Stanford team releases FoldDir, a Dirichlet flow-matching model for protein inverse folding
KevinKaichuang · x · 2026-09-16
A Stanford team (Tartici, Jewett, Altman et al.) released FoldDir, a flow-matching, structure-conditioned protein sequence design model for the inverse folding task — finding amino acid sequences compatible with a desired backbone.
The authors report strong computational benchmark results and several functional nanobody redesigns. The preprint, "Inverse FoldDir: Structure-conditioned Protein Sequence Design by Dirichlet Flow Matching," is on bioRxiv.
Related event: Stanford team releases FoldDir for structure-conditioned protein design(2 posts)→
More from Research
- DeepMind's Dream RSI lets agents learn from past attempts in a self-improvement loop — MickeySteamboat · 2026-09-17
- Research Culture Broken: Corrections, Replication, Negative Results All Unrewarded — tak3sh8 · 2026-09-17
- Keller Jordan: claiming AI could ruin math implies mathematicians can't self-govern — kellerjordan0 · 2026-09-17
- Dev Says Frontier Lab's Jev Architecture Mirrors His Open-Source Work From a Year Ago — Nandakishor_ml · 2026-09-17
- Nvidia's Agora: 13 LLM Agents Run 12 Days Unsupervised via Git-Based Shared Memory — nvidia · 2026-09-17
- HypoEvolve: Genetic Algorithms Orchestrate Multi-Agent LLMs for Cancer Drug Repurposing — Jieyuan Liu · 2026-09-17