31:T510,viewof variant_ranges = !auto_run ? formWithSumbit(html``) : form (html``)32:T4c9,variantPlotTemplate = (d, label, condition )=> { return { "$schema": "https://vega.github.io/schema/vega-lite/v4.json", "data": { "values": d }, "width": 800, "height": 600, "mark": {type: "circle", "opacity" : 0.8, tooltip : {"content" : "data"}}, "encoding": { "x": { "field": "x", "grid" : null, "title": "Variant count/sample", "type": "quantitative", "axis": false }, "y": { "field": "y", "type": "quantitative", "title" : "", "axis": false }, "size" : { //"value" : 3, "field" : "size", "scale" : {"range" : [4,30]}, "type": "quantitative", "legend" : { "title" : "AF, %", "labelFontSize" : 14, "titleFontSize" : 18, "orient" : "bottom" }, }, "color" : { "field" : "type", "condition": condition ? condition : {"test": "datum['type'] == 'other'", "value": "lightgrey"}, "legend" : { "title" : label || "Variant type", "labelFontSize" : 14, "titleFontSize" : 18, "orient" : "top" }, }, //"row" : {"field" : "cluster", "title" : "Variant cluster", "sort": "ascending"} } }; }33:[] 2f:{"title":"Exploring SARS-CoV-2 intrahost variation (patterns)","cells":[{"id":0,"value":"md`# Exploring SARS-CoV-2 intrahost variation (patterns)`","pinned":false,"hidden":false,"mode":"ojs"},{"id":40,"value":"md`This variant dataset contains information on **${N.count}** allelic variants from **${N.samples}** samples, and comprises **${N.variants}** unique allelic variants.`","pinned":false,"hidden":false,"mode":"ojs"},{"id":632,"value":"$31","pinned":false,"hidden":false,"mode":"ojs"},{"id":39,"value":"md`**Figure 1.** Co-occurence patterns of **${variantGrid.length}** variants across **${_.size (includedSamples)}** samples \n>rows = samples, columns = variants, x axis is **not** scaled to represent genomic positions; rows are arranged via hierarchical clustering`","pinned":false,"hidden":false,"mode":"ojs"},{"id":63,"value":"fig1 = vegalite (variantPlotTemplate (variantGrid))\n","pinned":false,"hidden":false,"mode":"ojs"},{"id":765,"value":"viewof K = text({title: \"Cluster variants\", placeholder: \"5\", description: \"2-20 is the permitted range\", submit: \"Cluster\", value : auto_run ? 5 : null })","pinned":false,"hidden":false,"mode":"ojs"},{"id":894,"value":"viewof distance = radio({title: \"Cluster by \", options: [\"AF by sample\",\"AF distribution\"], \"value\" : \"AF by sample\"})","pinned":false,"hidden":false,"mode":"ojs"},{"id":420,"value":"md`** Table 1 **. Variants clusters (K-medoid) based on co-occurence patterns including **${_.size (includedVariants)}** unique variants`","pinned":false,"hidden":false,"mode":"ojs"},{"id":418,"value":"variantClustersTable && variantClustersTable.length ? table (variantClustersTable,\n {\n limit: 100,\n enableCSVDownload: true,\n sort: true,\n enableFilter: false,\n columns: [\n \n {\n key: 'id',\n name: 'Cluster ID'\n \n },\n {\n key: 'size',\n name: 'Cluster Size',\n },\n {\n key: 'members',\n name: 'Variants assigned to cluster',\n },\n {\n key: 'together',\n name: 