25:["$","title",null,{"children":"Evidence of natural selection history operating on HIV-1 genomes | San Emmanuel James | Observable"}] 49:T4d2,{ let positive = site_type == "Positive"; let color_field = color_grade == "Sequences" ? (d)=>d.seqs : (d)=>d["T_int"]; let cells; const tpy = time_periods[time_period].getFullYear(); let tp = _.filter (siteHistory, (d)=>d.from.getFullYear() == tpy); if (color_grade != "Fraction of sites under selection") { cells = Plot.cell(tp, {x: "cluster", y: "gene", fill: color_field, inset: 0.5}); } else { cells = Plot.cell(tp, Plot.group ({"fill": d=>{return _.filter (d, (s)=>(positive ? s.alpha < s.beta : s.beta < s.alpha) && s.p <= pvp).length / d.length}}, {x: "cluster", y: "gene"})); } const pvp = parseFloat (pv); return Plot.plot({ marginLeft: 50, padding: 0, grid: true, x: {axis: "top", label: "Cluster"}, y: {label: "Gene"}, color: {scheme: "turbo", "type" : color_grade != "Fraction of sites under selection" ? "log" : "linear", "legend" : true, label : color_grade}, marks: [ cells, Plot.text(tp, Plot.group ({"text": d=>{return _.filter (d, (s)=>(positive ? s.alpha < s.beta : s.beta < s.alpha) && s.p <= pvp).length}}, {x: "cluster", y: "gene", "fill" : "white"})), ] }) }4a:T40e,{ let positive = site_type_force == "Positive"; let cells; let tp = _.filter (siteHistory, (d)=>d.gene == gene_to_view_force); cells = Plot.dotY (tp, Plot.groupX ({"y": d=>{return _.filter (d, (s)=>(positive ? s.alpha < s.beta : s.beta < s.alpha) && s.p <= pvp).length / d.length / (d.length > 0 ? d[0].T_int : 1)}}, {x: "to", "stroke" : "cluster", "tip" : true})); const pvp = parseFloat (pv); return Plot.plot({ marginLeft: 50, padding: 0, grid: false, x: {axis: "top", label: "Time period"}, y: {label: "Selection \"force\"", type : "linear"}, color: { "legend" : true, label : "Cluster", domain : unique_clusters}, marks: [ Plot.frame(), Plot.lineY (tp, Plot.groupX ({"y": d=>{return _.filter (d, (s)=>(positive ? s.alpha < s.beta : s.beta < s.alpha) && s.p <= pvp).length / d.length / (d.length > 0 ? d[0].T_int : 1)}}, {x: "to", "stroke" : "cluster", curve: "natural"})), cells ] }) }4b:T705,main_view = vegalite({ "title": null, data: {values: site_type_detail == "Both" ? forPlot : _.filter (forPlot, (d)=>site_type_detail == "Positive" ? d.alpha < d.beta : d.alpha > d.beta)}, transform: [{"calculate": "-log(datum.p)/log(10)", "as" : "psize"}], width : 700, layer: [ { "mark": {"type": "circle", "opacity" : 0.5, "stroke": "black", "strokeWidth": 1, size : 40, tooltip : true}, "encoding": { "x": {field: "to", timeUnit: "year", type: "temporal", scale: {nice: true, padding : 0.5, domain : date_range_obj}, axis: {"title": "Analysis using data from the time span", titleFontSize : 14, grid : false, "labelFontSize" : 12, labelAngle : 45}}, tooltip : [ {"field": "loc", "type": "ordinal", "title": "Site"}, {"field": "to", "type": "temporal", "title": "Analysis date"}, {"field": "p", "type": "quantitative", "title": "P-value", "format" : ".2g"}, {"field" : "seqs", "type": "quantitative", "title": "Repr. sequences used in analysis"} ], "y": {"sort": {"field" : "site"}, "field": "label", "type": "nominal", axis: { "titleFontSize" : 14, "labelFontSize" : 14, "grid" : false, "title" : null, "labelFont" : "courier" }, }, "size" : {"field" : "psize", "type" : "quantitative", "legend" : { "tickCount" : 5, "title" : "-log10 (p)", "orient" : "top"} }, "color": { "condition": {"test": "datum['alpha'] > datum['beta']", "value": "darkblue"}, "value": "darkred" } } } ] })4c:[] 29:{"id":"ae6d5ff8574dcb61","slug":null,"title":"Evidence of natural selection history operating on HIV-1 genomes","thumbnail":"55097380431d55dfdaeb69150f1133a622752b235c7faed663f2d34bdcb6c06c","access_level":"public","create_time":"$D2024-02-09T16:54:37.233Z","update_time":"$D2024-02-09T16:54:37.233Z","view_time":null,"first_public_time":"$D2024-02-09T16:54:37.233Z","has_unpublished_edits":null,"fork":true,"stars":0,"starred":false,"owner":{"type":"team","id":"c9eb24e2b90f32f1","login":"jsan4christ","name":"San