31:T1774,viewof chart = { let i = 0; let root = d3.hierarchy(tracking_root).eachBefore(d => d.index = i++); const nodes = root.descendants(); const svg = d3.create("svg") .attr("viewBox", [-nodeSize[0] / 2, -nodeSize[1] * 3 / 2, width, (nodes.length + 1) * nodeSize[1]]) .attr("font-family", "sans-serif") .attr("font-size", 10) .style("overflow", "visible"); let returnObject = svg.node(); returnObject.value = ""; svg.on ("click", (d)=>{returnObject.value="";returnObject.dispatchEvent(new CustomEvent('input'))}); let highlight = globalHighlight; if (highlight) { highlight = new Set (_.map (highlight.split (","), (d)=>d.replace (" ",""))); } else { highlight = new Set (); } const link = svg.append("g") .attr("fill", "none") .attr("stroke", "#999") .selectAll("path") .data(root.links()) .join("path") .attr("stroke-width", (d)=>2*tracking_info[d.target.data.id].CPI) .attr("stroke", (d)=>highlight.has (d.target.data.name) ? "red" : null) .attr("d", d => ` M${d.source.depth * nodeSize[0]},${d.source.index * nodeSize[1]} V${d.target.index * nodeSize[1]} h${nodeSize[0]} `); link.append ("title").text ((d)=>tracking_info[d.target.data.id].CPI); /*const link_labels = svg.append ("g").selectAll("text") .data(root.links()) .join("text") .attr ("x", (d)=>d.target.depth * nodeSize) .attr ("dx", "-0.2em") .attr ("y", (d)=>d.target.index * nodeSize) .attr("font-size", 7) .attr ("dy", "1em") .attr("text-anchor", "end") .attr("font-weight", "lighter") .text ((d)=>tracking_info[d.target.data.id].CPI);*/ let size_scaler = d3.scaleLog() .domain([1, N]) .rangeRound([1,6]) const node = svg.append("g") .selectAll("g") .data(nodes) .join("g") .attr("transform", d => `translate(0,${d.index * nodeSize[1]})`); _.each ([[100,510,"timeSeries","Mutation frequency"],[100,700,"timeSeriesSig","Signature frequency"]], (settings)=> { let tc_width = 100; let tc_offset = 400; let tc_data = "timeSeries"; let tc_title = "Frequency over time"; [tc_width,tc_offset,tc_data,tc_title] = settings; const time_scale = d3.scaleTime() .domain(date_range) .range([tc_offset, tc_offset+tc_width]); const freq_scale = d3.scaleLinear() .domain ([0,1]) .range ([nodeSize[1]/3,-nodeSize[1]/3]); const time_area = d3.area() .curve(d3.curveBasis) .x(d => time_scale(d.date)) .y0(freq_scale(0)) .y1(d => freq_scale(d.count)); let firstSeenTime = []; node.each ((d,i)=> { if ( tracking_mutations_table[d.data.id][tc_data].length) { firstSeenTime.push ({'y' :d.index * nodeSize[1] + nodeSize[1]/3 , 'x' : tracking_mutations_table[d.data.id][tc_data][0].date})}; }); /* trace the first time a mutation was seen */ firstSeenTime = _.sortBy (firstSeenTime, (d)=>d.y); const first_seen = d3.line() .curve(d3.curveLinear) .x(d => time_scale(d.x)) .y(d => d.y); svg.append ("path").datum (firstSeenTime).attr("stroke", "grey") .attr("stroke-width", 0.5) .attr("fill", "none") .attr("d", first_seen); const axis_g = svg.append ("g").attr("transform", `translate(0,${-2*nodeSize[1]})`) .call(d3.axisTop(time_scale) .ticks(d3.timeMonth.every(2)) .tickFormat(d3.timeFormat("%m"))) .call(g => g.select(".domain") .remove()); //.tickFormat(d => d <= d3.timeYear(d) ? d.getFullYear() : null)) svg.append ("text").attr ("x", tc_offset) .attr ("y", -nodeSize[1]) .attr("dy", "0.32em") .attr("text-anchor", "start") .attr("font-weight", "bold") .text(tc_title); node.append("path") .datum((d)=>tracking_mutations_table[d.data.id][tc_data]) .attr("stroke", "black") .attr("fill", "#999") .attr("d", time_area); }); node.append("circle") .attr("cx", d => d.depth * nodeSize[0]) .attr("r", d=>size_scaler(1+tracking_mutations_table[d.data.id]["mapped"][0])) .attr("fill", d => highlight.has (d.data.name) ? 'red' : (d.children ? null : "#999")) .on ("click", (e,d)=>{returnObject.value=sequences_with_tracking_info.mutation_paths[d.data.name].join (",");returnObject.dispatchEvent(new CustomEvent('input'));e.stopPropagation()}) .append("title").text(d=>tracking_mutations_table[d.data.id]["mapped"][0]); node.append("text") .attr("dy", "0.32em") .attr("x", d => d.depth * nodeSize[0] + 8) .on ("click", (e,d)=>{returnObject.value=d.data.name;returnObject.dispatchEvent(new CustomEvent('input')); e.stopPropagation();}) .text(d => d.data.name) .style ("fill", (d)=>highlight.has (d.data.name) ? 'red' : null); for (const {label, displayed, format, x, textOnly, clicker, explanation} of columns) { svg.append("text") .attr("dy", "0.32em") .attr("y", -nodeSize[1]) .attr("x", x) .attr("text-anchor", "end") .attr("font-weight", "bold") .text(displayed) .append ("title") .text (explanation); if (textOnly) { let nodes = node.append("text") .attr("dy", "0.32em") .attr("x", x) .attr("text-anchor", "end") .data(root.descendants().map ((d)=>{return {'value' :label (d.data)};})) .text(d => format(d.value, d)); if (clicker) { nodes.on ("click", clicker); } } else { node.each (function (d) { format (d, d3.select (this),nodeSize) }); } } return returnObject; }32:T811,genomicDist = vegalite ({ "$schema": "https://vega.github.io/schema/vega-lite/v4.json", "config" : { "bar": {continuousBandSize : 3} }, "data": { "values": other_variants, }, "vconcat" : [ { "width": 800, "height" : 100, "selection": { "brush": {"type": "interval", "encodings": ["x"]} }, "mark": {"type": "bar", "tooltip": {"content": "data"}, "filled": true, "clip" : true}, "encoding": { "y": { "field": "fraction", "type": "quantitative", "axis" : {"grid" : false, "title" : "Mutation frequency", "orient" : "left"}, "scale" : {"type" : "sqrt", domain: [0,1]} }, "x" : { "field": "coord", "type": "quantitative", "axis" : {"grid" : false, "title" : "Genomic Position"}, "scale" : {domain : [260,29880]} }, "color" : { "field" : "kind", "type" : "nominal", "title" : "SNP kind" } } }, { "width": 800, "height" : 100, "selection": { "brush": {"type": "interval", "encodings": ["x"]} }, "mark": {"type": "bar", "tooltip": {"content": "data"}, "filled": true, "clip" : true}, "encoding": { "y": { "field": "fraction", "type": "quantitative", "axis" : {"grid" : false, "title" : "Mutation frequency", "orient" : "left"}, "scale" : {"type" : "sqrt", domain: [0,1]} }, "x" : { "field": "coord", "type": "quantitative", "axis" : {"grid" : false, "title" : "Genomic Position"}, "scale" : {"domain": {"selection": "brush"}, zero:false, domainMin: 0, domainMax : 29880} }, "color" : { "field" : "kind", "type" : "nominal" } } //"shape": {"field": "species", "type": "nominal"} }] //"resolve": {"scale": {"y": "independent"}} })33:Tadf,trends = { const marginBottom = 20, marginLeft = 50, marginTop = 10, marginRight = 70; const x = d3.scaleTime() .domain(date_range) .range([marginLeft, trendWidth-marginRight]); const sampleCount = _.map (sequencesByWeekWithAttr, (d,k)=>{return {'date' : deltaweekToDate(k), 'count' : d}}); const y = d3.scaleLinear([0, 1], [trendHeight-marginBottom, marginTop]); const y2 = d3.scaleLinear([0, d3.max (sampleCount, (d)=>d.count)], [trendHeight-marginBottom, marginTop]); const z = d3.interpolateTurbo; const area = d3.area().curve(d3.curveBumpX) .x((d, i) => { //console.log (d.data.date); return x(d.data.date); }) .y0(d => y(d[0])) .y1(d => y(d[1])); const sampleCurve = d3.line().curve(d3.curveBasis) .x((d, i) => { //console.log (d); return x(d.date); }) .y(d => y2(d.count)); const svg = d3.create("svg") .attr("viewBox", [0, 0, trendWidth, trendHeight]); const path = svg.selectAll("path") .data(binStackstack (binnedDataForStacking)) .join("path") .attr("d", area) .attr ("stroke", "grey") .attr ("stroke-width", "0.5px") .attr("fill", (d,i) => { return binColorsWithPredef(binMutationClasses[i], i); }) .append ("title").text ((d,i)=>binMutationClasses[i]); const samplesPath = svg.append("path") .datum(sampleCount) .attr("d", sampleCurve) .attr("fill", "none") .attr ("stroke-width", "3px") .attr ("stroke", "#444444"); const axis_g = svg.append ("g").attr("transform", `translate(0,${trendHeight-marginBottom})`) .call(d3.axisBottom(x) .ticks(d3.timeMonth.every(2))) .call(g => g.select(".domain") .remove()).selectAll ("text") .attr ("font-family","Helvetica").attr ("font-size", "14"); const axis_yg = svg.append ("g").attr("transform", `translate(${marginLeft},0)`) .call(d3.axisLeft(y).tickFormat (report_fraction)) .call(g => g.select(".domain") .remove()).selectAll ("text") .attr ("font-family","Helvetica").attr ("font-size", "14"); const countFormat = d3.format(".2s"); const axis_y2g = svg.append ("g").attr("transform", `translate(${trendWidth-marginRight},0)`) .call(d3.axisRight(y2).tickFormat (countFormat)) .call(g => g.select(".domain") .remove()) .selectAll ("text") .attr ("font-family","Helvetica").attr ("font-size", "14"); svg.append ("text").attr("transform", "translate(" + (trendWidth-marginRight) + "," + (trendHeight-marginBottom)/2 + ") rotate(90)").text ("Sample Count").attr ("dy", "-3em").attr ("text-anchor", "middle").attr ("font-family","Helvetica").attr ("font-size", "18"); return svg.node(); }34:T6f8,columns = [ { label: function (d) {return "" + d["pos"] + d["variant"]}, displayed: "Variant", format: (d)=>d, x: 315, textOnly: true, clicker: (e,d)=>{ window.open( "https://nextstrain.org/ncov/global?c=gt-nuc_" + parseInt (d.value), "_blank") }, explanation: "The mutation (position/nucleotide) relative to the inferred ancestral strain" }, { label: function (d) {return tracking_mutations_table[d.id]["count"];}, displayed: "Freq.", format: report_fraction, x: 355, textOnly: true, clicker: null, explanation: "The fraction of sampled genomes with this ONE mutation" }, { label: function (d) {return tracking_mutations_table[d.id]["mapped"][0];}, displayed: "Mapped", format: report_int, x: 400, textOnly: true, clicker: null, explanation: "The fraction of sampled genomes with this mutation AND all the ancestral mutations" }, // { label: function (d) {return tracking_mutations_table[d.id]["firstSeenMut"];}, displayed: "First mutation", /*format: function (d,obj,size) { //console.log (obj); //let flag = obj.append ()); }, */ format : (d)=>d, x: 505, textOnly: true, clicker: null, explanation: "When did this ONE mutation first appear in sampled genomes" }, { label: function (d) {return tracking_mutations_table[d.id]["firstSeen"];}, displayed: "First signature", /*format: function (d,obj,size) { //console.log (obj); //let flag = obj.append ()); }, */ format : (d)=>d, x: 695, textOnly: true, clicker: null, explanation: "When did this mutation AND all the ancestral mutations first appear in sampled genomes" } ]35:T461,linkage_data = { if (loaderParagraph.value) { let rd = loaderParagraph.value[0]; let sbd = {}; _.each (rd.sequences, (d,id)=> { let m = {}; for (let i = 0; i < d.length; i+=2) { m[""+(+d[i]+1)+d[i+1]] = 1; } sbd[id] = m; }); let records = {}; let redD = d3.timeParse ("%Y%m%d")(metaData.reference).getTime(); _.each (rd.sequences, (d,id)=> { let r = [id,null,null]; let date = metaData.values[0][metaData.meta[id][0]]; if (date) { r[1] = new Date (redD + date*24*3600*1000); } let place = metaData.values[1][metaData.meta[id][1]]; if (place) { r[2] = [place,metaData.values[2][metaData.meta[id][2]],metaData.values[3][metaData.meta[id][3]],metaData.values[4][metaData.meta[id][4]]]; } records[id] = r; }); return { reference_base: rd.reference_base, variants: rd.variants, records : records, sequences: sbd }; } return { reference_base: [], variants: [], records : [], sequences: [] }; }36:T75b,sequencesByCountryAndWeek = (seqSet, sequenceKey) => { let sbcw = {"allweeks" : {}}; /* "country" -> {"total" : count "byweek" : { "week": X, "count" : Y } "allweeks" -> [array of weeks since start for which we have data] ... */ sequenceKey = sequenceKey || ((d,id)=>resolved_name (d[1])); _.each (seqSet || _.keys(linkage_data.sequences), (id)=> { let seqDate = linkage_data.records[id][1]; let seqLocation = linkage_data.records[id][2]; if (seqLocation) { if (seqLocation[1]) { seqLocation = sequenceKey(seqLocation,id); } else { seqLocation = null; } } else { seqLocation = null; } if (!(seqLocation in sbcw)) { sbcw [seqLocation] = {"total" : 0, byweek : {}}; } sbcw [seqLocation].total ++; if (seqDate) { seqDate = deltaWeeks (seqDate); sbcw["allweeks"][seqDate] = 0; if (!(seqDate in sbcw[seqLocation]["byweek"])) { sbcw [seqLocation]["byweek"][seqDate] = 0; } sbcw [seqLocation]["byweek"][seqDate]++; } }); sbcw["allweeks"] = _.sortBy (_.map(_.keys(sbcw["allweeks"]), (k)=>+k)); _.each (sbcw, (data, name) => { let country = lookupCountryID (name); if (country) { data ['id'] = country.ccn3; data ['name'] = name; if (doCumulativeCounts) { let sum = 0; _.each (sbcw["allweeks"], (wk,i)=> { if (wk in data['byweek']) { sum += data['byweek'][wk]; } data['byweek'][wk] = sum; }); } } }); return sbcw; }37:T489,tracking_for_display = { let parentShortcuts = {}; if (hideUnreliable) { let cleaned_tracker = []; _.each (tracking_info, (d)=> { let mr = _.clone (d); if (d.parent) { if ((!d.bootstrap || d.bootstrap <= 0.5)) { parentShortcuts[d.name] = d.parent.name; return; } mr.parent = d.parent.name } mr.children = []; cleaned_tracker.push (mr); }); let name_to_id = {}; _.each (cleaned_tracker, (d,i) => { d["id"] = i; name_to_id [d.name] = i; while (parentShortcuts[d.parent]) { d.parent = parentShortcuts[d.parent]; } }); _.each (cleaned_tracker, (d, i) => { if (d.parent) { let parent_object = cleaned_tracker[name_to_id[d.parent]]; if (!("children" in parent_object)) { parent_object["children"] = []; } parent_object["children"].push (d); d.parent_name = d.parent; d.parent = parent_object; } }); return cleaned_tracker; } return tracking_info; }38:T5c4, sequences_with_tracking_info = { let tagged_sequences = {}; // check if "reference" genome has some mutations in it already _.each (tracking_info, (data)=> { if (linkage_data.reference_base[data.pos-1] == data.variant) { data.reference_value = true; } }); _.each (linkage_data.sequences, (data, id)=>{ if (!sequenceFilter (id, data)) return; let tags = {}; _.each (tracking_info, (d) => { if (d.reference_value) { if (_.every (["A","C","G","T"], (n)=> (("" + d.pos + n) in data) == false)) { tags[d.name] = 1; } } else { let sig = "" + d.pos + d.variant; if (sig in data) { tags[d.name] = 1; } } }); tagged_sequences [id] = tags; }); let md = {}; _.each (tracking_info, (d)=> { md[d.name] = d; }); let mutation_data = []; let mutation_dict = {}; _.each (tracking_info, (d) => { let path = new Set ([d.name]); let parent = d.parent_name; let k = 0; while (parent && k < 50) { parent = md[parent]; path.add (parent.name); parent = parent.parent_name; k++; } mutation_dict [d.name] = [...path]; mutation_data.push (path); }); return { 'sequences' : tagged_sequences, 'mutations' : mutation_data, 'mutation_paths': mutation_dict }; }39:T8f2,makeAnimatedMap = (mapData, mapDate, colorScale, doCumulative) => { const container = d3.create("div"); const svg = container .append('svg') .attr('width', mapWidth) .attr('height', mapHeight); const lookupField = doCumulative ? "fraction_by_week" : "byweek"; const path = d3.geoPath(mapProjection); let makeLabel = function(d) { if (d.id in mapData) { if (mapDate) { if (mapDate in mapData[d.id][lookupField]) { return mapData[d.id].name + " :" + pf(mapData[d.id]["fraction_by_week"][mapDate]) + ", " + mapData[d.id]["byweek"][mapDate] + " sequences"; } return "N/A"; } return mapData[d.id].name + " :" + pf(mapData[d.id].fraction) + ", " + mapData[d.id].total + " sequences"; } return "N/A"; } let pf = d3.format (".2p"); let colorFunction = function(d) { if (d.id in mapData) { if (mapDate) { if (mapDate in mapData[d.id][lookupField]) return colorScale(mapData[d.id][lookupField][mapDate]); return "#ccc"; } return colorScale (mapData[d.id].fraction); } return "#ccc"; } let c = svg .append('g') .selectAll('path') .data(countryData.features) .join('path') .attr('fill', f => colorFunction(f)) .attr('stroke', '#ccc') .attr('stroke-width', 0.5) .attr('d', path) .attr("class", "country"); /*.append('title').text (d=>{ return makeLabel (d); });*/ svg .append('path') .attr('fill', 'none') .attr('stroke', 'black') .attr('pointer-events', 'none') .attr('d', path(countryData)); const tooltip = svg.append("g").style ("background-fill", "white"); svg .selectAll(".country") .on("touchmove mousemove", function(event, d) { tooltip.call( callout, makeLabel (d) ); tooltip.attr("transform", `translate(${d3.pointer(event, this)})`); d3.select(this) .attr("stroke", "red") .raise(); }) .on("touchend mouseleave", function() { tooltip.call(callout, null); d3.select(this) .attr("stroke", null) .lower(); }); return container.node(); }3a:T448,earliest_seq_from_set = (s)=>{ let date = null, date1 = null; let locations = [], locations1 = []; let set = _.sortBy (_.filter (s, (d)=>linkage_data.records[d][1]) , (m)=>linkage_data.records[m][1]); if (set.length) { date = linkage_data.records[set[0]][1]; _.some (set, (s)=> { if ((linkage_data.records[s][1] ? linkage_data.records[s][1].getTime() : null) == date.getTime()) { locations.push (linkage_data.records[s][2]); return false; } return true; }); date1 = linkage_data.records[set[set.length-1]][1]; locations1 = [linkage_data.records[set[set.length-1]][2]]; for (let k = set.length-2; k >= 0; k--) { if ((linkage_data.records[set[k]][1] ? linkage_data.records[set[k]][1].getTime() : null) == date1.getTime()) { locations1.push (linkage_data.records[set[k]][2]); } else { break; } } } return [date, merge_location_info(locations), date1, merge_location_info(locations1), locations]; }3b:Td68,tracking_mutations_table = { let by_mutation = [], by_position = {}, earliest_by_position = {}; /*for (const m of sequences_with_tracking_info.mutations[5].values()) { by_mutation.push (m); } return by_mutation;*/ let SQ = _.size (sequences_with_tracking_info.sequences); let sk = _.map (sequences_with_tracking_info.sequences, (s,k)=>[k,s]); let map_loc = (l)=> { if (!l) return ""; if (l[1].length) return l[1]; return l[0]; }; _.each (sequences_with_tracking_info.sequences, (d,seq_name)=>{ _.each (d, (ignore, m)=> { if (! (m in by_position)) by_position[m] = []; by_position[m].push (seq_name); } )}); _.each (sequences_with_tracking_info.mutations, (d, index)=> { if (! (tracking_info[index].name in by_position)) { by_position[tracking_info[index].name] = []; } let matched_seqs = _.map(_.filter (sk, (s)=> { for (const m of d.values()) { if (! (m in s[1])) { return false; } } return d.size == _.size (s[1]); }), (s)=>s[0]); //[date, location, date1,location1] = earliest_seq_from_set (matched_seqs); let locations = []; //[d1,l1,d2,l2,l3] = earliest_seq_from_set (by_position[tracking_info[index].name]); let time_series = _.map ([matched_seqs, by_position[tracking_info[index].name]], (ms,i)=> { let timeSeries = {}; let min_date = new Date(); locations.push ([]); min_date = min_date.getTime(); locations[i] = []; _.each(_.filter (ms, (d)=>(linkage_data.records[d]) && linkage_data.records[d][1]), (d)=> { //console.log (linkage_data.records[d][1]); let dtw = deltaWeeks(linkage_data.records[d][1]); let ttm = linkage_data.records[d][1].getTime(); if (ttm < min_date) { min_date = ttm; locations[i] = []; } if (ttm == min_date) { locations[i].push (linkage_data.records[d][2]); } if (timeSeries[dtw]) { timeSeries[dtw] ++; } else { timeSeries[dtw] = 1; } }); timeSeries = _.map (timeSeries, (d,i)=>{ return { 'date': deltaweekToDate (i), 'count' : d/sequencesByWeek[i]} }); return timeSeries; }); by_mutation.push ({ name: tracking_info[index].name, variant: ["" + tracking_info[index].pos + tracking_info[index].variant, tracking_info[index].reference_value], count: by_position[tracking_info[index].name].length/SQ, //sampled_on: [date, date1], //location: [map_loc(location),map_loc(location1)], mapped: [matched_seqs.length, [...d].join (",")], firstSeen: map_loc(merge_location_info(locations[0])), firstSeenMut: map_loc(merge_location_info(locations[1])), //last_seen_mut_location: map_loc(l2), timeSeries: time_series[1], timeSeriesSig: time_series[0]}); }); return by_mutation; }3c:[] 2f:{"title":"Tracking signature mutations in SARS-CoV-2 relative to the inferred progenitor strain enabled by data from ","cells":[{"id":0,"value":"intro = md`# Tracking signature mutations in SARS-CoV-2 relative to the inferred progenitor strain enabled by data from $\"gisaid-logo\"$
`","pinned":false,"hidden":false,"mode":"ojs"},{"id":3278,"value":"loaderParagraph = {\n let loader = html`

Loading variant data...

`;\n loader.value = null;\n yield loader;\n let rd = await obtainSourceData (db_files[0]);\n loader = html`

Loading metadata...

