Machine Learning of Allosteric Effects: The Analysis of Ligand-Induced Dynamics to Predict Functional Effects in TRAP1.

Mariarosaria Ferraro,Carlos Sanchez-Martin,Emiliano Ippoliti,Giorgio Colombo,Silvia Rinaldi,Luca F Pavarino,Elisabetta Moroni,Andrea Rasola

doi:10.1021/acs.jpcb.0c09742

Mariarosaria Ferraro, Carlos Sanchez-Martin + Show 6 more

Open Access

https://doi.org/10.1021/acs.jpcb.0c09742

Copy DOI

Abstract

Allosteric molecules provide a powerful means to modulate protein function. However, the effect of such ligands on distal orthosteric sites cannot be easily described by classical docking methods. Here, we applied machine learning (ML) approaches to expose the links between local dynamic patterns and different degrees of allosteric inhibition of the ATPase function in the molecular chaperone TRAP1. We focused on 11 novel allosteric modulators with similar affinities to the target but with inhibitory efficacy between the 26.3 and 76%. Using a set of experimentally related local descriptors, ML enabled us to connect the molecular dynamics (MD) accessible to ligand-bound (perturbed) and unbound (unperturbed) systems to the degree of ATPase allosteric inhibition. The ML analysis of the comparative perturbed ensembles revealed a redistribution of dynamic states in the inhibitor-bound versus inhibitor-free systems following allosteric binding. Linear regression models were built to quantify the percentage of experimental variance explained by the predicted inhibitor-bound TRAP1 states. Our strategy provides a comparative MD–ML framework to infer allosteric ligand functionality. Alleviating the time scale issues which prevent the routine use of MD, a combination of MD and ML represents a promising strategy to support in silico mechanistic studies and drug design.

Highlights

In silico hit-to-lead optimization is a challenging task in drug discovery
Rational selection of TRAP1MD descriptors was carried out restricting our choices to dimer subdomains with demonstrated key roles in TRAP1 conformational dynamics and ATPase function
We focused on residue-level solvation, contacts, and distances obtained from four inherently flexible regions of the buckled and straight monomers, belonging to N-terminal domains (NTD), small middle (SMD)−CTD linker, and the ATP sensor loop in the large middle (LMD) (Figure 1)

Summary

Introduction

High attrition rates in virtual screening campaigns are associated with prioritization of hits with a predicted binding affinity that does not always match the expected efficacy in vitro/vivo.[1] Determining a correlation between affinity and efficacy becomes even more challenging in the presence of allosteric compounds, as ligand effects at a distal site are often identified by monitoring substrate processing in the orthosteric pocket In this respect, occurrence of “flat SAR” or “functional switches” as a consequence of even small changes in ligand structure points out how efficacy is not a mere function of affinity.[2] Efficacy often depends on changes in system dynamics and kinetics. Even when structural transitions are only subtle or not readily observed, the change in conformational landscape can still be linked to a population shift that

Methods

Results

Discussion

Conclusion