Emmanuel James","avatar_url":"https://avatars-next.observableusercontent.com/27de0beb8da8eba37da2d750ff2820ef819226744bf3aa7a34f9e5a25fba20bb","tier":"starter_2024","bio":"","followed_by_you":false,"follows_you":false},"version":2028,"publish_version":null,"role":null,"authored":false,"authors":[{"type":"individual","id":"eac258e8777c8b2e","login":"jsan4christ","name":"San Emmanuel James","avatar_url":"https://avatars-next.observableusercontent.com/27de0beb8da8eba37da2d750ff2820ef819226744bf3aa7a34f9e5a25fba20bb","tier":null,"bio":"","followed_by_you":false,"follows_you":false}],"members":[{"type":"individual","id":"eac258e8777c8b2e","login":"jsan4christ","name":"San Emmanuel James","avatar_url":"https://avatars-next.observableusercontent.com/27de0beb8da8eba37da2d750ff2820ef819226744bf3aa7a34f9e5a25fba20bb","tier":null,"role":"editor"}],"comments":[],"custom_thumbnail":false,"trashed":false,"lapsed":null,"subscribed":null,"forks":0,"collection":null,"type":"notebook","body":{"titling":"auto","title":"Evidence of natural selection history operating on HIV-1 genomes","cells":[{"id":0,"value":"md`# Evidence of natural selection history operating on HIV-1 genomes`","pinned":false,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined","tool":"$undefined","providerMetadata":"$undefined","attachments":"$undefined","output":"$undefined","database":"$undefined"},{"id":1137,"value":"Using clustered HIV-1 sequences (${N} datasets) that have been processed to handle recombination events, track the history of selected sites. The sequences are split by time-periods as well. The earliest intervals starts in _${date_range[0]}_ and the latest ends in _${date_range[1]}_. [Download .csv data](https://dl.dropbox.com/scl/fi/hz41igmls6bk4t0b26ehg/hiv-fel-summary.csv?rlkey=vksh42e1on0x0omypl9j2whpy)","pinned":false,"hidden":false,"mode":"md","author":"$undefined","summary":"$undefined","tool":"$undefined","providerMetadata":"$undefined","attachments":"$undefined","output":"$undefined","database":"$undefined"},{"id":1712,"value":"viewof pv = Inputs.text ({\n 'value' : 0.0001,\n 'submit' : true,\n 'label' : 'p-value cutoff'\n})","pinned":false,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined","tool":"$undefined","providerMetadata":"$undefined","attachments":"$undefined","output":"$undefined","database":"$undefined"},{"id":1823,"value":"**Figure 1.** At a glance selection profile by cluster/gene. Text values are the number of selected sites at the current p-value cutoff.","pinned":false,"hidden":false,"mode":"md","author":"$undefined","summary":"$undefined","tool":"$undefined","providerMetadata":"$undefined","attachments":"$undefined","output":"","database":"$undefined"},{"id":1755,"value":"viewof time_period = Inputs.select (\n _.sortBy (_.map (time_periods, (d,k)=>k)),\n {label: \"Time-period\"}\n)","pinned":false,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined","tool":"$undefined","providerMetadata":"$undefined","attachments":"$undefined","output":"$undefined","database":"$undefined"},{"id":1827,"value":"viewof site_type = Inputs.radio (\n [\"Positive\", \"Negative\"],\n {label: \"Selection type\", \"value\" : \"Positive\"}\n)","pinned":false,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined","tool":"$undefined","providerMetadata":"$undefined","attachments":"$undefined","output":"$undefined","database":"$undefined"},{"id":1862,"value":"viewof color_grade = Inputs.select (\n [\"Sequences\",\"Tree length\",\"Fraction of sites under selection\"],\n {label: \"Color