@datagrok-libraries/bio 0.0.2

package/.eslintrc.json

@@ -0,0 +1,29 @@
+{
+	"env": {
+		"browser": true,
+		"es2021": true
+	},
+	"extends": [
+		"google"
+	],
+	"parserOptions": {
+		"ecmaVersion": 12,
+		"sourceType": "module"
+	},
+	"rules": {
+		"indent": [
+			"error",
+			2
+		],
+		"max-len": [
+			"error",
+			120
+		],
+		"require-jsdoc": "off",
+		"spaced-comment": "off"
+	},
+	"parser": "@typescript-eslint/parser",
+	"plugins": [
+		"@typescript-eslint"
+	]
+}

package/README.md

@@ -0,0 +1,3 @@
+# bio
+
+bio is a [package](https://datagrok.ai/help/develop/develop#packages) for the [Datagrok](https://datagrok.ai) platform.

package/detectors.js

@@ -0,0 +1,9 @@
+/**
+ * The class contains semantic type detectors.
+ * Detectors are functions tagged with `DG.FUNC_TYPES.SEM_TYPE_DETECTOR`.
+ * See also: https://datagrok.ai/help/develop/how-to/define-semantic-type-detectors
+ * The class name is comprised of <PackageName> and the `PackageDetectors` suffix.
+ * Follow this naming convention to ensure that your detectors are properly loaded.
+ */
+class BioPackageDetectors extends DG.Package {
+}

package/package.json

@@ -0,0 +1,42 @@
+{
+  "name": "@datagrok-libraries/bio",
+  "publishConfig": {
+    "access": "public"
+  },
+  "beta": true,
+  "friendlyName": "Datagrok bio library",
+  "version": "0.0.2",
+  "description": "",
+  "dependencies": {
+    "datagrok-api": ">=0.95.8",
+    "@datagrok-libraries/utils": ">=0.0.13",
+    "cash-dom": "latest",
+    "dayjs": "latest"
+  },
+  "devDependencies": {
+    "typescript": "^4.2.3",
+    "ts-loader": "^9.2.6",
+    "webpack": "latest",
+    "webpack-cli": "latest",
+    "@typescript-eslint/eslint-plugin": "^4.29.1",
+    "@typescript-eslint/parser": "^4.29.1",
+    "eslint": "^7.32.0",
+    "eslint-config-google": "^0.14.0"
+  },
+  "scripts": {
+    "link": "npm link",
+    "link-api": "npm link datagrok-api",
+    "link-utils": "npm link @datagrok-libraries/utils",
+    "link-all": "npm link datagrok-api @datagrok-libraries/utils",
+    "debug-bio": "grok publish --rebuild",
+    "release-bio": "grok publish --rebuild --release",
+    "build-bio": "webpack",
+    "build": "webpack",
+    "debug-bio-public": "grok publish public --rebuild",
+    "release-bio-public": "grok publish public --rebuild --release",
+    "debug-bio-local": "grok publish local --rebuild",
+    "release-bio-local": "grok publish local --rebuild --release",
+    "lint": "eslint src --ext .ts",
+    "lint-fix": "eslint src --ext .ts --fix"
+  }
+}

