Docking-based Virtual Screening with Multi-Task Learning

Creating new drugs is a complex and expensive process. Computer-aided drug discovery is used to accelerate this process and lower the market cost.

For instance, molecular docking is employed to predict the binding affinity and bound conformation. However, with the growing amount of data, the computational time of virtual screening emerges to be an issue.

A laboratory technician in the process of pipetting a sample. Image credit: CDC/ Von Roebuck/Lauren Bishop, Public Domain

A recent study on proposes Multi-Task Learning (MTL) to improve the accuracy of docking score prediction at the same time taking full advantage of the available data. MTL learns multiple related tasks jointly such that a task can use the knowledge contained in other tasks to improve its performance.

Experiments show that MTL achieves better accuracy of docking score prediction than alternative approaches. It is also shown that the model trained with MTL learns a better representation of the compounds and can be used to adapt to a new task like drug-target affinity prediction.

Machine learning shows great potential in virtual screening for drug discovery. Current efforts on accelerating docking-based virtual screening do not consider using existing data of other previously developed targets. To make use of the knowledge of the other targets and take advantage of the existing data, in this work, we apply multi-task learning to the problem of docking-based virtual screening. With two large docking datasets, the results of extensive experiments show that multi-task learning can achieve better performances on docking score prediction. By learning knowledge across multiple targets, the model trained by multi-task learning shows a better ability to adapt to a new target. Additional empirical study shows that other problems in drug discovery, such as the experimental drug-target affinity prediction, may also benefit from multi-task learning. Our results demonstrate that multi-task learning is a promising machine learning approach for docking-based virtual screening and accelerating the process of drug discovery.

Research paper: Liu, Z., Ye, X., Fang, X., Wang, F., Wu, H., and Wang, H., “Docking-based Virtual Screening with Multi-Task Learning”, 2021. Link: