@sjcrh/proteinpaint-server 2.129.1 → 2.129.2

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@sjcrh/proteinpaint-server",
-  "version": "2.129.1",
+  "version": "2.129.2",
   "type": "module",
   "description": "a genomics visualization tool for exploring a cohort's genotype and phenotype data",
   "main": "src/app.js",
@@ -62,10 +62,10 @@
   "dependencies": {
     "@sjcrh/augen": "2.121.0",
     "@sjcrh/proteinpaint-python": "2.118.0",
-    "@sjcrh/proteinpaint-r": "2.129.1",
-    "@sjcrh/proteinpaint-rust": "2.129.0",
-    "@sjcrh/proteinpaint-shared": "2.129.1",
-    "@sjcrh/proteinpaint-types": "2.129.0",
+    "@sjcrh/proteinpaint-r": "2.129.2",
+    "@sjcrh/proteinpaint-rust": "2.129.2",
+    "@sjcrh/proteinpaint-shared": "2.129.2",
+    "@sjcrh/proteinpaint-types": "2.129.2",
     "@types/express": "^5.0.0",
     "@types/express-session": "^1.18.1",
     "better-sqlite3": "^9.4.1",

package/routes/dataset.js

@@ -1,4 +1,3 @@
-import * as mds2_init from "#src/mds2.init.js";
 import * as mds3_init from "#src/mds3.init.js";
 import * as common from "#shared/common.js";
 import { datasetPayload } from "#types/checkers";
@@ -59,9 +58,6 @@ function mds_clientcopy(ds) {
   if (ds.queries) {
     ds2.queries = {};
   }
-  if (ds.track) {
-    ds2.track = mds2_init.client_copy(ds);
-  }
   if (ds.singlesamplemutationjson) {
     ds2.singlesamplemutationjson = 1;
   }

package/routes/{gdcGRIN2list.js → gdc.grin2.list.js}

@@ -88,12 +88,23 @@ async function listMafFiles(q, ds) {
   if (!Array.isArray(re.data?.hits))
     throw "re.data.hits[] not array";
   const files = [];
+  const filteredFiles = [];
   for (const h of re.data.hits) {
     const c = h.cases?.[0];
     if (!c)
       throw "h.cases[0] missing";
-    if (h.file_size >= maxFileSizeAllowed)
+    if (h.file_size >= maxFileSizeAllowed) {
+      filteredFiles.push({
+        fileId: h.id,
+        fileSize: h.file_size,
+        reason: `File size (${h.file_size} bytes) exceeds maximum allowed size (${maxFileSizeAllowed} bytes)`
+      });
+      console.log(
+        `File ${h.id} with a size of ${h.file_size} bytes is larger then the allowed file size. It is excluded from the list.
+If you want to include it, please increase the maxFileSizeAllowed in the code.`
+      );
       continue;
+    }
     const file = {
       id: h.id,
       project_id: c.project.project_id,
@@ -117,9 +128,42 @@ async function listMafFiles(q, ds) {
     file.sample_types = [...new Set(file.sample_types)];
     files.push(file);
   }
-  files.sort((a, b) => b.file_size - a.file_size);
+  const filesByCase = /* @__PURE__ */ new Map();
+  for (const file of files) {
+    const caseId = file.case_submitter_id;
+    if (!filesByCase.has(caseId)) {
+      filesByCase.set(caseId, []);
+    }
+    filesByCase.get(caseId).push(file);
+  }
+  const deduplicatedFiles = [];
+  let duplicatesRemoved = 0;
+  const caseDetails = [];
+  for (const [caseId, caseFiles] of filesByCase) {
+    if (caseFiles.length > 1) {
+      caseFiles.sort((a, b) => b.file_size - a.file_size);
+      deduplicatedFiles.push(caseFiles[0]);
+      duplicatesRemoved += caseFiles.length - 1;
+      caseDetails.push({
+        caseName: caseId,
+        fileCount: caseFiles.length,
+        keptFileSize: caseFiles[0].file_size
+      });
+      console.log(
+        `Case ${caseId}: Found ${caseFiles.length} MAF files, keeping largest (${caseFiles[0].file_size} bytes)`
+      );
+    } else {
+      deduplicatedFiles.push(caseFiles[0]);
+    }
+  }
+  if (duplicatesRemoved > 0) {
+    console.log(
+      `GRIN2 MAF deduplication: Removed ${duplicatesRemoved} duplicate files, kept ${deduplicatedFiles.length} unique cases`
+    );
+  }
+  deduplicatedFiles.sort((a, b) => b.file_size - a.file_size);
   const result = {
-    files,
+    files: deduplicatedFiles,
     filesTotal: re.data.pagination.total,
     maxTotalSizeCompressed,
     fileCounts: {
@@ -128,6 +172,13 @@ async function listMafFiles(q, ds) {
     appliedFilters: {
       fileTypes: shouldRetrieveMaf ? ["MAF"] : [],
       experimentalStrategy
+    },
+    deduplicationStats: {
+      originalFileCount: files.length,
+      deduplicatedFileCount: deduplicatedFiles.length,
+      duplicatesRemoved,
+      caseDetails,
+      filteredFiles
     }
   };
   return result;

