@datagrok/proteomics 1.0.0 → 1.2.0

package/tools/spectronaut-aggregate.sql

@@ -0,0 +1,80 @@
+-- Aggregate a long-form Spectronaut Report (peptide/precursor/fragment-level rows)
+-- down to one row per (protein-group × condition × replicate), in the shape
+-- packages/Proteomics/src/parsers/spectronaut-parser.ts expects.
+--
+-- This is the bundled, documented manual fallback (D-05) for a Spectronaut report
+-- too large for the in-browser streaming importer, AND the D-04 equivalence oracle
+-- the Wave-0 golden test pins to.
+--
+-- Template tokens __IN_PATH__ and __OUT_PATH__ are replaced by the shell wrapper
+-- before this script is passed to duckdb. (DuckDB's COPY ... TO does not accept
+-- variables, so we can't use SET VARIABLE here.)
+
+-- Streaming aggregation — duckdb spills to disk if it can't fit memory.
+PRAGMA memory_limit='8GB';
+PRAGMA threads=8;
+
+COPY (
+  SELECT
+    "PG.ProteinGroups",
+    -- DIVERGENCE FROM /tmp/spectronaut-aggregate.sql: the two carry-along
+    -- any_value() SELECT terms for the gene-symbol and protein-accession columns
+    -- (present in the /tmp original) were DROPPED here. The package's Spectronaut
+    -- data (files/demo/spectronaut-hye-mix.tsv and the synthetic precursor
+    -- fixture) does not carry those two columns and
+    -- pivotSpectronaut/aggToPivotResult never consume them, so they are not part
+    -- of the parity contract; keeping them would Binder-Error duckdb on the
+    -- fixture (ignore_errors does NOT cover Binder Errors) and the entire Wave-0
+    -- oracle chain (golden → sidecar → 12-03 golden test) would have no source.
+    --
+    -- ============================ WARNING ============================
+    -- REFERENCE-FILE-ONLY: the CASE below is a one-off correction for the
+    -- mislabeled reference file `2026-05-13 BP DMD WT.tsv` ONLY. Cross-tab
+    -- against R.FileName showed every WT* filename tagged DMD and every DMD*
+    -- filename tagged WT (24/24); this restores the convention so DE direction
+    -- matches what the filenames imply. It is a STRUCTURAL NO-OP on any data
+    -- whose R.Condition is not literally 'DMD'/'WT' — including the CondA/CondB
+    -- synthetic fixture, which is exactly why this same script doubles as the
+    -- D-04 golden oracle without perturbing the golden. The streaming TS
+    -- aggregator MUST NOT port this flip (RESEARCH Pitfall 1 — the single
+    -- highest-risk parity trap). Do not "generalize" or remove it either: the
+    -- manual-fallback path still needs it for the mislabeled reference file.
+    -- =================================================================
+    CASE "R.Condition"
+      WHEN 'DMD' THEN 'WT'
+      WHEN 'WT'  THEN 'DMD'
+      ELSE "R.Condition"
+    END                              AS "R.Condition",
+    "R.Replicate",
+    any_value("R.FileName")          AS "R.FileName",
+    -- PG.Quantity is constant per (protein-group, run) in Spectronaut output;
+    -- max() collapses the precursor-level duplicates safely.
+    max(TRY_CAST("PG.Quantity" AS DOUBLE)) AS "PG.Quantity",
+    -- Best precursor q-value backing this protein in this run.
+    min(TRY_CAST("EG.Qvalue" AS DOUBLE))   AS "EG.Qvalue"
+  FROM read_csv(
+    '__IN_PATH__',
+    delim='\t',
+    header=true,
+    sample_size=-1,           -- scan everything for type inference; columns are messy
+    ignore_errors=true,       -- tolerate stray malformed lines in a 2.6 GB file
+    nullstr=['', 'NaN', 'NA']
+  )
+  WHERE
+    -- Mirror the parser's precursor-level filter: drop EG rows with q-value > 0.01.
+    -- Non-numeric q-values (e.g. 'Profiled') pass — same as the TS parser.
+    (TRY_CAST("EG.Qvalue" AS DOUBLE) IS NULL OR TRY_CAST("EG.Qvalue" AS DOUBLE) <= 0.01)
+    -- Drop decoys / contaminants up front; parser does this too but it's cheaper here.
+    AND "PG.ProteinGroups" IS NOT NULL
+    AND "PG.ProteinGroups" NOT LIKE 'CON\_\_%' ESCAPE '\'
+    AND "PG.ProteinGroups" NOT LIKE 'REV\_\_%' ESCAPE '\'
+  GROUP BY "PG.ProteinGroups", "R.Condition", "R.Replicate"
+) TO '__OUT_PATH__' (FORMAT csv, DELIMITER '\t', HEADER);
+
+-- Summary so we can sanity-check the collapse ratio.
+SELECT
+  count(*)                                          AS output_rows,
+  count(DISTINCT "PG.ProteinGroups")                AS proteins,
+  count(DISTINCT ("R.Condition" || '_' || "R.Replicate")) AS samples,
+  list(DISTINCT "R.Condition")                      AS conditions
+FROM read_csv('__OUT_PATH__', delim='\t', header=true);

package/tsconfig.json

@@ -1,71 +1,18 @@
-{
-  "compilerOptions": {
-    /* Visit https://aka.ms/tsconfig.json to read more about this file */
-
-    /* Basic Options */
-    // "incremental": true,                         /* Enable incremental compilation */
-    "target": "es6",                                /* Specify ECMAScript target version: 'ES3' (default), 'ES5', 'ES2015', 'ES2016', 'ES2017', 'ES2018', 'ES2019', 'ES2020', or 'ESNEXT'. */
-    "module": "es2020",                             /* Specify module code generation: 'none', 'commonjs', 'amd', 'system', 'umd', 'es2015', 'es2020', or 'ESNext'. */
-    "lib": ["ES2022", "dom"],                       /* Specify library files to be included in the compilation. */
-    // "allowJs": true,                             /* Allow javascript files to be compiled. */
-    // "checkJs": true,                             /* Report errors in .js files. */
-    // "jsx": "preserve",                           /* Specify JSX code generation: 'preserve', 'react-native', 'react', 'react-jsx' or 'react-jsxdev'. */
-    // "declaration": true,                         /* Generates corresponding '.d.ts' file. */
-    // "declarationMap": true,                      /* Generates a sourcemap for each corresponding '.d.ts' file. */
-    "sourceMap": true,                              /* Generates corresponding '.map' file. */
-    // "outFile": "./",                             /* Concatenate and emit output to single file. */
-    // "outDir": "./",                              /* Redirect output structure to the directory. */
-    // "rootDir": "./",                             /* Specify the root directory of input files. Use to control the output directory structure with --outDir. */
-    // "composite": true,                           /* Enable project compilation */
-    // "tsBuildInfoFile": "./",                     /* Specify file to store incremental compilation information */
-    // "removeComments": true,                      /* Do not emit comments to output. */
-    // "noEmit": true,                              /* Do not emit outputs. */
-    // "importHelpers": true,                       /* Import emit helpers from 'tslib'. */
-    // "downlevelIteration": true,                  /* Provide full support for iterables in 'for-of', spread, and destructuring when targeting 'ES5' or 'ES3'. */
-    // "isolatedModules": true,                     /* Transpile each file as a separate module (similar to 'ts.transpileModule'). */
-
-    /* Strict Type-Checking Options */
-    "strict": true,                                 /* Enable all strict type-checking options. */
-    // "noImplicitAny": true,                       /* Raise error on expressions and declarations with an implied 'any' type. */
-    // "strictNullChecks": true,                    /* Enable strict null checks. */
-    // "strictFunctionTypes": true,                 /* Enable strict checking of function types. */
-    // "strictBindCallApply": true,                 /* Enable strict 'bind', 'call', and 'apply' methods on functions. */
-    // "strictPropertyInitialization": true,        /* Enable strict checking of property initialization in classes. */
-    // "noImplicitThis": true,                      /* Raise error on 'this' expressions with an implied 'any' type. */
-    // "alwaysStrict": true,                        /* Parse in strict mode and emit "use strict" for each source file. */
-
-    /* Additional Checks */
-    // "noUnusedLocals": true,                      /* Report errors on unused locals. */
