Last active
August 30, 2024 17:47
-
-
Save cmdcolin/3f2d4c205c06445507aa5995fbce5bd8 to your computer and use it in GitHub Desktop.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| // usage: | |
| // download this file to a file unprepare_seqs.js | |
| // then run: | |
| // node unprepare_seqs.js /path/to/seq/dir output_file.fa | |
| // after that, fold the lines to a constant line length with: | |
| // fold output_file.fa > output_file2.fa | |
| const fs = require('fs') | |
| const path = require('path') | |
| const dir = process.argv[2] || '.' | |
| const output = process.argv[3] || 'out.fa' | |
| const obj = {} | |
| fs.readdirSync(dir, { recursive: true }).forEach(d => { | |
| const ret = d.lastIndexOf('/') | |
| if (d.indexOf('-') !== -1) { | |
| const [chr] = d.slice(ret + 1).split('-') | |
| if (!obj[chr]) { | |
| obj[chr] = [] | |
| } | |
| obj[chr].push(d) | |
| } | |
| }) | |
| let ret = '' | |
| Object.entries(obj).forEach(([chr, files]) => { | |
| let arg = '' | |
| for (const file of files) { | |
| arg += fs.readFileSync(path.join(dir, file), 'utf8') | |
| } | |
| ret += `>${chr}\n${arg}\n` | |
| }) | |
| fs.writeFileSync(output, ret) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment