EMBER: pretrained gene-centric foundation model predicts multigene perturbation effects
jmuiuc · x · 2026-11-03
eigenNick (with @jmuiuc and @ericxing) introduced EMBER, a pretrained gene-centric foundation model that learns context-specific gene representations.
Key points:
- Core finding: contextualized gene representations work surprisingly well for predicting multigene perturbation effects
- Trained with innovations in single-cell pretraining and dataset curation
- With a lightweight probe it handles single-gene knockouts, genetic interactions (double knockouts), and drug perturbation prediction
- The author also released a thread and a walkthrough video
More from Research
- Recursive GPT-5-Mini calls often beat a single GPT-5 call for less money — lateinteraction · 2026-11-03
- Same Agent Reimplements Liquid in Rust vs C: Rust Uses 42% Fewer Tokens, C Runs 1.7x Faster — antirez · 2026-11-03
- After viral 'fly plays Beat Saber', researchers call for shared whole-brain emulation benchmark — rishabh16_ · 2026-11-03
- Researchers uncover 120 Google search twiddlers, including AI Mode's fan-out plan — VeryWellVersed · 2026-11-03
- Qwenputer compiles a full RISC-V CPU into Qwen3.5-4B weights, bit-exact, even running another LLM — udmrzn · 2026-11-03
- Astra IDs Breakout, Pong, Pac-Man and Freeway from raw model weights alone — burny_tech · 2026-11-03