32:T674,siteTableCaption = md` |Column|Definition| |---|----| | **Coordinate** | codon start in the [reference genome](https://www.ncbi.nlm.nih.gov/nuccore/1798174254), 1-based| | **AKA** | Other coordinate designations for this site| | **Gene** | the gene/ORF/unit that the codon is in | | **Site** | codon number in corresponding gene/ORF | | **MEME** | p-value for episodic diversifying selection on internal branches at this site [MEME](https://journals.plos.org/plosgenetics/article?id=10.1371/journal.pgen.1002764)| | **Events** | Number of selective "events" : individual branches with high exploratory support for selection [MEME](https://journals.plos.org/plosgenetics/article?id=10.1371/journal.pgen.1002764)| | **FEL** | p-value for pervasive selection on internal branches at this site [FEL](https://academic.oup.com/mbe/article/22/5/1208/1066893)| | **Type** | Type of selection detected by FEL [FEL](https://academic.oup.com/mbe/article/22/5/1208/1066893)| | **TrendZ** | Is the frequency of non-reference mutations at this site increasing over time? [JH test](https://en.wikipedia.org/wiki/Jonckheere%27s_trend_test)| | **Epitopes** | The number of CTL epitopes (predicted/validated) that overlap this site [1](https://www.biorxiv.org/content/10.1101/2020.03.30.016931v2), [2](https://www.nature.com/articles/s41590-020-00808-x)| | **MAF** | The frequency of non-reference mutations at this site| | **Unxpected** | How many of the codons at this site are "unexpected" based on the evolution of related βCoV (evolutionary imputation) | | **Composition** | Amino-acid composition of this site | `33:T6ca,vegalite ({ "data": {"values": sims}, "width" : 500, "height" : 200, "layer": [ { "mark": { "type": "errorbar", "extent": "iqr" }, "encoding": { "x": { "field": "value", "type": "quantitative", "scale": {"zero": false}, "axis" : {"title": "Sites count", grid : false} }, "y": {"field": "x", "type": "ordinal", "axis" : {"title" : null}} } }, { "mark": { "type": "point", "filled": true, "color": "black" }, "encoding": { "x": { "field": "value", "type": "quantitative", "scale": {"zero": false}, "aggregate": "mean", //"axis" : {"title": "count"} }, "y": {"field": "x", "type": "ordinal", "axis" : {"title" : null}} } }, { "data" : { "values" : _.map (_.toPairs (bloomprop), (d)=>{return {'x' : d[0], 'value' : d[1]}}) }, "mark": { "type": "point", "filled": true, "color": "red", "size" : 40 }, "encoding": { "x": { "field": "value", "type": "quantitative", "scale": {"zero": false}, "aggregate": "mean", //"axis" : {"title": "count"} }, "y": {"field": "x", "type": "ordinal", "axis" : {"title" : null}} } } /*{ "mark": { "type": "point", "filled": true, "color": "black" }, "encoding": { "x": { "field": "yield", "type": "quantitative", "aggregate": "mean" }, "y": {"field": "variety", "type": "ordinal"} } }*/ ] } )34:T7c6,loadAnnotationJSON = async (url)=> { let rawData = await d3.json (url); const sortedSites = _.sortBy (_.keys (rawData), (d)=>+d); const sortedGenes = _.chain (offsetsByGene).toPairs().sortBy ((d)=>d[1]).map ((d)=>[d[0],d[1]-1]).value(); let gene_range = [sortedGenes[0][1], sortedGenes[1][1], 0]; _.each (_.sortBy (_.keys (rawData), (d)=>+d), (site)=> { site = +site; let info = rawData [site]; if (site >= gene_range[1]) { gene_range[0] = gene_range[1]; gene_range[2] ++; if (gene_range[2] < sortedGenes.length - 1) { gene_range[1] = sortedGenes[gene_range[2]+1][1]; } else { gene_range[1] = 100000; } } if ("FEL" in info && info.FEL.a + info.FEL.b) { info ["FEL"]["kind"] = info.FEL.p < 1 ? (info.FEL.a < info.FEL.b ? "Pos." :(info.FEL.a > info.FEL.b) ? "Neg." : "N/A") : "N/A"; } info["segment"] = sortedGenes[gene_range[2]][0]; if (site >= offsetsByGene.RdRp && site < offsetsByGene.S) { info["SS"] = (site-gene_range[0]-1) / 3 + 1; } else { info["SS"] = (site-gene_range[0]) / 3 + 1; } info["n"] = site + 1; let maf = _.filter (_.toPairs(info.cdn), (d)=> new Set (d[0]).has ('-') == false); let all_non_gap = d3.sum (maf, (d)=>d[1]); let non_ref = d3.sum (_.filter(maf, (d)=>d[0] != info.bSC2), (d)=>d[1]); info.maf = non_ref/all_non_gap; if (info["evo"] ) { non_ref = _.filter (maf, (d)=> (d[0] in info['evo'])==false || (info['evo'][d[0]] < 1e-6)); info.unusual = non_ref.length; } info.aka = [info.G + "/" + info.S]; if (info['segment'] != info.G) { info.aka.push (info.segment + '/' + info.SS); } if (info.G == "ORF1a" || info.G == "ORF1b") { info.aka.push ('ORF1ab/' + ((info.n - 266)/3 + 1)); } }); return rawData; }35:T718,generateSiteRowList = (list, c2d, pval)=> { pval = pval || 1; const intFormat = d3.format ("d"); const nullOrFmt = (d, fmt) => _.isUndefined (d) || _.isNull (d) || _.isNaN (d) ? "N/A" : fmt (d); const fracFormat = d3.format (".3f"); const comp = (v)=> { return _.chain (v).toPairs().filter ((d)=>d[0].length == 1).sortBy ((d)=>-d[1]).map ((d)=>d[0] + "_{" + d[1] + "}").value().join (""); }; const pValueFormat = (v)=> { let pvv = nullOrFmt (v, fracFormat); if (v <= pval) { return "" + pvv + ""; } return pvv; } const floatFormat = d3.format (".1f"); if (list.length == 0) { return [ {"No sites selected" : ""} ] } const columnProcessor = { 'n' : ["Coordinate", (v)=>v], 'segment' : ["Gene", (v)=>v], 'SS' : ["Site", (v)=>intFormat(v)], 'MEME.p' : ["MEME", (v)=>pValueFormat (v)], 'MEME.br' : ["Events", (v)=>nullOrFmt(v,intFormat)], 'FEL.p' : ["FEL", (v)=>pValueFormat (v)], 'FEL.kind' : ["Type", (v)=>v == "Pos." ? "Pos." : (v == "Neg." ? "Neg." : null)], 'trend' : ["TrendZ", (v)=>nullOrFmt(v,floatFormat)], 'hla' : ["Epitopes", (v)=>nullOrFmt(_.size (v),intFormat)], 'maf' : ["MAF", (v)=>nullOrFmt(v,fracFormat)], 'unusual' : ["Unexpected", (v)=>nullOrFmt(v,intFormat)], 'aa' : ["Composition", (v)=>comp(v)], 'aka' : ["AKA", (v)=>"" + v.join (", ") + ""] }; let columns2View = c2d || columns2Display; return _.map (list, (row)=> { return _.fromPairs (_.map (columns2View, (c)=> { return [columnProcessor[c][0], columnProcessor[c][1](_.get (row,c))]; })); }); }36:[] 30:{"title":"[+ Search by Genes] Evolutionary annotation of global SARS-CoV-2/COVID-19 genomes enabled by data from ","cells":[{"id":0,"value":"md`# \\[+ Search by Genes\\] Evolutionary annotation of ${title} SARS-CoV-2/COVID-19 genomes enabled by data from $\"gisaid-logo\"$
\nMain analysis notebook is [here](https://observablehq.com/@spond/revised-sars-cov-2-analytics-page).\nLatest SARS-CoV-2 dashboard is [here](https://covid19.galaxyproject.org/dashboard).\n\n----------------------\n`","pinned":false,"hidden":false,"mode":"ojs"},{"id":37,"value":"md`There are **${_.size(annotationJSON)}** codons in the SARS-CoV-2 genome with available annotation evolutionary attributes and **${filteredListOfSites.length}** sites having all of the features selected below`","pinned":false,"hidden":false,"mode":"ojs"},{"id":39,"value":"viewof siteFilteringOptions = checkbox({\n options: [\n { value: \"g\", label: \"By Gene\" },\n { value: \"s\", label: \"+ sel.\" },\n { value: \"n\", label: \"- sel.