QComp: A QSAR-Based Imputation Framework for Drug Discovery
Bingjia Yang, Yunsie Chung, Archer Yi Yang, Bo Yuan, Tianchi Chen, Xiang Yu · Journal of Chemical Information and Modeling · 2025
In drug discovery, in vitro and in vivo experiments generate biochemical activity data that are crucial for evaluating the efficacy and toxicity of compounds. These data sets are massive, sparse, and ever-evolving. Quantitative structure-activity relationship (QSAR) models, which predict biochemical activities from compound structures, face challenges in integrating the evolving experimental data agilely as studies progress. We developed QSAR-Complete (QComp), an imputation framework, to address these challenges. While QSAR models are updated at a slow pace through extensive retraining on enlarging data sets, QComp leverages existing QSAR models to immediately exploit new experimental data and improves the imputation of missing data. We demonstrate that the improvement is robust and substantial for imputing in vivo assays with only in vitro experimental data. Additionally, QComp assists in finding the optimal sequence of experiments by quantifying the reduction in statistical uncertainty for specific end points, aiding in rational decision-making throughout the drug discovery process.