Protein–protein binding affinity prediction on a diverse set of structures

Abstract

Supplementary data are available at Bioinformatics online.

Minimalistic Predictor of Protein Binding Energy: Contribution of Solvation Factor to Protein Binding

“…S2). The root-mean-squared error is 2.6 kcal/mol, comparable to the root-mean-squared error of 2.25 kcal/mol from ZAPP calculation (19)(20)(21). Equivalent error estimates for GA-PLS and BIOQSAR were reported to be 0.8-1.5 kcal/mol (7,8).…”

Mapping, modeling, and characterization of protein–protein interactions on a proteomic scale

“…For example, they can reveal detailed binding interface residue information or can be used to calculate the affinity of the interaction [34][35][36][37]. Such data can also further our understanding of how changes in a protein (e.g., mutations and post-translational modifications) affect interaction or protein stability [38 ,39,40].…”

Prediction of protein–protein binding free energies

“…[4][5][6][7][8][9] However, as outlined in several recent papers, these high accuracy predictions are due to limitations in the data sets used for training and testing the algorithms. 3,[10][11][12] When a large number of approaches were tested on a larger and more reliable dataset, no correlations higher than 0.53 were observed. 12 A community-wide effort on the computational discrimination between binding and non-binding protein pairs highlighted the critical role that the dataset plays for a balanced assessment of the methods.…”

“…Most approaches use linear regression to obtain a weighted function of physical or knowledge-based terms, 2 although machine-learning algorithms have been applied as well. 3 Two decades ago, Horton and Lewis obtained a high correlation coefficient of 0.96 with experimental measurements, using only three terms in a linear combination. 2 Later works using different methods and datasets also reported high correlation coefficients, ranging from 0.75 to 0.95.…”

“…Most recently, Moal et al 3 used machine learning approaches to predict binding free energies, using the dataset as in this work excluding seven complexes. They used four different machine learning methods, of which Multivariate Adaptive Regression Splines (MARS) yielded the best r of 0.52.…”