Independent Training Trajectories Learn the Same Interaction Parameters in Coarse-Grained Protein Models
PRX Life · 04.11.2026 · 4 (4)
DOI: 10.1103/dmcv-sx8q ↗Kurz gefasst
Fachartikel in der Zeitschrift PRX Life, online erschienen am 04.11.2026. Verfasst von Marcos Lequerica-Mateos und 4 weiteren Autor:innen. Die Arbeit nennt 69 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Science Foundation, Welch Foundation, Cancer Prevention and Research Institute of Texas.
Abstract (Originalsprache)
This work introduces a self-consistent training framework for learning residue–residue interaction parameters in matrix-based coarse-grained protein models. By combining direct coupling analysis with a physics-based design model, we construct a feedback loop in which the interaction matrix is iteratively updated from sequences generated by the model itself. We provide a mathematical foundation for this behavior by showing that, for a given iterative map satisfying explicit contact-locality and spectral assumptions, the training process is a contraction, guaranteeing convergence to a unique fixed point independent of the initial interaction matrix. This fixed-point property is general for coarse-grained models in which the residue-residue energy is represented by a distance-dependent term modulated by a type-dependent coupling matrix, while the learned interaction parameters remain specific to the underlying model physics. We then examine the empirical consequence of this framework in Caterpillar, a coarse-grained potential for folding and design. Independent training trajectories, defined by different target structures and stochastic sampling, converge to statistically equivalent interaction matrices. Each trajectory recovers the full interaction solution without requiring ensemble averaging, and the averaged trajectory reaches the same result. The resulting framework provides a link between sequence statistics and physically modeled interaction energies. Applied to protein design, it yields interaction matrices associated with improved structural fidelity and accurate contact prediction, while clarifying how learned sequence patterns relate to the interactions that stabilize protein structure.
Förderung
- National Science Foundation
- Welch Foundation
- Cancer Prevention and Research Institute of Texas
- National Institutes of Health
- University of Texas at Dallas
- European Commission
Zitieren
APA
Lequerica-Mateos, M., Martin, J., Onuchic, J. N., Morcos, F., & Coluzza, I. (2026). Independent Training Trajectories Learn the Same Interaction Parameters in Coarse-Grained Protein Models. PRX Life, 4(4). https://doi.org/10.1103/dmcv-sx8q
Vancouver
Lequerica-Mateos M, Martin J, Onuchic JN, Morcos F, Coluzza I. Independent Training Trajectories Learn the Same Interaction Parameters in Coarse-Grained Protein Models. PRX Life. 2026;4(4). doi:10.1103/dmcv-sx8q
BibTeX
@article{LequericaMateos2026,
author = {Lequerica-Mateos, Marcos and Martin, Jonathan and Onuchic, José N. and Morcos, Faruck and Coluzza, Ivan},
title = {Independent Training Trajectories Learn the Same Interaction Parameters in Coarse-Grained Protein Models},
journal = {PRX Life},
year = {2026},
volume = {4},
number = {4},
doi = {10.1103/dmcv-sx8q}
}
EUVIMED