We present a feature functional theory–binding predictor (FFT–BP) for the protein–ligand binding affinity prediction. The underpinning assumptions of FFT–BP are as follows: (1) representability: There exists a microscopic feature vector that can uniquely characterize and distinguish one protein–ligand complex from another; (2) feature–function relationship: the macroscopic features, including binding free energy, of a complex is a functional of microscopic feature vectors; and (3) similarity: molecules with similar microscopic features have similar macroscopic features, such as binding affinity. Physical models, such as implicit solvent models and quantum theory, are utilized to extract microscopic features, while machine learning algorithms are employed to rank the similarity among protein–ligand complexes. A large variety of numerical validations and tests confirms the accuracy and robustness of the proposed FFT–BP model. The root-mean-square errors of FFT–BP blind predictions of a benchmark set of 100 complexes, the PDBBind v2007 core set of 195 complexes and the PDBBind v2015 core set of 195 complexes are 1.99, 2.02 and 1.92 kcal/mol, respectively. Their corresponding Pearson correlation coefficients are 0.75, 0.80, and 0.78, respectively.
|Journal||Theoretical Chemistry Accounts|
|State||Published - Apr 1 2017|
Bibliographical noteFunding Information:
This work was supported in part by NSF Grant IIS- 1302285 and MSU Center for Mathematical Molecular Biosciences Initiative. We thank Emil Alexov, Michael Gilson, Ray Luo, Wei Yang and John Zheng for useful discussions.
© 2017, Springer-Verlag Berlin Heidelberg.
- Implicit solvent model
- Microscopic feature
- Protein–ligand binding
- Scoring function
ASJC Scopus subject areas
- Physical and Theoretical Chemistry