-    // "noUnusedParameters": true,                  /* Report errors on unused parameters. */
-    // "noImplicitReturns": true,                   /* Report error when not all code paths in function return a value. */
-    // "noFallthroughCasesInSwitch": true,          /* Report errors for fallthrough cases in switch statement. */
-    // "noUncheckedIndexedAccess": true,            /* Include 'undefined' in index signature results */
-    // "noPropertyAccessFromIndexSignature": true,  /* Require undeclared properties from index signatures to use element accesses. */
-
-    /* Module Resolution Options */
-    "moduleResolution": "node",                     /* Specify module resolution strategy: 'node' (Node.js) or 'classic' (TypeScript pre-1.6). */
-    // "baseUrl": "./",                             /* Base directory to resolve non-absolute module names. */
-    // "paths": {},                                 /* A series of entries which re-map imports to lookup locations relative to the 'baseUrl'. */
-    // "rootDirs": [],                              /* List of root folders whose combined content represents the structure of the project at runtime. */
-    // "typeRoots": [],                             /* List of folders to include type definitions from. */
-    // "types": [],                                 /* Type declaration files to be included in compilation. */
-    // "allowSyntheticDefaultImports": true,        /* Allow default imports from modules with no default export. This does not affect code emit, just typechecking. */
-    "esModuleInterop": true,                        /* Enables emit interoperability between CommonJS and ES Modules via creation of namespace objects for all imports. Implies 'allowSyntheticDefaultImports'. */
-    // "preserveSymlinks": true,                    /* Do not resolve the real path of symlinks. */
-    // "allowUmdGlobalAccess": true,                /* Allow accessing UMD globals from modules. */
-
-    /* Source Map Options */
-    // "sourceRoot": "",                            /* Specify the location where debugger should locate TypeScript files instead of source locations. */
-    // "mapRoot": "",                               /* Specify the location where debugger should locate map files instead of generated locations. */
-    // "inlineSourceMap": true,                     /* Emit a single file with source maps instead of having a separate file. */
-    // "inlineSources": true,                       /* Emit the source alongside the sourcemaps within a single file; requires '--inlineSourceMap' or '--sourceMap' to be set. */
-
-    /* Experimental Options */
-    "experimentalDecorators": true,                 /* Enables experimental support for ES7 decorators. */
-    "emitDecoratorMetadata": true,                  /* Enables experimental support for emitting type metadata for decorators. */
-
-    /* Advanced Options */
-    "skipLibCheck": true,                          /* Skip type checking of declaration files. */
-    "forceConsistentCasingInFileNames": true,        /* Disallow inconsistently-cased references to the same file. */
-  }
-}
+{
+  "compilerOptions": {
+    "target": "ES2022",
+    "module": "ES2022",
+    "lib": ["ES2022", "dom"],
+    "sourceMap": true,
+    "strict": true,
+    "strictPropertyInitialization": false,
+    "moduleResolution": "node",
+    "esModuleInterop": true,
+    "sourceRoot": "",
+    "mapRoot": "",
+    "experimentalDecorators": true,
+    "emitDecoratorMetadata": true,
+    "skipLibCheck": true,
+    "forceConsistentCasingInFileNames": true
+  }
+}

