CS Fingerprints

Overview

The Connected Subgraph Fingerprint (CSFP) is a novel fingerprint method that, unlike other methods, captures all connected subgraphs as structural features of a compound. Therefore, the CSFP captures a complete feature space and has a highly adaptive potential. Apart from surpassing common methods in standard similarity-driven virtual screening settings, the CSFP has substantial structural advantages when applied to combinatorial fragment spaces or for machine learning.

Software Availability

The CSFP and four derivatives are available in the Python module CSFPy. The user can load molecules from a file or via a SMILES string, generate fingerprints, and derive similarity measurements.
The module is freely available for non-commercial and academic users for Linux, MacOS, and Windows as part of our NAOMI ChemBio Suite. To download CSFPy, register at https://software.zbh.uni-hamburg.de. Non-academic users can get an evaluation license free of charge. All feedback (software.zbh(at)uni-hamburg.de) is highly appreciated.

References

Bellmann, L.; Penner, P.; Rarey, M. Connected Subgraph Fingerprints: Representing Molecules Using Exhaustive Subgraph Enumeration. J Chem Inf Model 2019, 59 (11), 4625-4635. DOI: https://doi.org/10.1021/acs.jcim.9b00571