31:T8a7,summary_table = html`

${create_callout(summary_tiles.recent3p)} positively selected sites ${getTimeStamp(unique_times2[0])}	${create_callout(summary_tiles.p_add) + "↑" + create_callout(summary_tiles.p_drop) + "↓"} change since ${getTimeStamp(unique_times2[1])}	${summary_tiles.p_duration[0] + " [" + parseInt(summary_tiles.p_duration[1]) + "-" + parseInt(summary_tiles.p_duration[2]) + "]"} time periods under selection (median, 95%)	${create_callout(summary_tiles.allp)} positively selected at any point
${create_callout(summary_tiles.recent3n)} negatively selected sites ${getTimeStamp(unique_times2[0])}	${create_callout(summary_tiles.n_add) + "↑" + create_callout(summary_tiles.n_drop) + "↓"} change since ${getTimeStamp(unique_times2[1])}	${summary_tiles.n_duration[0] + " [" + parseInt(summary_tiles.n_duration[1]) + "-" + parseInt(summary_tiles.n_duration[2]) + "]"} time periods under selection (median, 95%)	${create_callout(summary_tiles.alln)} negatively selected at any point

`32:T889,figure1 = vegalite ({ "config": { // Configuration Object "facet": { // - Facet Configuration "columns": 4, }, }, "data": {"values": _.filter (data2plot, (d)=>let_us_in.has (d.Gene))}, "width" : 200, "height" : 200, "facet" : { "field": "Gene", "type": "ordinal", "header": {"labelFontSize" : 14, "title" : ""}, "sort": {"op": "max", "field": "pss2", "order" : "descending"} }, "spec" : { "layer" : [{ "mark": {"type": "line", "interpolate" : "monotone", "point" : true, "tooltip" : true}, "encoding": { "x": {"field": "Date", "type": "temporal", timeUnit: "yearmonth", "axis" : {"grid" : false, titleFontSize : 12, labelFontSize : 12, labelAngle : 45}, "title" : "Analysis Date"}, "y": {"scale" : {"type" : "linear"}, "field": "pss2", "type": "quantitative", "title": "Selection 'force'", "axis" : {"grid" : false, titleFontSize : 14, labelFontSize : 14}}, "color" : {"value" : "firebrick"} } }, { "mark": {"type": "line", "interpolate" : "monotone", "point" : true, "tooltip" : true}, "encoding": { "x": {"field": "Date", "type": "temporal", timeUnit: "yearmonth", "axis" : {"grid" : false, titleFontSize : 12, labelFontSize : 12, labelAngle : 45}, "title" : "Analysis Date"}, "y": {"scale" : {"type" : "linear"}, "field": "nss2", "type": "quantitative", "title": "Selection 'force'", "axis" : {"grid" : false, titleFontSize : 14, labelFontSize : 14}}, "color" : {"value" : "steelblue"} } }, /*{ "mark": { "type": "text", "color": "steelblue", "size" : 16, "align": "right", "y": -5 }, "encoding": { "x" : {"datum" : {"expr" : unique_times2[0].to.getTime()}, "type": "temporal"}, "text": {"datum" : time_series_ac['S'][0][0], "type": "quantitative"} } } */ ] } })33:T74d,

Analysis details

We regularly download and curate whole-genome data from GISAID. These data are passed through a SARS-CoV-2 analysis pipeline, which has not been published as a standalone tool, but has been used in a number of publications, including [1,2,3]. All sequences are partitoned into three-month intervals (by sampling dates) and subjected to a series of selection analyses. This notebook presents a temporal evolutionary history of selected sites, as characterized by the [FEL method]. During a given time interval, a site can be

Positively selected: natural selection may be promoting diversification (changes to different amino-acids) at this site.
Negatively selected: natural selection may be suppressing amino-acid variation at this site; the site is therefore evolutionary conserved at the protein level.
Evolving neutrally: all other cases; this includes cases where the FEL method lacks statistical power.

When a site is identified as evolving non-neutrally, a p-value from the likelihood ratio test is used to assess significance. These are reported in the plot. Note that p-values are not directly comparable across timepoints, because of different sample sizes and other factors.