'All variants appear together x times',\n render : (val)=>val.size\n },\n {\n key: 'expected',\n name: 'Expected # of co-occurences',\n render : (val)=>d3.format (\".2f\")(val)\n }\n ]\n}) : md`>_Clustering not yet performed_`;","pinned":false,"hidden":false,"mode":"ojs"},{"id":859,"value":"viewof viewC = select({description: \"Highlight variants in this cluster\", \"options\" : [\"All\"].concat(_.map (_.range (variantClusters.length), (d,i)=>i+1)), value : 1})","pinned":false,"hidden":false,"mode":"ojs"},{"id":928,"value":"md`**Figure 2.** Variants clustered according to the selected criteria. \n>rows = samples, columns = variants, x axis is **not** scaled to represent genomic positions`","pinned":false,"hidden":false,"mode":"ojs"},{"id":850,"value":"fig2 = vegalite (variantPlotTemplate (variantGridByCluster, \"Cluster\"))","pinned":false,"hidden":false,"mode":"ojs"},{"id":926,"value":"md`**Table 2**. Nucleotide subsitution biases`","pinned":false,"hidden":false,"mode":"ojs"},{"id":947,"value":"table (changeTableRows,\n {\n enableCSVDownload: false,\n sort: false,\n enableFilter: false,\n columns: [\n \n {\n key: 'from',\n name: 'From'\n \n },\n {\n key: 'A',\n name: 'A',\n },\n {\n key: 'C',\n name: 'C',\n },\n\n {\n key: 'G',\n name: 'G',\n },\n {\n key: 'T',\n name: 'T',\n },\n\n ]\n});","pinned":false,"hidden":false,"mode":"ojs"},{"id":8,"value":"md`### Data`","pinned":false,"hidden":false,"mode":"ojs"},{"id":21,"value":"variantTable = _.filter (await obtainSourceData(), (d)=>d.FILTER == \"PASS\" || (\"FILTER\" in d == false))","pinned":false,"hidden":false,"mode":"ojs"},{"id":28,"value":"byVariant = _.groupBy (variantTable, (v)=>variantKey(v))","pinned":false,"hidden":false,"mode":"ojs"},{"id":31,"value":"bySample = _.groupBy (variantTable, (v)=>v.Sample)","pinned":false,"hidden":false,"mode":"ojs"},{"id":538,"value":"sortedSampleKeys = _.chain (bySample).keys().sortBy().toPairs().map ((d)=>[d[1],+(d[0])]).fromPairs().value()","pinned":false,"hidden":false,"mode":"ojs"},{"id":547,"value":"sortedVariantKeys = _.chain (variantTable).sortBy ((d)=>d.POS).map ((d)=>variantKey(d)).uniq().map ((d,i)=>[d,i]).fromPairs().value()","pinned":false,"hidden":false,"mode":"ojs"},{"id":173,"value":"equiv_map = {\n return {\n 'SYNONYMOUS_CODING' : 'Synonymous',\n 'NON_SYNONYMOUS_CODING' : 'Non-synonymous',\n '.' : 'Non-coding',\n 'STOP_GAINED' : 'Stop'\n }\n}","pinned":false,"hidden":false,"mode":"ojs"},{"id":178,"value":"map2key = (d)=> {return d in equiv_map ? equiv_map[d] : \"Indel\"};","pinned":false,"hidden":false,"mode":"ojs"},{"id":654,"value":"sample_range = [+variant_ranges.min, +variant_ranges.max]","pinned":false,"hidden":false,"mode":"ojs"},{"id":882,"value":"af_range = [+variant_ranges.minAF, +variant_ranges.maxAF]","pinned":false,"hidden":false,"mode":"ojs"},{"id":941,"value":"changeTableRows = [\n {from : 'A', 'A': null, 'C' : changeCounts['A|C'], 'G' : changeCounts['A|G'], 'T' : changeCounts['A|T']},\n {from : 'C', 'C': null, 'A' : changeCounts['C|A'], 'G' : changeCounts['C|G'], 