Combined application of cheminformatics- and physical force field-based scoring functions improves binding affinity prediction for CSAR data sets

Jui Hua Hsieh, Shuangye Yin, Shubin Liu, Alexander Sedykh, Nikolay V. Dokholyan, Alexander Tropsha

Research output: Contribution to journalArticlepeer-review

20 Scopus citations

Abstract

The curated CSAR-NRC benchmark sets provide valuable opportunity for testing or comparing the performance of both existing and novel scoring functions. We apply two different scoring functions, both independently and in combination, to predict the binding affinity of ligands in the CSAR-NRC data sets. One reported here for the first time employs multiple chemical-geometrical descriptors of the protein-ligand interface to develop Quantitative Structure Binding Affinity Relationships (QSBAR) models. These models are then used to predict binding affinity of ligands in the external data set. Second is a physical force field-based scoring function, MedusaScore. We show that both individual scoring functions achieve statistically significant prediction accuracies with the squared correlation coefficient (R2) between the actual and predicted binding affinity of 0.44/0.53 (Set1/Set2) with QSBAR models and 0.34/0.47 (Set1/Set2) with MedusaScore. Importantly, we find that the combination of QSBAR models and MedusaScore into consensus scoring function affords higher prediction accuracy than any of the contributing methods achieving R2 values of 0.45/0.58 (Set1/Set2). Furthermore, we identify several chemical features and noncovalent interactions that may be responsible for the inaccurate prediction of binding affinity for several ligands by the scoring functions employed in this study.

Original languageEnglish (US)
Pages (from-to)2027-2035
Number of pages9
JournalJournal of Chemical Information and Modeling
Volume51
Issue number9
DOIs
StatePublished - Sep 26 2011

All Science Journal Classification (ASJC) codes

  • Chemistry(all)
  • Chemical Engineering(all)
  • Computer Science Applications
  • Library and Information Sciences

Fingerprint Dive into the research topics of 'Combined application of cheminformatics- and physical force field-based scoring functions improves binding affinity prediction for CSAR data sets'. Together they form a unique fingerprint.

Cite this