Sophia Tsoka

CLigOpt generates target-specific ligands with desired properties using a controllable fragment-based approach, improving the proportion of feasible active molecules by 10%.

This paper introduces WSUnet, a weakly supervised Unet that generates voxel-level explanations for image-level predictions, outperforming existing methods in lung cancer detection.

The paper applies modSAR, an optimisation-based method, to analyse OSM anti-malarial compounds to derive interpretable rules for predicting ligand activity and guide drug design.