30:T624,table1 = table (table_data, { limit: 5000, enableCSVDownload: true, sort: true, enableFilter: false, columns: [ { key: 'ID', name: 'ID' }, { key: 'Sequences', }, { key: 'Sites', }, { key: 'T', name: 'Tree length', render : (val)=>float_format(val) }, { key : 'RELAX p-value', render : (val)=>val <= 0.05 ? "" + d3.format (".4f") (val) + "" : d3.format (".4f") (val) }, { key : 'RELAX q-value', render : (val)=>val <= 0.10 ? "" + d3.format (".4f") (val) + "" : d3.format (".4f") (val) }, { key : 'Groups', render : (val)=> _.map (val, (v)=> (v[1] ? "" + v[0] + "" : v[0]) + "(" + v[2] + ")" ).join (", ") }, { key : 'RELAX c-AIC improvement', name : 'Δ c-AIC', render : (val)=>val >= 10.0 ? "" + d3.format (".4f") (val) + "" : d3.format (".4f") (val) }, { key : 'K range', name : 'Relax./intens. range', render : (val)=>_.map (val, (d)=>float_format(d)).join (" - ") }, { key : 'BUSTED', render : (val)=> _.map (val, (v)=> (v[1] <= 0.05 ? "" + v[0] + "" : v[0]) + "(" + float_format(v[1]) + ")" ).join (", ") } ] });31:T530,md` 1. ** ID ** : gene / alignment ID 2. ** Sequences ** : number of sequences in the aligment 3. ** Sites ** : number of sites in the alignment 4. ** Tree length ** : in subs/site 5. ** RELAX p-value ** : p-value of the RELAX test; if significant (bolded), implies that there are detectable differences in selection **intensity** between ciliate groups. 6. ** RELAX q-value ** : q-value of the RELAX test; if significant (bolded), implies that there are detectable differences in selection **intensity** between ciliate groups. 6. ** Groups ** : the ciliate groups used for testing (bold == reference group) 7. ** Δ c-AIC ** :comparison between the goodness of fit for the standard RELAX model and the more flexible model where ω distributions are completely separate between groups; if significant (bolded), implies that there are detectable differences in selection **distributions** between ciliate groups. This relationship can be complex (e.g. relaxed positve selection and increased negative selection, or different proportions of sites under selection) 8. ** Relaxation/intensification range ** : for the standard RELAX model, reports the range of inferred relaxation (K<1) or intensification (K>1) parameters for groups. 9. ** BUSTED ** : Positive selection tests for individual groups. `32:T733,fig2alt=vegalite ({ "vconcat" : _.map (["EF","NF"], (ref)=> { return { "data": { "values": _.filter (K_MLE, (d)=>d.mle <= 5 && d.Reference == ref && d.clade != ref && d.qv <= 0.10) }, "title" : "Reference " + ref, "vconcat" : [{ "width": 800, "height": {"step": 8}, "layer" : [ { "data" : {"values" : [{"K" : 1},{"K" : 1}]}, "mark" : "rule", "encoding" : {"x" : {"field" : "K", "type": "quantitative"}}, }, { "mark": {type: "point", "opacity" : 1.0, tooltip : true, line : true, filled: true, "size" : 64}, "encoding": { "color" : { "value" : "black" }, "x": { "field": "mle", "title": "K", "axis": { "grid" : false }, "type": "quantitative", }, "y": { "field" : "gene", "sort": "qv", "type": "nominal", "scale": {type : "linear"}, "title" : null }, "color" : { "field" : "clade" } // order bars based on newly created OriginOrder field }}, {"mark": {type: "rule", "opacity" : 1.0}, "encoding": { "color" : { "value" : "black" }, "x": { "field": "mle", "title": "K", "axis": { "grid" : false }, "type": "quantitative", }, "y": { "field" : "gene", "sort": "p", "type": "nominal", "scale": {type : "linear"}, "title" : null }, // order bars based on newly created OriginOrder field }} ] }]} }) })33:T51b,vegalite ({ "data": {"values": _.filter (detection_rates, (d)=>d.Seqs <= 50)}, "width": 500, "height": 250, "encoding": { "x": { "field": "Seqs", "type": "ordinal", "axis" : {"title" : "Max # branches in group", "titleFontSize" : 14}, }, "y": { "field": "Rate", "type": "quantitative", "scale" : {"type" : "sqrt"}, "axis" : {"grid" : false, "title" : "Fraction of ORF under selection", "titleFontSize" : 14} } }, "layer" : [ { "mark": {"type" : "line", "size" : 3, "opacity" : 