使用獎勵引導的推理時搜尋，透過 RFD4-Proteina 設計蛋白質
Design Proteins with RFD4-Proteina Using Reward-Guided Inference-Time Search
RFD4-Proteina 透過獎勵引導的推理時搜尋設計蛋白質，將蛋白質設計視為搜尋問題。選擇一條 8 個胺基酸的蛋白質序列，可能組合超過 25 billion；若序列長達 100 個胺基酸，可能性更超過可觀測宇宙中的原子數量。
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…
來源：NVIDIA Technical Blog：Agentic AI / Generative AI · developer.nvidia.com