`;\n loader.value = null;\n yield loader;\n let an = await obtainSourceData (db_files[1]);\n loader = md`Loaded **${_.size (rd.sequences)}** sequences.`;\n yield loader;\n loader.value = [rd,an];\n}","pinned":false,"hidden":false,"mode":"ojs"},{"id":3287,"value":"md`\n_See [the preprint](https://www.biorxiv.org/content/10.1101/2020.09.24.311845v2) describing the approach_
\n[Classify your sequence based on its genome](https://observablehq.com/@spond/sars-cov-2-classify)\n\nThese sequences have been sampled between ${report_date_f(date_range[0])} and ${report_date_f(date_range[1])} and is based on **${tracking_info.length} signature** mutations. Sequence annotation information contains data on ${variantFreqs.length} variants with minimal variant frequency of ${formatFraction(minVF)}.`","pinned":false,"hidden":false,"mode":"ojs"},{"id":3255,"value":"viewof db_date = select({\n options: [\"January 2021\",\"April 2021\"],\n title: `Use database stapshot as of`,\n value : \"January 2021\"\n})","pinned":false,"hidden":false,"mode":"ojs"},{"id":977,"value":"figure1Desc = md`**Figure 1** Signature mutations away from the inferred progenitor SARS-CoV-2 strain, in estimated order of appearance. _Mapped_ refers to the count of the genomes that include all the mutations in the **signature** (path leading to the listed mutation from the root of the tree), and no other signature mutations; click on the **node** to view geographic distribution of the signature; click on the **label** to view the geographic distribution of just this one mutation. Size of the nodes ~ to the number of mapped genomes, thickness of branch ~ co-occurence proportion (mouse over to view). Click on **variant** (e.g. 2416C) to view this mutation on [NextStrain](http://nextstrain.org).`","pinned":false,"hidden":false,"mode":"ojs"},{"id":1794,"value":"viewof as = autoSelect({\n options: _.uniq (_.flatten(_.map (linkage_data.sequences, (d,k)=>lookupLocation (k)))),\n title: `Restrict to specific country or region or locale (empty string to use all)`,\n placeholder: \"Select a location \"\n})","pinned":false,"hidden":false,"mode":"ojs"},{"id":1837,"value":"figure1View = md`Viewing data on ${_.size (sequences_with_tracking_info.sequences)} sequences with time and location information). Mouse over column headings for description.`","pinned":false,"hidden":false,"mode":"ojs"},{"id":3038,"value":"viewof hideUnreliable = checkbox({\n options: [{ value: \"toggle\", label: \"Hide mutations with uncertain order\" }],\n value: \"toggle\"\n})","pinned":false,"hidden":false,"mode":"ojs"},{"id":1465,"value":"$31","pinned":false,"hidden":false,"mode":"ojs"},{"id":732,"value":"figure2Desc = md`**Figure 2** Geographic distribution of sequences for ${chart.length ? chart : \"any\"} signature`","pinned":false,"hidden":false,"mode":"ojs"},{"id":2261,"value":"viewof mapDate = Scrubber(forMapPlot.allweeks, {\n delay: 500,\n loopDelay: 100000,\n autoplay: false,\n format: sliderDate\n})","pinned":false,"hidden":false,"mode":"ojs"},{"id":2300,"value":"geospatialLegend = legend({\n color: colorScale,\n title: \"Cumulative fraction of sequences with the \" + chart + \" signature\",\n tickFormat: \"%\"\n})","pinned":false,"hidden":false,"mode":"ojs"},{"id":2175,"value":"\nmakeAnimatedMap (forMapPlotID, mapDate, colorScale, true)","pinned":false,"hidden":false,"mode":"ojs"},{"id":2335,"value":"viewof doCumulativeCounts = checkbox({\n options: [{ value: \"toggle\", label: \"Cumulative\" }],\n value: \"toggle\"\n})","pinned":false,"hidden":false,"mode":"ojs"},{"id":752,"value":"figure3Desc = md`**Figure 3** Distribtion of other SNPs across the genome. _Click and drag in the top plot to zoom in_.`","pinned":false,"hidden":false,"mode":"ojs"},{"id":739,"value":"$32","pinned":false,"hidden":false,"mode":"ojs"},{"id":2346,"value":"figure4Desc = md`**Figure 4** Temporal distribution of signature mutation groups ${!majorOnly?\"that reach a minimum frequency of \" + report_fraction(minFreqBin) + \" during at least one week\" : \"that comprise major lineages\"} ${as.length? \"restricted to \" + as : \"\"}. The thick line shows the number of sequences sampled during each week.`","pinned":false,"hidden":false,"mode":"ojs"},{"id":3043,"value":"viewof majorOnly = checkbox({\n options: [{ value: \"toggle\", label: \"Track only major lineages\" }],\n value: \"toggle\"\n})","pinned":false,"hidden":false,"mode":"ojs"},{"id":2519,"value":"trendLegend = swatches({\n color: d3.scaleOrdinal(binMutationClasses, _.map (binMutationClasses, (d,i)=>binColorsWithPredef(d,i))),\n title: \"Proportion of sequences with a specific mutation signature by week\",\n //tickFormat: \"%\"\n})","pinned":false,"hidden":false,"mode":"ojs"},{"id":2427,"value":"$33","pinned":false,"hidden":false,"mode":"ojs"},{"id":2170,"value":"md`----- \n### Data and libraries from this point on`","pinned":false,"hidden":false,"mode":"ojs"},{"id":1254,"value":"trackingSignature = {\n let dict = {};\n _.each (chart.split (\",\"), (m)=>dict[m]=true);\n return _.map (_.filter (tracking_info, (d)=>d.name in dict), (d)=>toSignature(d)).join (\", \");\n \n};","pinned":false,"hidden":false,"mode":"ojs"},{"id":1514,"value":"$34","pinned":false,"hidden":false,"mode":"ojs"},{"id":3261,"value":"db_files = {\n if (db_date == \"April 2021\") {\n return [\"https://raw.githubusercontent.com/veg/SARS-CoV-2/compact/data/fasta/2021-04-10/sequences.variants.json\",\"https://raw.githubusercontent.com/veg/SARS-CoV-2/compact/data/fasta/2021-04-10/sequence-info.json\"]\n }\n return [\"https://raw.githubusercontent.com/veg/SARS-CoV-2/compact/data/fasta/2021-01-07/sequences.variants.json\",\"https://raw.githubusercontent.com/veg/SARS-CoV-2/compact/data/fasta/2021-01-07/sequence-info.json\"];\n}","pinned":false,"hidden":false,"mode":"ojs"},{"id":2981,"value":"$35","pinned":false,"hidden":false,"mode":"ojs"},{"id":2984,"value":"metaData=loaderParagraph.value[1]","pinned":false,"hidden":false,"mode":"ojs"},{"id":1760,"value":"mutation2track = \"\"","pinned":false,"hidden":false,"mode":"ojs"},{"id":499,"value":"countries = _.flatten ([[['World', -1,'']],_.sortBy (_.filter (_.map (_.countBy (linkage_data.records, (d)=>d[2] ? d[2][1] : \"\"), (d,k)=>[k,d,\"country\"]), (d)=>d[1]>=100), (d)=>-d[1]),_.sortBy (_.filter (_.map (_.countBy (linkage_data.records, (d)=>d[2] ? d[2][2] : \"\"), (d,k)=>[k,d,\"state\"]), (d)=>d[1]>=100 && d[0].length), (d)=>-d[1])],true)","pinned":false,"hidden":false,"mode":"ojs"},{"id":1803,"value":"lookupLocation = (id, level) => {\n if ((id in linkage_data.records) && linkage_data.records[id][2]) {\n if (level) {\n \n }\n return _.filter (linkage_data.records[id][2], (d)=>d.length);\n }\n return null;\n};","pinned":false,"hidden":false,"mode":"ojs"},{"id":1677,"value":"deltaWeeks = (d)=>Math.floor(((d)-date_range[0])/(3600*24*1000*7))","pinned":false,"hidden":false,"mode":"ojs"},{"id":1683,"value":"deltaweekToDate = (d)=> {\n return new Date (d*24*3600*7*1000+date_range[0].getTime());\n}","pinned":false,"hidden":false,"mode":"ojs"},{"id":1664,"value":"sequencesByWeek = _.countBy (_.filter (linkage_data.records, (k)=>k[1] && sequenceFilter (+(k[0]))),(d)=>deltaWeeks(d[1]))","pinned":false,"hidden":false,"mode":"ojs"},{"id":2480,"value":"sequencesByWeekWithAttr = _.countBy (_.filter (linkage_data.records, (k)=>k[1] && sequenceFilter (+(k[0]))),(d)=>deltaWeeks(d[1]))","pinned":false,"hidden":false,"mode":"ojs"},{"id":2087,"value":"extractSigMutations = ()=> {\n return _.map (_.map (trackingSignature.split (\",\"), (d)=>d.replace (\" \",\"\")), (s)=> {\n \n if (isNaN(parseInt(s[0]))) {\n return [s.substr (1,s.length-1), true]; \n }\n return [s, false];\n });\n}","pinned":false,"hidden":false,"mode":"ojs"},{"id":632,"value":"matched_sequences = {\n if (trackingSignature.length == 0) {\n return _.map (linkage_data.sequences, (d,k)=>k);\n }\n \n let sigs = extractSigMutations();\n \n return _.map (_.filter (_.map (linkage_data.sequences, (sd,sk)=>[sk,sd]), (s)=>_.every (sigs, (sig)=>{\n if (sig[1] == false) {\n return sig[0] in s[1];\n }\n return _.every ([\"A\",\"C\",\"G\",\"T\"], (n)=>((sig[0]+n) in s[1]) == false);\n })), (d)=>d[0]);\n}","pinned":false,"hidden":false,"mode":"ojs"},{"id":2836,"value":"matched_sequences_with_attr = _.filter (matched_sequences, (k)=>linkage_data.records[k][1] && _.some (linkage_data.records[k][2], (l)=>l.length))","pinned":false,"hidden":false,"mode":"ojs"},{"id":756,"value":"other_variants = {\n let variant_list = {};\n let sigs = {};\n _.each (extractSigMutations(), (sgm)=> {\n if (sgm[1]) {\n sigs[sgm[0]] = true;\n } else {\n sigs[sgm[0]] = false; \n }\n });\n let M = matched_sequences.length;\n _.each (matched_sequences, (id) => {\n if (id in linkage_data.sequences) {\n _.each (linkage_data.sequences[id], (m,k)=> {\n if (!(k in variant_list)) {\n variant_list[k] = 0;\n }\n variant_list[k]++;\n });\n }\n });\n return _.map (variant_list, (m,k)=> {\n return {'coord' : parseInt (k), 'fraction' : m/M, 'count' : m, 'mutation' : k, 'kind' : k in sigs ? 'Selected' : 'Other'};\n });\n}","pinned":false,"hidden":false,"mode":"ojs"},{"id":392,"value":"plot_divergence = _.map (matched_sequences, (k)=>{\n return {\n 'date' : linkage_data.records[k][1],\n 'location' : linkage_data.records[k][2] ? linkage_data.records[k][2][2] : \"\"\n }\n});","pinned":false,"hidden":false,"mode":"ojs"},{"id":2107,"value":"resolved_name = _.memoize ((name)=> {\n if (name == \"England\") {\n name = \"United Kingdom\"; \n }\n let c = _.find (country_equiv, (c)=>(c.name.common == name || c.name.official == name || c.cca3 == name || c.altSpellings.find ((e)=>e==name)!=undefined));\n if (c) {\n return c.name.common; \n }\n return \"N/A\";\n });","pinned":false,"hidden":false,"mode":"ojs"},{"id":2103,"value":"$36","pinned":false,"hidden":false,"mode":"ojs"},{"id":3167,"value":"lookupCountryID =(name) => {\n return _.find (country_equiv, (c)=>(c.name.common == name || c.name.official == name || c.cca3 == name || c.altSpellings.find ((e)=>e==name)!