31:T404,parsed_healthRecords = Promise.all( health_records.map(async record => { try { const proxiedUrl = `${WORKER_BASE}${encodeURIComponent(record.downloadUrl)}`; const res = await fetch(proxiedUrl); if (!res.ok) { throw new Error(`${res.status} ${res.statusText}`); } const text = await res.text(); const xml = new DOMParser().parseFromString(text, "application/xml"); const parserError = xml.getElementsByTagName("parsererror")[0]; if (parserError) { throw new Error(parserError.textContent); } const root = xml.documentElement; const parsedJson = { rootName: root.localName, data: xmlToJson(root) }; return { ...record, rawText: text, parsedJson, error: null }; } catch (error) { console.warn("Failed:", record.id, error); return { ...record, rawText: null, parsedJson: null, error: String(error) }; } }) )32:T17ce,// all23_flat = all23.flatMap(d => // (d.files ?? []).map(f => ({ // id: d.id, // number_of_files: d.number_of_files, // file_name: f.name, // dataType: f.dataType, // publishedDate: f.publishedDate, // genomeBuild: f.genomeBuild, // sizeMB: f.genomeBuildFiles?.[0]?.sizeMB, // zip: d.profile?.zip, // state: d.profile?.state, // gender: surveyGet(d, ["what is your gender", "sex/gender", "anatomical sex at birth"]), // race: surveyGet(d, ["what is your race", "race/ethnicity"]), // ethnicity: surveyGet(d, ["what is your ethnicity", "race/ethnicity"]), // birthYear: surveyGet(d, ["year of birth"]), // age: surveyGet(d, ["year of birth"]) ? (2026 - Number(surveyGet(d, ["year of birth"]))) : null, // public_profile_url: d.profile?.public_profile_url, // downloadUrl: f.downloadUrl // })) // ) // all23_flat = all23.flatMap(d => { // const s = surveyToObj(d); // const get = keys => { for (const k of keys) if (s[k] != null && s[k] !== "") return s[k]; return null; }; // return (d.files ?? []).map(f => ({ // id: d.id, // number_of_files: d.number_of_files, // file_name: f.name, // genomeBuild: f.genomeBuild, // sizeMB: f.genomeBuildFiles?.[0]?.sizeMB, // state: d.profile?.state, // zip: d.profile?.zip, // // clean common columns // gender: get(["What is your gender?", "Sex/Gender"]), // race: get(["What is your race? Pick all that apply.", "Race/ethnicity"]), // ethnicity: get(["What is your ethnicity?", "Race/ethnicity"]), // birthYear: get(["Year of birth"]), // smokes_now: get(["Do you currently smoke tobacco products?"]), // occupation: get(["Select the category that best describes your occupation."]), // downloadUrl: f.downloadUrl, // // everything else, untouched // ...s // })); // }) // all23_flat = all23.flatMap(d => { // const s = surveyToObj(d); // const get = keys => { for (const k of keys) if (s[k] != null && s[k] !== "") return s[k]; return null; }; // const by = get(["Year of birth"]); // const yearNum = by ? parseInt(by, 10) : null; // const age = (yearNum && yearNum > 1900 && yearNum <= 2026) ? 2026 - yearNum : null; // return (d.files ?? []).map(f => ({ // id: d.id, // number_of_files: d.number_of_files, // file_name: f.name, // genomeBuild: f.genomeBuild, // sizeMB: f.genomeBuildFiles?.[0]?.sizeMB, // state: d.profile?.state, // zip: d.profile?.zip, // gender: get(["What is your gender?", "Sex/Gender"]), // race: get(["What is your race? Pick all that apply.", "Race/ethnicity"]), // ethnicity: get(["What is your ethnicity?", "Race/ethnicity"]), // birthYear: by, // age, // <- computed here // smokes_now: get(["Do you currently smoke tobacco products?"]), // occupation: get(["Select the category that best describes your occupation."]), // downloadUrl: f.downloadUrl, // ...s // })); // }) // all23_flat = all23.flatMap(d => { // const s = surveyToObj(d); // const get = keys => { for (const k of keys) if (s[k] != null && s[k] !