\" },\n { value: \"m\", label: \"Multiple sel. events\" },\n { value: \"f\", label: \"High frequency\" },\n { value: \"t\", label: \"Trending up\" },\n { value: \"u\", label: \"Unexpected codons\" },\n { value: \"e\", label: \"CTL epitope\" }\n ],\n value: [],\n})","pinned":false,"hidden":false,"mode":"ojs"},{"id":647,"value":"viewof gene = text({placeholder: \"S,nsp2\", title: \"If 'By Gene' checked, which gene(s)?\", description: \"Display information about these genes, separated by commas. Options: leader, nsp2, nsp3, nsp4, 3C, nsp6, nsp7, nsp8, nsp9, nsp10, RdRp, helicase, exonuclease, endornase, methyltransferase, S, ORF3a, E, M, ORF6, ORF7a, ORF8, N, ORF10\", submit: \"Update\"})","pinned":false,"hidden":false,"mode":"ojs"},{"id":253,"value":"viewof pv = text({value: \"0.05\", title: \"p-value cutoff\", description: \"p-value cutoff for the selection analyses\", submit: \"Update\"})","pinned":false,"hidden":false,"mode":"ojs"},{"id":95,"value":"md`**Select columns to display**`","pinned":false,"hidden":false,"mode":"ojs"},{"id":93,"value":"viewof columns2Display = checkbox({\n \n options: [\n { value: \"n\", label: \"Coordinate\" },\n { value: \"aka\", label: \"AKA\"},\n { value: \"segment\", label: \"Gene\" },\n { value: \"SS\", label: \"Site\" },\n { value: \"MEME.p\", label: \"MEME\" },\n { value: \"MEME.br\", label: \"Events\" },\n { value: \"FEL.p\", label: \"FEL\" },\n { value: \"FEL.kind\", label: \"Type\" },\n { value: \"trend\", label: \"TrendZ\" },\n { value: \"hla\", label: \"Epitopes\" }, \n { value: \"maf\", label: \"MAF\"},\n { value: \"unusual\", label: \"Unexpected\"},\n { value: \"aa\", label: \"Composition\"}\n ],\n value: [\"n\",\"aka\",\"segment\",\"SS\",\"MEME.p\",\"MEME.br\",\"FEL.p\",\"FEL.kind\",\"trend\",\"hla\",\"maf\",\"aa\"],\n})","pinned":false,"hidden":false,"mode":"ojs"},{"id":107,"value":"report_table = table(rowsForTable, \n {enableFilter : true, enableDownload : true, limit : 500}\n )","pinned":false,"hidden":false,"mode":"ojs"},{"id":337,"value":"$32","pinned":false,"hidden":false,"mode":"ojs"},{"id":170,"value":"md`>To filter the table type in _string_ (e.g. nsp2)to search for a string in any of the columns, or column=value or column>value, e.g. **FEL<0.1 or **Site=\"501\"`","pinned":false,"hidden":false,"mode":"ojs"},{"id":14,"value":"md`--- \n### Code and data below this point`","pinned":false,"hidden":false,"mode":"ojs"},{"id":31,"value":"md`#### Data`","pinned":false,"hidden":false,"mode":"ojs"},{"id":98,"value":"rowsForTable = generateSiteRowList (filteredListOfSites, columns2Display, +pv)","pinned":false,"hidden":false,"mode":"ojs"},{"id":77,"value":"filteredListOfSites = {\n const p = pv;\n const g = gene.split (',');\n \n return _.chain (annotationJSON).\n filter (siteFilteringOptions.indexOf (\"g\") >= 0 ? ((d)=>(\"segment\" in d) && g.includes(d.segment)) : (d)=>true).\n filter (siteFilteringOptions.indexOf (\"s\") >= 0 ? ((d)=>(\"MEME\" in d) && d.MEME.p <= p || ((\"FEL\" in d) && d.FEL.p <= p && d.FEL.kind == \"Pos.\")) : (d)=>true).\n filter (siteFilteringOptions.indexOf (\"n\") >= 0 ? (d)=> ((\"FEL\" in d) && d.FEL.p <= p && d.FEL.kind == \"Neg.\") : (d)=>true).\n filter (siteFilteringOptions.indexOf (\"m\") >= 0 ? ((d)=>(\"MEME\" in d) && d.MEME.br > 1) : (d)=>true).\n filter (siteFilteringOptions.indexOf (\"t\") >= 0 ? ((d)=>d.trend >= 5) : (d)=>true).\n filter (siteFilteringOptions.indexOf (\"f\") >= 0 ? ((d)=>d.maf >= 0.05) : (d)=>true).\n filter (siteFilteringOptions.indexOf (\"e\") >= 0 ? ((d)=>_.size (d.hla) > 0) : (d)=>true).