Learning allosteric interactions in Gα proteins from molecular dynamics simulations
Yu, Y.; Yang, M.; Wang, W.
Show abstract
G is a key subunit of heterotrimeric guanine-nucleotide-binding regulatory proteins, yet its conformational dynamics are not fully understood. In this study, we developed a Transformer-based graph neural network framework, Dynamic-Mixed Transformer (DMFormer), to investigate conformational dynamics of Go. DMFormer achieved an AUC of 0.75 on the training set, demonstrating robustness in distinguishing active and inactive states. The interpretability of the model was enhanced using integrated gradients, identifying the Switch II as a critical motif in stabilizing the active state and revealing distinct movement patterns between GTPase and -Helix domains. Our findings suggest that the conformational rigidity of the Q205L mutant in the Switch II segment leads to persistent activation. Overall, our study showcases DMFormer as an effective tool for analyzing protein conformational dynamics, offering valuable insights into activation mechanisms of G protein.
Matching journals
The top 3 journals account for 50% of the predicted probability mass.
Similar papers in this journal
- Rationalize the Functional Roles of Protein-Protein Interactions in Targeted Protein Degradation by Kinetic Monte-Carlo Simulations 97%
- Effect of Mutations on Smlt1473 Binding to Various Substrates Using Molecular Dynamics Simulations 96%
- Dynamic Community Composition Unravels Allosteric Communication in PDZ3 96%
Similar papers in this journal
- A linear response theory based method for prediction of large scale protein conformational changes upon ligand binding 96%
- Ligand Gaussian accelerated molecular dynamics 2 (LiGaMD2): Improved calculations of ligand binding thermodynamics and kinetics with closed protein pocket 95%
- Coupling of conformational switches in calcium sensor unraveled with local Markov models and transfer entropy 95%
Similar papers in this journal
- Large-scale, dynamin-like motions of the human guanylate binding protein 1 revealed by multi-resolution simulations 95%
- A Topological Data Analytic Approach for Discovering Biophysical Signatures in Protein Dynamics 95%
- Atomistic simulation of protein evolution reveals sequence covariation and timedependent fluctuations of site-specific substitution rates 94%
"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.