Artificial Intelligence (AI)-aided drug discovery is an active research field, yet AI models often exhibit poor accuracy in regression tasks for molecular property prediction, and perform catastrophically poorly for out-of-distribution (OOD) molecules. Here, we present MolRuleLoss, a substructure-substitution-rule-informed framework that improves the accuracy and generalizability of multiple molecular property regression models (MPRMs) such as GEM and UniMol for diverse molecular property prediction tasks. MolRuleLoss incorporates partial derivative constraints for substructure substitution rules (SSRs) into an MPRM's loss function. When using GEM models for predicting lipophilicity, water solubility, and solvation-free energy (using lipophilicity, ESOL, and freeSolv datasets from MoleculeNet), the root mean squared error (RMSE) values with and without MolRuleLoss were 0.587 vs. 0.660, 0.777 vs. 0.798, and 1.252 vs. 1.877, respectively, representing 2.6-33.3% performance improvements. We show that both the number and the quality of SSRs contribute to the magnitude of prediction accuracy gains obtained upon adding MolRuleLoss to an MPRM. MolRuleLoss improved the generalizability of MPRMs for "activity cliff" molecules in a lipophilicity prediction task and improved the generalizability of MPRMs for OOD molecules in a melting point prediction task. In a molecular weight prediction task for OOD molecules, MolRuleLoss reduced the RMSE value of a GEM model from 29.507 to 0.007. We also provide a formal demonstration that the upper bound of the variation for property change of SSRs is positively correlated with an MPRM's error. Together, we show that using the MolRuleLoss framework as a bolt-on boosts the prediction accuracy and generalizability of multiple MPRMs, supporting diverse applications in areas like cheminformatics and AI-aided drug discovery.

翻译：人工智能辅助药物发现是一个活跃的研究领域，然而AI模型在分子性质预测的回归任务中往往表现出较差的准确性，并且对于分布外分子表现出灾难性的性能下降。本文提出MolRuleLoss，一个基于子结构替换规则的框架，旨在提升多种分子性质回归模型（如GEM和UniMol）在多样化分子性质预测任务中的准确性与泛化能力。MolRuleLoss将子结构替换规则的部分导数约束整合到分子性质回归模型的损失函数中。在使用GEM模型预测亲脂性、水溶性和溶剂化自由能（分别采用MoleculeNet中的亲脂性、ESOL和freeSolv数据集）时，使用与不使用MolRuleLoss的均方根误差值分别为0.587对比0.660、0.777对比0.798以及1.252对比1.877，性能提升幅度达2.6%至33.3%。我们证明，子结构替换规则的数量与质量共同决定了将MolRuleLoss整合到分子性质回归模型后所获得的预测精度提升幅度。在亲脂性预测任务中，MolRuleLoss提升了分子性质回归模型对"活性悬崖"分子的泛化能力；在熔点预测任务中，则提升了模型对分布外分子的泛化性能。在针对分布外分子的分子量预测任务中，MolRuleLoss将GEM模型的均方根误差从29.507降低至0.007。我们还通过形式化证明表明，子结构替换规则性质变化的上界与分子性质回归模型的误差呈正相关。综上，本研究表明将MolRuleLoss框架作为即插即用模块，能够显著提升多种分子性质回归模型的预测准确性与泛化能力，为化学信息学与人工智能辅助药物发现等领域的多样化应用提供支持。