package/src/sequence-encoder.ts

@@ -0,0 +1,177 @@
+import {assert} from '@datagrok-libraries/utils/src/operations';
+
+type SideChainScale = {[name: string]: number};
+type SideChainScaleCollection = {[name: string]: SideChainScale};
+
+class SideChainScales {
+  static scales: SideChainScaleCollection = {
+    // Wimley-White interfacial hydrophobicity scale
+    'WimleyWhite': {
+      '-': 0,
+      'A': 0.17,
+      'C': -0.24,
+      'D': -0.07, // Asp-: 1.23
+      'E': -0.01, // Glu-: 2.02
+      'F': -1.13, //
+      'G': 0.01,
+      'H': 0.17, // His+: 0.96
+      'I': -0.31,
+      'K': 0.99, // Lys+
+      'L': -0.56,
+      'M': -0.23,
+      'N': 0.42,
+      'P': 0.45,
+      'Q': 0.58,
+      'R': 0.81, // Arg+
+      'S': 0.13,
+      'T': 0.14,
+      'V': 0.07,
+      'W': -1.85,
+      'Y': -0.94,
+    },
+    'categorial': {
+      '-': 0,
+      'A': 1,
+      'C': 2,
+      'D': 3,
+      'E': 4,
+      'F': 5,
+      'G': 6,
+      'H': 7,
+      'I': 8,
+      'K': 9,
+      'L': 10,
+      'M': 11,
+      'N': 12,
+      'P': 13,
+      'Q': 14,
+      'R': 15,
+      'S': 16,
+      'T': 17,
+      'V': 18,
+      'W': 19,
+      'Y': 20,
+    },
+  };
+
+  static getAvailableScales(): string[] {
+    return Object.entries(this.scales).map(([k, _]) => k);
+  }
+
+  static getScale(name: string): SideChainScale {
+    assert(!(this.scales[name] === undefined), `Scale '${name}' was not found.`);
+    return this.scales[name];
+  }
+}
+
+/**
+ * Class to categorial encode/decode aligned amino acid residues sequence.
+ *
+ * @export
+ * @class AlignedSequenceEncoder
+ */
+export class AlignedSequenceEncoder {
+  protected aa2num: SideChainScale;
+  protected num2aa: {[code: number]: string};
+
+  constructor(scale: string = 'categorial') {
+    this.aa2num = SideChainScales.getScale(scale);
+    this.num2aa = {};
+    Object.entries(this.aa2num).forEach(([k, v]) => (this.num2aa[v] = k));
+  }
+
+  /**
+     * Truncate NH2 and -COOH terminals of the given sequence.
+     *
+     * @static
+     * @param {string} seq The sequence provided.
+     * @return {string} Truncated sequence.
+     * @memberof AlignedSequenceEncoder
+     */
+  static _truncateSequence(seq: string): string {
+    let start = 0;
+    let end = seq.length;
+    const termina = ['NH2', 'COOH'];
+
+    if (seq.startsWith(termina[0])) {
+      const l = termina[0].length; // Cut only 'NH2' without following '-'.
+      assert(seq[l] == '-', `Wrong sequence format: ${termina[0]} without following '-' in '${seq}'.`);
+      start = l;
+    }
+    if (seq.endsWith(termina[1])) {
+      const l = termina[1].length+1; // Cut both 'COOH' and precending '-'.
+      assert(seq[end-l] == '-', `Wrong sequence format: ${termina[1]} without '-' precending in '${seq}'.`);
+      end -= l;
+    }
+    return seq.substring(start, end);
+  }
+
+  /**
+     * Cuts auxiliary defises before a residue.
+     *
+     * @static
+     * @param {string} seq The sequence to process.
+     * @return {string} Processed sequence.
+     * @memberof AlignedSequenceEncoder
+     */
+  static _dropDefises(seq: string): string {
+    return seq.replace(/(-)([^-]+)/g, '$2');
+  }
+
+  /**
+     * Performs truncation and cutting auxiliary defises.
+     *
+     * @static
+     * @param {string} sequence The sequence work under process.
+     * @return {string} Result of cleaning.
+     * @memberof AlignedSequenceEncoder
+     */
+  static clean(sequence: string): string {
+    return AlignedSequenceEncoder._dropDefises(AlignedSequenceEncoder._truncateSequence(sequence));
+  }
+
+  /**
+     * Categorial encode of the sequence provided.
+     *
+     * @param {string} sequence The sequence.
+     * @return {number[]} Encoded vector.
+     * @memberof AlignedSequenceEncoder
+     */
+  public encode(sequence: string): number[] {
+    const nItems = sequence.length;
+    const values = new Array(nItems).fill(0);
+
+    for (let i = 0; i < nItems; ++i) {
+      const char = sequence[i];
+
+      assert(char in this.aa2num, `Unknown char '${char}' found in sequence '${sequence}'`);
+
+      values[i] = this.encodeLettter(char);
+    }
+    return values;
+  }
+
+  public encodeLettter(letter: string): number {
+    return this.aa2num[letter];
+  }
+
+  /**
+     * Decode the encoded vector into the sequence back.
+     *
+     * @param {number[]} value The vector encoded.
+     * @return {string} Decoded sequence.
+     * @memberof AlignedSequenceEncoder
+     */
+  public decode(value: number[]): string {
+    let s: string = '';
+
+    for (let i = 0; i < value.length; ++i) {
+      const code = value[i];
+
+      assert(code in this.num2aa, `Unknown code '${code}' found in vector '${value}'`);
+
+      s += this.num2aa[code];
+    }
+    return s;
+  }
+}

package/tsconfig.json

@@ -0,0 +1,71 @@
+{
+  "compilerOptions": {
+    /* Visit https://aka.ms/tsconfig.json to read more about this file */
+
+    /* Basic Options */
+    // "incremental": true,                         /* Enable incremental compilation */
+    "target": "es2018",                                /* 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": ["es2020", "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": false,                          /* Skip type checking of declaration files. */
+    "forceConsistentCasingInFileNames": true        /* Disallow inconsistently-cased references to the same file. */
+  }
+}