用新算法让药物合成规划速度提升近一倍，适合高通量筛选场景。
Fast and scalable retrosynthetic planning with a transformer neural network and speculative beam search
- 用推测性束搜索+Medusa策略加速分子合成路径生成
- 相同时间内可解决多26%至86%的分子目标
- 适合需要快速评估合成可行性的药物研发人员
基于AI的计算机辅助合成规划（CASP）系统是智能药物发现流程的关键组件。然而，现有CASP系统延迟较高，难以满足从头药物设计中高通量合成可行性筛查的需求。本文提出一种加速多步合成规划的新方法，针对依赖SMILES-to-SMILES Transformer的单步逆合成模型。通过将标准束搜索替换为结合推测性束搜索与可扩展的草稿策略Medusa的方法，显著降低AiZynthFinder中多步合成规划的延迟。在数秒时间约束下，该方法使CASP系统能解决的分子数量增加26%至86%。该技术使AI驱动的合成规划更接近高通量合成可行性筛查的严苛延迟要求，提升了整体用户体验。
原文摘要 · Abstract (English)
AI-based computer-aided synthesis planning (CASP) systems are in demand as components of AI-driven drug discovery workflows. However, the high latency of such CASP systems limits their utility for high-throughput synthesizability screening in de novo drug design. We propose a method for accelerating multi-step synthesis planning systems that rely on SMILES-to-SMILES transformers as single-step retrosynthesis models. Our approach reduces the latency of SMILES-to-SMILES transformers powering multi-step synthesis planning in AiZynthFinder through speculative beam search combined with a scalable drafting strategy called Medusa. Replacing standard beam search with our approach allows the CASP system to solve 26\% to 86\% more molecules under the same time constraints of several seconds. Our method brings AI-based CASP systems closer to meeting the strict latency requirements of high-throughput synthesizability screening and improving general user experience.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。