Characterizing conformational states in GPCR structures using machine learning

2024/01/11 by Ilya Buyanov, Petr Popov · 1 voice
Biochemistry, Genetics and Molecular Biology · Computer Science · Chemistry · #Receptor Mechanisms and Signaling #Computational Drug Discovery Methods #Mass Spectrometry Techniques and Applications

paper · pdf · doi:10.1038/s41598-023-47698-1

openalex publication_date 2024/01/11 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/29

Abstract

G protein-coupled receptors (GPCRs) play a pivotal role in signal transduction and represent attractive targets for drug development. Recent advances in structural biology have provided insights into GPCR conformational states, which are critical for understanding their signaling pathways and facilitating structure-based drug discovery. In this study, we introduce a machine learning approach for conformational state annotation of GPCRs. We represent GPCR conformations as high-dimensional feature vectors, incorporating information about amino acid residue pairs involved in the activation pathway. Using a dataset of GPCR conformations in inactive and active states obtained through molecular dynamics simulations, we trained machine learning models to distinguish between inactive-like and active-like conformations. The developed model provides interpretable predictions and can be used for the large-scale analysis of molecular dynamics trajectories of GPCRs.

Citations

• CHARMM‐GUI: A web‐based graphical user interface for CHARMM
• LINCS: A linear constraint solver for molecular simulations
• GROMACS: Fast, flexible, and free
• G Protein-Coupled Receptors as Targets for Approved Drugs: How Many Targets and How Many Drugs?
• Highly accurate protein structure prediction with AlphaFold

Discussions

• “Characterizing conformational states in GPCR structures using machine learning.” has been published SVM, random forests, and XGBoost models trained on ML simulations of GPCRs to distinguish the two [bsky, 0 points, 0 comments]

Related

• Characterizing the Conformational States of G Protein Coupled Receptors Generated with AlphaFold
• Long Short-Term Memory to predict 3D Amino acids Positions in GPCR Molecular Dynamics
• GPCR-BERT: Interpreting Sequential Design of G Protein Coupled Receptors Using Protein Language Models
• Virtual screening of GPCRs: an in silico chemogenomics approach
• GPCR‐CA: A cellular automaton image approach for predicting G‐protein–coupled receptor functional classes