34:T57e,data2plot = { let min_p = +pv; let mbg = {}; let sites = _.filter (_.map (_.groupBy (siteHistory, (d)=>d.gene + "|" + d.to), (gr)=> { let res = {'Gene' : gr[0].gene, 'Date' : gr[0].to, 'samples' : gr[0].seqs}; if ((gr[0].gene in mbg) == false) { mbg[gr[0].gene] = 0; } let pss = _.filter (siteHistory, (sh)=>sh.gene == gr[0].gene && sh.to.getTime() == gr[0].to.getTime() && (sh.p <= min_p) && (sh.beta > sh.alpha)).length / gene_size [gr[0].gene]; let nss = _.filter (siteHistory, (sh)=>sh.gene == gr[0].gene && sh.to.getTime() == gr[0].to.getTime() && (sh.p <= min_p) && (sh.beta < sh.alpha)).length / gene_size [gr[0].gene]; res.pss = pss;// / Math.sqrt (gr[0].seqs); res.pss2 = pss/gr[0].T_int; res.nss = nss;// / Math.sqrt (gr[0].seqs); res.nss2 = nss/gr[0].T_int; res.T = gr[0].T_total; res.TT = gr[0].T_int; mbg[gr[0].gene] = Math.max (mbg[gr[0].gene], res.pss2); return res; }), (d)=>d.T >= 0.5); const maxDate = d3.max (sites, (d)=>d.Date); let max_pss = _.mapValues (_.groupBy (sites, (d)=>d.Gene), (d)=>_.sortBy (d, (t)=>t.pss2)); let highlight = {}; _.each (max_pss, (l,g)=> { if (l[l.length-1].Date.getTime () == maxDate.getTime()) { highlight [g] = 1; } }); _.each (sites, (s)=>{s.m2 = mbg[s.Gene]; s.hl = highlight[s.Gene] || 0;}); return sites; }35:T720,summary_tiles = { const pv_cut = +pv; let psel = _.filter (siteHistory, (d)=>d.p <= pv && d.alpha < d.beta && let_us_in.has (d.gene)); let nsel = _.filter (siteHistory, (d)=>d.p <= pv && d.beta < d.alpha && let_us_in.has (d.gene)); let recent_psel = _.filter (psel, (d)=>d.to.getTime() == last3[2]); let prev_psel = _.filter (psel, (d)=>d.to.getTime() == last3[1]); let prev_nsel = _.filter (nsel, (d)=>d.to.getTime() == last3[1]); let recent_nsel = _.filter (nsel, (d)=>d.to.getTime() ==last3[2]); let last_p = new Set (_.map (prev_psel, (d)=>d.sorter)); let cur_p = new Set (_.map (recent_psel, (d)=>d.sorter)); let last_n = new Set (_.map (prev_nsel, (d)=>d.sorter)); let cur_n = new Set (_.map (recent_nsel, (d)=>d.sorter)); let all_psel = _.groupBy (psel, (d)=>d.sorter); let all_nsel = _.groupBy (nsel, (d)=>d.sorter); let duration_p = _.map (_.groupBy (psel, (d)=>d.sorter), (d)=>d.length); let duration_n = _.map (_.groupBy (nsel, (d)=>d.sorter), (d)=>d.length); return { 'p_all' : psel, 'n_all' : nsel, 'recent3p' : recent_psel, 'recent3n' : recent_nsel, 'prev3p' : prev_psel, 'prev3n' : prev_nsel, 'allp' : _.map (all_psel, (d)=>d[0]), 'alln' : _.map (all_nsel, (d)=>d[0]), 'p_add' : _.filter (recent_psel, (d)=>! (last_p.has (d.sorter))), 'p_drop' : _.filter (prev_psel, (d)=>! (cur_p.has (d.sorter))), 'n_add' : _.filter (recent_nsel, (d)=>! (last_n.has (d.sorter))), 'n_drop' : _.filter (prev_nsel, (d)=>! (cur_n.has (d.sorter))), 'p_duration' : [d3.median (duration_p), d3.quantile (duration_p, 0.025), d3.quantile (duration_p, 0.975)], 'n_duration' : [d3.median (duration_n), d3.quantile (duration_n, 0.025), d3.quantile (duration_n, 0.975)], }; }36:Td52,genome_view_spec = (d)=>({ "config": { "view": { "stroke": null }, }, "vconcat": [ { "layer": [ { "height": 40, "width": 800, "data": { "values": gene_coordinates_filtered }, "transform": [{ "calculate": "(datum['3'] % 2) ? -1 : 1", "as": "coloring" }, { "calculate": "(datum['3'] % 2) ? -1 : 0", "as": "y" }, { "calculate": "(datum['3'] % 2) ? 