@kent-tokyo/chematic 0.1.3

package/README.md

@@ -0,0 +1,39 @@
+# chematic-wasm
+
+WebAssembly bindings for [chematic](https://github.com/kent-tokyo/chematic), a pure-Rust cheminformatics library.
+
+This crate exposes `#[wasm_bindgen]` bindings so that chematic can be used directly from JavaScript and TypeScript in the browser or Node.js.
+
+## Features
+
+- Parse SMILES strings into molecule handles
+- Compute molecular descriptors: molecular weight, TPSA, formula, heavy atom count, H-bond donors/acceptors
+- Lipinski Rule-of-Five check
+- Canonical SMILES generation
+- ECFP4 fingerprints and Tanimoto similarity
+
+## Usage
+
+Build with [wasm-pack](https://rustwasm.github.io/wasm-pack/):
+
+```sh
+wasm-pack build --target web
+```
+
+Then in JavaScript/TypeScript:
+
+```js
+import init, { parse_smiles, tanimoto_ecfp4 } from './pkg/chematic_wasm.js';
+
+await init();
+
+const mol = parse_smiles('c1ccccc1');
+console.log(mol.atom_count());       // 6
+console.log(mol.molecular_weight()); // ~78.11
+console.log(mol.formula());          // "C6H6"
+console.log(mol.lipinski_passes());  // true
+
+const aspirin = parse_smiles('CC(=O)Oc1ccccc1C(=O)O');
+const sim = tanimoto_ecfp4(mol, aspirin);
+console.log(sim); // < 1.0
+```

package/chematic_wasm.d.ts

@@ -0,0 +1,69 @@
+/* tslint:disable */
+/* eslint-disable */
+
+/**
+ * A handle to a parsed molecule.  Owns the molecule behind an `Rc` so that
+ * it can be cheaply cloned on the JS side without copying atom/bond data.
+ */
+export class MolHandle {
+    private constructor();
+    free(): void;
+    [Symbol.dispose](): void;
+    /**
+     * Number of heavy atoms (explicit atoms in the graph; does not count implicit H).
+     */
+    atom_count(): number;
+    /**
+     * Number of bonds.
+     */
+    bond_count(): number;
+    /**
+     * Canonical SMILES string.
+     */
+    canonical_smiles(): string;
+    /**
+     * Molecular formula string (Hill notation: C first, H second, then alphabetical).
+     */
+    formula(): string;
+    /**
+     * Number of hydrogen bond acceptors (Lipinski: all N and O atoms).
+     */
+    hba_count(): number;
+    /**
+     * Number of hydrogen bond donors (N-H or O-H groups).
+     */
+    hbd_count(): number;
+    /**
+     * Number of non-hydrogen heavy atoms.
+     */
+    heavy_atom_count(): number;
+    /**
+     * Returns `true` if the molecule satisfies Lipinski's Rule of Five.
+     */
+    lipinski_passes(): boolean;
+    /**
+     * Average molecular weight (Da).
+     */
+    molecular_weight(): number;
+    /**
+     * Topological polar surface area (Ų).
+     */
+    tpsa(): number;
+}
+
+/**
+ * Compute the ECFP4 fingerprint as a bit-packed byte vector (256 bytes = 2048 bits).
+ */
+export function ecfp4_bitvec(mol: MolHandle): Uint8Array;
+
+/**
+ * Parse a SMILES string into a `MolHandle`.
+ *
+ * Returns a JS error string on parse failure.
+ */
+export function parse_smiles(s: string): MolHandle;
+
+/**
+ * Tanimoto similarity between two molecules using ECFP4 fingerprints.
+ */
+export function tanimoto_ecfp4(a: MolHandle, b: MolHandle): number;

package/chematic_wasm.js

@@ -0,0 +1,9 @@
+/* @ts-self-types="./chematic_wasm.d.ts" */
+import * as wasm from "./chematic_wasm_bg.wasm";
+import { __wbg_set_wasm } from "./chematic_wasm_bg.js";
+
+__wbg_set_wasm(wasm);
+wasm.__wbindgen_start();
+export {
+    MolHandle, ecfp4_bitvec, parse_smiles, tanimoto_ecfp4
+} from "./chematic_wasm_bg.js";

