Neural multi-task learning in drug design

Multi-task learning (MTL) is a machine learning paradigm that aims to enhance the generalization of predictive models by leveraging shared information across multiple tasks. The recent breakthroughs achieved by deep neural network models in various domains have sparked hope for similar advances in the chemical sciences. In this Perspective, we provide insights into the current state and future potential of neural MTL models applied to computer-assisted drug design. In the context of drug discovery, one prominent application of MTL is protein–ligand binding affinity prediction, in which individual proteins are considered tasks. Here we introduce the fundamental principles of MTL and propose a framework for categorizing MTL models on the basis of their architecture. This framework enables us to present a comprehensive overview and comparison of a selection of MTL models that have been successfully utilized in drug design. Subsequently, we delve into the current challenges associated with the applications of MTL. One of the key challenges lies in defining suitable representations of the molecular entities under investigation and the respective machine learning tasks. Training a machine learning model with multiple tasks can create more-useful representations and achieve better performance than training models for each task separately. In this Perspective, Allenspach et al. summarize and compare multi-task learning methods for computer-aided drug design.