@sjcrh/proteinpaint-server 2.139.0 → 2.140.0

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@sjcrh/proteinpaint-server",
-  "version": "2.139.0",
+  "version": "2.140.0",
   "type": "module",
   "description": "a genomics visualization tool for exploring a cohort's genotype and phenotype data",
   "main": "src/app.js",
@@ -60,11 +60,11 @@
   },
   "dependencies": {
     "@sjcrh/augen": "2.136.0",
-    "@sjcrh/proteinpaint-python": "2.139.0",
+    "@sjcrh/proteinpaint-python": "2.139.1",
     "@sjcrh/proteinpaint-r": "2.137.2-0",
     "@sjcrh/proteinpaint-rust": "2.138.3-7",
     "@sjcrh/proteinpaint-shared": "2.138.3-7",
-    "@sjcrh/proteinpaint-types": "2.139.0",
+    "@sjcrh/proteinpaint-types": "2.139.1",
     "@types/express": "^5.0.0",
     "@types/express-session": "^1.18.1",
     "better-sqlite3": "^9.4.1",

package/routes/grin2.js

@@ -60,7 +60,7 @@ async function runGrin2(g, ds, request) {
   }
   mayLog("[GRIN2] Processing sample data...");
   const processingStartTime = Date.now();
-  const { lesionData, processingSummary } = await processSampleData(samples, ds, request);
+  const { lesions, processingSummary } = await processSampleData(samples, ds, request);
   const processingTime = Date.now() - processingStartTime;
   const processingTimeToPrint = Math.round(processingTime / 1e3);
   mayLog(`[GRIN2] Data processing took ${processingTimeToPrint} seconds`);
@@ -70,13 +70,13 @@ async function runGrin2(g, ds, request) {
   if (processingSummary && processingSummary.failedSamples > 0) {
     mayLog(`[GRIN2] Warning: ${processingSummary.failedSamples} samples failed to process`);
   }
-  if (lesionData.length === 0) {
+  if (lesions.length === 0) {
     throw new Error("No lesions found after processing all samples. Check filter criteria and input data.");
   }
   const pyInput = {
     genedb: path.join(serverconfig.tpmasterdir, g.genedb.dbfile),
     chromosomelist: {},
-    lesion: JSON.stringify(lesionData)
+    lesion: JSON.stringify(lesions)
   };
   for (const c in g.majorchr) {
     if (ds.queries.singleSampleMutation.discoPlot?.skipChrM) {
@@ -85,7 +85,7 @@ async function runGrin2(g, ds, request) {
     }
     pyInput.chromosomelist[c] = g.majorchr[c];
   }
-  mayLog(`[GRIN2] Prepared ${lesionData.length.toLocaleString()} lesions for analysis`);
+  mayLog(`[GRIN2] Prepared ${lesions.length.toLocaleString()} lesions for analysis`);
   const grin2AnalysisStart = Date.now();
   const pyResult = await run_python("grin2PpWrapper.py", JSON.stringify(pyInput));
   if (pyResult.stderr?.trim()) {
@@ -126,35 +126,15 @@ async function processSampleData(samples, ds, request) {
     failedSamples: 0,
     failedFiles: []
   };
-  const dataTypeCounts = {
-    [dtsnvindel]: { samples: 0, entries: 0, processedLesions: 0 },
-    [dtcnv]: { samples: 0, entries: 0, processedLesions: 0 },
-    [dtfusionrna]: { samples: 0, entries: 0, processedLesions: 0 },
-    unknown: /* @__PURE__ */ new Map()
-  };
   mayLog(`[GRIN2] Processing JSON files for ${samples.length.toLocaleString()} samples`);
   for (const sample of samples) {
     try {
       const filepath = path.join(serverconfig.tpmasterdir, ds.queries.singleSampleMutation.folder, sample.name);
       await file_is_readable(filepath);
       const mlst = JSON.parse(await read_file(filepath));
-      const { sampleLesions, sampleDataTypeCounts } = await processSampleMlst(sample.name, mlst, lesionId, request);
+      const { sampleLesions } = await processSampleMlst(sample.name, mlst, lesionId, request);
       lesions.push(...sampleLesions);
       lesionId += sampleLesions.length;
-      for (const [dt, counts] of Object.entries(sampleDataTypeCounts.known)) {
-        if (counts.entries > 0) {
-          dataTypeCounts[dt].samples++;
-          dataTypeCounts[dt].entries += counts.entries;
-          dataTypeCounts[dt].processedLesions += counts.processedLesions;
