d == d) {\n for (let i = d; i > d-3; i--) {\n if (i in nucToCodons) {\n d = nucToCodons[i][0].split (\"/\");\n break;\n }\n }\n \n }\n if (d[0].substr (0,4) == \"ORF1\") {\n let eq = null;\n _.each (site_equiv[jsonCodonLookup [d[0]+\"/\"+d[1]]], (tr)=> {\n if (tr[0].substr (0,4) != \"ORF1\") {\n eq = tr[0];\n labels[eq] = d[0] + \"/\" + d[1];\n }\n });\n return eq;\n }\n return d[0] + \"/\" + d[1];\n}));\n return [sites, labels]\n}","pinned":false,"hidden":false,"mode":"ojs"},{"id":1341,"value":"params = new URLSearchParams(location.search)","pinned":false,"hidden":false,"mode":"ojs"},{"id":1344,"value":"sitelist = params.get(\"sites\")","pinned":false,"hidden":false,"mode":"ojs"},{"id":1569,"value":"import {translate_ambiguous_codon} from \"@spond/usual-vs-unusual-mutation-analyses\"","pinned":false,"hidden":false,"mode":"ojs"},{"id":1668,"value":"pair_frequency = (snp1, snp2, together, N) => {\n \n let f1 = snp1/N,\n f2 = snp2/N;\n \n let f12 = together/N;\n \n let D = f12-f1*f2;\n \n return {'f1' : f1,\n 'f2' :f2,\n 'f12': f12,\n 'r2' : D*D/(f1*(1-f1)*f2*(1-f2)),\n 'Dprime' : D / (D > 0 ? Math.min (f1*(1-f2),f2*(1-f1)) : Math.max (-f1*f2, -(1-f1)*(1-f2)))};\n}","pinned":false,"hidden":false,"mode":"ojs"},{"id":1702,"value":"import {twoByTwo} from \"@spond/sars-cov-2-gene-trends\"","pinned":false,"hidden":false,"mode":"ojs"},{"id":1777,"value":"t2 = _.map (_.filter (linkage_by_mutation, (d)=>(d.f1 < 0.5 && d.f2 < 0.5 && (d.OR >= 10 || d.OR <= 0.1) && d.p == 0.0)), (d)=>_.pick (d, ['SNP1','SNP2','OR','N00','N01','N10','N11','f1','f2']))","pinned":false,"hidden":false,"mode":"ojs"},{"id":1774,"value":"graph = {\n let unique_ids = {};\n let nodes = [];\n let links = [];\n for (let i = 0; i < t2.length; i++) {\n let idx = [];\n _.each ([[t2[i].SNP1,t2[i].f1], [t2[i].SNP2,t2[i].f2]], (n)=> {\n if (! (n[0] in unique_ids)) {\n unique_ids[n[0]] = nodes.length;\n nodes.push (\n {\n 'id' : nodes.length,\n 'SNP' : n[0],\n 'F' : n[1]\n }\n );\n }\n idx.push (unique_ids[n[0]]);\n \n });\n links.push ({'source' : idx[0], 'target' : idx[1], 'OR' : t2[i].OR});\n\n }\n\n\n return {\n 'nodes' : nodes,\n 'links' : links\n }\n}","pinned":false,"hidden":false,"mode":"ojs"},{"id":1767,"value":"drag = simulation => {\n \n function dragstarted(event, d) {\n if (!event.active) simulation.alphaTarget(0.3).restart();\n d.fx = d.x;\n d.fy = d.y;\n }\n \n function dragged(event,d) {\n d.fx = event.x;\n d.fy = event.y;\n }\n \n function dragended(event,d) {\n if (!event.active) simulation.alphaTarget(0);\n d.fx = null;\n d.fy = null;\n }\n \n return d3.drag()\n .on(\"start\", dragstarted)\n .on(\"drag\", dragged)\n .on(\"end\", dragended);\n}","pinned":false,"hidden":false,"mode":"ojs"},{"id":1771,"value":"color = {\n const scale = d3.scaleOrdinal(d3.schemeCategory10);\n return d => scale(d.diff);\n}","pinned":false,"hidden":false,"mode":"ojs"}],"files":"$W34","stdlib":"1","titling":"auto"}