structRFM: structure-guided RNA foundation model trained on 21M pairs lands in Nature
EricTopol · x · 2026-11-05
Eric Topol highlights a new Nature paper on structRFM, an RNA foundation model extending the sequence-to-structure paradigm beyond proteins. It is pre-trained on 21M RNA sequence-structure pairs, integrating base-pairing interactions into masked language modeling via a pair-matching operation, plus MUSES (a multi-source ensemble of secondary structures to reduce predictor bias) and a dynamic masking ratio. The authors argue prior RNA models rely on noisy annotations or task-specific objectives that hurt generalizability.
More from Research
- 2-person lab Linum trains 2B text-to-image model from scratch for just $21K, Apache 2.0 — ycombinator · 2026-11-05
- Trained an MoE across two GPU clusters 25 Gbps apart — the compute islands guide — _arohan_ · 2026-11-05
- AutoDNA: AI agents run multi-step molecular biology experiments with minimal human input — james_y_zou · 2026-11-05
- The Stacks Project, algebraic geometry's giant reference, is now formalized in Lean — LinusEkenstam · 2026-11-05
- Perceptron Egocentric 1.0 turns egocentric video into robot training data at $29/hour — rohanpaul_ai · 2026-11-05
- Study benchmarks divergent creativity of LLMs against 100,000 humans in Scientific Reports — korymath · 2026-11-05