Searcharxiv⌕ Search

arXiv subjects

Aldo S. Pasos-Trejo

Publications and source records attributed to Aldo S. Pasos-Trejo.

4 recordsLinked to original sources

An Exploration of Physical and Chemical Representation in Coarse-Grained, Machine-Learned Protein Models

Machine-learned coarse-graining has emerged as a reliable framework for building protein models that accurately and efficiently sample their relevant conformational landscape. Existing studies assume a predefined map from full- to coarse-grained resolution. However, the choice of map strongly affects the quality of the models. Here, we study the dependence of system-specific machine-learned coarse-grained (MLCG) models across 7 mapping choices, spanning different resolutions and embedding types for coarse-grained beads. We show that resolution and chemical diversity do not always correlate with accuracy, and that accurate protein-specific models can be generated using minimal chemical diversity if the latent space representation of the system has high enough dimensionality.

q-bio.BM↗

Exploring the World of Lipids with Machine-Learned Coarse-Grained Models

Lipid bilayers are central to cellular organization and function, yet their atomistic modelling remains constrained by its high computational cost. While coarse-grained (CG) models can overcome this bottleneck, they are limited in accuracy due to the use of simplified functional forms based on molecular mechanics. Using a hybrid functional form combining physics-based terms with a graph neural network, we present implicit-solvent, machine-learned CG models for POPC. When trained on single-lipid data, the model recovers the atomistic conformational landscape. By adding short atomistic simulations of a small flat bilayer to the training data and combining force matching with a denoising objective, we train a model that accurately reproduces bilayer structure and dynamics, in closer agreement with the atomistic reference than existing models, like Martini3 and DryMartini. Beyond its training data, the model stabilizes curved geometries, including vesicles, and captures complex cooperative phenomena such as bilayer and vesicle self-assembly and pore sealing. While limitations remain, particularly regarding chemical transferability, our results establish machine-learned coarse-grained potentials as a promising path towards robust and accurate CG models of lipids and membranes.

physics.bio-ph↗

A strategic roadmap for an atomistic machine-learning ecosystem

Data-driven machine learning (ML) techniques have become an essential tool in many domains of science. Their application to atomistic simulations of matter is particularly widespread and impactful. This success is due largely to the existence of a well-developed and established physics-based modeling framework, ranging from first-principles electronic-structure calculations to molecular dynamics and statistical sampling, into which ML was integrated naturally to reshape long-standing trade-offs between accuracy, efficiency, and scale. Nevertheless, this integration raises both conceptual and practical challenges, from choosing between data-centric and physics-based modeling approaches to adapting established software stacks to modern hardware accelerators and ML libraries. As the field evolves rapidly, fueled in part by widespread enthusiasm but also by tangible impact, it seems appropriate to take a moment to consider the current state of the art and open challenges, and reflect on what can be done to better coordinate efforts across the community. With this goal in mind, several members of this community met in Lausanne in January 2026 at CECAM to discuss algorithms, models, software and hardware infrastructure, and the most promising scientific applications that have become possible thanks to the use of artificial intelligence in atomic-scale simulations. This strategic roadmap paper summarizes the outcomes of these discussions, suggesting some long-term goals, and some concrete actions, to establish a healthy, sustainable and impactful atomistic ML ecosystem.

physics.chem-ph↗

Navigating protein landscapes with a machine-learned transferable coarse-grained model

The most popular and universally predictive protein simulation models employ all-atom molecular dynamics (MD), but they come at extreme computational cost. The development of a universal, computationally efficient coarse-grained (CG) model with similar prediction performance has been a long-standing challenge. By combining recent deep learning methods with a large and diverse training set of all-atom protein simulations, we here develop a bottom-up CG force field with chemical transferability, which can be used for extrapolative molecular dynamics on new sequences not used during model parametrization. We demonstrate that the model successfully predicts folded structures, intermediates, metastable folded and unfolded basins, and the fluctuations of intrinsically disordered proteins while it is several orders of magnitude faster than an all-atom model. This showcases the feasibility of a universal and computationally efficient machine-learned CG model for proteins.

q-bio.BM↗