package/chematic_wasm_bg.js

@@ -0,0 +1,283 @@
+/**
+ * A handle to a parsed molecule.  Owns the molecule behind an `Rc` so that
+ * it can be cheaply cloned on the JS side without copying atom/bond data.
+ */
+export class MolHandle {
+    static __wrap(ptr) {
+        const obj = Object.create(MolHandle.prototype);
+        obj.__wbg_ptr = ptr;
+        MolHandleFinalization.register(obj, obj.__wbg_ptr, obj);
+        return obj;
+    }
+    __destroy_into_raw() {
+        const ptr = this.__wbg_ptr;
+        this.__wbg_ptr = 0;
+        MolHandleFinalization.unregister(this);
+        return ptr;
+    }
+    free() {
+        const ptr = this.__destroy_into_raw();
+        wasm.__wbg_molhandle_free(ptr, 0);
+    }
+    /**
+     * Number of heavy atoms (explicit atoms in the graph; does not count implicit H).
+     * @returns {number}
+     */
+    atom_count() {
+        const ret = wasm.molhandle_atom_count(this.__wbg_ptr);
+        return ret >>> 0;
+    }
+    /**
+     * Number of bonds.
+     * @returns {number}
+     */
+    bond_count() {
+        const ret = wasm.molhandle_bond_count(this.__wbg_ptr);
+        return ret >>> 0;
+    }
+    /**
+     * Canonical SMILES string.
+     * @returns {string}
+     */
+    canonical_smiles() {
+        let deferred1_0;
+        let deferred1_1;
+        try {
+            const ret = wasm.molhandle_canonical_smiles(this.__wbg_ptr);
+            deferred1_0 = ret[0];
+            deferred1_1 = ret[1];
+            return getStringFromWasm0(ret[0], ret[1]);
+        } finally {
+            wasm.__wbindgen_free(deferred1_0, deferred1_1, 1);
+        }
+    }
+    /**
+     * Molecular formula string (Hill notation: C first, H second, then alphabetical).
+     * @returns {string}
+     */
+    formula() {
+        let deferred1_0;
+        let deferred1_1;
+        try {
+            const ret = wasm.molhandle_formula(this.__wbg_ptr);
+            deferred1_0 = ret[0];
+            deferred1_1 = ret[1];
+            return getStringFromWasm0(ret[0], ret[1]);
+        } finally {
+            wasm.__wbindgen_free(deferred1_0, deferred1_1, 1);
+        }
+    }
+    /**
+     * Number of hydrogen bond acceptors (Lipinski: all N and O atoms).
+     * @returns {number}
+     */
+    hba_count() {
+        const ret = wasm.molhandle_hba_count(this.__wbg_ptr);
+        return ret >>> 0;
+    }
+    /**
+     * Number of hydrogen bond donors (N-H or O-H groups).
+     * @returns {number}
+     */
+    hbd_count() {
+        const ret = wasm.molhandle_hbd_count(this.__wbg_ptr);
+        return ret >>> 0;
+    }
+    /**
+     * Number of non-hydrogen heavy atoms.
+     * @returns {number}
+     */
+    heavy_atom_count() {
+        const ret = wasm.molhandle_heavy_atom_count(this.__wbg_ptr);
+        return ret >>> 0;
+    }
+    /**
+     * Returns `true` if the molecule satisfies Lipinski's Rule of Five.
+     * @returns {boolean}
+     */
+    lipinski_passes() {
+        const ret = wasm.molhandle_lipinski_passes(this.__wbg_ptr);
+        return ret !== 0;
+    }
+    /**
+     * Average molecular weight (Da).
+     * @returns {number}
