2d:null 2e:["$","title",null,{"children":"Trends in mutational patterns across SARS-CoV-2 genes enabled by data from | Sergei Pond | Observable"}] 33:Tcec,fig1 = { const fieldname2idx = {'none' : -1, 'country' : 2, 'pangolin' : 5, 'nextstrain' : 6, 'matches' : 7}; let yscale = fig_options1.indexOf ('q') >= 0 ? "sqrt" : "linear"; let cumulative = fig_options1.indexOf ('c') >= 0; let normalized = fig_options1.indexOf ('n') >= 0; let timeslice = + fig_options2; let stratify_field = fieldname2idx[fig1strat]; let values = null; let color = {}; let transform = []; let yfield = "y"; //let mm =_.chain (_.toPairs (sigMatches)).filter ((d)=>d[1] >= 7).map ((d)=>d[0]).value(); let mm = matches; if (stratify_field < 0) { values = _.map (aggregateDatesBy (extractFromList (mm,0), timeslice, timeSpan[0], cumulative, normalized ? extractFromList (null,0) : null), (d)=> {return {'sampled' : d[0], 'y' : d[1]}}); } else { values = _.filter (_.flatten(_.map (aggregateDatesBy (extractMultipleFromList (mm,[0,stratify_field]),timeslice, timeSpan[0], false, null, _.groupBy), (d)=>{ return _.map (_.countBy (d[1], (r)=>r[1]), (cnt, field) => { let rr = { 'sampled' : d[0], 'y' : cnt, }; rr[fig1strat] = field; return rr; }); })), (d)=>d[fig1strat] != "null"); if (cumulative) { transform = [{ "window": [{ "op": "sum", "field": "y", "as": "total_count" }], "groupby": [fig1strat], "frame" : [null, 0] }, { "window": [{ "op": "sum", "field": "y", "as": "N" }], "groupby": [fig1strat], "frame" : [null, null] }, { "filter": {"field": "N", "gt": 1} }]; yfield = "total_count"; } else { transform = [{ "window": [{ "op": "sum", "field": "y", "as": "N" }], "groupby": [fig1strat], "frame" : [null, null] }, { "filter": {"field": "N", "gt": 1} }]; } color = {'field' : fig1strat, 'type' : 'nominal', 'sort' : {'field' : "N", "order" : "descending"}, "legend" : {"orient" : "top-left", labelFont : "monospace"}}; } //return values; return vegalite ({ "width" : 700, "height" : 400, "data": {"values": values}, transform: transform, "encoding": { "x": { "type" : "temporal", timeUnit: "yearmonthdate", "field": "sampled", "axis" : {"title" : "Sample Date", "grid" : false, labelFontSize : 14, titleFontSize : 18, labelAngle :30,labelAlign: "left"}, "scale" : {"nice" : "month"} }, "y": {"field" : yfield, "type" : "quantitative", "axis" : {"title" : normalized ? "Fraction" : "Count", "grid" : false, labelFontSize : 14, titleFontSize : 18}, "scale" : {"type" : yscale}}, "color" : color, }, "layer" : [ {"mark": {type : "line", "interpolate" : "monotone", tooltip : true, size : 5, color : "firebrick", "opacity" : 0.5}}, {"mark": {type : "point", size : 25, color : "firebrick", filled : true, tooltip : true}}, ] }); }34:T845,fig2 = { let yscale = fig2_options.indexOf ('l') >= 0 ? "sqrt" : "linear"; let cumulative = fig2_options.indexOf ('c') >= 0; let normalized = fig2_options.indexOf ('n') >= 0; let timeslice = + fig2_options2; let normalizer = normalized ? extractFromList (null,0) : null; let values = _.mapValues (patternsTrends, (m)=>_.map (aggregateDatesBy (extractFromList (m,0), timeslice, timeSpan[0], cumulative, normalizer), (d)=> {return {'sampled' : d[0], 'y' : d[1]}})); values = _.flatten (_.map (values, (v, k)=> _.map (v, (r)=> _.extend (r, {'signature' :k})))); let sort_order = _.map(_.sortBy (_.toPairs (_.mapValues (_.groupBy (values, (d)=>d.signature), (d)=>d3.sum (d, (e)=>e.y))), (d)=>-d[1]), (d)=>d[0]); let color = {'field' : 'signature', "type" : "nominal", 'title' : "Signature", "legend" : {"orient" : "top-left", labelFont : "monospace", labelFontSize : 10, titleFontSize: 14}, "scale": {"scheme": "category20b"}, "sort" : sort_order}; return vegalite ({ "width" : 700, "height" : 500, "data": {"values": values}, "encoding": { "x": { timeUnit: "yearmonthdate", "type" : "temporal", "field": "sampled", "axis" : {"title" : "Sample Date", "grid" : false, labelFontSize : 14, titleFontSize : 18, labelAngle :30, labelAlign: "left", //labelExpr: "[timeFormat(datum.value, '%b'), timeFormat(datum.value, '%m') == '01' ? timeFormat(datum.value, '%Y') : '']" }, "scale" : {"nice" : "month"} }, "y": {"field" : "y", "type" : "quantitative", "axis" : {"title" : normalized ? "Fraction" : "Count", "grid" : false, labelFontSize : 14, titleFontSize : 18}, "scale" : {"type" : yscale}}, "color" : color, }, "layer" : [ {"mark": {type : "line", "interpolate" : "monotone", tooltip : true, size : 3, color : "firebrick", "opacity" : 0.5}}, {"mark": {type : "point", size : 25, color : "firebrick", filled : true, tooltip : true}}, ] }); }35:T90b,loadVariantData = async function (urls) { let res = {}; for (var k in urls) { res[k] = await d3.json (urls[k]); } // convert duplicates to look like an array of [i] => index into "variants" [sequences] let N = res['annotation']['meta'].length; let seq2var = {}; for (let i = 0; i < N; i++) { if (i in res.variants.sequences) { seq2var [i] = i; if (i in res['duplicates']) { for (let d = 0; d < res['duplicates'][i].length; d++) { seq2var[res['duplicates'][i][d]] = i; } } } } res.duplicates = seq2var; // convert meta data for dates (which is in days since reference) to dates let ref_date = d3.timeParse ("%Y%m%d") (res.annotation.reference).getTime(); res.annotation.values [0] = _.map ( res.annotation.values [0], (d)=> { if (d) return new Date (ref_date + d*24*3600*1000); return null; }); // compute amino-acid variants for sequences res.variants.ref_AA = translateSequence (res.variants.reference); res.variants.aa_variants = {}; _.each (res.variants.sequences, (v,id)=> { let aa_vars = extractAAVariants (res.variants.reference, res.variants.ref_AA, getVariantsByID (id, res)); if (aa_vars.length) { res.variants.aa_variants[id] = _.fromPairs (aa_vars); } }); let values = {}; _.each (res.variants.aa_variants, (d, id)=> { let cnt = 0; for (let r in d) { let v = d[r]; if ((r in sig_set) && (sig_set[r].has (v))) { cnt ++; } } if (!(cnt in values)) { values[cnt] = _.size (values); } let idx = values[cnt]; if (res.annotation.meta[id].length < 8) { res.annotation.meta[id].push (idx); } else { res.annotation.meta[id][7] = idx; } }); _.each (res.duplicates, (unid, id)=> { if (res.annotation.meta[id].length < 8) { res.annotation.meta[id].push (res.annotation.meta[unid][7]); } else { res.annotation.meta[id][7] = res.annotation.meta[unid][7]; } }); res.annotation.values.push (_.chain (values).toPairs().sortBy ((d)=>d[1]).map ((d)=>+d[0]).value()); return res; }36:T5bc,aggregateDatesBy = (dates, days, from, cumulative, normalize, f)=> { f = f || _.countBy; from = from.getTime(); days = days * 24 * 3600 * 1000; let binned = []; if (dates.length) { if (_.isArray (dates[0])) { binned = f (dates, (d)=>d[0] ? Math.floor ((d[0].getTime()-from)/days) : null); } else { binned = f (dates, (d)=>d ? Math.floor ((d.getTime()-from)/days) : null); } } if (null in binned) { delete binned[null]; } binned = _.toPairs (binned); if (normalize) { normalize = f (normalize, (d)=>d ? Math.floor ((d.getTime()-from)/days) : null); if (null in normalize) { delete normalize[null]; } normalize = _.toPairs (normalize); } if (cumulative) { binned = _.sortBy (binned, d=>+d[0]); let sum = 0; _.each (binned, (d) => { sum += d[1]; d[1] = sum; }); if (normalize) { normalize = _.sortBy (normalize, d=>+d[0]); let sum = 0; _.each (normalize, (d) => { sum += d[1]; d[1] = sum; }); } } if (normalize) { normalize = _.fromPairs (normalize); _.each (binned, (d) => { if (normalize[d[0]]) d[1] = d[1]/normalize[d[0]]; else d[1] = null; }) } return _.map (binned, (d)=>[new Date (days*(+d[0])+from), d[1]]); };37:T9f3,prepareMappingData = (list_of_ids, cumulative, normalize_by)=> { let countryData = _.map (aggregateDatesBy (extractMultipleFromList (list_of_ids,[0,2]), 7, timeSpan[0], false, null, _.groupBy), (d)=> { return [d[0], _.map (d[1], (c)=>c)]; }); let byCountry = {}; let countsByDate = {}; _.each (countryData, (ids, date)=> { let dateID = ids[0].getTime(); countsByDate[dateID] = ids[1].length; _.each (ids[1], (id)=> { let ccn3 = lookupCountryIDCached (id[1]); if (!ccn3) return; ccn3 = ccn3.ccn3; if (normalize_by && (ccn3 in normalize_by) == false) return; if ((ccn3 in byCountry) == false) { byCountry[ccn3] = { name: id[1], id: lookupCountryIDCached (id[1]).ccn3, byweek : {}, fraction_by_week : {} }; } byCountry[ccn3].byweek[dateID] = 1 + (byCountry[ccn3].byweek[dateID] ? byCountry[ccn3].byweek[dateID] : 0); }); }); let alldates = _.sortBy (_.map (countryData, (date)=>date[0].getTime())); if (cumulative) { _.each (byCountry, (data, country)=> { let c = 0; for (let i = 0; i < alldates.length; i++) { if (alldates[i] in data.byweek) { c += data.byweek[ alldates[i]]; data.byweek[ alldates[i]] = c; } else { if (c) { data.byweek[ alldates[i]] = c; } } } }); let c = 0; for (let i = 0; i < alldates.length; i++) { c+=countsByDate[alldates[i]]; countsByDate[alldates[i]] = c; } } if (normalize_by) { _.each (countryData, (ids, date)=> { let dateID = ids[0].getTime(); _.each (byCountry, (data, country)=> { if (dateID in data.byweek) { console.log (country, dateID, data.byweek [dateID], normalize_by[country].byweek[dateID]); data.fraction_by_week [dateID] = data.byweek [dateID] / normalize_by[country].byweek[dateID]; } }); }); } else { _.each (countryData, (ids, date)=> { let dateID = ids[0].getTime(); _.each (byCountry, (data, country)=> { if (dateID in data.byweek) { data.fraction_by_week [dateID] = data.byweek [dateID] / countsByDate[dateID]; } }); }); } byCountry ['alltime'] = alldates; return byCountry; }38:T10d3,expr_array = (query)=>_.map (boolean (query).rpn, (d)=> { if (d.type == "term") { d.tokens = Array.from (lexer.reset(d.value)); switch (d.tokens.length) { case 1: // not a gap if (d.tokens[0].type == "number") { let coord = -1 + parseInt (d.tokens[0].value); d.act = (v,stack)=>stack.push (v[coord] != "-"); return d; } if (d.tokens[0].type == "field") { let term_tokens = Array.from (lexer_term.reset(d.tokens[0].value)); if (term_tokens.length == 2) { if (term_tokens[0].type == "query" && term_tokens[1].type == "field") { let field_id = -1; let gt = false; switch (term_tokens[1].value.substr (1,term_tokens[1].value.length-2).toLowerCase()) { case 'pangolin': field_id = 5; break; case 'country': field_id = 2; break; case 'nextstrain': field_id = 6; break; case 'before': field_id = 0; break; case 'after': field_id = 0; gt = true; break; case 'matches': field_id = 7; break; } if (field_id > 0) { d.act = (v,stack,id)=>stack.push (getFieldValue (id, field_id) == term_tokens[0].value); d.meta = true; return d; } if (field_id == 0) { let check_date = d3.timeParse ("%Y%m%d")(term_tokens[0].value); d.meta = true; if (gt) { d.act = (v,stack,id)=>{ let val =getFieldValue (id, field_id); stack.push ( val && val > check_date); } } else { d.act = (v,stack,id)=>{ let val =getFieldValue (id, field_id); stack.push ( val && val < check_date); } } return d; } } } } break; case 2: // specific residue if (d.tokens[0].type == "number" && d.tokens[1].type == "letter") { let coord = -1 + parseInt (d.tokens[0].value); d.act = (v, stack)=>{stack.push (v[coord] == d.tokens[1].value);} return d; } if (d.tokens[0].type == "letter" && d.tokens[1].type == "number") { let coord = -1 + parseInt (d.tokens[1].value); d.act = (v, stack)=>stack.push(!v[coord] && data.variants.ref_AA [coord] == d.tokens[0].value); return d; } break; case 3: // specific mutation if (d.tokens[1].type == "number" && d.tokens[0].type == "letter" && d.tokens[2].type == "letter") { let coord = -1 + parseInt (d.tokens[1].value); d.act = (v, stack)=>{stack.push (v[coord] == d.tokens[2].value && data.variants.ref_AA [coord] == d.tokens[0].value);} return d; } break; } throw ("Invalid term '" + d.value + "'"); } else { switch (d.operation) { case 'NOT': d.act = (v, stack)=> stack.push (!stack.pop()); return d; case 'AND': d.act = (v, stack)=> { let a = stack.pop(); let b = stack.pop(); stack.push (a&&b); } return d; case 'OR': d.act = (v, stack)=> { let a = stack.pop(); let b = stack.pop(); stack.push (a||b); } return d; } throw ("Invalid operation '" + d.operation + "'"); } return d; });39:T65c,runQuery = (query)=>{ let expr = expr_array (query); let has_meta = _.groupBy (expr, (d)=>d.meta); if (_.size (has_meta) == 2) { let matched = []; let i = 0; _.each (data.duplicates, (dup, id) => { let stack = []; let vars = data.variants.aa_variants[dup]; if (vars) { _.each (expr, (r)=> { if (r.act) r.act (vars, stack, id); }); if (stack[0]) { matched.push (id); } } }); return matched; } else { if (true in has_meta) { let matched = []; let i = 0; _.each (data.duplicates, (dup, id) => { let stack = []; _.each (expr, (r)=> { if (r.act) r.act ([], stack, id); }); if (stack[0]) { matched.push (id); } }); return matched; } else { let matched = []; let i = 0; _.each (data.variants.aa_variants, (vars, k) => { let stack = []; _.each (expr, (r)=> { if (r.act) r.act (vars, stack); }); if (stack[0]) { matched.push ([k,1]); } }); matched = _.fromPairs (matched); let with_dups = []; _.each (data.duplicates, (d,k)=> { if (matched[d]) { with_dups.push (k); } }); return with_dups; } } }3a:[] 31:{"id":"b279f2f2c32d3673","slug":"spike-trends","title":"Trends in mutational patterns across SARS-CoV-2 genes enabled by data from ","thumbnail":"e249e413dfd5f48179cd33ac55eef99e01afb5bbdfbfba3a151b116c3c720f72","access_level":"public","create_time":"$D2021-03-08T17:21:07.226Z","update_time":"$D2022-06-08T19:03:57.477Z","view_time":null,"first_public_time":"$D2021-03-09T23:08:24.307Z","has_unpublished_edits":null,"fork":false,"stars":1,"starred":false,"owner":{"type":"team","id":"9bf992815a7b66f2","login":"spond","name":"Sergei Pond","avatar_url":"https://avatars-next.observableusercontent.com/23c8c466a3ef27f1444c95a9ed8e52bcf08888403b6d4efbd039319b0761c13d","tier":"starter_2024"},"version":1636,"publish_version":1636,"role":null,"authored":false,"authors":[{"type":"individual","id":"f439ea11e6786e12","login":"spond","name":"Sergei Pond","avatar_url":"https://avatars-next.observableusercontent.com/23c8c466a3ef27f1444c95a9ed8e52bcf08888403b6d4efbd039319b0761c13d","tier":null}],"members":[{"type":"individual","id":"f439ea11e6786e12","login":"spond","name":"Sergei