Proteo-chemometrics interaction fingerprints of protein-ligand complexes predict binding affinity

Research output: Journal Publications and Reviews (RGC: 21, 22, 62)21_Publication in refereed journalpeer-review

5 Scopus Citations
View graph of relations

Author(s)

Related Research Unit(s)

Detail(s)

Original languageEnglish
Pages (from-to)2570-2579
Journal / PublicationBioinformatics
Volume37
Issue number17
Online published27 Feb 2021
Publication statusPublished - 1 Sep 2021

Abstract

Motivation: Reliable predictive models of protein–ligand binding affinity are required in many areas of biomedicalresearch. Accurate prediction based on current descriptors or molecular fingerprints (FPs) remains a challenge. Wedevelop novel interaction FPs (IFPs) to encode protein–ligand interactions and use them to improve the prediction. 
Results: Proteo-chemometrics IFPs (PrtCmm IFPs) formed by combining extended connectivity fingerprints (ECFPs)with the proteo-chemometrics concept. Combining PrtCmm IFPs with machine-learning models led to efficient scoring models, which were validated on the PDBbind v2019 core set and CSAR-HiQ sets. The PrtCmm IFP Score outperformed several other models in predicting protein–ligand binding affinities. Besides, conventional ECFPs were simplified to generate new IFPs, which provided consistent but faster predictions. The relationship between the baseatom properties of ECFPs and the accuracy of predictions was also investigated. 
Availability: PrtCmm IFP has been implemented in the IFP Score Toolkit on github (https://github.com/debbydanwang/IFPscore). 
Supplementary information: Supplementary data are available at Bioinformatics online. 

Research Area(s)

  • SCORING FUNCTION, RANDOM FOREST, DESCRIPTORS, BENCHMARK