'T' : changeCounts['C|T']},\n {from : 'G', 'G': null, 'C' : changeCounts['G|C'], 'A' : changeCounts['G|A'], 'T' : changeCounts['G|T']},\n {from : 'T', 'T': null, 'C' : changeCounts['T|C'], 'G' : changeCounts['T|G'], 'A' : changeCounts['T|A']}\n ]","pinned":false,"hidden":false,"mode":"ojs"},{"id":934,"value":"changeCounts = _.countBy (_.toPairs(includedVariants), (d)=>d[0].split ('|').splice (1).join ('|'))","pinned":false,"hidden":false,"mode":"ojs"},{"id":617,"value":"includedVariants = _.chain (byVariant).toPairs().filter ((d)=>d[1].length >= sample_range[0] && d[1].length <= sample_range[1] && _.every (d[1], (v)=>v.AF >= af_range[0] && v.AF <= af_range[1])).map ((d,i)=>[d[0],i]).fromPairs ().value();","pinned":false,"hidden":false,"mode":"ojs"},{"id":671,"value":"includedSamples = _.chain (bySample).toPairs().filter ((d)=>_.some (d[1], (v)=>variantKey(v) in includedVariants)).map ((d,i)=>[d[0],i]).fromPairs().value()","pinned":false,"hidden":false,"mode":"ojs"},{"id":733,"value":"sampleReverseMap = _.chain (includedSamples).toPairs().map ((d)=>[d[1],d[0]]).fromPairs().value()","pinned":false,"hidden":false,"mode":"ojs"},{"id":810,"value":"variantReverseMap = _.chain (includedVariants).toPairs().map ((d)=>[d[1],d[0]]).fromPairs().value()","pinned":false,"hidden":false,"mode":"ojs"},{"id":701,"value":"distanceMatrix = {\n let S = _.size (includedSamples);\n let D = _.size (includedVariants);\n let R = _.map (_.range (S), (d)=>_.map (_.range (D), (d)=>0.));\n _.each (includedVariants, (k,v)=> {\n _.each (byVariant[v], (s)=> {\n if (s.Sample in includedSamples) {\n R[includedSamples[s.Sample]][k] = variant_ranges.af ? s.AF : (s.AF > 0 ? 1 : 0);\n }\n });\n });\n return R;\n}","pinned":false,"hidden":false,"mode":"ojs"},{"id":904,"value":"distributionBinner = d3.scaleThreshold ().domain ([0.075,0.10,0.15,0.2,0.3,0.4,0.5,0.6,0.7,0.8,0.9,0.95,0.98]).range (_.range (14))","pinned":false,"hidden":false,"mode":"ojs"},{"id":792,"value":"distanceMatrixByVariant = {\n if (distance == \"AF by sample\") {\n let S = _.size (includedSamples);\n let D = _.size (includedVariants);\n let R = _.map (_.range (D), (d)=>_.map (_.range (S), (d)=>0.));\n _.each (includedVariants, (k,v)=> {\n _.each (byVariant[v], (s)=> {\n if (s.Sample in includedSamples) {\n R[k][includedSamples[s.Sample]] = variant_ranges.af ? s.AF : (s.AF > 0 ? 1 : 0);\n }\n });\n });\n return R;\n } else {\n let S = _.size (includedSamples);\n let D = _.size (includedVariants);\n let N = distributionBinner.range ().length;\n let R = _.map (_.range (D), (d)=>_.map (_.range (N), (d)=>0.));\n _.each (includedVariants, (k,v)=> {\n let n = 1./byVariant[v].length;\n _.each (byVariant[v], (s)=> {\n R[k][distributionBinner(s.AF)] ++;\n });\n _.each (_.range (N), (i)=>R[k][i] *= n);\n });\n return R;\n }\n} ","pinned":false,"hidden":false,"mode":"ojs"},{"id":800,"value":"variantClusters = {\n if (K) {\n let k = parseInt (K);\n if (k < 2) k = 2;\n if (k > 20) k = 20;\n let clusters = peformKM (distanceMatrixByVariant, k);\n return _.map (clusters, (d)=>_.map (d, (v)=>variantReverseMap[v]));\n }\n return [];\n}","pinned":false,"hidden":false,"mode":"ojs"},{"id":840,"value":"variant2Cluster = {\n let v2c = {};\n _.each (variantClusters, (d,i)=> {\n _.each (d, (v)=> {\n v2c [v] = i+1; \n })\n });\n return v2c;\n}","pinned":false,"hidden":false,"mode":"ojs"},{"id":817,"value":"variantClustersTable = _.map (variantClusters, (c,i)=> {\n let N = _.size (bySample);\n return {\n 'id' : \"Cluster \" + (i+1),\n 'size' : c.length,\n 'members' : c.length <= 10 ? c.join (\", \") : _.slice (c, 0, 10).concat([\"...\"]).join (\", \"),\n 'together' : _.chain (c).reduce((isect,s)=> {\n let sample_set = new Set (_.map (byVariant[s], (st)=>st.Sample));\n return new Set([...isect].filter(x => sample_set.has(x)))\n}, new Set (_.map (byVariant[c[0]], (st)=>st.Sample))).value(),\n 'expected' : _.reduce (_.map (c, (i)=>byVariant[i].length / N), (a,v)=> a * v, 1) * N\n }\n});","pinned":false,"hidden":false,"mode":"ojs"},{"id":714,"value":"sampleOrdering = {\n let orderingArray = {};\n let orderAppearance = 0;\n let post_order = (node)=> {\n if (node.left) {\n post_order (node.left); \n }\n if (node.right) {\n post_order (node.right); \n }\n if (node.index !== undefined) {\n orderingArray[sampleReverseMap[node.index]] = orderAppearance;\n orderAppearance ++;\n }\n };\n let root = peformHC (distanceMatrix);\n post_order(root.root);\n return orderingArray;\n}","pinned":false,"hidden":false,"mode":"ojs"},{"id":559,"value":"variantGrid = { \n return makeVariantGrid(_.filter (variantTable, (d)=>variantKey(d) in includedVariants), sampleOrdering);\n}","pinned":false,"hidden":false,"mode":"ojs"},{"id":1057,"value":"_.map (_.filter (_.toPairs (_.groupBy (variantGridByCluster, (d)=>d.Sample)), (d)=>d[1].length >= 5), (d)=>d[0]).join (\", \")","pinned":false,"hidden":false,"mode":"ojs"},{"id":845,"value":"variantGridByCluster = {\n \n return _.map (variantGrid, (d)=> {\n let dc = _.clone (d);\n dc.type = variant2Cluster[variantKey (d)];\n if (viewC != 'All') {\n if (dc.type != viewC) dc.type = \"other\";\n }\n return dc;\n });\n}","pinned":false,"hidden":false,"mode":"ojs"},{"id":42,"value":"N = {\n return {\n variants: _.size (byVariant),\n samples: _.size (bySample),\n count: _.size (variantTable)\n };\n}","pinned":false,"hidden":false,"mode":"ojs"},{"id":491,"value":"params = new URLSearchParams(location.search)","pinned":false,"hidden":false,"mode":"ojs"},{"id":1022,"value":"auto_run = (new URLSearchParams(location.search)).get (\"auto\")","pinned":false,"hidden":false,"mode":"ojs"},{"id":24,"value":"md`### Utility functions`","pinned":false,"hidden":false,"mode":"ojs"},{"id":835,"value":"$32","pinned":false,"hidden":false,"mode":"ojs"},{"id":687,"value":"peformHC = (data)=>{\n const X = druid.Matrix.from(data); // X is the data as object of the Matrix class.\n const DR = druid[\"Hierarchical_Clustering\"]; // DR is the selected DR class\n const hc = new DR(X, \"complete\", /*druid.manhattan*/);\n return hc;\n}","pinned":false,"hidden":false,"mode":"ojs"},{"id":787,"value":"peformKM = (data, K)=>{\n const X = druid.Matrix.from(data); // X is the data as object of the Matrix class.