Pond","avatar_url":"https://avatars-next.observableusercontent.com/23c8c466a3ef27f1444c95a9ed8e52bcf08888403b6d4efbd039319b0761c13d","tier":null,"role":"editor"}],"comments":[],"custom_thumbnail":false,"trashed":false,"lapsed":null,"subscribed":null,"forks":2,"collection":null,"type":"notebook","body":{"title":"Trends in mutational patterns across SARS-CoV-2 genes enabled by data from ","cells":[{"id":0,"value":"md`# Trends in mutational patterns across SARS-CoV-2 genes enabled by data from $\"gisaid-logo\"$ `","pinned":false,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined","output":"$undefined","database":"$undefined"},{"id":1587,"value":"viewof gene = select ({\n options: [\"S\",\"3C\",\"E\",\"endornase\",\"exonuclease\",\"helicase\",\"leader\",\"M\",\"methyltransferase\",\"N\",\"nsp2\",\"nsp3\",\"nsp4\",\"nsp6\",\"nsp7\",\"nsp8\",\"nsp9\",\"nsp10\",\"ORF3a\",\"ORF6\",\"ORF7a\",\"ORF8\",\"RdRp\"],\n description: \"Use this gene\",\n value: \"S\"\n})","pinned":false,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined","output":"$undefined","database":"$undefined"},{"id":489,"value":"md`Loaded variant information and metadata on ${N} sequences sampled between ${timeFormat(timeSpan[0])} and ${timeFormat(timeSpan[1])}.`","pinned":false,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined","output":"$undefined","database":"$undefined"},{"id":321,"value":"viewof query = textarea({\n title: \"Input a spike mutational pattern and/or metadata to query\", \n placeholder: \"N501Y AND NOT E484 AND NOT 69 AND NOT 70\", \n spellcheck: true,\n width: \"100%\",\n rows: 5,\n submit: \"Search\"\n})","pinned":false,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined","output":"$undefined","database":"$undefined"},{"id":696,"value":"help = md`\n

**Search examples**

\n1. N501Y: presence of a specific residue at a site\n2. D614: presence of a reference residue at a site\n3. NOT N501: non-consenus residue at a site\n4. NOT 69: deletion at a site\n5. \"B.1.1.7[pangolin]\" : specific value of a given attribute (possible attributes are **country**, **pangolin**, **nextstrain**, **matches** -- the latter is the number of mutations matching a predefined signature)\n6. \"20210101[before]\" : select all sequences sampled prior to a specific date (YYYYMMDD)\n7. \"20210101[after]\" AND \"20210201[before]\" : select all sequences sampled between specific dates.\n8. N501Y AND (NOT 69 AND NOT 70) AND NOT E484 AND \"United Kingdom[country]\": a complex compound query to look from sequences sampled in the United Kingdom, with the N501Y mutation, deletions at 69 and 70, and a non-reference residue at 484\n

\n`","pinned":false,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined","output":"$undefined","database":"$undefined"},{"id":1055,"value":"viewof lookup_possible_values = select ({\n options: [\"country\", \"pangolin\", \"nextstrain\", \"matches\"],\n description: \"Look up possible values for an attribute\"\n})","pinned":false,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined","output":"$undefined","database":"$undefined"},{"id":1069,"value":"viewof value_list = autoSelect ({\n options: validFieldOptions,\n description: \"Start typing to select among \" + validFieldOptions.length + \" valid options\"\n})","pinned":false,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined","output":"$undefined","database":"$undefined"},{"id":469,"value":"md`The search query matches **${matches?matches.length:0}** sequences`","pinned":false,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined","output":"$undefined","database":"$undefined"},{"id":501,"value":"fig1_caption = md`**Figure 1**. Temporal distribution of sequences matching the query`","pinned":false,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined","output":"$undefined","database":"$undefined"},{"id":672,"value":"viewof fig_options1 = checkbox ({\n options: [{'value' : 'c', 'label' : \"Cumulative\"},\n {'value' : 'n', 'label' : \"Normalized as fraction of total\"},\n {'value' : 'q', 'label' : \"Sqrt y-axis\"}\n ],\n value: ['n'],\n title: \"Figure options\"\n});","pinned":false,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined","output":"$undefined","database":"$undefined"},{"id":1130,"value":"viewof fig1strat = select ({\n options: [\"none\", \"country\", \"pangolin\", \"nextstrain\", \"matches\"],\n title: \"Stratify plot by field\"\n});","pinned":false,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined","output":"$undefined","database":"$undefined"},{"id":682,"value":"viewof fig_options2 = radio ({\n options: [{'value' : '1', 'label' : \"Days\"},\n {'value' : '7', 'label' : \"Weeks\"},\n {'value' : '30', 'label' : \"Months\"}\n ],\n value: '7',\n title : \"Time interval for binning\"\n});","pinned":false,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined","output":"$undefined","database":"$undefined"},{"id":510,"value":"$33","pinned":false,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined","output":"$undefined","database":"$undefined"},{"id":786,"value":"viewof sites2track = multiAutoSelect ({\n options: _.map (_.range (1,data.variants.ref_AA.length+1), (d)=>\"Site \" + d),\n title: \"Track mutation signatures at these sites (up to 20 most common)\"\n});","pinned":false,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined","output":"$undefined","database":"$undefined"},{"id":818,"value":"viewof fig2_options = checkbox ({\n options: [{'value' : 'c', 'label' : \"Cumulative\"},\n {'value' : 'n', 'label' : \"Normalized as fraction of total\"},\n {'value' : 'l', 'label' : \"Sqrt y-axis\"},\n {'value' : 'u', 'label' : \"Differences from reference\"}\n ],\n value: ['n'],\n title: \"Figure options\"\n});","pinned":false,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined","output":"$undefined","database":"$undefined"},{"id":823,"value":"viewof fig2_options2 = radio ({\n options: [{'value' : '1', 'label' : \"Days\"},\n {'value' : '7', 'label' : \"Weeks\"},\n {'value' : '30', 'label' : \"Months\"}\n ],\n value: '7',\n title : \"Time interval for binning\"\n});","pinned":false,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined","output":"$undefined","database":"$undefined"},{"id":776,"value":"fig2_caption = md`**Figure 2**. Temporal evolution of amino-acid signatures at selected sites.`","pinned":false,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined","output":"$undefined","database":"$undefined"},{"id":804,"value":"$34","pinned":false,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined","output":"$undefined","database":"$undefined"},{"id":912,"value":"fig3_caption = md`**Figure 3**. The geographic distribution of selected sequences stratified by week. The fraction is computed relative to all the sequences collected in a particular country.`","pinned":false,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined","output":"$undefined","database":"$undefined"},{"id":919,"value":"geospatialLegend = legend({\n color: colorScale,\n title: \"Fraction of total selected sequences\",\n tickFormat: \"%\"\n})","pinned":false,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined","output":"$undefined","database":"$undefined"},{"id":932,"value":"viewof mapDate = Scrubber(mappingData.alltime, {\n delay: 500,\n loopDelay: 100000,\n autoplay: false,\n format: scrubberFormat\n})","pinned":false,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined","output":"$undefined","database":"$undefined"},{"id":946,"value":"viewof doCumulativeCounts = checkbox({\n options: [{ value: \"toggle\", label: \"Cumulative\" }],\n value: \"toggle\"\n})","pinned":false,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined","output":"$undefined","database":"$undefined"},{"id":891,"value":"makeAnimatedMap (mappingData, mapDate, colorScale, true)","pinned":false,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined","output":"$undefined","database":"$undefined"},{"id":1392,"value":"tab1caption = md`**Table 1**. Sequence attributes for sequences matching the query (limited to the first 500)`","pinned":false,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined","output":"$undefined","database":"$undefined"},{"id":1398,"value":"table1 = table (forTable, {format: {\n Sampled : x=>timeFormat(x),\n Matches: x=>x\n}})","pinned":false,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined","output":"$undefined","database":"$undefined"},{"id":1601,"value":"viewof signaturesToTrack = textarea({\n title: \"Signature mutations to track\", \n spellcheck: false,\n value: \"18F, 26L, 26R, 26S, 69- , 70-, 98F , 138H, 138Y, 144-, 215G, 215H, 215V, 215Y, 241-, 242-, 243-, 417N, 417T, 484K, 501Y, 655Y , 681L, 681R, 681H , 701V, 716I, 1027I , 1118H, 1176F, 1264L\",\n width: \"100%\",\n rows: 4,\n submit: \"Update\"\n})","pinned":false,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined","output":"$undefined","database":"$undefined"},{"id":5,"value":"md`\n#### Data`","pinned":false,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined","output":"$undefined","database":"$undefined"},{"id":1610,"value":"$35","pinned":false,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined","output":"$undefined","database":"$undefined"},{"id":47,"value":"data = {\n return loadVariantData (dataFileNames);\n}","pinned":false,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined","output":"$undefined","database":"$undefined"},{"id":1471,"value":"sigN501Y = _.flatten (_.map ([[\"5\",\"F\"],[\"18\",\"F\"],[\"26\",\"RS\"],[\"67\",\"VS\"],[\"69\",\"-\"],[\"80\",\"ASY\"],[\"98\",\"F\"],[\"138\",\"HY\"],[\"144\",\"-\"],[\"215\",\"GHV\"],[243,\"-\"],[\"417\",\"NT\"],[\"427\",\"N\"],[\"484\",\"KQ\"],[\"501\",\"Y\"],[\"520\",\"S\"],[\"655\",\"Y\"],[\"681\",\"LHR\"],[\"701\",\"V\"],[\"716\",\"I\"],[\"1027\",\"I\"],[\"1117\",\"I\"],[1118,\"H\"],[\"1176\",\"F\"],[\"1219\",\"VC\"],[\"1264\",\"L\"]], (d)=>{\n return _.map (d[1], (c)=>d[0] + c);\n})).join (\", \")","pinned":false,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined","output":"$undefined","database":"$undefined"},{"id":1475,"value":"sigVOCVOI = \"18F, 26S, 69-, 95I, 144-, 144T, 215G, 242-, 246I, 246M, 346K, 417N, 417T, 439K, 452R, 452Q, 477N, 478K, 478R, 484K, 484Q, 490S, 494P, 501Y, 655Y, 681H, 681R\"","pinned":false,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined","output":"$undefined","database":"$undefined"},{"id":1177,"value":"sig_set = _.mapValues (_.groupBy (_.map (signaturesToTrack.split(\", \"), (d)=>[d.substr (0, d.length-1),d.substr (-1)]), (d)=>+d[0]-1), (v)=>new Set (_.map (v, (e)=>e[1])))","pinned":false,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined","output":"$undefined","database":"$undefined"},{"id":478,"value":"timeSpan = d3.extent (data.annotation.values[0])","pinned":false,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined","output":"$undefined","database":"$undefined"},{"id":832,"value":"mappingData = prepareMappingData (matches, doCumulativeCounts,doCumulativeCounts ? allMappingDataCumulative: allMappingData)","pinned":false,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined","output":"$undefined","database":"$undefined"},{"id":764,"value":"patternsTrends = {\n let diffcons = fig2_options.indexOf ('u') >= 0;\n let sites = _.map (sites2track, (d)=> (+d.split (\" \")[1])-1);\n //let sites = _.map (sig_set, (d,k)=>+k);\n if (sites.length) {\n return extractAASignatures (matches, sites, diffcons, 20);\n }\n return {};\n}","pinned":false,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined","output":"$undefined","database":"$undefined"},{"id":969,"value":"allMappingData = prepareMappingData (_.keys(data.duplicates))","pinned":false,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined","output":"$undefined","database":"$undefined"},{"id":1006,"value":"allMappingDataCumulative = prepareMappingData (_.keys(data.duplicates), true)","pinned":false,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined","output":"$undefined","database":"$undefined"},{"id":483,"value":"N = _.size (data.duplicates)","pinned":false,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined","output":"$undefined","database":"$undefined"},{"id":343,"value":"matches = runQuery (query)","pinned":false,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined","output":"$undefined","database":"$undefined"},{"id":1344,"value":"field2idx = {return {\n 'country' : 2,\n 'pangolin' : 5,\n 'nextstrain' : 6,\n 'matches' : 7\n}\n }","pinned":false,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined","output":"$undefined","database":"$undefined"},{"id":1087,"value":"validFieldOptions = {\n return _.sortBy(_.filter (data.annotation.values[field2idx[lookup_possible_values]], (d)=>d));\n}","pinned":false,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined","output":"$undefined","database":"$undefined"},{"id":1486,"value":"topMotifs = _.sortBy (_.toPairs(_.groupBy (forTable, (d)=>d.Matches)), (d)=>-d[1].length)","pinned":false,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined","output":"$undefined","database":"$undefined"},{"id":1518,"value":"coreMotif = {\n let coreSet = new Set ();\n _.each (topMotifs, (d)=>{\n if (d[1].length > 5) {\n _.each (_.split (d[0], \", \"), (m)=> {\n coreSet.add (parseInt(m));\n });\n \n }\n });\n return _.sortBy ([...coreSet], (d)=>d)\n}","pinned":false,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined","output":"$undefined","database":"$undefined"},{"id":1401,"value":"forTable = {\n let subset = matches.slice (0, 40000);\n return _.map (extractMultipleFromList (subset, [0,1,2,3,4,5,6]), (d,i)=> {\n return {\n 'ID' : subset[i],\n 'Sampled' : timeFormat (d[0]),\n 'Location' : d.slice (1,4).join (\", \"),\n 'Clade' : \"\" + d[5] + \"/\" + d[6],\n 'Matches' : sigMatchSet (subset[i]).join (\", \")\n }\n });\n}","pinned":false,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined","output":"$undefined","database":"$undefined"},{"id":33,"value":"md`#### Parameters`","pinned":false,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined","output":"$undefined","database":"$undefined"},{"id":612,"value":"refDate = d3.timeParse (\"%Y%m%d\")(data.annotation.reference)","pinned":false,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined","output":"$undefined","database":"$undefined"},{"id":36,"value":"baseURL = {\n if (gene == \"S\") return \"https://data.hyphy.org/web/SARS-CoV-2/S/\";\n return \"https://data.hyphy.org/web/SARS-CoV-2/variants/\";\n}","pinned":false,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined","output":"$undefined","database":"$undefined"},{"id":1616,"value":"getVariantFileNames = (gene, base) => {\n base = base || \"https://raw.githubusercontent.com/spond/SARS-CoV-2-variation/master/\";\n return {\n 'variants' : base + gene + '/variants-clear.json',\n 'duplicates' : base + gene + '/duplicates-compressed.json',\n 'annotation' : base + 'sequence_info.json' \n };\n}","pinned":false,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined","output":"$undefined","database":"$undefined"},{"id":43,"value":"dataFileNames = { \n return getVariantFileNames (gene);\n}","pinned":false,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined","output":"$undefined","database":"$undefined"},{"id":225,"value":"lexer = moo.compile({\n field: /.+\\[[a-zA-Z]+\\]/,\n number: /0|[1-9][0-9]*/,\n letter: /[A-Za-z]+/,\n })","pinned":false,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined","output":"$undefined","database":"$undefined"},{"id":412,"value":"lexer_term = moo.compile({\n field: /\\[[a-zA-Z]+\\]/,\n query: {match: /[^\\[\\]]+/, lineBreaks: true},\n })","pinned":false,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined","output":"$undefined","database":"$undefined"},{"id":908,"value":"mapColorScaleCount = d3.scaleSequential([0,N],d3.interpolateOrRd)","pinned":false,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined","output":"$undefined","database":"$undefined"},{"id":54,"value":"md`#### Notebook imports and functions`","pinned":false,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined","output":"$undefined","database":"$undefined"},{"id":1406,"value":"sigMatchSet = (id)=> {\n let d = data.variants.aa_variants[data.duplicates[id]];\n let matched_set = [];\n for (let r in d) {\n let v = d[r];\n if ((r in sig_set) && (sig_set[r].has (v))) {\n matched_set.push (\"\" + (1+(+r)) + v);\n }\n }\n return matched_set;\n}","pinned":false,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined","output":"$undefined","database":"$undefined"},{"id":526,"value":"$36","pinned":false,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined","output":"$undefined","database":"$undefined"},{"id":963,"value":"$37","pinned":false,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined","output":"$undefined","database":"$undefined"},{"id":137,"value":"translateSequence = (seq)=> {\n let AA = [];\n for (let i = 0; i < seq.length; i+=3) {\n const aa = translate_ambiguous_codon (seq.substr (i,3));\n AA.push (aa.length == 1 ? aa : \"?\" );\n }\n return AA;\n}","pinned":false,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined","output":"$undefined","database":"$undefined"},{"id":155,"value":"getVariantsByID = (id, d)=> {\n return _.map (d.variants.sequences[id], (i)=>d.variants.codes[i]);\n}","pinned":false,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined","output":"$undefined","database":"$undefined"},{"id":214,"value":"$38","pinned":false,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined","output":"$undefined","database":"$undefined"},{"id":146,"value":"extractAAVariants = (ref_seq, ref_AA, variants) => {\n let byCodon = _.groupBy (variants, (v)=>Math.floor (v[0] / 3));\n return _.filter (_.mapValues (byCodon, (vars, index)=> {\n let in_codon = _.map (vars, (v)=> [(v[0] % 3), v[1]]);\n let new_codon = _.map (ref_seq.substr (+index*3, 3), (c)=>c);\n _.each (vars, (v)=> {\n new_codon [v[0]%3] = v[1];\n });\n new_codon = translate_ambiguous_codon(new_codon.join (\"\")); \n if (new_codon.length > 1) new_codon = '?';\n if (new_codon != ref_AA[index]) {\n return [+index,new_codon]; \n }\n return [+index,\".\"];\n }), (d)=>d[1] != '.');\n}","pinned":false,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined","output":"$undefined","database":"$undefined"},{"id":358,"value":"extractFromList = (list, pos)=> {\n if (list)\n return _.map (list, (l)=>data.annotation.values[pos][data.annotation.meta[l][pos]]);\n \n return _.map (data.duplicates, (i,l)=>data.annotation.values[pos][data.annotation.meta[l][pos]]);\n}","pinned":false,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined","output":"$undefined","database":"$undefined"},{"id":856,"value":"extractMultipleFromList = (list, positions)=> {\n if (list)\n return _.map (list, (l)=>_.map (positions, (pos)=> data.annotation.values[pos][data.annotation.meta[l][pos]]));\n \n return _.map (data.duplicates, (i,l)=>_.map (positions, (pos)=> data.annotation.values[pos][data.annotation.meta[l][pos]]));\n}","pinned":false,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined","output":"$undefined","database":"$undefined"},{"id":761,"value":"extractAASignatureForSeq = (id, sites, diffs)=> {\n let variantList = data.variants.aa_variants [data.duplicates[id]];\n if (!variantList) return \"\";\n return _.map (sites, (s)=> {\n return (s in variantList) ? variantList[s] : (diffs ? \".