\n value();\n}","pinned":false,"hidden":false,"mode":"ojs"},{"id":34,"value":"annotationJSON = {\n let params = new URLSearchParams(location.search);\n const base_dir = params.get (\"dir\") || \"data/\";\n return loadAnnotationJSON ((base_dir.indexOf (\"http\") == 0 ? \"\": \"https://raw.githubusercontent.com/veg/SARS-CoV-2/compact/\") + base_dir + \"/comparative-annotation.json\");\n}","pinned":false,"hidden":false,"mode":"ojs"},{"id":564,"value":"title = new URLSearchParams(location.search).get (\"title\") || \"global\"","pinned":false,"hidden":false,"mode":"ojs"},{"id":394,"value":"RBD = _.filter (annotationJSON, (d)=>d.G == \"S\" && d.S >= 330 && d.S <= 583)","pinned":false,"hidden":false,"mode":"ojs"},{"id":508,"value":"bloomset = //new Set ([18,20,26,138,190,417,484,501,655,1027])\n new Set ([365,369,383,384,396,443,444,445,446,447,448,449,450,455,456,472,473,484,485,486,490,496,499])","pinned":false,"hidden":false,"mode":"ojs"},{"id":511,"value":"bloomprop = _.countBy (_.map (_.filter (annotationJSON, (d)=>d.G == \"S\" && bloomset.has (d.S)), (d)=>classify(d)))","pinned":false,"hidden":false,"mode":"ojs"},{"id":413,"value":"sims = {\n let sms = _.chain (_.range (5000)).map ((d)=>_.countBy (_.map(_.sampleSize (RBD, 10), classify))).value();\n let data = [];\n _.each (sms, (d)=>{\n //_.each ([\"Typical\", \"Unusual\"], (k)=> {\n\n _.each ([\"Neutral\", \"Pos.sel.\", \"Neg.sel.\", \"Conserved\"], (k)=> {\n data.push ({'x' : k, 'value' : d[k] || 0});\n });\n });\n \n return data;\n}","pinned":false,"hidden":false,"mode":"ojs"},{"id":402,"value":"classify = (d, p)=> {\n p = 0.05;\n if (\"MEME\" in d) {\n if (d.MEME.p <= p) return \"Pos.sel.\";\n if (d.FEL.p <= p && d.FEL.a < d.FEL.b) return \"Pos.sel.\";\n if (d.FEL.p <= p && d.FEL.b < d.FEL.a) return \"Neg.sel.\";\n //if (d.unusual > 0) return \"Unusual\";\n //return \"Typical\";\n if (_.filter (d.aa, (c,a)=>a.length == 1 && a!='?').length == 1) return \"Conserved\";\n }\n return \"Neutral\";\n}","pinned":false,"hidden":false,"mode":"ojs"},{"id":536,"value":"_.filter (sims, (d=> d.x == \"Pos.sel.\" && d.value >=3 )).length/sims.length","pinned":false,"hidden":false,"mode":"ojs"},{"id":441,"value":"$33","pinned":false,"hidden":false,"mode":"ojs"},{"id":382,"value":"md`#### Functions`","pinned":false,"hidden":false,"mode":"ojs"},{"id":568,"value":"$34","pinned":false,"hidden":false,"mode":"ojs"},{"id":309,"value":"$35","pinned":false,"hidden":false,"mode":"ojs"},{"id":17,"value":"md`#### Module Requires`","pinned":false,"hidden":false,"mode":"ojs"},{"id":445,"value":"vegalite = require (\"vega-embed\")","pinned":false,"hidden":false,"mode":"ojs"},{"id":22,"value":"d3 = require (\"d3\")","pinned":false,"hidden":false,"mode":"ojs"},{"id":64,"value":"_ = require (\"lodash\")","pinned":false,"hidden":false,"mode":"ojs"},{"id":25,"value":"md`#### Imports`","pinned":false,"hidden":false,"mode":"ojs"},{"id":28,"value":"import {select,checkbox, autoSelect, text} from \"@jashkenas/inputs\"","pinned":false,"hidden":false,"mode":"ojs"},{"id":43,"value":"import {translation_table,translate_ambiguous_codon} from \"@spond/usual-vs-unusual-mutation-analyses\"","pinned":false,"hidden":false,"mode":"ojs"},{"id":46,"value":"import { table } from \"@gampleman/table\"","pinned":false,"hidden":false,"mode":"ojs"},{"id":51,"value":"import {offsetsByGene} from \"@spond/revised-sars-cov-2-analytics-page\"","pinned":false,"hidden":false,"mode":"ojs"}],"files":"$W36","stdlib":"1","titling":"auto"}