+     */
+    molecular_weight() {
+        const ret = wasm.molhandle_molecular_weight(this.__wbg_ptr);
+        return ret;
+    }
+    /**
+     * Topological polar surface area (Ų).
+     * @returns {number}
+     */
+    tpsa() {
+        const ret = wasm.molhandle_tpsa(this.__wbg_ptr);
+        return ret;
+    }
+}
+if (Symbol.dispose) MolHandle.prototype[Symbol.dispose] = MolHandle.prototype.free;
+
+/**
+ * Compute the ECFP4 fingerprint as a bit-packed byte vector (256 bytes = 2048 bits).
+ * @param {MolHandle} mol
+ * @returns {Uint8Array}
+ */
+export function ecfp4_bitvec(mol) {
+    _assertClass(mol, MolHandle);
+    const ret = wasm.ecfp4_bitvec(mol.__wbg_ptr);
+    var v1 = getArrayU8FromWasm0(ret[0], ret[1]).slice();
+    wasm.__wbindgen_free(ret[0], ret[1] * 1, 1);
+    return v1;
+}
+
+/**
+ * Parse a SMILES string into a `MolHandle`.
+ *
+ * Returns a JS error string on parse failure.
+ * @param {string} s
+ * @returns {MolHandle}
+ */
+export function parse_smiles(s) {
+    const ptr0 = passStringToWasm0(s, wasm.__wbindgen_malloc, wasm.__wbindgen_realloc);
+    const len0 = WASM_VECTOR_LEN;
+    const ret = wasm.parse_smiles(ptr0, len0);
+    if (ret[2]) {
+        throw takeFromExternrefTable0(ret[1]);
+    }
+    return MolHandle.__wrap(ret[0]);
+}
+
+/**
+ * Tanimoto similarity between two molecules using ECFP4 fingerprints.
+ * @param {MolHandle} a
+ * @param {MolHandle} b
+ * @returns {number}
+ */
+export function tanimoto_ecfp4(a, b) {
+    _assertClass(a, MolHandle);
+    _assertClass(b, MolHandle);
+    const ret = wasm.tanimoto_ecfp4(a.__wbg_ptr, b.__wbg_ptr);
+    return ret;
+}
+export function __wbg___wbindgen_throw_1506f2235d1bdba0(arg0, arg1) {
+    throw new Error(getStringFromWasm0(arg0, arg1));
+}
+export function __wbindgen_cast_0000000000000001(arg0, arg1) {
+    // Cast intrinsic for `Ref(String) -> Externref`.
+    const ret = getStringFromWasm0(arg0, arg1);
+    return ret;
+}
+export function __wbindgen_init_externref_table() {
+    const table = wasm.__wbindgen_externrefs;
+    const offset = table.grow(4);
+    table.set(0, undefined);
+    table.set(offset + 0, undefined);
+    table.set(offset + 1, null);
+    table.set(offset + 2, true);
+    table.set(offset + 3, false);
+}
+const MolHandleFinalization = (typeof FinalizationRegistry === 'undefined')
+    ? { register: () => {}, unregister: () => {} }
+    : new FinalizationRegistry(ptr => wasm.__wbg_molhandle_free(ptr, 1));
+
+function _assertClass(instance, klass) {
+    if (!(instance instanceof klass)) {
+        throw new Error(`expected instance of ${klass.name}`);
+    }
+}
+
+function getArrayU8FromWasm0(ptr, len) {
+    ptr = ptr >>> 0;
+    return getUint8ArrayMemory0().subarray(ptr / 1, ptr / 1 + len);
+}
+
+function getStringFromWasm0(ptr, len) {
+    return decodeText(ptr >>> 0, len);
+}
+
+let cachedUint8ArrayMemory0 = null;
+function getUint8ArrayMemory0() {
+    if (cachedUint8ArrayMemory0 === null || cachedUint8ArrayMemory0.byteLength === 0) {
+        cachedUint8ArrayMemory0 = new Uint8Array(wasm.memory.buffer);
+    }
+    return cachedUint8ArrayMemory0;
+}
+
