Niccolò Pancino (University of Siena)

When: Jan 12th, 2022 – 11:00 – 11:45 AM

Where: Google meet link

Description

Using Domain-Specific Fingerprints Generated Through Neural Networks to Enhance Ligand-Based Virtual Screening by Janosch Menke and Oliver Koch

Similarity-based virtual screening is a fundamental tool in the early drug discovery process and relies heavily on molecular fingerprints. The authors of the paper propose a novel strategy of generating domain-specific fingerprints, by training neural networks on target-specific bioactivity datasets. Neural networks are expected to combine information of already known bioactive compounds with unique information of the molecular structure which is integrated in the fingerprint. This strategy has been evaluated on a large kinase-specific bioactivity dataset. A comparison between some neural network architectures and their fingerprints to the well-establisched Extended-Connectivity Fingerprint (ECFP) shows that neural network fingerprint produces better results in similarity search.