== "") return s[k]; return null; }; // const by = get(["Year of birth"]); // const yearNum = by ? parseInt(by, 10) : null; // const age = (yearNum && yearNum > 1900 && yearNum <= 2026) ? 2026 - yearNum : null; // // distinct data types from profile.files, joined into one string // const profileFileTypes = [ // ...new Set((d.profile?.files ?? []).map(pf => pf.data_type).filter(Boolean)) // ].join(", "); // return (d.files ?? []).map(f => ({ // id: d.id, // number_of_files: d.number_of_files, // file_name: f.name, // dataType: f.dataType, // profileFileTypes, // <- new column // profileFileCount: (d.profile?.files ?? []).length, // genomeBuild: f.genomeBuild, // sizeMB: f.genomeBuildFiles?.[0]?.sizeMB, // state: d.profile?.state, // zip: d.profile?.zip, // gender: get(["What is your gender?", "Sex/Gender"]), // race: get(["What is your race? Pick all that apply.", "Race/ethnicity"]), // ethnicity: get(["What is your ethnicity?", "Race/ethnicity"]), // birthYear: by, // age, // smokes_now: get(["Do you currently smoke tobacco products?"]), // occupation: get(["Select the category that best describes your occupation."]), // downloadUrl: f.downloadUrl, // ...s // })); // }) all23_flat = all23andme_users_cloud.flatMap(d => { const s = surveyToObj(d); const get = keys => { for (const k of keys) if (s[k] != null && s[k] !== "") return s[k]; return null; }; const by = get(["Year of birth"]); const yearNum = by ? parseInt(by, 10) : null; const age = (yearNum && yearNum > 1900 && yearNum <= 2026) ? 2026 - yearNum : null; // count of valid 23andMe files in the top-level files[] const num_23files = (d.files ?? []).filter(f => f.valid23File === true).length; // profile file data_types const pfTypes = (d.profile?.files ?? []).map(pf => pf.data_type).filter(Boolean); const has = t => pfTypes.some(x => x === t); return (d.files ?? []).map(f => ({ id: d.id, num_23files, // <- was number_of_files // one column per data type — filterable independently has_veritas: has("Veritas Genetics"), has_valid23: (d.files ?? []).some(f => f.valid23File === true),//has_23andme: has("23andMe"), has_ftdna: has("Family Tree DNA"), has_ancestry: has("AncestryDNA"), profileFileTypes: [...new Set(pfTypes)].join(", "), // keep the summary too profileFileCount: pfTypes.length, file_name: f.name, dataType: f.dataType, genomeBuild: f.genomeBuild, sizeMB: f.genomeBuildFiles?.[0]?.sizeMB, state: d.profile?.state, zip: d.profile?.zip, gender: get(["What is your gender?", "Sex/Gender"]), race: get(["What is your race? Pick all that apply.", "Race/ethnicity"]), ethnicity: get(["What is your ethnicity?", "Race/ethnicity"]), birthYear: by, age, downloadUrl: f.downloadUrl, ...s })); })33:T42f,function toc(selector = "h2", heading = "Table of Contents") { return Generators.observe(notify => { let headings = []; function observed() { const h = Array.from(document.querySelectorAll(selector)); if (h.length !== headings.length || h.some((h, i) => headings[i] !== h)) { notify(html`${heading}

${DOM.text(h.textContent)}