=undefined));\n}","pinned":false,"hidden":false,"mode":"ojs"},{"id":2117,"value":"unfilteredByCountryAndWeek = sequencesByCountryAndWeek()","pinned":false,"hidden":false,"mode":"ojs"},{"id":2123,"value":"filteredByCountryAndWeek = sequencesByCountryAndWeek(_.filter (matched_sequences, sequenceFilter))","pinned":false,"hidden":false,"mode":"ojs"},{"id":2128,"value":"forMapPlot = {\n _.each (filteredByCountryAndWeek, (data,country) => {\n data.fraction = data.total / unfilteredByCountryAndWeek[country].total;\n data.fraction_by_week = {};\n _.each (data.byweek, (dt,wk)=> {\n if (unfilteredByCountryAndWeek[country][\"byweek\"][wk]) {\n data.fraction_by_week[wk] = dt / unfilteredByCountryAndWeek[country][\"byweek\"][wk];\n } else {\n data.fraction_by_week[wk] = null;\n }\n });\n });\n return filteredByCountryAndWeek;\n} ","pinned":false,"hidden":false,"mode":"ojs"},{"id":2208,"value":"forMapPlotID = {\n let fmpi = {};\n _.each (forMapPlot, (d)=> {\n fmpi[d.id] = d;\n });\n return fmpi;\n}","pinned":false,"hidden":false,"mode":"ojs"},{"id":707,"value":"country_equiv = d3.json (\"https://raw.githubusercontent.com/mledoze/countries/master/dist/countries.json\")","pinned":false,"hidden":false,"mode":"ojs"},{"id":1981,"value":"countryToCode = {\n let c2c = {};\n _.each (country_equiv, (country_info)=> {\n c2c[country_info.name.common] = country_info.cca2.toLowerCase();\n });\n return c2c;\n}","pinned":false,"hidden":false,"mode":"ojs"},{"id":711,"value":"country_codes = d3.json(\"https://raw.githubusercontent.com/lukes/ISO-3166-Countries-with-Regional-Codes/master/slim-3/slim-3.json\")","pinned":false,"hidden":false,"mode":"ojs"},{"id":714,"value":"world = d3.json(\"https://unpkg.com/world-atlas@1/world/110m.json\")","pinned":false,"hidden":false,"mode":"ojs"},{"id":2164,"value":"countryData = topojson.feature(world, world.objects.countries)","pinned":false,"hidden":false,"mode":"ojs"},{"id":2167,"value":"graticule = d3.geoGraticule10()","pinned":false,"hidden":false,"mode":"ojs"},{"id":52,"value":"N = _.size (linkage_data.sequences)","pinned":false,"hidden":false,"mode":"ojs"},{"id":3242,"value":"variantFreqs = _.map (linkage_data.variants, (d)=>d[2]/N)","pinned":false,"hidden":false,"mode":"ojs"},{"id":3247,"value":"minVF = d3.min (variantFreqs)","pinned":false,"hidden":false,"mode":"ojs"},{"id":3250,"value":"formatFraction = d3.format (\".2p\")","pinned":false,"hidden":false,"mode":"ojs"},{"id":9,"value":"d3 = require (\"d3\")","pinned":false,"hidden":false,"mode":"ojs"},{"id":11,"value":"vegalite = require (\"vega-embed\")","pinned":false,"hidden":false,"mode":"ojs"},{"id":16,"value":"_=require(\"lodash\")","pinned":false,"hidden":false,"mode":"ojs"},{"id":256,"value":"import {select, slider, checkbox, text, autoSelect} from \"@jashkenas/inputs\"","pinned":false,"hidden":false,"mode":"ojs"},{"id":571,"value":"genes = {\n let genes = [\n [266,'ORF1a',13483],\n [13471, 'ORF1b',21555],\n [21563,'S',25385],\n [25393,'ORF3a',26220],\n [26523,'M',27191],\n [27202,'ORF6',27387],\n [27394,'ORF7a',27759],\n [27894,'ORF8',28259],\n [28274,'N',29533],\n [266, \"leader\", 805],\n [806, \"nsp2\", 2719],\n [2720, \"nsp3\", 8554],\n [8555, \"nsp4\", 10054],\n [10055, \"3C\", 10972],\n [10973, \"nsp6\",11842],\n [11843, \"nsp7\", 12091],\n [12092, \"nsp8\", 12685],\n [12686, \"nsp9\", 13024],\n [13025, \"nsp10\",13442],\n [16237, \"helicase\",18039],\n [18040, \"exonuclease\", 19620],\n [19621, \"endornase\", 20658],\n [20659, \"methyltransferase\", 21552],\n [26244, \"E\",26471],\n [29557, \"ORF10\",29673],\n [13441,\"RdRp\",16235]];\n \n return _.flatten ([[[0,\"genome\",30000]],_.sortBy (genes, (d)=>d[1])], true);\n }","pinned":false,"hidden":false,"mode":"ojs"},{"id":1478,"value":"nodeSize=[10,14]","pinned":false,"hidden":false,"mode":"ojs"},{"id":3107,"value":"$37","pinned":false,"hidden":false,"mode":"ojs"},{"id":2950,"value":"tracking_root = {\n return _.find (tracking_for_display, (d)=> !d.parent);\n /*return {\n \"name\" : \"ancestor\",\n children : [rt]\n };*/\n}","pinned":false,"hidden":false,"mode":"ojs"},{"id":786,"value":"tracking_info = {\n //let raw_list = await d3.json (\"https://dl.dropbox.com/s/t2aglsv6j895wuu/SC2-tracking-mutations.json\");\n let raw_list = await d3.json (\"https://dl.dropboxusercontent.com/s/fi2zxx1vir8v8kf/tracking.json\");\n let name_to_id = {};\n _.each (raw_list, (d,i) => {\n d[\"id\"] = i;\n name_to_id [d.name] = i;\n });\n \n _.each (raw_list, (d, i) => {\n if (d.parent) {\n let parent_object = raw_list[name_to_id[d.parent]];\n if (!(\"children\" in parent_object)) {\n parent_object[\"children\"] = []; \n }\n parent_object[\"children\"].push (d);\n d.parent_name = d.parent;\n d.parent = parent_object;\n }\n });\n return raw_list;\n}","pinned":false,"hidden":false,"mode":"ojs"},{"id":1775,"value":"sequenceFilter = (id,data)=>{\n if (id in linkage_data.records) {\n if (linkage_data.records[id][2]) {\n if (as.length) {\n return _.some (linkage_data.records[id][2], (d)=>d == as);\n } \n return true;\n }\n } else {\n console.log (\"Missing => \" + id); \n }\n return false;\n};","pinned":false,"hidden":false,"mode":"ojs"},{"id":3212,"value":"_.groupBy (sequences_with_tracking_info.sequences, (d)=>d.ζ1)","pinned":false,"hidden":false,"mode":"ojs"},{"id":792,"value":"$38","pinned":false,"hidden":false,"mode":"ojs"},{"id":2368,"value":"binnedByMutationClassFiltered = sequencesByCountryAndWeek (_.filter (matched_sequences_with_attr, sequenceFilter), (d,id)=>sequencesByMutationClass [id])","pinned":false,"hidden":false,"mode":"ojs"},{"id":2384,"value":"binnedDataForStacking = {\n \n const majorOnlyClass = new Set (['μ+α','μ+α+β','μ+α+β+γ','μ+α+β+γ+δ','μ+α+β+ε','μ+α+β+ε+η','μ+α+β+ζ']);\n let result = [];\n let maxbyclass = {};\n _.each (binnedByMutationClassFiltered.allweeks, (wk)=> {\n let weekrecord = {'date' : deltaweekToDate(wk)};\n \n _.each (binnedByMutationClassFiltered, (data, mut) => {\n if (\"byweek\" in data) {\n weekrecord[mut] = (wk in data.byweek) ? data.byweek[wk] : 0;\n weekrecord[mut] = weekrecord[mut] / sequencesByWeekWithAttr[wk];\n if (! maxbyclass[mut] || weekrecord[mut] > maxbyclass[mut]){\n maxbyclass[mut] = weekrecord[mut];\n }\n }\n });\n result.push (weekrecord);\n });\n \n let ignore_keys = _.map (_.filter (_.map (maxbyclass, (d,k)=>[k,d]), (d)=>d[1] <= minFreqBin || (majorOnly && majorOnlyClass.has (d[0]) == false)), (d)=>d[0]);\n \n return _.map (result, (d)=>_.omit(d, ignore_keys)) ;\n}","pinned":false,"hidden":false,"mode":"ojs"},{"id":2896,"value":"binMutationClasses = _.filter (_.keys (binnedDataForStacking[0]), (d)=>d!