RosettaSearch uses LLMs to optimize protein sequence design, improving fidelity by up to 68%

Researchers have developed RosettaSearch, a novel method that uses large language models as generative optimizers for protein sequence design. This approach integrates LLMs within a search algorithm that leverages rewards from structure prediction models like RosettaFold3 to explore and refine protein sequences. In evaluations, RosettaSearch significantly improved structural fidelity and design success rates compared to existing methods, demonstrating its effectiveness across different LLM families and protein structures. AI

影响 Introduces a new LLM-driven optimization technique for protein design, potentially accelerating drug discovery and materials science.

排序理由 This is a research paper detailing a new method for protein sequence design using LLMs.

在 arXiv cs.AI 阅读 →

• Dayhoff atlas
• Gemini-3
• LigandMPNN
• Meghana Kshirsagar
• ProteinMPNN
• RosettaFold3
• RosettaSearch
• o4-mini

• 论文
• 模型发布

AI 生成摘要 · Google Gemini · 来自 1 个来源。 我们如何撰写摘要 →