14 : 15", "as": "y2" }, ], "mark": { "type": "bar", "stroke": "#000", "tooltip" : null, }, "encoding": { "x": { "field": "0", "type": "quantitative", "axis": null, "scale" : {"zero" : false} }, "x2": { "field": "2" }, "y": { "field": "y", "type": "quantitative", "axis": null }, "y2": { "field": "y2" }, "fill": { "condition": {"test": "datum['coloring'] < 0", "value": "lightgrey"}, "value" : "white" }, //"href": {"field": "url"}, "opacity": { "value": "0.5" } } }, { "data" : {"values" : d}, "transform": [{ "calculate": "3", "as": "y" }, { "calculate": "12", "as": "y2" }], "mark": { type: "rule", "tooltip": [ {"field": "coord", "type": "quantitative", "title" : "Nucleotide coordinate"} ], }, "encoding": { "x": { "field": "coord", "type": "quantitative", "axis": null, }, "y": { "field": "y", "type": "quantitative", "axis": null, }, "y2": { "field": "y2", "type": "quantitative", "axis": null, }, "size" : {"value" : 2.}, "color" : { "condition": [ {"test": "datum['type'] == 'Pos'", "value": "firebrick"}, ], "value" : "steelblue" }, } }, { "data": { "values": gene_coordinates_filtered }, "transform": [ { "calculate": "-15 + ((datum['3'] % 2) ? 30 : 0) ", "as": "y" }, { "calculate": "(datum['0'])+50 + (datum['3'] == 22 ? 300 : 0) + (datum['3'] == 19 ? -300 : 0)", "as": "x" }], "mark": { "type": "text", "fontSize": 9, "baseline": "bottom", "tooltip" : false, "align" : "left" }, "encoding": { "x": { "field": "x", "type": "quantitative", }, "y": { "field": "y", "type": "quantitative" }, "text": { "field": "1", "legend" : null, }, } }, ] }, ], })37:Tc29,html` `38:[] 2f:{"title":"Examining natural selection history on global SARS-CoV-2 genomes enabled by data from ","cells":[{"id":0,"value":"md`# Examining natural selection history on global SARS-CoV-2 genomes enabled by data from $\"gisaid-logo\"$
`","pinned":false,"hidden":false,"mode":"ojs"},{"id":1137,"value":"View history of natural selection pressures on the SARS-CoV-2 genome, through analyses of **${unique_times.length}** three-month overlapping intervals going back to the beginning of the pandemic. The earliest intervals ends in _${date_range[0]}_ and the latest - in _${date_range[1]}_.
[Examine the evolution of individual sites](https://observablehq.com/@spond/sars-cov-2-selected-sites) or [Download .csv data](https://github.com/spond/SARS-CoV-2-variation)","pinned":false,"hidden":false,"mode":"md"},{"id":1627,"value":"$31","pinned":false,"hidden":false,"mode":"ojs"},{"id":2064,"value":"genome_view = vegalite(genome_view_spec (genome_display (summary_tiles.recent3p, summary_tiles.recent3n)))","pinned":false,"hidden":false,"mode":"ojs"},{"id":1702,"value":"viewof genes2view = multiAutoSelect ( {\"options\" : genes, \"value\" : [], \"title\" : \"Include these genomic regions\", \"description\" : \"Click on numbers in the dashboard to open site-level views\"})","pinned":false,"hidden":false,"mode":"ojs"},{"id":1622,"value":"viewof pv = Inputs.text({label: html`p-value threshold`, value: \"0.01\", submit: \"Update\"})","pinned":false,"hidden":false,"mode":"ojs"},{"id":1877,"value":"fig1_label = md`**Figure 1.** Temporal evolution of selection force, defined as the number of positively and negatively selected sites normalized by kilobase of gene length and the internal tree length (sites/[substitutions across the tree x gene length]); this quantity should be directly comparable between genes and time points. Genes are sorted by maximal 'force' of positive selection over all time.