0.8}, "encoding" : { "color": { "field": "Group", "type": "nominal", "scale" : {"domain" : ["EF","KA","NF","HE"]}, "legend" : {"orient" : "top"} } } }, { "mark": {"type" : "point", "filled" : true}, "encoding" : { "color": { "field": "Group", "type": "nominal", }, "size": { "field": "Count", "type": "quantitative", "legend" : {"orient" : "right"} } } } ], "config": { "view": { "stroke": "transparent" } } }) 34:T850,displayed_tree = { let tree = tree_object[0]; let dim = treeDim.length ? _.map (treeDim.split ("x"), (d)=>+d) : null; var t = tree.render({ 'height':dim && dim[0], 'width':dim && dim[1], 'show-scale' : true, 'left-right-spacing': 'fit-to-size', 'top-bottom-spacing': 'fit-to-size', //'internal-names' : true, 'is-radial' : false, 'node_circle_size' : (n)=>0 }); let nodeStates = null; /*t.phylotree.branch_length_accessor = n=> { //console.log (summary_json[segment_id]); let bl = tree_object[1][n.data.name][2]; if (bl > 0.25) { n.data.censored_bl = true; return 0.25; } else { n.data.censored_bl = false; } return bl; }*/ t.nodeLabel ((n)=>{ return n.data.name.split ("_").slice (0,3).join (" "); //return n.data.name; }); function sort_nodes (asc) { tree.traverse_and_compute (function (n) { var d = 1; if (n.children && n.children.length) { d += d3.max (n.children, function (d) { return d["count_depth"];}); } n["count_depth"] = d; }); tree.resortChildren (function (a,b) { return (a["count_depth"] - b["count_depth"]) * (asc ? 1 : -1); }); } sort_nodes (true); t.style_nodes ((e,n) => { e.selectAll ("title").data ([n.data.name]).join ("title").text ((d)=>d); if (n.data.name in tree_object[1]) { let binfo = tree_object[1][n.data.name]; e.selectAll ("circle").style ('fill', species_colors (binfo)); e.selectAll ("text").style ('fill', species_colors (binfo)); } //} }); t.style_edges ((e,d) => { if (d.target.data.name in tree_object[1]) { let binfo = tree_object[1][d.target.data.name]; console.log (e); e.style ('stroke', species_colors (binfo)); e.style ('stroke-width', 2); } }); t.placenodes(); t.update(); return t; }35:T7aa,plotPie = (values, id, skipK)=>{ let K = _.get (result_json,[id,"tests","relaxation or intensification parameter"]); if (_.isNumber (K)) { K = {'Test' : K, 'Reference' : 1.}; } return vegalite ({ "columns": 3, "hconcat": _.map (_.groupBy (values, (d)=>d.type), (d, type) => { let is_dnds = "omega" in d[0]; let title = (is_dnds ? "dN/dS for " : "") + type + (type == baseline_by_segment[id] ? " (reference)" : "") + (is_dnds && !skipK ? ", K = " + float_format(K[type]) : ""); let rate = is_dnds ? "omega" : "rate"; return { "title" : title, "data" : {"values" : d}, "encoding": { "theta": {"field": "proportion", "type": "quantitative", "stack": true}, "color": {"field": rate, "type": "quantitative", "title" : "Rate", "scale": { "domain" : [0,1,4], "type" : "sqrt", "clamp" : true, "scheme": "lightmulti" } }}, "layer" : [ { "mark": {"type": "arc", "innerRadius": 40, "outerRadius" : 60, tooltip : true, padAngle : 0.0, strokeWidth : 1, strokeOpacity: 1}, "encoding" : { "stroke" : {value : "black"}, } }, { "mark": {"type": "text", "outerRadius" : 70, "fontSize" : 18}, "encoding": { "color" : {"value" : "black"}, "text": { "field": rate, "type": "nominal", "format" : ".2f", "condition": {"test": "datum['" + rate +"'] <= 1.", "value": ""}, } } }, { "mark": {"type": "text", "outerRadius" : 20, "fontSize" : 18}, "encoding": { "color" : {"value" : "black"}, "text": { "field": "proportion", "type": "nominal", "format" : ".2p", "condition": {"test": "datum['" + rate +"'] <= 1.", "value": ""} } } } ]} }), "view": {"stroke": null} }) }36:T790,table_data = { let table = _.map (_.toPairs (result_json), (d)=> { let res = { "ID" : d[0] }; let daic = (info)=> { return - _.get (info, ["fits", "RELAX partitioned descriptive", "AIC-c"]) + _.get (info, ["fits", "RELAX alternative", "AIC-c"]); }; let get_groups = (info, tag)=> { let kr = _.get (info, ["tests", "relaxation or intensification parameter"]); if (_.isNumber (kr)) { return [["NF", true], ["HE", false]]; } let tested_counts = _.countBy (_.toPairs (_.get (info, ["tested","0"])), (d)=>d[1]); return _.map (_.toPairs (kr), (d)=>[d[0], d[1] == 1, tested_counts[d[0]]]); }; let krange = (info)=> { let kr = _.get (info, ["tests", "relaxation or intensification parameter"]); if (_.isNumber (kr)) { return d3.extent ([1,kr]); } return d3.extent (_.map (kr, (d)=>d)); }; let get_busted = (info, tag)=> { return _.map (_.get (info, ["BUSTED"]), (d,k)=> { return [k, d["p"]]; }); } let treeLength = (info, tag)=> { const nwk = _.get (info, "tree"); if (nwk) { const pt = new phylotree.phylotree(nwk); const L = 0; return d3.sum (pt.getBranchLengths()); } return 0; } let inject = [ ["Sequences", ["sequences"]], ["Sites", ["sites"]], ["T", treeLength], ["RELAX p-value", ["tests","p-value"]], ["Groups", get_groups], ["RELAX c-AIC improvement", daic], ["K range", krange], ["BUSTED", get_busted], ]; _.each (inject, (i)=> { res[i[0]] = _.isFunction (i[1]) ? i[1](d[1], d[0]) :_.get (d[1], i[1]); }); return res; }); let N = table.length; _.each ( _.sortBy (table, (d)=>d["RELAX p-value"]), (d,i)=> { d["RELAX q-value"] = d["RELAX p-value"] * N / (i+1); }); return table; }37:T5dd,BUSTED_corrected = { let busted = []; _.each (result_json, (data, gene)=> { if (data.tested) { let group_counts = _.countBy (data.tested[0]); _.each (data.BUSTED, (info, group)=> { busted.push ({ 'gene' : gene, 'group' : group, 'count' : group_counts[group], 'p' : info.p, 'omega' : info.distribution.Test[2].omega, 'proportion' : info.distribution.Test[2].proportion }); }); } }); busted = _.map (_.sortBy (busted, (d)=>d.p), (d,i)=> { d.q = d.p * busted.length / (i+1); return d; }); //busted = _.filter (busted, (d)=>d.count >= 10 && d.count <= 20); return [_.map (_.groupBy (busted, (d)=>d.group), (d, k)=> { let sigs = _.filter (d, (c)=>c.q <= 0.1).length; let branches = d3.mean (d, (c)=>c.count); return {'Group' : k, 'Genes' : d.length, 'Positive' : sigs, 'Fraction' : sigs /d.length, "Branches" : branches}; }), _.map (_.countBy (_.filter (_.map (_.groupBy (busted, (d)=>d.gene), (busted, k)=> { let result = {'EF' : null, 'NF' : null, 'HE' : null, 'KA' : null}; _.each (busted, (b)=> { result[b.group] = b.q <= 0.1 ? '+' : '-'; }); return result; }), (d)=>_.find (d, (c)=>c == '+')), (d)=>_.map (d)), (d,k)=>{ k = k.split (','); return {'EF' : k[0], 'NF' : k[1], 'HE' : k[2], 'KA' : k[3], 'Count' : d}; //return k; }), busted]; }38:[] 2e:{"title":"Visualizing comparative selection analysis results for ciliate gene-family analyses","cells":[{"id":0,"value":"md`# Visualizing comparative selection analysis results for ciliate gene-family analyses`","pinned":false,"hidden":false,"mode":"ojs"},{"id":2156,"value":"md`### Summary of RELAX analyses\nRELAX[S] results are available for **${_.size (_.filter (result_json, (d)=>\"fits\" in d))}** alignments. Of those, **${_.filter (table_data, (d)=>d[\"RELAX q-value\"] <= 0.1).length}** yielded a sigfinicant result (FDR≤0.10) for differences in selective intensity between ciliate groups. Of those, **${_.filter (table_data, (d)=>d[\"RELAX q-value\"] <= 0.1 && d['RELAX c-AIC improvement'] >= 10).length}** prefer the general descriptive model.\n`","pinned":false,"hidden":false,"mode":"ojs"},{"id":2809,"value":"table1_title = md`**Table 1** Selection inference results for individual alignments`","pinned":false,"hidden":false,"mode":"ojs"},{"id":2817,"value":"$30","pinned":false,"hidden":false,"mode":"ojs"},{"id":2838,"value":"$31","pinned":false,"hidden":false,"mode":"ojs"},{"id":2912,"value":"fig1_label = md`**Figure 1**. Disributions of mean ω by group`","pinned":false,"hidden":false,"mode":"ojs"},{"id":2920,"value":"fig1=vegalite ({\n \"data\": {\n \"values\": _.filter (mean_dnds_plot, (r)=>r.omega > 0)\n },\n \"width\": 800,\n \n \"mark\": {type: \"boxplot\", \"opacity\" : 0.5, tooltip : true, line : true},\n \"encoding\": {\n \"x\": {\n \"field\": \"omega\",\n \"grid\" : null,\n \"title\": \"Mean dN/dS\",\n \"type\": \"quantitative\",\n \"axis\": {\"grid\": false},\n \"scale\" : {\"type\" : \"sqrt\"}\n },\n \"y\": {\n \"field\": \"clade\",\n \"type\": \"ordinal\",\n \"title\" : \"\",\n \"axis\": {\"grid\": false}\n },\n \"color\" : {\"value\" : \"black\"},\n //\"row\" : {\"field\" : \"clade\", \"title\" : \"Variant type\", \"sort\": \"ascending\"}\n }\n})\n\n","pinned":false,"hidden":false,"mode":"ojs"},{"id":3372,"value":"fig1a_label = md`**Figure 1a**. Disributions of branch counts by taxonomic group`","pinned":false,"hidden":false,"mode":"ojs"},{"id":3378,"value":"fig1a=vegalite ({\n \"data\": {\n \"values\": _.flatten (_.map (table_data, (d)=>{\n /*return _.map (['EF', 'HE', 'NF', 'KA'], (clade)=> {\n let cldinfo = _.find (d.Groups, (dd)=>dd[0] == clade);\n if (cldinfo) return {'Type' : clade, 'Branches' : cldinfo[2]};\n return {'Type' : clade, 'Branches' : 0};\n })*/\n return _.map (d.Groups, (dd)=>({'Type' : dd[0], 'Branches' : dd[2]}));\n }))\n },\n \n //\"facet\": {\"row\": {\"field\": \"Type\"}},\n //\"spec\" : {\n \"width\": 400,\n \"height\" : 100,\n \"mark\": {type: \"boxplot\", \"opacity\" : 0.5, tooltip : true, line : true},\n \"encoding\": {\n \"x\": {\n \"field\": \"Branches\",\n \"grid\" : null,\n //\"bin\": {\"maxbins\": 100},\n \"title\": \"Branch count\",\n \"type\": \"quantitative\",\n \"axis\": {\"grid\": false},\n \"scale\" : {\"type\" : \"sqrt\"}\n },\n \"y\": {\"field\": \"Type\", \"type\": \"nominal\", \"title\" : null},\n \"color\" : {\"value\" : \"black\"},\n //\"row\" : {\"field\" : \"Clade\", \"title\" : \"Variant type\", \"sort\": \"ascending\"}\n // }\n}})\n","pinned":false,"hidden":false,"mode":"ojs"},{"id":3118,"value":"fig2_label = md`**Figure 2**. Disributions of relaxation/intensification (K) by group, conditioned on a significant RELAX test and not a significantly better partitioned descriptive fit`","pinned":false,"hidden":false,"mode":"ojs"},{"id":3821,"value":"Inputs.table (pairwise, {'columns' : ['source', 'EF', 'KA', 'NF', 'HE']})","pinned":true,"hidden":false,"mode":"ojs"},{"id":3135,"value":"fig2=vegalite ({\n \"vconcat\" : _.map ([\"EF\",\"NF\"], (ref)=> {\n return {\n \"data\": {\n \"values\": _.filter (K_MLE, (d)=>d.mle <= 5 && d.Reference == ref && d.clade != ref && d.qv <= 0.1 && d.daic <= 10)\n },\n \"title\" : \"Reference \" + ref,\n \"vconcat\" : [{\n \"width\": 400,\n \"mark\": {type: \"boxplot\", \"opacity\" : 0.8, tooltip : true, line : true},\n \"encoding\": {\n \"color\" : {\n \"value\" : \"steelblue\"\n },\n \"x\": {\n \"field\": \"mle\",\n \"title\": \"K\",\n \"axis\": {\n \"grid\" : false\n },\n \"type\": \"quantitative\",\n },\n \"y\": {\n \"field\" : \"clade\",\n \"type\": \"nominal\",\n \"scale\": {type : \"linear\"},\n \"title\" : null\n },\n // order bars based on newly created OriginOrder field\n }\n }]}\n })\n})","pinned":false,"hidden":false,"mode":"ojs"},{"id":3528,"value":"$32","pinned":false,"hidden":false,"mode":"ojs"},{"id":2943,"value":"table2_label = md`**Table 2**. Disributions of mean ω by group`","pinned":false,"hidden":false,"mode":"ojs"},{"id":2946,"value":"table2 = table (mean_dnds_groups,{\n limit: 5000,\n enableCSVDownload: true,\n sort: true,\n enableFilter: false,\n columns: [\n {\n key : 'group',\n name: \"Group\"\n }, \n {\n key : 'mean',\n name: \"Mean\",\n render: (val)=>float_format (val)\n }, \n {\n key : 'median',\n name: \"Median\",\n render: (val)=>float_format (val)\n }, \n {\n key : 'Q1',\n name: \"5%\",\n render: (val)=>float_format (val)\n },\n {\n key : 'Q3',\n name: \"95%\",\n render: (val)=>float_format (val)\n }\n ]\n})\n ","pinned":false,"hidden":false,"mode":"ojs"},{"id":3460,"value":"table2a_label = md`**Table 2a**. BUSTED results by group`","pinned":false,"hidden":false,"mode":"ojs"},{"id":3463,"value":"table2a = table (BUSTED_corrected[0],{\n limit: 5000,\n enableCSVDownload: true,\n sort: true,\n enableFilter: false,\n columns: [\n {\n key : 'Group',\n }, \n {\n key : 'Genes',\n }, \n {\n key : 'Branches',\n name: \"Mean # branches\",\n render: (val)=>float_format (val)\n },\n {\n key : 'Positive',\n name: \"Positively Selected\",\n }, \n {\n key : 'Fraction',\n name: \"Detection\",\n render: (val)=>float_format (val)\n }\n ]\n})","pinned":false,"hidden":false,"mode":"ojs"},{"id":3618,"value":"table2b_label = md`**Table 2b**. BUSTED results by pattern`","pinned":false,"hidden":false,"mode":"ojs"},{"id":3621,"value":"table2b = table (BUSTED_corrected[1],{\n limit: 5000,\n rows : 50,\n enableCSVDownload: true,\n sort: true,\n enableFilter: false,\n})","pinned":false,"hidden":false,"mode":"ojs"},{"id":3647,"value":"figure2a_label = md`**Figure 2a**. BUSTED mean ω > 1`","pinned":false,"hidden":false,"mode":"ojs"},{"id":3628,"value":"fig2a=vegalite ({\n \"vconcat\" : _.map ([\"EF\",\"NF\",\"HE\",\"KA\"], (ref)=> {\n return {\n \"data\": {\n \"values\": _.map (_.filter (BUSTED_corrected[2], (d)=>d.group == ref), (d)=>{let dd = _.clone (d); dd.omega = Math.min (1000000,d.omega);return dd;})\n },\n \"title\" : \"\"+ ref,\n \"vconcat\" : [{\n \"width\": 800,\n \"mark\": {type: \"boxplot\", \"opacity\" : 0.5, tooltip : true, line : true},\n \"encoding\": {\n \"color\" : {\n \"value\" : \"black\"\n },\n \"x\": {\n \"field\": \"omega\",\n \"title\": \"ω > 1\",\n \"axis\": {\n \"grid\" : false\n },\n \"type\": \"quantitative\",\n \"scale\" : {\"type\" : \"log\"}\n },\n // order bars based on newly created OriginOrder field\n }\n }]}\n })\n})","pinned":false,"hidden":false,"mode":"ojs"},{"id":3654,"value":"figure2b_label = md`**Figure 2b**. BUSTED mean proportion of ω > 1`","pinned":false,"hidden":false,"mode":"ojs"},{"id":3657,"value":"fig2b=vegalite ({\n \"vconcat\" : _.map ([\"EF\",\"NF\",\"HE\",\"KA\"], (ref)=> {\n return {\n \"data\": {\n \"values\":_.filter (BUSTED_corrected[2], (d)=>d.group == ref)\n },\n \"title\" : \"\"+ ref,\n \"vconcat\" : [{\n \"width\": 800,\n \"mark\": {type: \"boxplot\", \"opacity\" : 0.5, tooltip : true, line : true},\n \"encoding\": {\n \"color\" : {\n \"value\" : \"black\"\n },\n \"x\": {\n \"field\": \"proportion\",\n \"title\": \"P(ω > 1)\",\n \"axis\": {\n \"grid\" : false\n },\n \"type\": \"quantitative\",\n \"scale\" : {\"type\" : \"sqrt\"}\n },\n // order bars based on newly created OriginOrder field\n }\n }]}\n })\n})","pinned":false,"hidden":false,"mode":"ojs"},{"id":3830,"value":"pairwise = {\n let Ks = _.mapValues (_.groupBy (_.filter (K_MLE, (d)=>d.qv < 0.1), (d)=>d.gene), (d)=>_.sortBy (_.map (d, (c)=>[c.clade, c.mle]), d=>d[1]));\n let orderings = {};\n _.each (Ks, (order)=> {\n for (let from = 0; from < order.length; from ++) {\n let F = order[from][0];\n for (let to = from + 1; to < order.length; to++) {\n let T = order[to][0];\n if (! (T in orderings)) orderings [T] = {};\n if (! (F in orderings[T])) orderings [T][F] = 0;\n orderings [T][F] ++;\n }\n }\n });\n return _.map (orderings, (d,k)=> {\n d['source'] = k;\n return d;\n });\n}","pinned":false,"hidden":false,"mode":"ojs"},{"id":3881,"value":"$33","pinned":false,"hidden":false,"mode":"ojs"},{"id":3854,"value":"detection_rates = _.chain (_.groupBy (BUSTED_corrected[2], (d)=>Math.floor (d.count / 5))).toPairs().filter ((d)=>d[1].length > 20).map (d=>[d[0], _.groupBy (d[1], (c)=>c.group)]).map ((d)=>[d[0],_.mapValues (d[1], (c)=>[_.filter (c, (r)=>r.q <= 0.01).length,c.length])]).map ((d)=>{\n return _.map (_.filter (_.toPairs (d[1]), (c)=>c[1][1]>=10), (v)=> {\n return {'Seqs' : ((+d[0]+1)*5),'Group' : v[0], 'Rate' : v[1][0]/v[1][1], 'Count' : v[1][1]};\n });\n}).flatten().value()","pinned":false,"hidden":false,"mode":"ojs"},{"id":2992,"value":"md`### Summary of BUSTED[S] analyses\nBUSTED[S] results are available for **${_.size (_.filter (result_json, (d)=>\"BUSTED\" in d))}** alignments. Of those, **${busted_significant.length}** yeilded a sigfinicant result (p≤0.05) for epidosic selection in at least one group.\n`","pinned":false,"hidden":false,"mode":"ojs"},{"id":2233,"value":"md`### Gene-by-gene information`","pinned":false,"hidden":false,"mode":"ojs"},{"id":966,"value":"viewof gene_id = {\n const dd3 = autoSelect ({\n title: \"Gene ID\",\n options: _.keys (result_json)\n \n });\n dd3.input.style.fontSize = \"12px\";\n dd3.input.style.marginTop = \"8px\";\n return dd3;\n}","pinned":false,"hidden":false,"mode":"ojs"},{"id":2643,"value":"md`#### Standard RELAX test`","pinned":false,"hidden":false,"mode":"ojs"},{"id":2636,"value":"md`\n**${gene_id}** has \n${_.get (result_json,[gene_id,\"sequences\"])} sequences and ${_.get (result_json,[gene_id,\"sites\"])} sites.