clusterSam/index.js

"use strict";
var __awaiter = (this && this.__awaiter) || function (thisArg, _arguments, P, generator) {
    function adopt(value) { return value instanceof P ? value : new P(function (resolve) { resolve(value); }); }
    return new (P || (P = Promise))(function (resolve, reject) {
        function fulfilled(value) { try { step(generator.next(value)); } catch (e) { reject(e); } }
        function rejected(value) { try { step(generator["throw"](value)); } catch (e) { reject(e); } }
        function step(result) { result.done ? resolve(result.value) : adopt(result.value).then(fulfilled, rejected); }
        step((generator = generator.apply(thisArg, _arguments || [])).next());
    });
};
Object.defineProperty(exports, "__esModule", { value: true });
exports.clusterSam = void 0;
const child_process_1 = require("child_process");
/* (c) Thomas Steimlé 2022
 * cat bwa_mem_splitters_on_HG38_Viral.sam | awk '$0~/^@/{next}{lxa=split($0,xa,"XA:Z:"); print $1"\t"$3"\t"$4; if(lxa>1){split(xa[2],xap,","); print $1"\t"xap[1]"\t"substr(xap[2],2)"\tXA"}}' | more
 * require os : cat, awk, sort, uniq
 *
 */
const async_exec = (prog, args, onData, onErr) => {
    return new Promise((resolve, reject) => {
        const child = (0, child_process_1.spawn)(prog, args, { shell: true });
        child.stdout.on('data', data => onData(data /*.toString().trim()*/));
        child.stderr.on('data', data => onErr(data.toString().trim()));
        child.on('error', err => reject(err));
        child.on('exit', code => resolve(code));
    });
};
const clusterSam = (input_sam, threshold, minReads, blackList) => {
    return new Promise((resolve, _reject) => __awaiter(void 0, void 0, void 0, function* () {
        let inputSam = Array.isArray(input_sam) ? input_sam.join(' ') : input_sam;
        let lineAcc = '';
        let byContigs = {};
        yield async_exec('cat', [
            inputSam,
            '|',
            'awk', '\'$0~/^@/{next}{lxa=split($0,xa,"XA:Z:"); print $1"\t"$3"\t"$4; if(lxa>1){split(xa[2],xap,","); print $1"\t"xap[1]"\t"substr(xap[2],2)"\tXA"}}\'',
            '|',
            'sort',
            '|',
            'uniq'
        ], (m) => {
            let tmpSeq = (lineAcc + m).split(/\n/);
            lineAcc = tmpSeq.pop(); // 'uck typescript
            tmpSeq.map(e => {
                let tmpName = '';
                let tmpPos = { rname: '', position: 0 };
                e.split(/\t/).map((el, i) => {
                    switch (i) {
                        case 0:
                            tmpPos['rname'] = el;
                            break;
                        case 1:
                            tmpName = el;
                            break;
                        case 2:
                            tmpPos['position'] = Number(el);
                            break;
                        default:
                            break;
                    }
                });
                let add = true;
                if (blackList) {
                    add = blackList.includes(tmpName) ? false : true;
                }
                if (add) {
                    if (Array.isArray(byContigs[tmpName])) {
                        byContigs[tmpName].push(tmpPos);
                    }
                    else {
                        byContigs[tmpName] = [tmpPos];
                    }
                }
            });
        }, console.log);
        let byReads = {};
        let posAll = {};
        Object
            .keys(byContigs)
            .map(name => {
            let cluster = 0;
            let firstPos = 0;
            byContigs[name]
                .sort((a, b) => a.position - b.position)
                .map((e, i, a) => {
                var _a, _b;
                if (i === 0) {
                    if (typeof posAll[name] === 'undefined')
                        posAll[name] = {};
                    firstPos = e.position;
                }
                if (a.length === 1) {
                    posAll[name][String(cluster)] = String(firstPos);
                }
                if (Math.abs(e.position - ((_a = a[i - 1]) === null || _a === void 0 ? void 0 : _a.position)) > threshold) {
                    posAll[name][String(cluster)] = firstPos + '-' + ((_b = a[i - 1]) === null || _b === void 0 ? void 0 : _b.position);
                    cluster = cluster + 1;
                    firstPos = e.position;
                }
                // cluster = Math.abs(e.position - a[i-1]?.position) > threshold ? cluster + 1 : cluster
                const clutserName = cluster + '@' + name;
                byReads[e.rname] = Array.isArray(byReads[e.rname]) ? [...new Set([...byReads[e.rname], clutserName])] : [clutserName];
            });
        });
        let byClusters = {};
        Object.keys(byReads).map(rname => {
            const tmpClusterName = byReads[rname].sort().map(e => {
                const splited = e.split(/@/);
                return splited[1] + ':' + posAll[splited[1]][splited[0]] + '(' + splited[0] + ')';
            }).join('<--->');
            byClusters[tmpClusterName] = Array.isArray(byClusters[tmpClusterName]) ? [...new Set([...byClusters[tmpClusterName], rname])] : [rname];
        });
        Object.keys(byClusters).map(e => byClusters[e].length < minReads ? delete byClusters[e] : null);
        resolve((Object.keys(byClusters).map(clusterName => ({ clusterName, rnames: byClusters[clusterName] })).sort((a, b) => b.rnames.length - a.rnames.length)));
    }));
};
exports.clusterSam = clusterSam;
/*
(async () => {
    console.log(await clusterSam('/home/thomas/Documents/Programmes/ttest/bwa_mem_splitters_on_HG38_Viral.sam', 333, 55,
    ['NR_145819.1', 'NR_145822.1']));
})()
*/