`","pinned":false,"hidden":false,"mode":"ojs"},{"id":1831,"value":"$32","pinned":false,"hidden":false,"mode":"ojs"},{"id":1123,"value":"$33","pinned":false,"hidden":false,"mode":"html"},{"id":5,"value":"md`### Libraries and data`","pinned":false,"hidden":false,"mode":"ojs"},{"id":9,"value":"d3 = require(\"d3@6\")","pinned":false,"hidden":false,"mode":"ojs"},{"id":1194,"value":"import {select} from \"@jashkenas/inputs\"","pinned":false,"hidden":false,"mode":"ojs"},{"id":12,"value":"vegalite = require (\"vega-embed\")","pinned":false,"hidden":false,"mode":"ojs"},{"id":15,"value":"_ = require (\"lodash\")","pinned":false,"hidden":false,"mode":"ojs"},{"id":1785,"value":"create_callout = (list, direct)=> {\n return 'd.sorter)).join (\",\") + '\" target = \"_blank\">' + list.length + '';\n}","pinned":false,"hidden":false,"mode":"ojs"},{"id":22,"value":"import {gene_coordinates} from \"@spond/revised-sars-cov-2-analytics-page\"","pinned":false,"hidden":false,"mode":"ojs"},{"id":1365,"value":"import {Wrangler, op} from \"@observablehq/data-wrangler\"","pinned":false,"hidden":false,"mode":"ojs"},{"id":692,"value":"site_equiv = _.groupBy (_.toPairs (jsonCodonLookup), (d)=>d[1])","pinned":false,"hidden":false,"mode":"ojs"},{"id":49,"value":"import {jsonCodonLookup} from \"@spond/sars_cov_2_sites\"","pinned":false,"hidden":false,"mode":"ojs"},{"id":58,"value":"import {multiAutoSelect} from \"@spond/untitled/3\"","pinned":false,"hidden":false,"mode":"ojs"},{"id":1433,"value":"unique_times = _.sortBy (_.keys(_.countBy (siteHistory, (d)=>d.to.getTime())))","pinned":false,"hidden":false,"mode":"ojs"},{"id":1890,"value":"unique_times2 = _.sortBy (_.uniqBy (siteHistory, (d)=>d.to.getTime()), (d)=>-d.to.getTime())","pinned":false,"hidden":false,"mode":"ojs"},{"id":1897,"value":"getTimeStamp = (d)=> {\n const fmt = d3.timeFormat (\"%Y%m%d\");\n return fmt (d.from.getTime() + 24*3600*1000) + \"-\" + fmt (d.to.getTime() + 24*3600*1000);\n}","pinned":false,"hidden":false,"mode":"ojs"},{"id":1454,"value":"last3 = _.map (unique_times.slice (-3), (d)=>+d)","pinned":false,"hidden":false,"mode":"ojs"},{"id":1327,"value":"dr = d3.extent (siteHistory, (d)=>d.to)","pinned":false,"hidden":false,"mode":"ojs"},{"id":1402,"value":"pad_array = (arr)=>_.map (arr, (d)=>\"Site \" + d.toUpperCase())","pinned":false,"hidden":false,"mode":"ojs"},{"id":1825,"value":"$34","pinned":false,"hidden":false,"mode":"ojs"},{"id":1233,"value":"date_range = _.map (dr, (d)=>d3.timeFormat (\"%B %Y\")(d))","pinned":false,"hidden":false,"mode":"ojs"},{"id":1349,"value":"date_range_obj = _.map (dr, (d)=>({'year' : d.getFullYear(), 'month': 1+d.getMonth(), 'day' : d.getDate() + 1}))","pinned":false,"hidden":false,"mode":"ojs"},{"id":1696,"value":"genes = [\"Whole Genome\"].concat (_.sortBy (_.map (_.uniqBy (siteHistory, (d)=>d.gene), d=>d.gene)))","pinned":false,"hidden":false,"mode":"ojs"},{"id":2075,"value":"genome_display = (pset, nset)=> {\n let site_info = [];\n _.each ([[pset,'Pos'],[nset,'Neg']], (d)=> {\n _.each (d[0], (s)=> {\n site_info.push ({\n 'coord' : s.sorter,\n 'label' : s.label,\n 'p' : s.p,\n 'alpha' : s.alpha,\n 'beta' : s.beta,\n 'type' : d[1]\n });\n });\n });\n return site_info;\n \n}","pinned":false,"hidden":false,"mode":"ojs"},{"id":1639,"value":"$35","pinned":false,"hidden":false,"mode":"ojs"},{"id":1837,"value":"let_us_in = {\n let let_us_in = new Set();\n if (genes2view.length == 0) {\n let_us_in = new Set (genes);\n } else {\n _.each (genes2view, (g)=> {\n if (g == \"Whole Genome\") {\n _.each (genes, (g2)=>let_us_in.add (g2));\n } else {\n let_us_in.add (g);\n }\n });\n }\nreturn let_us_in;}","pinned":false,"hidden":false,"mode":"ojs"},{"id":1947,"value":"dd = _.sortBy (_.filter (data2plot, (d)=> d.Gene == \"S\"), (d)=>d.Date.getTime())","pinned":false,"hidden":false,"mode":"ojs"},{"id":1980,"value":"cc = require('https://bundle.run/calculate-correlation@1.2.2')","pinned":false,"hidden":false,"mode":"ojs"},{"id":2092,"value":"gene_coordinates_filtered = _.filter (gene_coordinates, (d)=>let_us_in.has (d[1]))","pinned":false,"hidden":false,"mode":"ojs"},{"id":1991,"value":"ac = import('https://cdn.skypack.dev/autocorrelation@0.0.5?min')","pinned":false,"hidden":false,"mode":"ojs"},{"id":2004,"value":"time_series_ac = {\n return _.fromPairs (_.map (genes, (g)=> {\n let dd = _.sortBy (_.filter (data2plot, (d)=> d.Gene == g), (d)=>d.Date.getTime());\n if (dd.length) {\n let acc = _.map (['pss2','nss2'], (f)=> {\n let acv = ac.autocorrelation (_.map (dd, (d)=>d[f]));\n let mc = -1;\n let mci = 0;\n _.each (acv, (cc, i)=> {\n if (i) {\n if (cc > mc) {\n mc = cc;\n mci = i;\n }\n }});\n return [mc,mci];\n });\n return [g,acc];\n }\n return [\"\",\"\"];\n }));\n //ac.autocorrelation (_.map (dd, (d)=>d.pss2))\n}","pinned":false,"hidden":false,"mode":"ojs"},{"id":46,"value":"siteHistory = {\n let raw_data = await d3.csv (\"https://raw.githubusercontent.com/spond/SARS-CoV-2-variation/master/windowed-sites-fel-current.json\", d3.autoType);\n //let raw_data = d3.csvParse (await FileAttachment(\"windowed-sites-fel-current.json.txt\").text(), d3.autoType);\n _.each (raw_data, (s)=>{\n s.loc = s.gene.toUpperCase() + \"/\" + s.site;\n /*if (s.loc in siteList[1]) {\n s.label = siteList[1][s.loc]; \n } (else { */\n s.label = s.loc;\n //}\n s.sorter = parseInt(jsonCodonLookup[s.loc]);\n s.p = Math.max (s.p, 1e-16);\n \n });\n return raw_data;\n}","pinned":false,"hidden":false,"mode":"ojs"},{"id":1259,"value":"nucToCodons = _.chain (_.toPairs (jsonCodonLookup)).groupBy ((d)=>d[1]).mapValues ((d)=>_.map (d, (c)=>c[0])).value()","pinned":false,"hidden":false,"mode":"ojs"},{"id":596,"value":"parseSiteList = (site_list) => {\n let labels = {};\n site_list = _.map (site_list, (d)=>d.split (\"/\"));\n \n let sites = new Set (_.map (site_list, (d)=>{\n if (+d == d) {\n for (let i = d; i > d-3; i--) {\n if (i in nucToCodons) {\n d = nucToCodons[i][0].split (\"/\");\n break;\n }\n }\n \n }\n if (d[0].substr (0,4) == \"ORF1\") {\n let eq = null;\n _.each (site_equiv[jsonCodonLookup [d[0]+\"/\"+d[1]]], (tr)=> {\n if (tr[0].substr (0,4) != \"ORF1\") {\n eq = tr[0];\n labels[eq] = d[0] + \"/\" + d[1];\n }\n });\n return eq;\n }\n return d[0] + \"/\" + d[1];\n}));\n return [sites, labels]\n}","pinned":false,"hidden":false,"mode":"ojs"},{"id":1341,"value":"params = new URLSearchParams(location.search)","pinned":false,"hidden":false,"mode":"ojs"},{"id":1821,"value":"import {gene_size} from \"@spond/sc2-temporal-selection-trends\"","pinned":false,"hidden":false,"mode":"ojs"},{"id":2105,"value":"$36","pinned":false,"hidden":false,"mode":"ojs"},{"id":1630,"value":"$37","pinned":false,"hidden":false,"mode":"ojs"},{"id":1633,"value":"html``","pinned":false,"hidden":false,"mode":"ojs"}],"files":"$W38","stdlib":"1","titling":"auto"}