A simple spatial extension to the extended connectivity interaction features for binding affinity prediction.
R Soc Open Sci
The Royal Society
MetadataShow full item record
Orhobor, O. I., Rehim, A. A., Lou, H., Ni, H., & King, R. (2022). A simple spatial extension to the extended connectivity interaction features for binding affinity prediction.. R Soc Open Sci, 9 (5) https://doi.org/10.1098/rsos.211745
The representation of the protein-ligand complexes used in building machine learning models play an important role in the accuracy of binding affinity prediction. The Extended Connectivity Interaction Features (ECIF) is one such representation. We report that (i) including the discretized distances between protein-ligand atom pairs in the ECIF scheme improves predictive accuracy, and (ii) in an evaluation using gradient boosted trees, we found that the resampling method used in selecting the best hyperparameters has a strong effect on predictive performance, especially for benchmarking purposes.
Machine Learning, Scoring Functions, Protein Binding Affinity Prediction
Engineering and Physical Sciences Research Council (EP/R022925/1)
External DOI: https://doi.org/10.1098/rsos.211745
This record's URL: https://www.repository.cam.ac.uk/handle/1810/338185
Attribution 4.0 International
Licence URL: https://creativecommons.org/licenses/by/4.0/