\n\n_Test summary._\n\n1. The p-value for differences in selective pressures between groups is **${float_format(_.get (result_json,[gene_id,\"tests\",\"p-value\"]))}**.\n2. The difference between c-AIC scores between the RELAX alternative model and the RELAX partitioned descriptive model is **${float_format(_.get (result_json,[gene_id,\"fits\",\"RELAX alternative\",\"AIC-c\"])-_.get (result_json,[gene_id,\"fits\",\"RELAX partitioned descriptive\",\"AIC-c\"]))}**\n\n_BUSTED[S] test summary._\n\n${_.map (result_json[gene_id].BUSTED, (d,k)=> '**' + k + '**, p = ' + float_format (d['p']) + \"
\")}\n`","pinned":false,"hidden":false,"mode":"ojs"},{"id":2137,"value":"fig3_label = md`**Figure 3**. Rate distributions _by group_ inferred for this gene using the RELAX alternative model, and the synonymous substitution rate distribution`","pinned":false,"hidden":false,"mode":"ojs"},{"id":3180,"value":"{\n let rates = _.groupBy (_.flatten (_.map (_.get (result_json, [gene_id,\"fits\",\"RELAX alternative\",\"Rate Distributions\"]), (d,k)=> {\n return _.map (d, (r)=>{\n let rp = _.clone(r);\n rp.omega = Math.max (1e-10, rp.omega);\n rp.type = k;\n return rp;});\n \n})), (d)=>d.type);\n let clades = _.sortBy (_.toPairs (_.get (result_json, [gene_id,\"tests\",\"relaxation or intensification parameter\"])), (d)=>d[1]);\n\n let toPlot = [[],[]];\n _.each (clades, (d)=> {\n if (d[1] == 1) {\n toPlot [0].push (d[0] + \" ref\");\n } else {\n toPlot [0].push (d[0] + \" K=\" + d[1].toFixed (2));\n }\n toPlot[1].push (rates[d[0]]);\n });\n\n \n \n return renderNDiscreteDistributions (toPlot[1],{\"label\" : {\"chart\" : \"dN/dS\", \"series\" : toPlot[0]}, \"height\" : 30, \"width\" : 600, \"scale\" : \"log\", \"x\" : \"omega\", \"w\" : \"proportion\", \"margin\" : {top: 5, right: 100, bottom: 32, left: 20}})\n}","pinned":false,"hidden":false,"mode":"ojs"},{"id":3246,"value":"{\n let rates = _.groupBy (_.flatten (_.map (_.get (result_json, [gene_id,\"fits\",\"RELAX alternative\",\"Rate Distributions\"]), (d,k)=> {\n return _.map (d, (r)=>{\n let rp = _.clone(r);\n rp.rate = Math.max (1e-10, rp.rate);\n rp.type = k;\n return rp;});\n \n})), (d)=>d.type);\n \n return renderNDiscreteDistributions ([rates[\"Synonymous site-to-site rates\"]],{\"label\" : {\"chart\" : \"α\"}, \"height\" : 30, \"width\" : 510, \"scale\" : \"log\", \"x\" : \"rate\", \"w\" : \"proportion\", \"margin\" : {top: 5, right: 10, bottom: 32, left: 20}})\n}","pinned":false,"hidden":false,"mode":"ojs"},{"id":2662,"value":"fig4_label = md`**Figure 4**. Rate distributions _by group_ inferred for this gene using the RELAX partitioned descriptive model`","pinned":false,"hidden":false,"mode":"ojs"},{"id":3259,"value":"{\n let rates = _.groupBy (_.flatten (_.map (_.get (result_json, [gene_id,\"fits\",\"RELAX partitioned descriptive\",\"Rate Distributions\"]), (d,k)=> {\n return _.map (d, (r)=>{\n let rp = _.clone(r);\n rp.omega = Math.max (1e-10, rp.omega);\n rp.type = k;\n return rp;});\n \n})), (d)=>d.type);\n let clades = _.sortBy (_.toPairs (_.get (result_json, [gene_id,\"tests\",\"relaxation or intensification parameter\"])), (d)=>d[1]);\n\n let toPlot = [[],[]];\n _.each (clades, (d)=> {\n if (d[1] == 1) {\n toPlot [0].push (d[0] + \" ref\");\n } else {\n toPlot [0].push (d[0] + \" K=\" + d[1].toFixed (2));\n }\n toPlot[1].push (rates[d[0]]);\n });\n\n \n \n return renderNDiscreteDistributions (toPlot[1],{\"label\" : {\"chart\" : \"dN/dS\", \"series\" : toPlot[0]}, \"height\" : 30, \"width\" : 600, \"scale\" : \"log\", \"x\" : \"omega\", \"w\" : \"proportion\", \"margin\" : {top: 5, right: 100, bottom: 32, left: 20}})\n}","pinned":false,"hidden":false,"mode":"ojs"},{"id":3019,"value":"fig5_label = md`**Figure 5**. Rate distributions _by group_ inferred for this gene using the BUSTED[S] model, and the synonymous site-to-site substitution rate.