Improved prediction of ligand-protein binding affinities by meta-modeling
This work addresses the need for more accurate and scalable computational methods in drug development, though it is incremental as it builds on existing ensembling techniques.
The authors tackled the problem of predicting ligand-protein binding affinities for drug screening by developing a meta-modeling framework that integrates force-field-based docking and sequence-based deep learning models. Their best meta-models achieved comparable performance to state-of-the-art deep learning tools, with improved generalization on large-scale benchmarks.
The accurate screening of candidate drug ligands against target proteins through computational approaches is of prime interest to drug development efforts. Such virtual screening depends in part on methods to predict the binding affinity between ligands and proteins. Many computational models for binding affinity prediction have been developed, but with varying results across targets. Given that ensembling or meta-modeling approaches have shown great promise in reducing model-specific biases, we develop a framework to integrate published force-field-based empirical docking and sequence-based deep learning models. In building this framework, we evaluate many combinations of individual base models, training databases, and several meta-modeling approaches. We show that many of our meta-models significantly improve affinity predictions over base models. Our best meta-models achieve comparable performance to state-of-the-art deep learning tools exclusively based on 3D structures, while allowing for improved database scalability and flexibility through the explicit inclusion of features such as physicochemical properties or molecular descriptors. We further demonstrate improved generalization capability by our models using a large-scale benchmark of affinity prediction as well as a virtual screening application benchmark. Overall, we demonstrate that diverse modeling approaches can be ensembled together to gain meaningful improvement in binding affinity prediction.