研究人员开发了 Project Ariadne，这是一种用于逆合成规划的新型解码器模型，可生成多步化学合成路线。与需要专用算法或针对不同约束条件使用不同模型的先前方法不同，Ariadne 将目标分子、约束条件和路线整合到单个提示-完成序列中。这种方法显著提高了在 RetroCast/PaRoutes 等基准测试上的性能，在深度和所需叶子约束方面，其速度和准确性均优于传统规划器。虽然在标准重建方面与现有先进模型相当，但 Ariadne 提供了更快的推理时间和将序列生成能力扩展到提示条件结构路线生成。 AI
影响 该模型可以通过提供更快、更准确的路线生成来加速药物发现和化学合成。
排序理由 该集群描述了一篇详细介绍用于特定科学任务的新型 AI 模型的研究论文。
AI 生成摘要 · Google Gemini · 来自 3 个来源。 我们如何撰写摘要 →
arXiv:2606.24184v1 Announce Type: new Abstract: Retrosynthetic planning seeks to connect a target molecule to commercially available starting materials through a multistep route. Classical planners construct such routes by iteratively applying single-step reaction models within a…
Retrosynthetic planning seeks to connect a target molecule to commercially available starting materials through a multistep route. Classical planners construct such routes by iteratively applying single-step reaction models within a search procedure; constrained variants often re…
Retrosynthetic planning seeks to connect a target molecule to commercially available starting materials through a multistep route. Classical planners construct such routes by iteratively applying single-step reaction models within a search procedure; constrained variants often re…