Finding the breakthrough compounds hiding in chemical space
Download the guide and learn what generative chemistry is, where it fits in the discovery workflow, and best practices to avoid common pitfalls.
Summary
To compare chemical structures, we can look at a number of 2D and 3D characteristics. In this paper, a group of 358 drugs with overlapping pharmacology were assessed for chemical similarity, using a new framework.
The method generates a chemical similarity score for new molecules based on a known set of molecules with a shared effect. For prediction of primary targets, the benefit of 3D over 2D was relatively small, but for prediction of off-targets, the added benefit was large.
Citation details
Emmanuel R. Yera et al., J. Med. Chem. 2011, 54, 19, 6771–6785.
More publications to browse
How can I predict binding affinity without a target protein structure?
Why traditional ligand-based QSAR methods have fallen short You might be sceptical about ligand-based QSAR approaches; many researchers are. We discussed why there has…
Ensemble-based conformational modelling for macrocycles
From X-ray refinement to lead optimisation Conventional ligand-fitting and refinement methods in X-ray electron density maps often yield models with…
