Abstract

Predicting the binding affinities of large sets of diverse molecules against a range of macromolecular targets is an extremely challenging task. The scoring functions that attempt such computational prediction are essential for exploiting and analysing the outputs of molecular docking, which is in turn an important tool for structural biology, chemical biology and drug discovery. Traditional scoring functions assume a predetermined theory-inspired functional form for the relationship between the variables that characterise the X-ray crystal structure of the complex and its binding affinity. The inherent problem of this approach is in the difficulty of explicitly modelling the various contributions of intermolecular interactions to binding affinity.

New scoring functions based on machine learning, which are able to exploit effectively much larger amounts of experimental data and circumvent the need for a predetermined functional form, have recently been shown to outperform a broad range of state-of-the-art scoring functions. In this talk, I will review work in this emerging research area, focusing on the different types of approaches and the presented studies to assess their performance against that of traditional scoring functions.

The talk is part of the CCBI seminar series and the DTP graduate course Reviews in Computational Biology, but is open to all attendees.