`); } } const observer = new MutationObserver(observed); observer.observe(document.body, { childList: true, subtree: true }); observed(); return () => observer.disconnect(); }); }34:T589,xmlToJson = { function convert(node) { // Text node if (node.nodeType === Node.TEXT_NODE) { const text = node.nodeValue.trim(); return text ? text : null; } // Only handle document or element nodes if ( node.nodeType !== Node.ELEMENT_NODE && node.nodeType !== Node.DOCUMENT_NODE ) { return null; } const obj = {}; // Attributes if (node.attributes && node.attributes.length > 0) { obj["@attributes"] = {}; for (const attr of node.attributes) { obj["@attributes"][attr.name] = attr.value; } } // Element children for (const childNode of node.childNodes) { if (childNode.nodeType === Node.TEXT_NODE) { const text = childNode.nodeValue.trim(); if (text) obj["#text"] = text; } if (childNode.nodeType === Node.ELEMENT_NODE) { const name = childNode.localName || childNode.nodeName; const value = convert(childNode); if (obj[name]) { if (!Array.isArray(obj[name])) { obj[name] = [obj[name]]; } obj[name].push(value); } else { obj[name] = value; } } } // If simple text-only element, return just the text const keys = Object.keys(obj); if (keys.length === 1 && keys[0] === "#text") { return obj["#text"]; } return obj; } return convert; }35:[{"id":"cc6d965d376506b6f4709a64a35258f7bec649a6f988994cf459ce583a5c7dca9c4ce469362d4633816f52bbe8bdd927baca688054f78343406554d05ff6a80b","href":"https://static.observableusercontent.com/files/cc6d965d376506b6f4709a64a35258f7bec649a6f988994cf459ce583a5c7dca9c4ce469362d4633816f52bbe8bdd927baca688054f78343406554d05ff6a80b","name":"pgp_participants_1017_with_profiles@2.json","type":"application/json","lastModified":1783953468476.481,"size":10617236},{"id":"5bda1ac433190d267bb44c181ac2bb55e25510d6510dfa967687bd1302ecd1ace051045927bf8534b404bb01396c6489ffa4750a784ac3da5b7a58c076dd7b4b","href":"https://static.observableusercontent.com/files/5bda1ac433190d267bb44c181ac2bb55e25510d6510dfa967687bd1302ecd1ace051045927bf8534b404bb01396c6489ffa4750a784ac3da5b7a58c076dd7b4b","name":"pgp_participants_1017.json","type":"application/json","lastModified":1783609385431.73,"size":1147043}] 2f:{"title":" Polygenic Risk Scores - SDK Examples","cells":[{"id":0,"value":"# Polygenic Risk Scores - SDK Examples\n\nBrowser-native JavaScript SDK for loading genomic [data](https://my.pgp-hms.org/public_genetic_data), polygenic score [files](https://www.pgscatalog.org/), PRS calculation and visualization.\nUI found [here](https://lorenasandoval88.github.io/diseasome/). Full notebook found [here](https://observablehq.com/@lorenasandoval88/polygenic_risk_scores2).\n","pinned":false,"hidden":false,"mode":"md"},{"id":42,"value":"sdk = await import (\"https://lorenasandoval88.github.io/diseasome/dist/sdk.mjs\")","pinned":false,"hidden":false,"mode":"ojs"},{"id":33,"value":"toc()","pinned":false,"hidden":false,"mode":"ojs"},{"id":16,"value":"## 1. Personal Genome Project Module","pinned":false,"hidden":false,"mode":"md"},{"id":45,"value":"Object.keys(sdk.pgp)","pinned":false,"hidden":false,"mode":"ojs"},{"id":245,"value":"### Available Data types (17) incl. 23andme, image, health records - CCR XML, etc.","pinned":false,"hidden":false,"mode":"md"},{"id":47,"value":"data_types = sdk.pgp.fetchAvailableDataTypes()","pinned":false,"hidden":false,"mode":"ojs"},{"id":406,"value":"### All users with Image Data (66)","pinned":false,"hidden":false,"mode":"md"},{"id":409,"value":"image_data = await sdk.pgp.allUsersMetaDataByType_fast(\"image\")","pinned":false,"hidden":false,"mode":"ojs"},{"id":371,"value":"### All users with Health Records Data (23)","pinned":false,"hidden":false,"mode":"md"},{"id":51,"value":"health_records = await sdk.pgp.allUsersMetaDataByType_fast(\"health records - CCR XML\")","pinned":false,"hidden":false,"mode":"ojs"},{"id":184,"value":"$31","pinned":false,"hidden":false,"mode":"ojs"},{"id":248,"value":"### All users with 23andme data (1017) - API call","pinned":false,"hidden":false,"mode":"md"},{"id":49,"value":"all_23andme_users = await sdk.pgp.allUsersMetaDataByType_fast(\"23andMe\") //23andme users","pinned":false,"hidden":false,"mode":"ojs"},{"id":565,"value":"---\n","pinned":false,"hidden":false,"mode":"md"},{"id":204,"value":"### One user: profile and 23andme file","pinned":false,"hidden":false,"mode":"md"},{"id":477,"value":"genome_id = \"hu50801B\" //>Melinda, \"hu2843C9\">John Adams","pinned":false,"hidden":false,"mode":"ojs"},{"id":56,"value":"hu50801B_profile = await sdk.pgp.fetchProfile(genome_id )// Melinda","pinned":false,"hidden":false,"mode":"ojs"},{"id":145,"value":"hu50801B_23andme_txt = await sdk.pgp.get23Txt(\"https://my.pgp-hms.org/user_file/download/4162\",genome_id,true)","pinned":false,"hidden":false,"mode":"ojs"},{"id":434,"value":"### Three 23andMe Files for PRS calculation","pinned":false,"hidden":false,"mode":"md"},{"id":121,"value":"first3_23andme_txts = Promise.all(\n all_23andme_users.slice(0,3).map(user => \n sdk.pgp.get23Txt(user.downloadUrl)\n )\n)","pinned":false,"hidden":false,"mode":"ojs"},{"id":467,"value":"---","pinned":false,"hidden":false,"mode":"md"},{"id":819,"value":"# Precomputed in Google Cloud","pinned":false,"hidden":false,"mode":"md"},{"id":513,"value":"### All Users with 23andme data (855) Precomputed in GCS. [See Notebook](https://observablehq.com/@lorenasandoval88/23andme-files-from-the-personal-genome-project?collection=@lorenasandoval88/23andme-data)","pinned":false,"hidden":false,"mode":"md"},{"id":587,"value":"all23andme_users_cloud = FileAttachment(\"pgp_participants_1017_with_profiles@2.json\").json()\n//all23_sorted = [...all23].sort((a, b) => b.number_of_files - a.number_of_files)","pinned":false,"hidden":false,"mode":"ojs"},{"id":623,"value":"$32","pinned":false,"hidden":false,"mode":"ojs"},{"id":889,"value":"all23_flat","pinned":true,"hidden":false,"mode":"ojs"},{"id":448,"value":"### 23andMe Users with WGS Veritas Data (32 unique users, 25 valid VCF)","pinned":false,"hidden":false,"mode":"md"},{"id":927,"value":"_23andme_users_with_veritas_BAM_VCF = all23andme_users_cloud.filter(user => {\n // 1) has at least one file with valid23File === true\n const hasValid23 = (user.files ?? []).some(f => f.valid23File === true);\n\n // 2) has a profile file that is Veritas Genetics AND name ends in \"- VCF\"\n const hasVeritasVcf = (user.profile?.files ?? []).some(f =>\n f.data_type === \"Veritas Genetics\" \n );\n\n return hasValid23 && hasVeritasVcf;\n})","pinned":false,"hidden":false,"mode":"ojs"},{"id":922,"value":"_23andme_users_with_veritas_VCF_only= all23andme_users_cloud.filter(user => {\n // 1) has at least one file with valid23File === true\n const hasValid23 = (user.files ?? []).some(f => f.valid23File === true);\n\n // 2) has a profile file that is Veritas Genetics AND name ends in \"- VCF\"\n const hasVeritasVcf = (user.profile?.files ?? []).some(f =>\n f.data_type === \"Veritas Genetics\" &&\n (f.name ?? \"\").endsWith(\"- VCF\")\n );\n\n return hasValid23 && hasVeritasVcf;\n})","pinned":false,"hidden":false,"mode":"ojs"},{"id":375,"value":"### 23andMe Users with Health Records Data (8)","pinned":false,"hidden":false,"mode":"md"},{"id":222,"value":"_23andme_users_with_healthRecords = {\n const overlapIds = new Set(all_23andme_users.filter(user =>\n (new Set(health_records.map(d => d.id))).has(user.id))\n .map(d => d.id));\n\n return parsed_healthRecords\n .filter(record => overlapIds.has(record.id))\n .slice(0, 10)\n .map(record => ({\n id: record.id,\n name: record.name,\n publishedDate: record.publishedDate,\n dataType: record.dataType,\n downloadUrl: record.downloadUrl,\n\n // raw XML/text file\n rawText: record.rawText,\n\n // parsed full XML → JSON\n parsedJson: record.parsedJson,\n\n error: record.error\n }));\n}","pinned":false,"hidden":false,"mode":"ojs"},{"id":988,"value":"_23andme_users_with_veritas_VCF_only.map(user=> user.id).toString()","pinned":true,"hidden":false,"mode":"ojs"},{"id":469,"value":"---","pinned":false,"hidden":false,"mode":"md"},{"id":22,"value":"## 2. PGS Catalog Module","pinned":false,"hidden":false,"mode":"md"},{"id":178,"value":"Object.keys(sdk.pgs)","pinned":false,"hidden":false,"mode":"ojs"},{"id":94,"value":"all_pgs_models_meta_data = await sdk.pgs.fetchAllScores()","pinned":false,"hidden":false,"mode":"ojs"},{"id":100,"value":"PGS000001_txt = sdk.pgs.getPgsTxt(\"PGS000001\")","pinned":false,"hidden":false,"mode":"ojs"},{"id":440,"value":"### Three 23andMe Files for PRS calculation","pinned":false,"hidden":false,"mode":"md"},{"id":152,"value":"first3PGSTxts = {\n const first3PGSIds = all_pgs_models_meta_data.scores\n .slice(0, 3)\n .map(s => s.id);\n\n const results = [];\n\n for (const pgsId of first3PGSIds) {\n const pgsTxt = await sdk.pgs.getPgsTxt(pgsId);\n results.push(pgsTxt);\n }\n\n return results;\n}","pinned":false,"hidden":false,"mode":"ojs"},{"id":28,"value":"## 3. PRS Matching & Calculation\n","pinned":false,"hidden":false,"mode":"md"},{"id":103,"value":"polygenic_risk_score_results_one_model_one_user = sdk.prs.Match2(PGS000001_txt[0],hu50801B_23andme_txt)","pinned":false,"hidden":false,"mode":"ojs"},{"id":157,"value":"polygenic_risk_score_results_3models_3_users = Promise.all(\n first3PGSTxts.map(async (pgsTxt, i) => {\n return Promise.all(\n first3_23andme_txts.map(async (userTxt, j) => ({\n pgsIndex: i,\n userIndex: j,\n result: await sdk.prs.Match2(pgsTxt, userTxt)\n }))\n );\n })\n).then(rows => rows.flat())","pinned":false,"hidden":false,"mode":"ojs"},{"id":13,"value":"## 4. Clustering & Visualization Module","pinned":false,"hidden":false,"mode":"md"},{"id":106,"value":"viewof clusterRows = Inputs.toggle({\n label: \"Cluster Rows\",\n value: true\n})","pinned":false,"hidden":false,"mode":"ojs"},{"id":108,"value":"viewof clusterCols = Inputs.toggle({\n label: \"Cluster Columns\",\n value: true\n})","pinned":false,"hidden":false,"mode":"ojs"},{"id":112,"value":"viewof plot1 = {\n const div = document.createElement(\"div\")\n const svg = cluster_svg\n div.appendChild(svg)\n return div\n}","pinned":false,"hidden":false,"mode":"ojs"},{"id":110,"value":"cluster_svg = await sdk.clustjs.hclust_plot({\n // data: matrix,\n // rowNames: users,\n // colNames: snps,\n