Autoencoder-based detection of the residues involved in G protein-coupled receptor signaling

Abstract

Regulator binding and mutations alter protein dynamics. The transmission of the signal of these alterations to distant sites through protein motion results in changes in protein expression and cell function. The detection of residues involved in signal transmission contributes to an elucidation of the mechanisms underlying processes as vast as cellular function and disease pathogenesis. We developed an autoencoder (AE) based method that detects residues essential for signaling by comparing the fluctuation data, particularly the time fluctuation of the side-chain distances between residues, during molecular dynamics simulations between the ligand-bound and -unbound forms or wild-type and mutant forms of proteins. Here, the AE-based method was applied to the G protein-coupled receptor (GPCR) system, particularly a class A-type GPCR, CXCR4, to detect the essential residues involved in signaling. Among the residues involved in the signaling of the homolog CXCR2, which were extracted from the literature based on the complex structures of the ligand and G protein, our method could detect more than half of the essential residues involved in G protein signaling, including those spanning the fifth and sixth transmembrane helices in the intracellular region, despite the lack of information regarding the interaction with G protein in our CXCR4 models.

The application of artificial intelligence to accelerate G protein‐coupled receptor drug discovery

“…Machine learning models have also analysed molecular dynamics data to give insights into GPCR signalling. An autoencoder-based method analysed fluctuation data generated from molecular dynamics simulation of ligand-bound and -unbound forms of wild-type and mutant CXCR4 chemokine receptors to detect residues essential for signalling (Tsuchiya et al, 2021). Similarly, an unsupervised learning model analysed differences in Gα s activity induced by 7800 mutations of the β 2 -adrenoceptor (generated by deep mutational scanning) to predict residues important for signalling (Jones et al, 2020).…”

Machine learning‐based approach for prediction of ion channels and their subclasses

“…PCA aims to extract the key data from the data set and consider it as a pair of orthogonal variables known as principal components (PCs). 21,22 Many authors of the paper used PC analysis for G-protein coupled receptor classification, [23][24][25] prediction of protein-protein interactions, [26][27][28][29] protein subcellular localization prediction, [30][31][32] multilabel protein subcellular localization prediction, 33,34 and DNA binding domain. 35 F I G U R E 1 The number of sequences in every ion channel classes along with its subclasses SINGH AND TIWARI | 75…”