-        }
-      }
-      for (const [dt, counts] of sampleDataTypeCounts.unknown) {
-        if (!dataTypeCounts.unknown.has(dt)) {
-          dataTypeCounts.unknown.set(dt, { samples: /* @__PURE__ */ new Set(), entries: 0 });
-        }
-        dataTypeCounts.unknown.get(dt).samples.add(sample.name);
-        dataTypeCounts.unknown.get(dt).entries += counts;
-      }
       processingSummary.successfulSamples++;
     } catch (error) {
       processingSummary.failedSamples++;
@@ -164,176 +144,86 @@ async function processSampleData(samples, ds, request) {
       );
     }
   }
-  mayLog(`[GRIN2] === DATA TYPE ANALYSIS SUMMARY ===`);
-  mayLog(
-    `[GRIN2] SNV/Indel (dt=${dtsnvindel}): ${dataTypeCounts[dtsnvindel].samples} samples, ${dataTypeCounts[dtsnvindel].entries} entries, ${dataTypeCounts[dtsnvindel].processedLesions} lesions`
-  );
-  mayLog(
-    `[GRIN2] CNV (dt=${dtcnv}): ${dataTypeCounts[dtcnv].samples} samples, ${dataTypeCounts[dtcnv].entries} entries, ${dataTypeCounts[dtcnv].processedLesions} lesions`
-  );
-  mayLog(
-    `[GRIN2] Fusion (dt=${dtfusionrna}): ${dataTypeCounts[dtfusionrna].samples} samples, ${dataTypeCounts[dtfusionrna].entries} entries, ${dataTypeCounts[dtfusionrna].processedLesions} lesions`
-  );
-  if (dataTypeCounts.unknown.size > 0) {
-    mayLog(`[GRIN2] Unknown data types:`);
-    for (const [dt, counts] of dataTypeCounts.unknown) {
-      mayLog(`[GRIN2]   dt="${dt}": ${counts.samples.size} samples, ${counts.entries} entries`);
-    }
-  }
   mayLog(`[GRIN2] Total lesions processed: ${lesions.length.toLocaleString()}`);
   return {
-    lesionData: lesions,
+    lesions,
     processingSummary
   };
 }
 async function processSampleMlst(sampleName, mlst, startId, request) {
   const lesions = [];
-  const sampleDataTypeCounts = {
-    known: {
-      [dtsnvindel]: { entries: 0, processedLesions: 0 },
-      [dtcnv]: { entries: 0, processedLesions: 0 },
-      [dtfusionrna]: { entries: 0, processedLesions: 0 }
-    },
-    unknown: /* @__PURE__ */ new Map()
-  };
   for (const m of mlst) {
     switch (m.dt) {
       case dtsnvindel: {
-        sampleDataTypeCounts.known[dtsnvindel].entries++;
         if (!request.snvindelOptions)
           break;
         const snvIndelLesion = filterAndConvertSnvIndel(sampleName, m, request.snvindelOptions);
         if (snvIndelLesion) {
           lesions.push(snvIndelLesion);
-          sampleDataTypeCounts.known[dtsnvindel].processedLesions++;
         }
         break;
       }
       case dtcnv: {
-        sampleDataTypeCounts.known[dtcnv].entries++;
         if (!request.cnvOptions)
           break;
         const cnvLesion = filterAndConvertCnv(sampleName, m, request.cnvOptions);
         if (cnvLesion) {
           lesions.push(cnvLesion);
-          sampleDataTypeCounts.known[dtcnv].processedLesions++;
         }
         break;
       }
       case dtfusionrna: {
-        sampleDataTypeCounts.known[dtfusionrna].entries++;
         if (!request.fusionOptions)
           break;
         const fusionLesion = filterAndConvertFusion(sampleName, m, request.fusionOptions);
         if (fusionLesion) {
           lesions.push(fusionLesion);
-          sampleDataTypeCounts.known[dtfusionrna].processedLesions++;
         }
         break;
       }
       default: {
-        const currentCount = sampleDataTypeCounts.unknown.get(m.dt) || 0;
-        sampleDataTypeCounts.unknown.set(m.dt, currentCount + 1);
         break;
       }
     }
   }
   return {
-    sampleLesions: lesions,
-    sampleDataTypeCounts
+    sampleLesions: lesions
   };
 }
 function filterAndConvertSnvIndel(sampleName, entry, options) {
-  const opts = {
-    minTotalDepth: options?.minTotalDepth ?? 10,
-    minAltAlleleCount: options?.minAltAlleleCount ?? 2,
-    consequences: options?.consequences ?? [],
-    hyperMutator: options?.hyperMutator ?? 1e3
