D2ML: Models for Direct-to-Biology Small Molecule Screening

AI4S DSMSD
“直接面向生物学”(D2B)筛选技术可在无需纯化的情况下,快速测试新合成分子的生物活性。然而,粗产物混合物中化合物浓度不确定,加之经纯化的化合物测定数据有限,给这类数据在机器学习中的应用带来了挑战。本文表明,针对D2B数据结构专门设计的模型,可提升预测性能,并有效指导更具活性与选择性的化合物的发现。我们构建的“检测方法感知型”(assay-aware)模型能够:基于单点筛选结果预测分子活性;利用粗产物剂量-反应实验数据,预测同一分子在不同靶标间的相对活性;并借助纯化化合物的测定数据,预测其绝对活性。对于粗产物实验,即便浓度未知,只要多个靶标在同一孔中同步测试,其测得的活性比值仍能保留关键的选择性信息。进一步地,我们开发了一种联合模型,该模型在不同实验阶段间共享信息,并动态平衡各阶段数据对模型训练的贡献,其预测性能显著优于为各阶段单独训练的神经网络模型。其中提升最为显著的是粗产物剂量-反应实验中的选择性预测能力,其排序相关系数(rank correlation)由0.27提升至0.40。在另一项独立实验中,我们使用分别训练的模型指导筛选出84个全新化合物,在增强ROS1激酶抑制活性的同时,严格限制其对反靶标TRKB的活性。经实际合成与测试验证,所获化合物拓展了实测的帕累托前沿(Pareto front),实现了较训练集化合物更优的活性与选择性协同组合:其中选择性最优的新化合物对ROS1的IC₅₀达14.7 nM,且对TRKB的选择性高达233倍;相比之下,训练集中选择性最优的化合物对ROS1的IC₅₀为20.3 nM,对TRKB的选择性仅为79倍。ATLAS平台为此方法提供了完整的实验支撑体系,可在两到三周的周期内,完成由模型推荐的1,000–10,000个化合物的自动化合成与生物学筛选。综上,本研究展示了如何通过“检测方法感知型”建模策略,充分利用整套D2B筛选流程所产生的多源异构数据,实现面向多重优化目标的分子理性设计。
Direct-to-biology (D2B) screening enables rapid testing of newly synthesized molecules without purification. However, uncertain concentrations in crude mixtures and limited purified-compound measurements complicate the use of these data in machine learning. Here we show that models tailored to the structure of D2B data can improve prediction and guide the discovery of more potent and selective compounds. Our assay-aware models predict activity from single-point screens, relative potency across targets from crude dose-response assays, and absolute potency from purified-compound measurements. For crude assays, potency ratios between targets tested from the same well can retain selectivity information despite uncertain concentrations. A joint model that shares information across stages and balances their contributions to training improved predictions over separate neural networks. The largest gain was in crude dose-response selectivity prediction, where rank correlation increased from 0.27 to 0.40. In a separate experiment, independently trained models guided the selection of 84 new compounds to improve ROS1 potency while limiting activity against the anti-target TRKB. Synthesis and testing identified compounds that extended the measured Pareto front, achieving better combinations of potency and selectivity than those in the training data. The most selective new compound achieved a ROS1 IC50 of 14.7 nM and 233-fold selectivity over TRKB. By comparison, the most selective training compound had a ROS1 IC50 of 20.3 nM and 79-fold selectivity. ATLAS provides the experimental setting for this approach, supporting synthesis and screening of 1,000-10,000 model-selected compounds in two- to three-week cycles. Together, these results show how assay-aware learning can use the full D2B assay sequence to guide multi-objective molecular optimization.
许愿