package/webpack.config.js

@@ -1,45 +1,86 @@
-const path = require('path');
-const FuncGeneratorPlugin = require('datagrok-tools/plugins/func-gen-plugin');
-const packageName = path.parse(require('./package.json').name).name.toLowerCase().replace(/-/g, '');
-
-module.exports = {
-  cache: {
-    type: 'filesystem',
-  },
-  mode: 'development',
-  entry: {
-    test: {filename: 'package-test.js', library: {type: 'var', name: `${packageName}_test`}, import: './src/package-test.ts'},
-    package: './src/package.ts',
-  },
-  resolve: {
-    extensions: ['.wasm', '.mjs', '.ts', '.json', '.js', '.tsx'],
-  },
-  module: {
-    rules: [
-      {test: /\.tsx?$/, loader: 'ts-loader', options: {allowTsInNodeModules: true}},
-    ],
-  },
-  plugins: [
-    new FuncGeneratorPlugin({outputPath: './src/package.g.ts'}),
-  ],
-  devtool: 'source-map',
-  externals: {
-    'datagrok-api/dg': 'DG',
-    'datagrok-api/grok': 'grok',
-    'datagrok-api/ui': 'ui',
-    'openchemlib/full.js': 'OCL',
-    'rxjs': 'rxjs',
-    'rxjs/operators': 'rxjs.operators',
-    'cash-dom': '$',
-    'dayjs': 'dayjs',
-    'wu': 'wu',
-    'exceljs': 'ExcelJS',
-    'html2canvas': 'html2canvas',
-  },
-  output: {
-    filename: '[name].js',
-    library: packageName,
-    libraryTarget: 'var',
-    path: path.resolve(__dirname, 'dist'),
-  },
-};
+const path = require('path');
+const {execSync} = require('child_process');
+const packageName = path.parse(require('./package.json').name).name.toLowerCase().replace(/-/g, '');
+
+function getDatagrokTools() {
+  const pluginPath = 'datagrok-tools/plugins/func-gen-plugin';
+  try {
+    return require(pluginPath);
+  } catch (e) {
+    try {
+      const globalPath = execSync('npm root -g').toString().trim();
+      return require(path.join(globalPath, pluginPath));
+    } catch (globalErr) {
+      console.error('\n' + '='.repeat(60));
+      console.error('ERROR: datagrok-tools not found!');
+      console.error('To fix this, please install the tools globally by running:');
+      console.error('\n    npm install -g datagrok-tools\n');
+      console.error('='.repeat(60) + '\n');
+      process.exit(1);
+    }
+  }
+}
+
+const FuncGeneratorPlugin = getDatagrokTools();
+
+module.exports = {
+  cache: {
+    type: 'filesystem',
+  },
+  mode: 'production',
+  entry: {
+    package: ['./src/package.ts'],
+    test: {
+      filename: 'package-test.js',
+      library: {type: 'var', name: `${packageName}_test`},
+      import: './src/package-test.ts',
+    },
+  },
+  devServer: {
+    contentBase: './dist',
+  },
+  target: 'web',
+  module: {
+    rules: [
+      {
+        test: /\.ts?$/,
+        use: 'ts-loader',
+        exclude: /node_modules/,
+      },
+      {
+        test: /\.css$/i,
+        use: ['style-loader', 'css-loader'],
+      },
+      {
+        // Plan 12-03 R5 drift guard: the test bundle statically imports the
+        // committed tools/spectronaut-aggregate.{sql,sh} as raw strings so a
+        // deletion / rename / content change fails the build + grok test (the
+        // tools/ dir is not deployed under files/, so it is unreachable via
+        // _package.files at runtime — webpack asset/source is the only way to
+        // pin the committed fallback content into the test).
+        test: /\.(sql|sh)$/i,
+        type: 'asset/source',
+      },
+    ],
+  },
+  resolve: {
+    extensions: ['.mjs', '.ts', '.js', '.json', '.tsx'],
+  },
+  devtool: 'source-map',
+  externals: {
+    'datagrok-api/dg': 'DG',
+    'datagrok-api/grok': 'grok',
+    'datagrok-api/ui': 'ui',
+    'rxjs': 'rxjs',
+    'rxjs/operators': 'rxjs.operators',
+  },
+  output: {
+    filename: '[name].js',
+    library: 'proteomics',
+    libraryTarget: 'var',
+    path: path.resolve(__dirname, 'dist'),
+  },
+  plugins: [
+    new FuncGeneratorPlugin({outputPath: './src/package.g.ts'}),
+  ],
+};

package/.eslintignore

@@ -1 +0,0 @@
-src/**/*.d.ts*

package/.eslintrc.json

@@ -1,56 +0,0 @@
-{
-  "env": {
-    "browser": true,
-    "es2022": true
-  },
-  "extends": [
-    "google"
-  ],
-  "parser": "@typescript-eslint/parser",
-  "parserOptions": {
-    "ecmaVersion": 2022,
-    "project": "./tsconfig.json",
-    "sourceType": "module"
-  },
-  "plugins": [
-    "@typescript-eslint"
-  ],
-  "rules": {
-    "indent": [
-      "error", 2, {
-        "SwitchCase": 0
-      }
-    ],
-    "max-len": ["error", 120],
-    "no-unused-vars": "off",
-    "@typescript-eslint/no-unused-vars": [
-      "warn", {
-        "varsIgnorePattern": "^(_|ui$|grok$|DG$)",
-        "argsIgnorePattern": "^_"
-      }
-    ],
-    "require-jsdoc": "off",
-    "valid-jsdoc": "warn",
-    "spaced-comment": "off",
-    "linebreak-style": "off",
-    "curly": [
-      "error",
-      "multi-or-nest"
-    ],
-    "brace-style": [
-      "error", "1tbs", {
-        "allowSingleLine": true
-      }
-    ],
-    "block-spacing": [2, "always"],
-    "comma-dangle": [
-      "error", {
-        "arrays": "only-multiline",
-        "functions": "only-multiline",
-        "objects": "only-multiline",
-        "imports": "only-multiline"
-      }
-    ],
-    "guard-for-in": "off"
-  }
-}