32:T6c5,renderTable = (data, humanize = defaultHumanize, nully = () => '-') => { let columns = Object.keys(data[0]).map(name => ({ name, type: typeof data[0][name], decimalNumber: data.reduce((memo, d) => { if (typeof d[name] === 'number') { let frac = (d[name] || '').toString().split('.')[1]; if (frac) return Math.max(memo, frac.length); } return memo; }, 0) })); return html` ${columns.map(c => ``).join('')} ${data.slice(0, 25).map(datum => ` ${columns.map(c => { let val = datum[c.name]; if (c.decimalNumber && typeof val === 'number') { return ``; } if (val == null || val == undefined) val = nully(val); return ``; }).join('')} `).join('')}

${humanize(c.name)}
${val.toFixed(c.decimalNumber)}	${val}

${data.length > 25 ? `

This table has been truncated from ${data.length} rows to 25. Download to view all

` : ''}` }33:[{"id":"5f2992eff857908b0c293183f48e6095a58dea3a489ce13544eec9def595dd6894204d6679147d83d8c55a272398623d782318a2798357b73b7aa4af17343d23","href":"https://static.observableusercontent.com/files/5f2992eff857908b0c293183f48e6095a58dea3a489ce13544eec9def595dd6894204d6679147d83d8c55a272398623d782318a2798357b73b7aa4af17343d23","name":"genomic_SA_SARS2_Spike_filtered.fas_protein.msa_table.csv","type":"text/csv","lastModified":1611349602502.859,"size":124218},{"id":"a878fcae2c38c4eeb5af8e85d3a41a09f542683e7a98d6654a5175a19a5290abc03bc252833a7198e1bba1e2161942359d80b3ce758de7d385aa1ae9c6f079d8","href":"https://static.observableusercontent.com/files/a878fcae2c38c4eeb5af8e85d3a41a09f542683e7a98d6654a5175a19a5290abc03bc252833a7198e1bba1e2161942359d80b3ce758de7d385aa1ae9c6f079d8","name":"SA_SARS2_Spike_filtered.fas_nuc.fas@1.table","type":"application/octet-stream","lastModified":1611349602566.44,"size":180770},{"id":"fa42cad57507b3b7777d3bcadac47ce15edebb4ece9b69c950f53de0fa8b778789e8e6ee707c40c8f71d551e3482a669d4ca96b32a5298b00305218406847b9a","href":"https://static.observableusercontent.com/files/fa42cad57507b3b7777d3bcadac47ce15edebb4ece9b69c950f53de0fa8b778789e8e6ee707c40c8f71d551e3482a669d4ca96b32a5298b00305218406847b9a","name":"SA_wg_variation_daybyday_coloredbycountry@2.csv","type":"text/csv","lastModified":1611349602573.973,"size":318866}] 30:{"title":"InDel Genome Variation in SARS-CoV-2, for South African sequences","cells":[{"id":0,"value":"md`# InDel Genome Variation in SARS-CoV-2, for South African sequences` ","pinned":false,"hidden":false,"mode":"ojs"},{"id":18,"value":"md`### Introduction \n\nIn addition to attempts to characterize point mutations and the effects of recombination in the evolution of the ongoing outbreak of SARS-CoV-2, this analysis focuses on another mechanism.\n\nInsertion or Deletion events (InDels) may be a key mechanistic advantage this novel virus uses as a strategy for adaptation. \n\nIn addition, we will explore what means for a sequene to have variance from the reference for SARS-CoV-2, which was sampled from the initial outbreak in Wuhan city Hubei province. \n\nOf note: all of the analysis below relies on consensus sequences submitted to GISAID.\n` \n//More to the story than point mutations and recombination.\n\n/*Implications for InDels this may have for bioinformatic analysis that relies on reference based indexes. \n\nBiological implications for UTR regions and coding regions, along with host-immune adaptive implicatios, drug targeting, detection, diagnosis.