\" : data.variants.ref_AA[s]);\n }).join (\"\");\n}","pinned":false,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined","output":"$undefined","database":"$undefined"},{"id":758,"value":"extractAASignatures = (ids, sites, diffs, cap) => {\n let res = _.groupBy (ids, (id)=> extractAASignatureForSeq (id, sites, diffs));\n delete res[\"\"];\n if (cap) {\n return _.chain (res).toPairs().sortBy ((d)=>-d[1].length).slice (0,cap).fromPairs().value();\n } \n return res;\n}","pinned":false,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined","output":"$undefined","database":"$undefined"},{"id":438,"value":"getFieldValue = (id, field)=> {\n let annotation = data.annotation.meta[id];\n if (annotation) {\n return data.annotation.values[field][annotation[field]];\n }\n return null;\n}","pinned":false,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined","output":"$undefined","database":"$undefined"},{"id":491,"value":"timeFormat = d3.timeFormat (\"%Y/%m/%d\")","pinned":false,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined","output":"$undefined","database":"$undefined"},{"id":751,"value":"$39","pinned":false,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined","output":"$undefined","database":"$undefined"},{"id":901,"value":"lookupCountryIDCached = _.memoize (lookupCountryID)","pinned":false,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined","output":"$undefined","database":"$undefined"},{"id":936,"value":"scrubberFormat = (d)=> {\n return timeFormat (new Date (d))\n}","pinned":false,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined","output":"$undefined","database":"$undefined"},{"id":59,"value":"import {translation_table, translate_ambiguous_codon, ambiguous_codes} from \"@spond/usual-vs-unusual-mutation-analyses\"","pinned":false,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined","output":"$undefined","database":"$undefined"},{"id":323,"value":"import {checkbox, radio, textarea,select,autoSelect} from \"@jashkenas/inputs\"","pinned":false,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined","output":"$undefined","database":"$undefined"},{"id":783,"value":"import {multiAutoSelect} from \"@spond/untitled/3\"","pinned":false,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined","output":"$undefined","database":"$undefined"},{"id":888,"value":"import {colorScale,makeAnimatedMap,lookupCountryID} from \"@spond/distribution-of-sars-cov-2-sequences-that-have-a-particular\"","pinned":false,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined","output":"$undefined","database":"$undefined"},{"id":920,"value":"import { legend } from \"@d3/color-legend\"","pinned":false,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined","output":"$undefined","database":"$undefined"},{"id":927,"value":"import { Scrubber } from \"@mbostock/scrubber\"","pinned":false,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined","output":"$undefined","database":"$undefined"},{"id":1458,"value":"import { table } from '@gnestor/table'","pinned":false,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined","output":"$undefined","database":"$undefined"},{"id":21,"value":"md`#### Required packages`","pinned":false,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined","output":"$undefined","database":"$undefined"},{"id":30,"value":"_ = require (\"lodash\")","pinned":false,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined","output":"$undefined","database":"$undefined"},{"id":62,"value":"boolean = require('https://bundle.run/bqpjs@0.1.1')","pinned":false,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined","output":"$undefined","database":"$undefined"},{"id":27,"value":"d3 = require (\"d3\")","pinned":false,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined","output":"$undefined","database":"$undefined"},{"id":222,"value":"moo = require (\"moo\")","pinned":false,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined","output":"$undefined","database":"$undefined"},{"id":506,"value":"vegalite = require (\"vega-embed\")","pinned":false,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined","output":"$undefined","database":"$undefined"}],"files":"$W3a","stdlib":"1","titling":"auto"}} 32:"$31:body"