Profluent Bio applies language models to design gene editors, says Nathan Benaich
nathanbenaich · x · 2026-11-03
At Nathan Benaich's MTS Live conversation on the State of AI Report 2026, he explained that protein sequences can be written as strings of letters, and language models can learn to design them. Air Street Capital portfolio company Profluent Bio is applying this approach to gene editors.
It's a representative AI-for-Science case in biotech: treating protein engineering as a language generation problem to create novel sequences, rather than merely screening natural ones. The full discussion is available via the stateof.ai report.
More from Apps
- Astrocade brings AI no-code game creation to iOS with 1M daily players — _amirabs · 2026-11-03
- LM Studio's Bionic Ships Built-in Terminal Powered by libghostty — mattturck · 2026-11-03
- My Local AI: free iOS app runs local models on-device with MLX, no account needed — TheOyinbooke · 2026-11-03
- Track 100 rejected AI drafts over 30 days to cut revision rounds from 8 to 1 — petesena · 2026-11-03
- X integrates Interactive Brokers: trade stocks and crypto directly from the timeline — RachelVT42 · 2026-11-03
- Sudden user influx crushes Emergent Labs: 100% CPU, 28% error rate — IndraVahan · 2026-11-03