How does your feedback shape new StarDrop features?
In the fast-paced world of drug discovery, your time is precious. You’re under pressure to design better compounds, do it…
Abstract
Binding affinity prediction is frequently addressed using computational models constructed solely with molecular structure and activity data.
We present a hybrid structure-guided strategy that combines molecular similarity, docking, and multiple-instance learning such that information from protein structures can be used to inform models of structure–activity relationships. The Surflex-QMOD approach has been shown to produce accurate predictions of binding affinity by constructing an interpretable physical model of a binding site with no experimental binding site structural information.
We introduce a method to integrate protein structure information into the model induction process in order to construct more robust physical models. The structure-guided models accurately predict binding affinities over a broad range of compounds while producing more accurate representations of the protein pockets and ligand binding modes. Structure-guidance for the QMOD method yielded significant performance improvements, both for affinity and pose prediction, especially in cases where predictions were made on ligands very different from those used for model induction.
More publications to browse
Switching to StarDrop is easy: Your step-by-step guide
If your current software has hidden costs, performance that can’t keep pace, poor support, or limited visualisation options, it might be time for a change. The good news is, switching to StarDrop is easier than you may think and this guide will walk you through every step.
Why does conformational flexibility matter in drug design?
What are conformational ensembles? A conformational ensemble is a collection of the different 3D shapes a molecule can adopt in…