field\"}\n)","pinned":false,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined","tool":"$undefined","providerMetadata":"$undefined","attachments":"$undefined","output":"$undefined","database":"$undefined"},{"id":1737,"value":"$49","pinned":false,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined","tool":"$undefined","providerMetadata":"$undefined","attachments":"$undefined","output":"$undefined","database":"$undefined"},{"id":2003,"value":"viewof gene_to_view_force = Inputs.select (unique_genes,{label: \"Gene\"})","pinned":false,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined","tool":"$undefined","providerMetadata":"$undefined","attachments":"$undefined","output":"$undefined","database":"$undefined"},{"id":2008,"value":"viewof site_type_force = Inputs.radio (\n [\"Positive\", \"Negative\"],\n {label: \"Selection type\", \"value\" : \"Positive\"}\n)","pinned":false,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined","tool":"$undefined","providerMetadata":"$undefined","attachments":"$undefined","output":"$undefined","database":"$undefined"},{"id":1968,"value":"$4a","pinned":false,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined","tool":"$undefined","providerMetadata":"$undefined","attachments":"$undefined","output":"$undefined","database":"$undefined"},{"id":1192,"value":"viewof cluster_to_view = Inputs.select (\n _.sortBy (_.keys (_.countBy (siteHistory, (d)=>d.cluster)), d=>+d),\n {label: \"Select a sequence cluster to view\"}\n)","pinned":false,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined","tool":"$undefined","providerMetadata":"$undefined","attachments":"$undefined","output":"$undefined","database":"$undefined"},{"id":1678,"value":"viewof gene_to_view = Inputs.select (_.sortBy (_.keys (_.countBy (_.filter (siteHistory, (d)=>d.cluster == cluster_to_view), (d)=>d.gene))),{label: \"Select a gene to view\"})","pinned":false,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined","tool":"$undefined","providerMetadata":"$undefined","attachments":"$undefined","output":"$undefined","database":"$undefined"},{"id":1152,"value":"**Figure 3.** Evolutionary trajectories **${gene_to_view}** genes from cluster **${cluster_to_view}**. If a site was found to be positively (negatively) selected during a specific time period, a bubble will be drawn at a corresponding point on the plot. The area of the bubble is scaled as -log₁₀ (p), where p is the p-value of the FEL likelihood ratio test. Larger bubbles correspond to smaller p-values; p-values are not directly comparable between different time windows and different genes due to differences in sample sizes and other factors. The x-axis shows the **endpoint** of the time-window; e.g., 2021 the previous time point (or 1995) until the current time point.","pinned":false,"hidden":false,"mode":"md","author":"$undefined","summary":"$undefined","tool":"$undefined","providerMetadata":"$undefined","attachments":"$undefined","output":"$undefined","database":"$undefined"},{"id":2020,"value":"viewof site_type_detail = Inputs.radio (\n [\"Positive\", \"Negative\", \"Both\"],\n {label: \"Selection type\", \"value\" : \"Positive\"}\n)","pinned":false,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined","tool":"$undefined","providerMetadata":"$undefined","attachments":"$undefined","output":"$undefined","database":"$undefined"},{"id":588,"value":"$4b","pinned":false,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined","tool":"$undefined","providerMetadata":"$undefined","attachments":"$undefined","output":"$undefined","database":"$undefined"},{"id":1378,"value":"md`**Table 1.