Abstract
Despite substantial progress in machine learning for scientific discovery in recent years, truly de novo design of small molecules which exhibit a property of interest remains a significant challenge. We introduce LambdaZero, a generative active learning approach to search for synthesizable molecules. Powered by deep reinforcement learning, LambdaZero learns to search over the vast space of molecules to discover candidates with a desired property. We apply LambdaZero with molecular docking to design novel small molecules that inhibit the enzyme soluble Epoxide Hydrolase 2 (sEH), while enforcing constraints on synthesizability and drug-likeliness. LambdaZero provides an exponential speedup in terms of the number of calls to the expensive molecular docking oracle, and LambdaZero de novo designed molecules reach docking scores that would otherwise require the virtual screening of a hundred billion molecules. Importantly, LambdaZero discovers novel scaffolds of synthesizable, drug-like inhibitors for sEH. In in vitro experimental validation, a series of ligands from a generated quinazoline-based scaffold were synthesized, and the lead inhibitor N-(4,6-di(pyrrolidin-1-yl)quinazolin-2-yl)-N-methylbenzamide (UM0152893) displayed sub-micromolar enzyme inhibition of sEH.
Abstract (translated)
尽管在近年来机器学习在科学发现方面取得了实质性进展,但真正实现新药小分子设计仍然是一个重要的挑战。我们引入了LambdaZero,一种基于生成式主动学习搜索合成分子的人工智能方法。LambdaZero借助深度强化学习学会了在庞大的分子空间中搜索有目标性质的分子,并发现具有所需性质的候选分子。我们将LambdaZero与分子对接应用于设计抑制酶可溶性E暴露2(sEH)的新小分子,同时满足合成性和药物相似性的约束。LambdaZero在分子对接或acle的调用次数方面提供了指数级的速度提升,LambdaZero设计的分子达到了其他方法需要进行虚拟筛选的100亿分子数量级。重要的是,LambdaZero发现了sEH的新型可合成、药物类似抑制性支架。在体内实验验证中,基于产生的喹啉支架的一组配体被合成,其中主抑制剂N-(4,6-二(吡咯烷基)-1-yl)喹啉-2-yl)-N-甲基苯胺(UM0152893)显示出对sEH的亚摩尔抑制。
URL
https://arxiv.org/abs/2405.01616