31 Mar 2022

ICLR 2022

Authors: Héléna A. Gaspar, Matthew P. Seddon


Quantitative structure-activity relationships (QSAR) models have been used for decades to predict the activity of small molecules, using encodings of the molecular structure, for which simple 2D descriptors of the molecular graph are still most commonly used. One of the recurrent problems of QSAR is that relationships observed for a specific scaffold (pruned molecular skeleton) are often not transferable to another; this is often addressed by building several local models from subsets of the chemical space. Similarly, single task models sometimes outperform large multi-task models in predicting the activity of small molecules against specific proteins. In this paper, we introduce Glolloc, a global-local MoE-QSAR architecture, based on a Mixture of Experts (MoE) framework. Glolloc combines predictions from global and local experts, provides a built-in model introspection tool, can enhance model performance, and removes the need to maintain several local models.

Back to publications

Latest publications

09 Oct 2023
Learning the kernel for rare variant genetic association test
Read more
24 Aug 2023
Associating biological context with protein-protein interactions through text mining at PubMed scale
Read more
07 Dec 2022
NeurIPS 2022
sEHR-CE: Language modelling of structured EHR data for efficient and generalizable patient cohort expansion
Read more