** Explore the underlying data`","pinned":false,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined","tool":"$undefined","providerMetadata":"$undefined","attachments":"$undefined","output":"$undefined","database":"$undefined"},{"id":1368,"value":"viewof wrangled = Wrangler(siteHistory)","pinned":false,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined","tool":"$undefined","providerMetadata":"$undefined","attachments":"$undefined","output":"$undefined","database":"$undefined"},{"id":5,"value":"md`### Libraries and data`","pinned":false,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined","tool":"$undefined","providerMetadata":"$undefined","attachments":"$undefined","output":"$undefined","database":"$undefined"},{"id":9,"value":"d3 = require(\"d3@6\")","pinned":false,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined","tool":"$undefined","providerMetadata":"$undefined","attachments":"$undefined","output":"$undefined","database":"$undefined"},{"id":1194,"value":"import {select} from \"@jashkenas/inputs\"","pinned":false,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined","tool":"$undefined","providerMetadata":"$undefined","attachments":"$undefined","output":"$undefined","database":"$undefined"},{"id":12,"value":"vegalite = require (\"vega-embed\")","pinned":false,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined","tool":"$undefined","providerMetadata":"$undefined","attachments":"$undefined","output":"$undefined","database":"$undefined"},{"id":15,"value":"_ = require (\"lodash\")","pinned":false,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined","tool":"$undefined","providerMetadata":"$undefined","attachments":"$undefined","output":"$undefined","database":"$undefined"},{"id":22,"value":"import {gene_coordinates} from \"@spond/revised-sars-cov-2-analytics-page\"","pinned":false,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined","tool":"$undefined","providerMetadata":"$undefined","attachments":"$undefined","output":"$undefined","database":"$undefined"},{"id":1365,"value":"import {Wrangler, op} from \"@observablehq/data-wrangler\"","pinned":false,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined","tool":"$undefined","providerMetadata":"$undefined","attachments":"$undefined","output":"$undefined","database":"$undefined"},{"id":49,"value":"import {jsonCodonLookup} from \"@spond/sars_cov_2_sites\"","pinned":false,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined","tool":"$undefined","providerMetadata":"$undefined","attachments":"$undefined","output":"$undefined","database":"$undefined"},{"id":58,"value":"import {multiAutoSelect} from \"@spond/untitled/3\"","pinned":false,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined","tool":"$undefined","providerMetadata":"$undefined","attachments":"$undefined","output":"$undefined","database":"$undefined"},{"id":1433,"value":"unique_times = _.sortBy (_.keys(_.countBy (siteHistory, (d)=>d.to.getTime())))","pinned":false,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined","tool":"$undefined","providerMetadata":"$undefined","attachments":"$undefined","output":"$undefined","database":"$undefined"},{"id":1896,"value":"N = _.uniqBy (siteHistory, (d)=>\"\" + d.cluster + \"|\" + d.gene + \"|\" + d.from).length","pinned":false,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined","tool":"$undefined","providerMetadata":"$undefined","attachments":"$undefined","output":"$undefined","database":"$undefined"},{"id":1439,"value":"all_times = _.toPairs (_.groupBy (_.filter (siteHistory, (d)=>d.alpha < d.beta && d.p < 0.01), (d)=>d.loc))","pinned":false,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined","tool":"$undefined","providerMetadata":"$undefined","attachments":"$undefined","output":"$undefined","database":"$undefined"},{"id":1550,"value":"all_timesN = _.toPairs (_.groupBy (_.filter (siteHistory, (d)=>d.alpha > d.beta && d.p < 0.01), (d)=>d.loc))","pinned":false,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined","tool":"$undefined","providerMetadata":"$undefined","attachments":"$undefined","output":"$undefined","database":"$undefined"},{"id":1987,"value":"unique_clusters = _.sortBy (_.map (_.uniqBy (siteHistory, (d)=>d.cluster), (d)=>d.cluster), (d)=>+d)","pinned":false,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined","tool":"$undefined","providerMetadata":"$undefined","attachments":"$undefined","output":"$undefined","database":"$undefined"},{"id":2000,"value":"unique_genes = _.sortBy (_.map (_.uniqBy (siteHistory, (d)=>d.gene), (d)=>d.gene), (d)=>d)","pinned":false,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined","tool":"$undefined","providerMetadata":"$undefined","attachments":"$undefined","output":"$undefined","database":"$undefined"},{"id":1327,"value":"dr = [d3.min (siteHistory, (d)=>d.from), d3.max (siteHistory, (d)=>d.to)]","pinned":false,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined","tool":"$undefined","providerMetadata":"$undefined","attachments":"$undefined","output":"$undefined","database":"$undefined"},{"id":1762,"value":"time_periods = _.fromPairs (_.map (_.uniqBy (siteHistory, (d)=> d.from.getFullYear()), d=> [\"\" + d.from.getFullYear () + \"-\" + d.to.getFullYear(), d.from]))","pinned":false,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined","tool":"$undefined","providerMetadata":"$undefined","attachments":"$undefined","output":"$undefined","database":"$undefined"},{"id":1402,"value":"pad_array = (arr)=>_.map (arr, (d)=>\"Site \" + d.toUpperCase())","pinned":false,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined","tool":"$undefined","providerMetadata":"$undefined","attachments":"$undefined","output":"$undefined","database":"$undefined"},{"id":1233,"value":"date_range = _.map (dr, (d)=>d3.timeFormat (\"%B %Y\")(d))","pinned":false,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined","tool":"$undefined","providerMetadata":"$undefined","attachments":"$undefined","output":"$undefined","database":"$undefined"},{"id":1349,"value":"date_range_obj = _.map (dr, (d)=>({'year' : d.getFullYear(), 'month': 1+d.getMonth(), 'day' : d.getDate() + 1}))","pinned":false,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined","tool":"$undefined","providerMetadata":"$undefined","attachments":"$undefined","output":"$undefined","database":"$undefined"},{"id":46,"value":"siteHistory = {\n let raw_data = await d3.csv (\"https://dl.dropbox.com/scl/fi/hz41igmls6bk4t0b26ehg/hiv-fel-summary.csv?rlkey=vksh42e1on0x0omypl9j2whpy\", d3.autoType);\n //let raw_data = d3.csvParse (await FileAttachment(\"windowed-sites-fel-current@1.txt\").text(), d3.autoType);\n let time_parser = d3.timeParse (\"%Y/%m/%d\");\n _.each (raw_data, (s)=>{\n s.loc = s.gene.toUpperCase() + \"/\" + s.site;\n s.cluster = \"\" + s.cluster;\n s.from = time_parser (s.from);\n s.to = time_parser (s.to);\n /*if (s.loc in siteList[1]) {\n s.label = siteList[1][s.loc]; \n } (else { */\n s.label = s.loc;\n //}\n s.p = Math.max (s.p, 1e-16);\n \n });\n return raw_data;\n}","pinned":false,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined","tool":"$undefined","providerMetadata":"$undefined","attachments":"$undefined","output":"$undefined","database":"$undefined"},{"id":1382,"value":"forPlot = {\n let pp = parseFloat (pv);\n let selected = _.filter (siteHistory, (d)=>d.cluster == cluster_to_view && d.gene == gene_to_view && d.p <= pp);\n \n return selected;\n}","pinned":false,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined","tool":"$undefined","providerMetadata":"$undefined","attachments":"$undefined","output":"$undefined","database":"$undefined"},{"id":1341,"value":"params = new URLSearchParams(location.search)","pinned":false,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined","tool":"$undefined","providerMetadata":"$undefined","attachments":"$undefined","output":"$undefined","database":"$undefined"},{"id":1344,"value":"sitelist = params.get(\"sites\") ? params.get(\"sites\").toUpperCase() : null","pinned":false,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined","tool":"$undefined","providerMetadata":"$undefined","attachments":"$undefined","output":"$undefined","database":"$undefined"}],"files":"$W4c","stdlib":"1"}} 24:null