-  };
-  if (opts.consequences.length > 0 && entry.class && !opts.consequences.includes(entry.class)) {
-    return null;
-  }
-  const chromosome = entry.chromosome || entry.chr;
-  const position = entry.start || entry.position || entry.pos;
-  if (!chromosome) {
-    return null;
-  }
-  if (position === void 0 || position === null || position === "undefined") {
+  if (!options?.consequences) {
     return null;
   }
-  const numPosition = parseInt(String(position));
-  if (isNaN(numPosition)) {
+  if (options.consequences.length > 0 && entry.class && !options.consequences.includes(entry.class)) {
     return null;
   }
-  const endPosition = entry.end || position;
-  const numEndPosition = parseInt(String(endPosition));
-  if (isNaN(numEndPosition)) {
+  if (!Number.isInteger(entry.pos)) {
     return null;
   }
-  return [sampleName, normalizeChromosome(chromosome), String(numPosition), String(numEndPosition), "mutation"];
+  return [sampleName, entry.chr, entry.pos, entry.pos, "mutation"];
 }
 function filterAndConvertCnv(sampleName, entry, options) {
-  const opts = {
-    lossThreshold: options?.lossThreshold ?? -0.4,
-    gainThreshold: options?.gainThreshold ?? 0.3,
-    maxSegLength: options?.maxSegLength ?? 0,
-    minSegLength: options?.minSegLength ?? 0,
-    hyperMutator: options?.hyperMutator ?? 500
-  };
-  const log2Ratio = entry.log2Ratio ?? entry.value ?? entry.ratio;
-  if (log2Ratio === void 0 || log2Ratio === null) {
-    return null;
-  }
-  const numLog2Ratio = parseFloat(String(log2Ratio));
-  if (isNaN(numLog2Ratio)) {
+  if (!options || options.gainThreshold === void 0 || options.lossThreshold === void 0 || options.maxSegLength === void 0) {
     return null;
   }
-  const isGain = numLog2Ratio >= opts.gainThreshold;
-  const isLoss = numLog2Ratio <= opts.lossThreshold;
-  if (!isGain && !isLoss) {
+  if (!Number.isInteger(entry.start)) {
     return null;
   }
-  const chromosome = entry.chromosome || entry.chr;
-  const start = entry.start || entry.begin;
-  const end = entry.end || entry.stop;
-  if (!chromosome) {
+  if (!Number.isInteger(entry.stop)) {
     return null;
   }
-  if (start === void 0 || start === null || start === "undefined") {
+  if (options.maxSegLength > 0 && entry.stop - entry.start > options.maxSegLength) {
     return null;
   }
-  if (end === void 0 || end === null || end === "undefined") {
-    return null;
-  }
-  const numStart = parseInt(String(start));
-  const numEnd = parseInt(String(end));
-  if (isNaN(numStart) || isNaN(numEnd)) {
-    return null;
-  }
-  const lesionType = numLog2Ratio >= opts.gainThreshold ? "gain" : "loss";
-  return [sampleName, normalizeChromosome(chromosome), String(numStart), String(numEnd), lesionType];
-}
-function filterAndConvertFusion(sampleName, entry, options) {
-  const opts = {
-    fusionTypes: options?.fusionTypes ?? ["gene-gene", "gene-intergenic", "readthrough"],
-    minConfidence: options?.minConfidence ?? 0.7
-  };
-  if (entry.fusionType && !opts.fusionTypes.includes(entry.fusionType))
-    return null;
-  if (entry.confidence && entry.confidence < opts.minConfidence)
+  const isGain = entry.value >= options.gainThreshold;
+  const isLoss = entry.value <= options.lossThreshold;
+  if (!isGain && !isLoss)
     return null;
-  return [
-    sampleName,
-    normalizeChromosome(entry.chromosome || entry.chr),
-    String(entry.start || entry.position),
-    String(entry.end || entry.position),
-    "fusion"
-  ];
+  const lesionType = isGain ? "gain" : "loss";
+  return [sampleName, entry.chr, entry.start, entry.stop, lesionType];
 }
-function normalizeChromosome(chrom) {
-  if (!chrom)
-    return "chr?";
-  return chrom.startsWith("chr") ? chrom : `chr${chrom}`;
+function filterAndConvertFusion(sampleName, entry, _options) {
+  return [sampleName, entry.chrA, entry.posA, entry.posB, "fusion"];
 }
 export {
   api