width: 900,\n height: 400,\n clusterRows: clusterRows,\n clusterCols: clusterCols,\n clusteringDistanceRows: \"euclidean\",\n clusteringDistanceCols: \"euclidean\",\n clusteringMethodRows: \"complete\",\n clusteringMethodCols: \"complete\"\n})","pinned":false,"hidden":false,"mode":"ojs"},{"id":71,"value":"## Documentation\n[https://observablehq.com/@lorenasandoval88/polygenic_risk_scores2](https://observablehq.com/@lorenasandoval88/polygenic_risk_scores2) ","pinned":false,"hidden":false,"mode":"md"},{"id":166,"value":"## Github Code \n[https://github.com/lorenasandoval88/polygenic_risk_scores](https://github.com/lorenasandoval88/polygenic_risk_scores)","pinned":false,"hidden":false,"mode":"md"},{"id":81,"value":"---","pinned":false,"hidden":false,"mode":"md"},{"id":272,"value":"#### Imports/helper functions","pinned":false,"hidden":false,"mode":"md"},{"id":10,"value":"$33","pinned":false,"hidden":false,"mode":"ojs"},{"id":260,"value":"function findAnswer(surveyObj, keyword) {\n const key = Object.keys(surveyObj).find(q =>\n q.toLowerCase().includes(keyword.toLowerCase())\n );\n return key ? surveyObj[key] : undefined;\n}","pinned":false,"hidden":false,"mode":"ojs"},{"id":317,"value":"function isNonEmpty(x) {\n return x != null && String(x).trim() !== \"\";\n}\n\n","pinned":false,"hidden":false,"mode":"ojs"},{"id":325,"value":"\nfunction uniqueArray(arr) {\n return [...new Set(arr.filter(isNonEmpty))];\n}","pinned":false,"hidden":false,"mode":"ojs"},{"id":323,"value":"\nfunction splitConditions(answer) {\n if (!isNonEmpty(answer)) return [];\n\n return String(answer)\n .split(\",\")\n .map(x => x.trim())\n .filter(Boolean);\n}\n","pinned":false,"hidden":false,"mode":"ojs"},{"id":187,"value":"WORKER_BASE = \"https://lorena-api.lorenasandoval88.workers.dev/?url=\";","pinned":false,"hidden":false,"mode":"ojs"},{"id":320,"value":"function findAnswers(surveyObj, keyword) {\n return Object.entries(surveyObj)\n .filter(([q, a]) =>\n q.toLowerCase().includes(keyword.toLowerCase()) && isNonEmpty(a)\n )\n .map(([q, a]) => String(a).trim());\n}\n","pinned":false,"hidden":false,"mode":"ojs"},{"id":339,"value":"function safeDxKey(condition) {\n return \"dx_\" + String(condition)\n .toLowerCase()\n .replace(/\$[^)]*\$/g, \"\") // remove parentheses text\n .replace(/[^a-z0-9]+/g, \"_\") // punctuation/spaces -> _\n .replace(/^_+|_+$/g, \"\"); // trim _\n}\n","pinned":false,"hidden":false,"mode":"ojs"},{"id":193,"value":"$34","pinned":false,"hidden":false,"mode":"ojs"},{"id":643,"value":"surveyGet = (d, needles) => {\n // flatten all survey sub-arrays into one list of [question, answer] pairs\n const rows = (d.profile?.google_survey_results ?? []).flat();\n const wants = Array.isArray(needles) ? needles : [needles];\n for (const n of wants) {\n const hit = rows.find(([q]) => q?.toLowerCase().includes(n.toLowerCase()));\n if (hit && hit[1] != null && hit[1] !== \"\") return hit[1];\n }\n return null;\n}","pinned":false,"hidden":false,"mode":"ojs"},{"id":655,"value":"surveyToObj = d => {\n const rows = (d.profile?.google_survey_results ?? []).flat();\n const obj = {};\n for (const pair of rows) {\n if (Array.isArray(pair) && pair.length >= 2) {\n const [q, a] = pair;\n if (q != null) obj[q.trim()] = a; // last answer wins if duplicated\n }\n }\n return obj;\n}","pinned":false,"hidden":false,"mode":"ojs"}],"files":"$W35","stdlib":"1","titling":"auto"}