重新评估从头分子生成中的样本效率
Re-evaluating sample efficiency in de novo molecule generation
AI总结：
本研究调整了从头分子生成的样本效率基准以兼顾化学质量，重新评估后发现考量分子量、LogP与化学多样性会改变模型排名，且Augmented Hill-Climb方法在样本效率和分子化学性质上均表现最优。
摘要：
从头分子生成可能存在数据效率低下的问题：需要大量训练数据或大量采样数据点来进行目标优化。当深度生成模型与计算机辅助药物设计中常用的计算成本高昂的分子评分函数（又称预言机oracle）结合使用时，后者（采样数据需求大）是一个特别不利的因素。因此，近期的研究聚焦于提升从头分子药物设计场景下样本效率的方法，或是对该效率进行基准测试。在本研究中，我们讨论并调整了一项近期的样本效率基准，使其能更好地反映现实目标——同时兼顾生成分子的化学质量，这是小分子药物设计场景下必须始终考虑的因素；随后我们重新评估了所有参与基准测试的生成模型。我们发现，将相对于训练数据的分子量与LogP、以及生成分子的化学多样性纳入考量后，生成模型的排名会发生变化。此外，我们对近期提出的一种提升样本效率的方法（Augmented Hill-Climb，增强爬山法）进行了基准测试，发现当同时考虑样本效率和生成分子的化学性质时，该方法排名第一。样本效率和化学适用性的持续提升，能让计算成本高昂的评分函数在更符合实际的时间尺度上更常态化地集成应用。
英文摘要：
De novo molecule generation can suffer from data inefficiency; requiring large amounts of training data or many sampled data points to conduct objective optimization. The latter is a particular disadvantage when combining deep generative models with computationally expensive molecule scoring functions (a.k.a. oracles) commonly used in computer-aided drug design. Recent works have therefore focused on methods to improve sample efficiency in the context of de novo molecule drug design, or to benchmark it. In this work, we discuss and adapt a recent sample efficiency benchmark to better reflect realistic goals also with respect to the quality of chemistry generated, which must always be considered in the context of small-molecule drug design; we then re-evaluate all benchmarked generative models. We find that accounting for molecular weight and LogP with respect to the training data, and the diversity of chemistry proposed, re-orders the ranking of generative models. In addition, we benchmark a recently proposed method to improve sample efficiency (Augmented Hill-Climb) and found it ranked top when considering both the sample efficiency and chemistry of molecules generated. Continual improvements in sample efficiency and chemical desirability enable more routine integration of computationally expensive scoring functions on a more realistic timescale.
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。