`","pinned":false,"hidden":false,"mode":"ojs"},{"id":3028,"value":"plotPie (_.flatten(_.map (_.get (result_json, [gene_id,\"BUSTED\"]), (d,gr)=> {\n return _.map (d['distribution']['Test'], (r)=>{\n let rp = r;\n rp.type = gr;\n return rp;\n });\n})) || [], gene_id, true)","pinned":false,"hidden":false,"mode":"ojs"},{"id":3310,"value":"fig6_label = md`**Figure 6**. Test significance by alignment size and divergence.`","pinned":false,"hidden":false,"mode":"ojs"},{"id":3026,"value":"fig5 = plotPie (_.flatten (_.map (_.get (result_json, [gene_id,\"BUSTED\",\"RELAX partitioned descriptive\",\"Rate Distributions\"]), (d,k)=> {\n return _.map (d, (r)=>{\n let rp = r;\n rp.type = k;\n return rp;});\n \n})) || [], gene_id, false)","pinned":false,"hidden":false,"mode":"ojs"},{"id":2236,"value":"md`### Tree for ${gene_id}`","pinned":false,"hidden":false,"mode":"ojs"},{"id":3080,"value":"viewof treeDim = text({placeholder : \"1024 x 800\", description: \"Tree dimension (height x width in pixels), leave blank to auto-scale\", submit: \"Resize\"})","pinned":false,"hidden":false,"mode":"ojs"},{"id":1941,"value":"trendLegend = swatches({\n color: species_colors,\n title: \"Viral species\",\n //tickFormat: \"%\"\n})","pinned":false,"hidden":false,"mode":"ojs"},{"id":3084,"value":"displayed_tree.show()","pinned":false,"hidden":false,"mode":"ojs"},{"id":870,"value":"html`\n \n

`","pinned":false,"hidden":false,"mode":"ojs"},{"id":5,"value":"md`---`","pinned":false,"hidden":false,"mode":"ojs"},{"id":2701,"value":"md`### Libraries and data`","pinned":false,"hidden":false,"mode":"ojs"},{"id":9,"value":"d3 = require (\"d3\")","pinned":false,"hidden":false,"mode":"ojs"},{"id":11,"value":"phylotree=require (\"phylotree\")","pinned":false,"hidden":false,"mode":"ojs"},{"id":13,"value":"_=require(\"lodash\")","pinned":false,"hidden":false,"mode":"ojs"},{"id":78,"value":"//resolve(\"phylotree@0.1/phylotree.css\")\n//require (\"https://dl.dropbox.com/s/mjhii51tjy1o5gt/phylotree.js\")\nhtml`\n\n`","pinned":false,"hidden":false,"mode":"ojs"},{"id":1905,"value":"tree_object = [new phylotree.phylotree(_.get (result_json, [gene_id,\"tree\"]) || \"()\"), _.get (result_json, [gene_id,\"tested\",0]) || []]","pinned":false,"hidden":false,"mode":"ojs"},{"id":127,"value":"$34","pinned":false,"hidden":false,"mode":"ojs"},{"id":874,"value":"import { table } from \"@gampleman/table\"","pinned":false,"hidden":false,"mode":"ojs"},{"id":174,"value":"import {select,text,checkbox, autoSelect} from \"@jashkenas/inputs\"","pinned":false,"hidden":false,"mode":"ojs"},{"id":488,"value":"vegalite = require(\"vega-embed\")","pinned":false,"hidden":false,"mode":"ojs"},{"id":2288,"value":"float_format = d3.format (\".3g\");","pinned":false,"hidden":false,"mode":"ojs"},{"id":2217,"value":"$35","pinned":false,"hidden":false,"mode":"ojs"},{"id":2321,"value":"report_ratio = (a,b)=> {\n if (a == 0 && b == 0) return 'N.D.';\n if (a == 0) return 'Infinite';\n return float_format (b/a);\n}","pinned":false,"hidden":false,"mode":"ojs"},{"id":1929,"value":"species = new Set(_.flatten(_.map (has_relax, (f)=>_.map (_.uniqBy (_.toPairs (f[\"tested\"][0]), (d)=>d[1]), (d)=>d[1]))))","pinned":false,"hidden":false,"mode":"ojs"},{"id":3030,"value":"has_relax = _.chain (result_json).toPairs().filter ((d)=>\"tested\" in d[1]).fromPairs().value()","pinned":false,"hidden":false,"mode":"ojs"},{"id":3565,"value":"{\n let grpd = _.groupBy (_.filter (K_MLE, (d)=>d.mle <= 5 && d.Reference == 'EF' && d.clade != 'EF' && d.pv <= 0.05), (d)=>d.gene);\n return grpd;\n}","pinned":false,"hidden":false,"mode":"ojs"},{"id":1937,"value":"species_colors = d3.scaleOrdinal(d3.schemeCategory10).domain ([...species]);","pinned":false,"hidden":false,"mode":"ojs"},{"id":2785,"value":"$36","pinned":false,"hidden":false,"mode":"ojs"},{"id":3363,"value":"relax_p = 0.05","pinned":false,"hidden":false,"mode":"ojs"},{"id":2454,"value":"relax_significant = _.filter (_.toPairs (result_json), (f)=>f[1].tests && f[1].tests[\"p-value\"] <= relax_p)","pinned":false,"hidden":false,"mode":"ojs"},{"id":2998,"value":"busted_significant = _.filter (_.toPairs (result_json), (f)=>f[1].BUSTED && d3.min (_.map(f[1].BUSTED, (test)=>test.p)) <= 0.05)","pinned":false,"hidden":false,"mode":"ojs"},{"id":2475,"value":"baseline_by_segment = _.chain (result_json).toPairs().filter ((d)=>\"fits\" in d[1]).map ((d)=> {\n let ref = '';\n const K = _.get (d[1], ['tests','relaxation or intensification parameter']);\n for (let i in K) {\n if (K[i] == 1) {\n d[1] = i;\n break;\n }\n }\n return d;\n}).fromPairs().value();","pinned":false,"hidden":false,"mode":"ojs"},{"id":2952,"value":"mean_dnds_groups = _.chain (_.groupBy (mean_dnds_plot, (d)=>d.clade)).map ((d,k)=>{\n return {\n group : k,\n mean : d3.mean (d, (e)=>e.omega),\n median : d3.median (d, (e)=>e.omega),\n Q1 : d3.quantile (d, 0.05, (e)=>e.omega),\n Q3 : d3.quantile (d, 0.95, (e)=>e.omega)\n };\n}).value()","pinned":false,"hidden":false,"mode":"ojs"},{"id":2904,"value":"mean_dnds_plot = _.filter (_.flatten (_.map (mean_dnds, (d, f)=> {\n return _.map (d, (dnds, gr)=> { \n return {'clade' : gr, \"omega\" : dnds, \"gene\" : f};\n });\n})), (r)=>_.isNumber (r.omega) && r.clade != \"Unclassified\")","pinned":false,"hidden":false,"mode":"ojs"},{"id":2865,"value":"mean_dnds = {\n return _.mapValues (result_json, (d,f)=> {\n if (\"fits\" in d == false) return; \n let test_groups = new Set (_.values (d.tested[0]));\n let mapper = {\"Unclassified\" : \"Unclassified\"};\n if (test_groups.has (\"Test\")) {\n _.some (d.tested[0], (g,s) => {\n if (g == \"Test\") {\n mapper[\"Test\"] = s.split (\"_\")[0]; \n } else {\n mapper[\"Reference\"] = s.split (\"_\")[0]; \n }\n return _.size (mapper) == 3;\n }\n );\n } else {\n mapper = _.fromPairs ( _.map ([...test_groups], (d)=>[d,d]));\n }\n return _.fromPairs ([['mapping', mapper]].concat(_.map ([...test_groups], (g)=> {\n return ([mapper[g],d.fits[\"MG94xREV with separate rates for branch sets\"][\"Rate Distributions\"][\"non-synonymous/synonymous rate ratio for *\" + g + \"*\"][0][0]]);\n })));\n })\n}","pinned":false,"hidden":false,"mode":"ojs"},{"id":3688,"value":"qv = _.groupBy (table_data, (d)=>d.ID)","pinned":false,"hidden":false,"mode":"ojs"},{"id":3124,"value":"K_MLE = {\n let R = [];\n _.each (result_json, (d,f)=> {\n const K = _.get (d, [\"tests\", \"relaxation or intensification parameter\"]);\n if (!K) {\n return; \n }\n let k = {\n 'gene' : f,\n 'Reference' : baseline_by_segment[f],\n 'pv' : _.get (d, [\"tests\", \"p-value\"])\n };\n let D = [];\n _.each (K, (mle, clade)=> {\n let kk = _.clone (k);\n kk.qv = qv [kk.gene][0][\"RELAX q-value\"];\n kk.clade = clade;\n kk.mle = mle;\n kk.sequences = d.sequences;\n kk.daic = _.get (d, [\"fits\", \"RELAX alternative\",\"AIC-c\"]) - _.get (d, [\"fits\", \"RELAX partitioned descriptive\",\"AIC-c\"]);\n R.push (kk);\n });\n });\n return R;\n}","pinned":false,"hidden":false,"mode":"ojs"},{"id":3485,"value":"$37","pinned":false,"hidden":false,"mode":"ojs"},{"id":754,"value":"result_json = await d3.json (\"https://data.hyphy.org/web/ciliates/relax-2022.json\");","pinned":false,"hidden":false,"mode":"ojs"},{"id":3558,"value":"druid = require(\"@saehrimnir/druidjs\")","pinned":false,"hidden":false,"mode":"ojs"},{"id":3561,"value":"peformHC = (data)=>{\n const X = druid.Matrix.from(data); // X is the data as object of the Matrix class.\n const DR = druid[\"Hierarchical_Clustering\"]; // DR is the selected DR class\n const hc = new DR(X, \"complete\", /*druid.manhattan*/);\n return hc;\n}","pinned":false,"hidden":false,"mode":"ojs"},{"id":1943,"value":"import { legend, swatches } from \"@d3/color-legend\"","pinned":false,"hidden":false,"mode":"ojs"},{"id":2060,"value":"import {translation_table} from \"@spond/usual-vs-unusual-mutation-analyses\"","pinned":false,"hidden":false,"mode":"ojs"},{"id":3183,"value":"import {renderNDiscreteDistributions} from \"@spond/omega-plots\"","pinned":false,"hidden":false,"mode":"ojs"}],"files":"$W38","stdlib":"1","titling":"auto"}