Andrew Dalke

Does anyone find the Klekota-Roth #cheminformatics fingerprints useful, or even potentially interesting? I'm considering adding them to chemfp.

Original paper, https://academic.oup.com/bioinformatics/article/24/21/2518/192573 . "Using diverse phenotypic assays, we defined bioactivity for multiple compound libraries. Many substructures were associated with bioactivity ... validating the privileged substructure concept."

CDK implements them (4860 SMARTS tests). At #ICCS2025 I found light curiosity but no strong interest.

Jun 13, 2025 at 7:10pmWeb
Show threadAndrew DalkeJun 13, 2025

Google Scholar finds papers using K-R fingerprints, but none identified a domain where they are useful.

To be honest, some didn't seem to know what they were doing, and some were software tools which implemented or integrated with many fingerprint methods. I didn't find a paper trying to validate an appropriate domain.