\n\nAnything that relies on precise matches with an assumption on divergence\n*/","pinned":false,"hidden":false,"mode":"ojs"},{"id":20,"value":"md`### Figures\n\nDemonstrates the distribution of Whole Genome lengths (in bp) we observe in sequences submitted for the SARS-CoV-2 entries in GISAID. This dataset compromises whole genomes which were pulled down from the GISAID repository on **${last_update}**. Additionally, sequences were filtered to include whole genomes (> 27,000 bp) and represent samples from Human hosts only in order to examine intrahost evolution. This dataset is comprised of **n=${data2.length}** whole genome sequences. Date represents the collection date of the sample.` ","pinned":false,"hidden":false,"mode":"ojs"},{"id":514,"value":"md`#### (Figure 1)\nBreakdown of Whole Genome length sequence distributions by Collection Date and colored by submitting Country\n` ","pinned":false,"hidden":false,"mode":"ojs"},{"id":533,"value":"vl.markPoint().data(flt_data2)\n .width(width - 200)\n .height(height-100)\n .encode(\n vl.x().fieldT('Date'),\n vl.y().fieldQ('WG_Length')\n .scale({domain: [29000, 31400]}).scale({domain: [29200, 30000]}),\n vl.color().fieldN('Locale'),\n vl.tooltip(['ID', 'Locale', 'Date', 'WG_Length']) // show the Name and Origin fields in a tooltip\n).render()","pinned":false,"hidden":false,"mode":"ojs"},{"id":548,"value":"md`#### (Figure 2)\nWhat does whole genome length variability mean in the context of an individual gene? \n\nFor this, we examine a single gene within SARS-CoV-2, the spike protein as an example\n\nThe figure below shows spike gene size (in bp) distributed across the submission date to GISAID.\n` \n//Additionally, whole genomes display wide variability but genes, such as spike, have relatively low sequence length variance. Question is what are the hot spots?","pinned":false,"hidden":false,"mode":"ojs"},{"id":614,"value":"viewof layeredTrend = vl.data(spikeData)\n .width(width - 200)\n .title(\"[SARS-CoV-2] SPIKE Protein\")\n .encode(\n vl.x().fieldT(\"Date\"),\n vl.y().fieldQ(\"Nucleotides\")\n .scale({domain: [3450, 4000]}),\n vl.tooltip(['ID', 'Date', 'Nucleotides'])\n )\n .layer(\n vl.markCircle(),\n vl.markErrorband({extent: \"iqr\" , interpolate: \"basis\"}),\n vl.markLine()\n .encode(\n vl.y().mean(\"Nucleotides\")\n )\n )\n .render()","pinned":false,"hidden":false,"mode":"ojs"},{"id":1285,"value":"vl.markTick()\n .data(spikeInDelsTable)\n .width(width - 100)\n .height(height - 550)\n .config({\"tick\": {\"thickness\": 1, \"bandSize\": 40}})\n .encode(\n vl.x().fieldQ('Site_Indel(AA)').title(\"Indel Location\"),\n vl.tooltip(['Sequence_ID','Genomic_Position(NT)', 'Site_Indel(AA)', 'Consensus(AA)'])\n )\n .render()","pinned":false,"hidden":false,"mode":"ojs"},{"id":550,"value":"md`#### (Table 1)\nInferred Indel Sites from protein alignments.\n` \n\n//Can point to alignment errors","pinned":false,"hidden":false,"mode":"ojs"},{"id":668,"value":"renderTable(spikeInDelsTable)","pinned":false,"hidden":false,"mode":"ojs"},{"id":6,"value":"md`### Data ` ","pinned":false,"hidden":false,"mode":"ojs"},{"id":523,"value":"data2 = d3.csvParse(await FileAttachment(\"SA_wg_variation_daybyday_coloredbycountry@2.csv\").text(), d3.autoType)","pinned":false,"hidden":false,"mode":"ojs"},{"id":526,"value":"//flt_data2 = data2.filter(d => d.Date > 2018)\n//flt_data2 = data2.filter(d => d.Date > new Date(2018, 0, 1))\nflt_data2 = data2.filter(d => d.Date > new Date(2018, 0, 1))\n//flt_data2 = data2.filter(d => d.Date)\n//flt_data2 = data2.filter(d => d.Date > new Date(2018, 0, 1))","pinned":false,"hidden":false,"mode":"ojs"},{"id":573,"value":"//Nucleotide length variability\nspikeData = d3.csvParse(await FileAttachment(\"SA_SARS2_Spike_filtered.fas_nuc.fas@1.table\").text(), d3.autoType)","pinned":false,"hidden":false,"mode":"ojs"},{"id":994,"value":"md`### Table