Machine Learning on DNA-Encoded Libraries: A New Paradigm for Hit Finding

DNA-encoded small molecule libraries (DELs) have enabled discovery of novel inhibitors for many distinct protein targets of therapeutic value. We demonstrate a new approach applying machine learning to DEL selection data by identifying active molecules from large libraries of commercial and easily synthesizable compounds. We train models using only DEL selection data and apply automated or automatable filters to the predictions. We perform a large prospective study (∼2000 compounds) across three diverse protein targets: sEH (a hydrolase), ERα (a nuclear receptor), and c-KIT (a kinase). The approach is effective, with an overall hit rate of ∼30% at 30 μM and discovery of potent compounds (IC50 < 10 nM) for every target. The system makes useful predictions even for molecules dissimilar to the original DEL, and the compounds identified are diverse, predominantly drug-like, and different from known ligands. This work demonstrates a powerful new approach to hit-finding.DNA编码小分子库（DNA-encoded small molecule libraries, DELs）已助力发现多种具备临床治疗价值的蛋白质靶点的新型抑制剂。本研究提出一种全新策略：将机器学习应用于DEL筛选数据，从商业化且易于合成的大型化合物库中筛选活性分子。我们仅依托DEL筛选数据训练模型，并对预测结果应用自动化或可自动化的过滤流程。我们针对三类不同的蛋白质靶点开展了大规模前瞻性研究，共涉及约2000个化合物：sEH（水解酶）、ERα（核受体）以及c-KIT（激酶）。该策略效果显著：在30 μM浓度下整体命中率约为30%，且为所有靶点均发现了强效化合物（半数抑制浓度IC50 < 10 nM）。即便对于与原始DEL库中分子结构差异显著的化合物，该系统仍可给出具有参考价值的预测；所鉴定得到的化合物结构多样，且大多符合类药特性，同时区别于已知配体。本研究证实了一种用于活性分子发现的高效全新策略。