Computer-aided drug design: Virtual screening and structural bioinformatics for discovery of new GPCR ligands

G-protein coupled receptor (GPCRs) form the largest superfamily of membrane proteins in human. 34% of the marketed small molecule drugs bind to GPCRs. Tens of millions of compounds are commercially available for screening against GPCRs in experimental setting, which is impractical for academia and industry.

Recent breakthroughs in molecular structure determination both in experiment (x-ray crystallography and cryo-EM) and homology modeling (e.g., DeepMind’s Alphafold) have ushered a hope for accelerated pace in structure-based drug design against GPCRs. In this context, virtual screening and computer aided drug design have already proven useful in selecting a small subset of promising ligands for later tests thereby reducing cost and efficiency in biomedical research.

Read more about the project (mn.uio.no)

Tags: Active learning, Deep learning/neural networks, Statistical methods
Published July 4, 2023 9:52 AM - Last modified Oct. 23, 2023 11:45 AM