Data ` ","pinned":false,"hidden":false,"mode":"ojs"},{"id":993,"value":"spikeInDelsTable = d3.csvParse(\n await FileAttachment(\"genomic_SA_SARS2_Spike_filtered.fas_protein.msa_table.csv\").text()\n)","pinned":false,"hidden":false,"mode":"ojs"},{"id":571,"value":"md`### Plotting ` ","pinned":false,"hidden":false,"mode":"ojs"},{"id":484,"value":"bins = d3.histogram()\n .domain(x.domain())\n .thresholds(x.ticks(40))\n (data2)","pinned":false,"hidden":false,"mode":"ojs"},{"id":485,"value":"x = d3.scaleLinear()\n .domain(d3.extent(spikeInDelsTable)).nice()\n .range([margin.left, width - margin.right])","pinned":false,"hidden":false,"mode":"ojs"},{"id":488,"value":"y = d3.scaleLinear()\n .domain([0, d3.max(bins, d => d.length)]).nice()\n .range([height - margin.bottom, margin.top])","pinned":false,"hidden":false,"mode":"ojs"},{"id":49,"value":"md`### Declares ` ","pinned":false,"hidden":false,"mode":"ojs"},{"id":710,"value":"last_update = \"01-22-2021\"","pinned":false,"hidden":false,"mode":"ojs"},{"id":88,"value":"margin = ({top: 25, right: 20, bottom: 35, left: 40})","pinned":false,"hidden":false,"mode":"ojs"},{"id":97,"value":"height = 600","pinned":false,"hidden":false,"mode":"ojs"},{"id":103,"value":"grid = g => g\n .attr(\"stroke\", \"currentColor\")\n .attr(\"stroke-opacity\", 0.1)\n .call(g => g.append(\"g\")\n .selectAll(\"line\")\n .data(x.ticks())\n .join(\"line\")\n .attr(\"x1\", d => 0.5 + x(d))\n .attr(\"x2\", d => 0.5 + x(d))\n .attr(\"y1\", margin.top)\n .attr(\"y2\", height - margin.bottom))\n .call(g => g.append(\"g\")\n .selectAll(\"line\")\n .data(y.ticks())\n .join(\"line\")\n .attr(\"y1\", d => 0.5 + y(d))\n .attr(\"y2\", d => 0.5 + y(d))\n .attr(\"x1\", margin.left)\n .attr(\"x2\", width - margin.right));","pinned":false,"hidden":false,"mode":"ojs"},{"id":491,"value":"xAxis = g => g\n .attr(\"transform\", `translate(0,${height - margin.bottom})`)\n .call(d3.axisBottom(x).ticks(width / 80 ).tickSizeOuter(0))\n .call(g => g.append(\"text\")\n .attr(\"x\", width - margin.right)\n .attr(\"y\", -4)\n .attr(\"fill\", \"currentColor\")\n .attr(\"font-weight\", \"bold\")\n .attr(\"text-anchor\", \"end\")\n .text(data2.x))","pinned":false,"hidden":false,"mode":"ojs"},{"id":494,"value":"yAxis = g => g\n .attr(\"transform\", `translate(${margin.left},0)`)\n .call(d3.axisLeft(y).ticks(height / 40))\n .call(g => g.select(\".domain\").remove())\n .call(g => g.select(\".tick:last-of-type text\").clone()\n .attr(\"x\", 4)\n .attr(\"text-anchor\", \"start\")\n .attr(\"font-weight\", \"bold\")\n .text(data2\n .y))","pinned":false,"hidden":false,"mode":"ojs"},{"id":8,"value":"md`### Dependencies ` ","pinned":false,"hidden":false,"mode":"ojs"},{"id":671,"value":"import {table} from \"@tmcw/tables@513\"","pinned":false,"hidden":false,"mode":"ojs"},{"id":529,"value":"import {vl} from '@vega/vega-lite-api'","pinned":false,"hidden":false,"mode":"ojs"},{"id":530,"value":"import {printTable} from '@uwdata/data-utilities'","pinned":false,"hidden":false,"mode":"ojs"},{"id":42,"value":"d3 = require(\"d3@5\")","pinned":false,"hidden":false,"mode":"ojs"},{"id":652,"value":"embed = require(\"vega-embed@3\")","pinned":false,"hidden":false,"mode":"ojs"},{"id":985,"value":"defaultHumanize = str => str.replace(/[-_]/g, ' ')","pinned":false,"hidden":false,"mode":"ojs"},{"id":984,"value":"$32","pinned":false,"hidden":false,"mode":"ojs"},{"id":1124,"value":"vegalite = require(\"@observablehq/vega-lite@0.2\")","pinned":false,"hidden":false,"mode":"ojs"}],"files":"$W33","stdlib":"1","titling":"auto"}