\n const DR = druid[\"KMedoids\"]; // DR is the selected DR class\n const hc = new DR(X, K, druid.hamming);\n return hc.get_clusters();\n}","pinned":false,"hidden":false,"mode":"ojs"},{"id":554,"value":"makeVariantGrid = (vt, sampleOrdering)=>{\n vt = vt || variantTable;\n _.each (vt, (x)=> {\n x.x = sortedVariantKeys [variantKey (x)];\n x.y = sampleOrdering ? sampleOrdering [x.Sample] : sortedSampleKeys [x.Sample];\n x.size = x.AF * 100;\n x.type = map2key (x.EFFECT);\n })\n return vt;\n}","pinned":false,"hidden":false,"mode":"ojs"},{"id":476,"value":"generate_summary_stats = (counts)=> {\n return _.map (_.groupBy (counts, (d)=>d.kind), (c,k)=> {\n return {'kind' : k, \n 'mean' : d3.mean (c, (cc)=>cc.count), \n 'median' : d3.median (c, (cc)=>cc.count), \n 'range' : [d3.min (c, (cc)=>cc.count),d3.max (c, (cc)=>cc.count)],\n 'IQR' : [d3.quantile (c, 0.25, (cc)=>cc.count),d3.quantile (c, 0.75, (cc)=>cc.count)]\n };\n })\n}","pinned":false,"hidden":false,"mode":"ojs"},{"id":124,"value":"variantKey = (d)=> {return \"\" + d.POS + \"|\" + d.REF + \"|\" + d.ALT}","pinned":false,"hidden":false,"mode":"ojs"},{"id":233,"value":"frequency_scale = d3.scaleQuantize()\n .domain([0, 1])\n .range(_.range (20))","pinned":false,"hidden":false,"mode":"ojs"},{"id":251,"value":"cov = (freqs)=> {\n let sum = 0,\n sum2 = 0,\n n = freqs.length;\n \n _.each (freqs, (f)=> {sum += f; sum2 += f*f;});\n let mean = sum/n;\n let variance = sum2/n - mean*mean;\n return [mean,variance,Math.sqrt (variance)/mean,n];\n}","pinned":false,"hidden":false,"mode":"ojs"},{"id":439,"value":"float_format = d3.format (\".2f\")","pinned":false,"hidden":false,"mode":"ojs"},{"id":485,"value":"frac_format = d3.format (\".2p\")","pinned":false,"hidden":false,"mode":"ojs"},{"id":5,"value":"md`### Libraries/Modules`","pinned":false,"hidden":false,"mode":"ojs"},{"id":12,"value":"d3 = require (\"d3\")","pinned":false,"hidden":false,"mode":"ojs"},{"id":15,"value":"_ = require (\"lodash\")","pinned":false,"hidden":false,"mode":"ojs"},{"id":683,"value":"druid = require(\"@saehrimnir/druidjs@^0.3.7\")","pinned":false,"hidden":false,"mode":"ojs"},{"id":18,"value":"vegalite = require (\"vega-embed\")","pinned":false,"hidden":false,"mode":"ojs"},{"id":415,"value":"import {table} from \"@gampleman/table\"","pinned":false,"hidden":false,"mode":"ojs"},{"id":628,"value":"import {form} from \"@mbostock/form-input\"","pinned":false,"hidden":false,"mode":"ojs"},{"id":887,"value":"import {formWithSumbit} from \"@forresto/form-input-with-submit\"","pinned":false,"hidden":false,"mode":"ojs"},{"id":766,"value":"import {text,select, radio} from \"@jashkenas/inputs\"","pinned":false,"hidden":false,"mode":"ojs"},{"id":874,"value":"import {obtainSourceData} from \"@spond/exploring-sars-cov-2-intrahost-variation-descriptive\"","pinned":false,"hidden":false,"mode":"ojs"}],"files":"$W33","stdlib":"1","titling":"auto"}