Chemical space is too large to enumerate explicitly. Thus, it represents a so-called intensionally defined design space. Search strategies for intensionally designed spaces are a current area of interest in machine learning. In the context of a drug design problem, we have investigated the application of a data-driven adaptive Markov chain approach, where the acceptance probability is given by a probabilistic surrogate of the target property, modelled with a maximum entropy conditional model. We have applied the approach to a lead development search for an antagonist of an alpha-v integrin, using a molecular docking score as the optimisation function. The RGD integrin receptors are thought to play a key role in fibrosis. Antagonism of alpha-V-beta-6 is one promising avenue for the development of a novel therapeutic treatment and some success has been reported in discovering compounds with significant activity against alpha-V-beta-6 and physicochemical properties commensurate with oral bioavailability. Molecular docking was performed using OpenEye FRED, which uses a rigid ligand approach, where a large number of conformations are generated and each of those are docked successively. We have discovered compounds with greater predicted activity than compounds found in our previous work by employing two strategies. We have substantially increased the search space explored, to the order of ~1020 possible compounds, and we have considered receptor flexibility by docking to an ensemble of snapshots from molecular dynamics simulations.

Machine learning for the discovery of αVβ6 integrin antagonists

2019 Fall National Meeting

The official archive and repository for all ACS Meetings & Expositions abstracts and select posters or presentations.