=\"date\")","pinned":false,"hidden":false,"mode":"ojs"},{"id":2863,"value":"binColorsWithPredef = (value, idx)=> {\n const lookup = {\n 'μ+α' : \"#ed7d31\",\n 'μ+α+β' : \"#a5a5a5\",\n 'μ+α+β+γ' : \"#ffc000\",\n 'μ+α+β+γ+δ' : \"#5b9bd5\",\n 'μ+α+β+ε' : \"#70ad47\",\n 'μ+α+β+ε+η' : \"#ff99ff\",\n 'μ+α+β+ζ' : \"#9e480e\"\n };\n return lookup[value] || binColorScale (idx);\n}","pinned":false,"hidden":false,"mode":"ojs"},{"id":2495,"value":"binColorScale = d3.scaleSequential((d)=>d3.interpolateTurbo((1+d)/binMutationClasses.length))","pinned":false,"hidden":false,"mode":"ojs"},{"id":2408,"value":"binStackstack = d3.stack()\n .keys(binMutationClasses)\n //.offset(0)\n .order(d3.stackOrderNone)","pinned":false,"hidden":false,"mode":"ojs"},{"id":2401,"value":"minFreqBin = 0.005","pinned":false,"hidden":false,"mode":"ojs"},{"id":3155,"value":"$39","pinned":false,"hidden":false,"mode":"ojs"},{"id":3095,"value":"params = new URLSearchParams(location.search)","pinned":false,"hidden":false,"mode":"ojs"},{"id":3150,"value":"globalHighlight = params.get (\"highlight\");","pinned":false,"hidden":false,"mode":"ojs"},{"id":2353,"value":"sequencesByMutationClass = {\n let tm_dict = {};\n _.each (tracking_info, (d)=>tm_dict[d.name] = d);\n let result = {};\n \n _.each (sequences_with_tracking_info.sequences, (data, id)=> {\n //if (sequenceFilter (id)) {\n let groups = {};\n _.each (data, (ignore, mutation)=> {\n groups[tm_dict[mutation].group] = 1;\n });\n\n result [id] = _.map (groups, (d,k)=>k).join (\"+\");\n //}\n });\n \n return result;\n \n}","pinned":false,"hidden":false,"mode":"ojs"},{"id":1032,"value":"merge_location_info = (set)=> {\n let result = _.clone (set[0]);\n const levels = [3,2,1,0];\n for (let i = 1; i < set.length; i++) {\n for (let j = 0; j < levels.length; j++) {\n let lvl = levels[j];\n if (result[lvl].length == 0 && levels.length > 1) {\n levels.splice (0,1); \n j--;\n continue;\n } \n \n if (result[lvl] != set[i][lvl]) {\n if (j == levels.length - 1\n ) {\n result[lvl] = \"Multiple Regions\"; \n } else {\n result[lvl] = \"\"; \n }\n }\n }\n }\n return result;\n};","pinned":false,"hidden":false,"mode":"ojs"},{"id":926,"value":"$3a","pinned":false,"hidden":false,"mode":"ojs"},{"id":935,"value":"report_fraction = d3.format (\".2p\")","pinned":false,"hidden":false,"mode":"ojs"},{"id":969,"value":"report_date_f = d3.timeFormat (\"%m/%d/%Y\")","pinned":false,"hidden":false,"mode":"ojs"},{"id":1010,"value":"report_date = (f)=> {\n if (f) return report_date_f(f);\n return \"\";\n}","pinned":false,"hidden":false,"mode":"ojs"},{"id":1553,"value":"report_int = d3.format (\",\");","pinned":false,"hidden":false,"mode":"ojs"},{"id":824,"value":"$3b","pinned":false,"hidden":false,"mode":"ojs"},{"id":1168,"value":"date_range = d3.extent (_.map(linkage_data.records, (d)=>d[1]))","pinned":false,"hidden":false,"mode":"ojs"},{"id":1312,"value":"toSignature = (m)=>{\n if (m.reference_value) {\n return linkage_data.reference_base[m.pos-1]+m.pos;\n } \n return \"\"+m.pos+m.variant;\n}","pinned":false,"hidden":false,"mode":"ojs"},{"id":2188,"value":"mapHeight = 550","pinned":false,"hidden":false,"mode":"ojs"},{"id":2192,"value":"mapWidth = 960","pinned":false,"hidden":false,"mode":"ojs"},{"id":2428,"value":"trendWidth = 960","pinned":false,"hidden":false,"mode":"ojs"},{"id":2432,"value":"trendHeight = 500","pinned":false,"hidden":false,"mode":"ojs"},{"id":2157,"value":"topojson = require(\"topojson-client@3\")","pinned":false,"hidden":false,"mode":"ojs"},{"id":2179,"value":"mapProjection = d3.geoMercator().translate ([mapWidth/2,mapHeight*0.65]);//.fitSize([mapWidth, mapHeight], { type: \"Sphere\" })","pinned":false,"hidden":false,"mode":"ojs"},{"id":2258,"value":"import { Scrubber } from \"@mbostock/scrubber\"","pinned":false,"hidden":false,"mode":"ojs"},{"id":2263,"value":"sliderDate = wk =>\n report_date_f (deltaweekToDate(wk))","pinned":false,"hidden":false,"mode":"ojs"},{"id":2305,"value":"colorScheme = d3.interpolateOrRd\n","pinned":false,"hidden":false,"mode":"ojs"},{"id":2310,"value":"colorScale = d3.scaleSequential([0,1],colorScheme);","pinned":false,"hidden":false,"mode":"ojs"},{"id":3271,"value":"pako = require('https://bundle.run/pako@2.0.3')","pinned":false,"hidden":false,"mode":"ojs"},{"id":3182,"value":"import { callout } from \"@d3/line-chart-with-tooltip\"","pinned":false,"hidden":false,"mode":"ojs"},{"id":2298,"value":"import { legend, swatches } from \"@d3/color-legend\"","pinned":false,"hidden":false,"mode":"ojs"},{"id":3268,"value":"obtainSourceData = async (sourceURL)=> {\n if (sourceURL.indexOf (\".gz\") == sourceURL.length - 3) {\n return JSON.parse(pako.inflate(await d3.buffer (sourceURL),{ to: 'string' }), d3.autoType);\n }\n \n return await d3.json (sourceURL);\n}","pinned":false,"hidden":false,"mode":"ojs"},{"id":1139,"value":"html``","pinned":false,"hidden":false,"mode":"ojs"},{"id":3275,"value":"html`