package/routes/{gdcGRIN2run.js → gdc.grin2.run.js}

@@ -26,13 +26,14 @@ function init({ genomes }) {
       const ds = g.datasets.GDC;
       if (!ds)
         throw "hg38 GDC missing";
-      const caseFiles = req.query;
-      console.log(`[GRIN2] Request received: ${JSON.stringify(caseFiles)}`);
-      if (!caseFiles) {
-        throw "Missing or invalid cases data";
-      }
+      console.log(`[GRIN2] Request received:`, JSON.stringify(req.query));
+      const parsedRequest = req.query;
+      console.log(`[GRIN2] Parsed request: ${JSON.stringify(parsedRequest)}`);
       console.log("[GRIN2] Calling Rust for file processing...");
-      const rustInput = JSON.stringify(caseFiles);
+      const rustInput = JSON.stringify({
+        caseFiles: parsedRequest.caseFiles,
+        mafOptions: parsedRequest.mafOptions
+      });
       console.log("[GRIN2] Executing Rust function...");
       const rustResult = await run_rust("gdcGRIN2", rustInput);
       console.log("[GRIN2] Rust execution completed");
@@ -40,11 +41,23 @@ function init({ genomes }) {
         throw new Error("Failed to process MAF files: No result from Rust");
       }
       let parsedRustResult;
+      let dataForR = [];
       try {
         parsedRustResult = typeof rustResult === "string" ? JSON.parse(rustResult) : rustResult;
-        console.log(`[GRIN2] Parsed Rust result: ${JSON.stringify(parsedRustResult).substring(0, 200)}...`);
+        console.log(`[GRIN2] Parsed Rust result structure received`);
+        if (parsedRustResult.successful_data && Array.isArray(parsedRustResult.successful_data)) {
+          dataForR = parsedRustResult.successful_data.flat();
+          console.log(`[GRIN2] Extracted ${dataForR.length} records for R script`);
+          console.log(
+            `[GRIN2] Success: ${parsedRustResult.summary.successful_files}, Failed: ${parsedRustResult.summary.failed_files}`
+          );
+        } else {
+          console.warn("[GRIN2] Unexpected Rust result format");
+          dataForR = [];
+        }
       } catch (parseError) {
         console.error("[GRIN2] Error parsing Rust result:", parseError);
+        dataForR = [];
       }
       const genedbfile = path.join(serverconfig.tpmasterdir, g.genedb.dbfile);
       const imagefile = path.join(serverconfig.cachedir, `grin2_${Date.now()}_${Math.floor(Math.random() * 1e9)}.png`);
@@ -52,7 +65,7 @@ function init({ genomes }) {
         genedb: genedbfile,
         chromosomelist: g.majorchr,
         imagefile,
-        lesion: rustResult
+        lesion: dataForR
         // The mutation string from Rust
       });
       console.log(`R input: ${rInput}`);
@@ -64,7 +77,8 @@ function init({ genomes }) {
         resultData = JSON.parse(rResult);
         console.log("[GRIN2] Finished R analysis");
         const pngImg = resultData.png[0];
-        return res.json({ pngImg });
+        const topGeneTable = resultData.topGeneTable || null;
+        return res.json({ pngImg, topGeneTable, rustResult: parsedRustResult, status: "success" });
       } catch (parseError) {
         console.error("[GRIN2] Error parsing R result:", parseError);
         console.log("[GRIN2] Raw R result:", rResult);