Imputation of sensory properties using deep learning
In this article, the team demonstrates the application of Alchemite™, a deep learning imputation method which underpins our Cerella™ technology, to physicochemical and sensory data.
XGen: real-space fitting of complex ligand conformational ensembles to x-ray electron density maps
We report a new method for X-ray density ligand fitting and refinement that is suitable for a wide variety of small-molecule ligands, including macrocycles.
Conformational strain of macrocyclic peptides in ligand–receptor complexes based on advanced refinement of bound-state conformers
To better understand conformational propensities, global strain energies were estimated for 156 protein-macrocyclic peptide cocrystal structures.
Predicting reactivity to drug metabolism: beyond P450s – modelling FMOs and UGTs
Methods for modelling two enzyme families, flavin-containing monoxygenases (FMOs) and uridine 5′-diphospho-glucuronosyltransferases (UGTs), to predict reactivity to drug metabolism.
Practical applications of deep learning to impute heterogeneous drug discovery data
This article outlines practical applications of deep learning on drug discovery data. It introduces some of the research behind our…
Structure- and ligand-based virtual screening on DUD-E+: performance dependence on approximations to the binding pocket
Using the DUD-E+ benchmark, we explore the impact of using a single protein pocket or ligand for virtual screening compared with using ensembles of alternative pockets, ligands, and sets thereof.
Predicting pKa using a combination of quantum mechanical and machine learning methods
This study aimed to create a model for predicting pKa using a semi-empirical quantum mechanics (QM) approach combined with machine learning (ML).
Quantitative surface field analysis: learning causal models to predict ligand binding affinity and pose
We introduce the QuanSA method for inducing physically meaningful field-based models of ligand binding pockets based on structure-activity data alone.
Transferable machine learning interatomic potential for bond dissociation energy prediction of drug-like molecules
Predicting metabolism at an early stage is important in maximising the chance of a drug’s success. However, accurate, useful models…
Experimental validation of predictive models in a series of novel antimalarials
In this study, we identified a new antimalarial with an unusual structure – the only compound in the competition to be proven active, opening up new chemistry for exploration.
Deep imputation on large-scale drug discovery data
OA paper outlining the practical applications of deep imputation on large-scale drug discovery data. It compares deep learning to traditional QSAR methods.
Advances in multi-parameter optimisation methods for de novo drug design
Summary This review article discusses recent developments in the methods and opinions around multi-parameter optimisation, focusing on applications to de novo drug…
Structure-based pose prediction: Non-cognate docking extended to macrocyclic ligands
In this paper, we describe an extended benchmark for non-cognate docking of macrocyclic ligands, and the superior performance of Surflex-Dock…
