From Deep Mutational Mapping of Allosteric Protein Landscapes to Deep Learning of Allostery and Hidden Allosteric Sites: Zooming in on “Allosteric Intersection” of Biochemical and Big Data Approaches

Abstract

The recent advances in artificial intelligence (AI) and machine learning have driven the design of new expert systems and automated workflows that are able to model complex chemical and biological phenomena. In recent years, machine learning approaches have been developed and actively deployed to facilitate computational and experimental studies of protein dynamics and allosteric mechanisms. In this review, we discuss in detail new developments along two major directions of allosteric research through the lens of data-intensive biochemical approaches and AI-based computational methods. Despite considerable progress in applications of AI methods for protein structure and dynamics studies, the intersection between allosteric regulation, the emerging structural biology technologies and AI approaches remains largely unexplored, calling for the development of AI-augmented integrative structural biology. In this review, we focus on the latest remarkable progress in deep high-throughput mining and comprehensive mapping of allosteric protein landscapes and allosteric regulatory mechanisms as well as on the new developments in AI methods for prediction and characterization of allosteric binding sites on the proteome level. We also discuss new AI-augmented structural biology approaches that expand our knowledge of the universe of protein dynamics and allostery. We conclude with an outlook and highlight the importance of developing an open science infrastructure for machine learning studies of allosteric regulation and validation of computational approaches using integrative studies of allosteric mechanisms. The development of community-accessible tools that uniquely leverage the existing experimental and simulation knowledgebase to enable interrogation of the allosteric functions can provide a much-needed boost to further innovation and integration of experimental and computational technologies empowered by booming AI field.

Designing drugs and chemical probes with the dualsteric approach

“…It was not easy to rationally design bitopic modulators in early days, probably because in many proteins, only the orthosteric binding site was recognized, while bitopic modulators require double binding sites. 51,52 Usually, bitopic molecules were found by serendipity, either like the previous example, that a randomly designed bivalent modulator is found to be bitopic, or sometimes a designed monovalent molecule was found to be dualsteric. For example, SB269652 53 was developed to be an allosteric inhibitor of Dopamine D 2 Receptor (D 2 R).…”

Decrypting Allostery in Membrane-Bound K-Ras4B Using Complementary In Silico Approaches Based on Unbiased Molecular Dynamics Simulations

“…21,23,25,28,59 ), as well as the combination with machine learning. 60 Markov State Model analysis, Replica Exchange MD, and Principal Component Analysis have also been applied specifically to K-Ras4B. 48,49,51,54 In this context, there exist atomistic-resolution methods rooted in unbiased MD that, while starting from different initial assumptions, aim to tackle the question of unveiling the atomistic and mechanistic details of allosteric modulation and the key residues involved in this process.…”

“…, , in the field of molecular diagnostics. While the time scales accessible by atomistic simulations (now on the microsecond scale) remain on the short side when it comes to capturing complete allosteric conformational changes, a number of solutions, including coarse-graining and enhanced sampling MD, have become available over the years (cf. ,,,, ), as well as the combination with machine learning . Markov State Model analysis, Replica Exchange MD, and Principal Component Analysis have also been applied specifically to K-Ras4B. ,,, …”

Decrypting the languages of allostery in membrane-bound K-Ras4B using four complementaryin silicoapproaches

“…21,23,27,58 ), as well as the combination with machine learning. 59 Markov State Model (MSM) analysis, Replica Exchange MD, and Principal Component Analysis (PCA) have also been applied specifically to K- Ras4B. 47,48,50,53…”