Leap：带中间体的分子可合成性评分
Leap: molecular synthesisability scoring with intermediates
AI总结：
针对现有分子可合成性评分方法无法动态适配中间体可得性的问题，本研究提出基于GPT-2的Leap模型，在合成路线深度数据上训练，推理时可纳入中间体信息，AUC得分较现有方法提升至少5%，且能随相关中间体调整评分。
摘要：
评估分子是否可合成是药物发现中的一项核心任务，它能让计算化学家筛选出可行的化合物，或是对分子生成模型施加偏向性约束。可合成性的概念是动态的，会随着关键化合物的可获得性变化而演变。药物发现中一种常用策略是探索可合成中间体周围的化学空间，由于关键中间体可得，该策略能提升衍生分子的可合成性。现有的可合成性评分方法，如SAScore、SCScore和RAScore，都无法动态地以中间体为条件进行计算。我们提出的方法Leap是一个GPT-2模型，在预测合成路线的深度（即最长线性路径）数据上训练，可在推理时纳入关键中间体的可获得性信息。实验表明，在识别可合成分子时，Leap的AUC得分比所有其他评分方法高出至少5%，并且在提供相关中间体化合物时能成功调整预测得分。
英文摘要：
Assessing whether a molecule can be synthesised is a primary task in drug discovery. It enables computational chemists to filter for viable compounds or bias molecular generative models. The notion of synthesisability is dynamic as it evolves depending on the availability of key compounds. A common approach in drug discovery involves exploring the chemical space surrounding synthetically-accessible intermediates. This strategy improves the synthesisability of the derived molecules due to the availability of key intermediates. Existing synthesisability scoring methods such as SAScore, SCScore and RAScore, cannot condition on intermediates dynamically. Our approach, Leap, is a GPT-2 model trained on the depth, or longest linear path, of predicted synthesis routes that allows information on the availability of key intermediates to be included at inference time. We show that Leap surpasses all other scoring methods by at least 5% on AUC score when identifying synthesisable molecules, and can successfully adapt predicted scores when presented with a relevant intermediate compound.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
