Does a More Precise Chemical Description of Protein–Ligand Complexes Lead to More Accurate Prediction of Binding Affinity?

Abstract

Predicting the binding affinities of large sets of diverse molecules against a range of macromolecular targets is an extremely challenging task. The scoring functions that attempt such computational prediction are essential for exploiting and analyzing the outputs of docking, which is in turn an important tool in problems such as structure-based drug design. Classical scoring functions assume a predetermined theory-inspired functional form for the relationship between the variables that describe an experimentally determined or modeled structure of a protein–ligand complex and its binding affinity. The inherent problem of this approach is in the difficulty of explicitly modeling the various contributions of intermolecular interactions to binding affinity. New scoring functions based on machine-learning regression models, which are able to exploit effectively much larger amounts of experimental data and circumvent the need for a predetermined functional form, have already been shown to outperform a broad range of state-of-the-art scoring functions in a widely used benchmark. Here, we investigate the impact of the chemical description of the complex on the predictive power of the resulting scoring function using a systematic battery of numerical experiments. The latter resulted in the most accurate scoring function to date on the benchmark. Strikingly, we also found that a more precise chemical description of the protein–ligand complex does not generally lead to a more accurate prediction of binding affinity. We discuss four factors that may contribute to this result: modeling assumptions, codependence of representation and regression, data restricted to the bound state, and conformational heterogeneity in data.

Performance of machine-learning scoring functions in structure-based virtual screening

“…Several cross-validation scenarios show that in any application RF-Score-VS comfortably outperforms classical SFs, even when using the most crude RF-Score v1 features1422.…”

Machine‐learning scoring functions to improve structure‐based binding affinity prediction and virtual screening

“…Overall, machine‐learning SFs have exhibited a substantial improvement over classical SFs in different binding affinity prediction benchmarks . Furthermore, a number of studies have shown that a classical SF can easily be improved by substituting their linear regression model with nonparametric machine‐learning regression, either using RF or SVR .…”

Acoplamiento Molecular: Avances Recientes y Retos

“…To this end, efforts have been conducted to make additional models for binding. Yet, this may not be necessarily the case as very specific descriptors and models do not show significant improvement on the prediction of binding affinity (Ballester, Schreyer & Blundell, 2014).…”

“…Their apparent underperformance can be attributed to the lack of implicit solvation and, in some cases, to the protonation state as it further deviates the RMSD when compared to crystal structures (Ballester, Schreyer & Blundell, 2014;Gürsoy & Smieško, 2017).…”