跳到正文
NVIDIA BioNeMo 博客· Elizabeth Goodman·· 26 天前AI 评分26

通过奖励引导的推理时搜索,用 RFD4-Proteina 设计蛋白质

Design Proteins with RFD4-Proteina Using Reward-Guided Inference-Time Search

AI 导读

RFD4-Proteina 通过奖励引导的推理时搜索设计蛋白质,将蛋白质设计视为搜索问题。8 个氨基酸残基的序列存在超过 25 billion 种组合,100 个残基的组合数则超过可观测宇宙的原子数。

正文 · 原文

Protein design is a search problem. Choose amino acids for an eight-residue protein sequence and more than 25 billion combinations are possible. Choose amino...

Protein design is a search problem. Choose amino acids for an eight-residue protein sequence and more than 25 billion combinations are possible. Choose amino acids for a 100-residue protein sequence and the number of possibilities exceeds the number of atoms in the observable universe. Somewhere in that space is a protein that opens a path to a new therapy. There are too many combinations to…

Source

来源:NVIDIA BioNeMo 博客 · developer.nvidia.com