+function passStringToWasm0(arg, malloc, realloc) {
+    if (realloc === undefined) {
+        const buf = cachedTextEncoder.encode(arg);
+        const ptr = malloc(buf.length, 1) >>> 0;
+        getUint8ArrayMemory0().subarray(ptr, ptr + buf.length).set(buf);
+        WASM_VECTOR_LEN = buf.length;
+        return ptr;
+    }
+
+    let len = arg.length;
+    let ptr = malloc(len, 1) >>> 0;
+
+    const mem = getUint8ArrayMemory0();
+
+    let offset = 0;
+
+    for (; offset < len; offset++) {
+        const code = arg.charCodeAt(offset);
+        if (code > 0x7F) break;
+        mem[ptr + offset] = code;
+    }
+    if (offset !== len) {
+        if (offset !== 0) {
+            arg = arg.slice(offset);
+        }
+        ptr = realloc(ptr, len, len = offset + arg.length * 3, 1) >>> 0;
+        const view = getUint8ArrayMemory0().subarray(ptr + offset, ptr + len);
+        const ret = cachedTextEncoder.encodeInto(arg, view);
+
+        offset += ret.written;
+        ptr = realloc(ptr, len, offset, 1) >>> 0;
+    }
+
+    WASM_VECTOR_LEN = offset;
+    return ptr;
+}
+
+function takeFromExternrefTable0(idx) {
+    const value = wasm.__wbindgen_externrefs.get(idx);
+    wasm.__externref_table_dealloc(idx);
+    return value;
+}
+
+let cachedTextDecoder = new TextDecoder('utf-8', { ignoreBOM: true, fatal: true });
+cachedTextDecoder.decode();
+const MAX_SAFARI_DECODE_BYTES = 2146435072;
+let numBytesDecoded = 0;
+function decodeText(ptr, len) {
+    numBytesDecoded += len;
+    if (numBytesDecoded >= MAX_SAFARI_DECODE_BYTES) {
+        cachedTextDecoder = new TextDecoder('utf-8', { ignoreBOM: true, fatal: true });
+        cachedTextDecoder.decode();
+        numBytesDecoded = len;
+    }
+    return cachedTextDecoder.decode(getUint8ArrayMemory0().subarray(ptr, ptr + len));
+}
+
+const cachedTextEncoder = new TextEncoder();
+
+if (!('encodeInto' in cachedTextEncoder)) {
+    cachedTextEncoder.encodeInto = function (arg, view) {
+        const buf = cachedTextEncoder.encode(arg);
+        view.set(buf);
+        return {
+            read: arg.length,
+            written: buf.length
+        };
+    };
+}
+
+let WASM_VECTOR_LEN = 0;
+
+
+let wasm;
+export function __wbg_set_wasm(val) {
+    wasm = val;
+}

package/package.json

@@ -0,0 +1,36 @@
+{
+  "name": "@kent-tokyo/chematic",
+  "type": "module",
+  "collaborators": [
+    "kent-tokyo <kent-tokyo@users.noreply.github.com>"
+  ],
+  "description": "WebAssembly bindings for chematic — use chematic from JavaScript/TypeScript",
+  "version": "0.1.3",
+  "license": "MIT OR Apache-2.0",
+  "repository": {
+    "type": "git",
+    "url": "https://github.com/kent-tokyo/chematic"
+  },
+  "files": [
+    "chematic_wasm_bg.wasm",
+    "chematic_wasm.js",
+    "chematic_wasm_bg.js",
+    "chematic_wasm.d.ts"
+  ],
+  "main": "chematic_wasm.js",
+  "homepage": "https://github.com/kent-tokyo/chematic",
+  "types": "chematic_wasm.d.ts",
+  "sideEffects": [
+    "./chematic_wasm.js",
+    "./snippets/*"
+  ],
+  "keywords": [
+    "cheminformatics",
+    "chemistry",
+    "smiles",
+    "wasm",
+    "rdkit",
+    "fingerprints",
+    "tanimoto"
+  ]
+}