PINN-MEP: Continuous Neural Representations for Minimum-Energy Path Discovery in Molecular Systems

• URL: http://arxiv.org/abs/2504.16381v2
• Date: Mon, 28 Apr 2025 12:15:04 GMT
• Title: PINN-MEP: Continuous Neural Representations for Minimum-Energy Path Discovery in Molecular Systems
• Authors: Magnus Petersen, Roberto Covino,
• Abstract summary: We present a method that reformulates transition path generation as a continuous optimization problem solved through physics-informed neural networks (PINNs)<n>By representing transition paths as implicit neural functions, our method enables the efficient discovery of physically realistic transition pathways without requiring expensive path sampling.<n>We demonstrate our method's effectiveness on two proteins, including an explicitly hydrated bovine pancreatic trypsin inhibitor (BPTI) system with over 8,300 atoms.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Characterizing conformational transitions in physical systems remains a fundamental challenge in the computational sciences. Traditional sampling methods like molecular dynamics (MD) or MCMC often struggle with the high-dimensional nature of molecular systems and the high energy barriers of transitions between stable states. While these transitions are rare events in simulation timescales, they often represent the most biologically significant processes - for example, the conformational change of an ion channel protein from its closed to open state, which controls cellular ion flow and is crucial for neural signaling. Such transitions in real systems may take milliseconds to seconds but could require months or years of continuous simulation to observe even once. We present a method that reformulates transition path generation as a continuous optimization problem solved through physics-informed neural networks (PINNs) inspired by string methods for minimum-energy path (MEP) generation. By representing transition paths as implicit neural functions and leveraging automatic differentiation with differentiable molecular dynamics force fields, our method enables the efficient discovery of physically realistic transition pathways without requiring expensive path sampling. We demonstrate our method's effectiveness on two proteins, including an explicitly hydrated bovine pancreatic trypsin inhibitor (BPTI) system with over 8,300 atoms.

Related papers

• Conditional Synthesis of 3D Molecules with Time Correction Sampler [58.0834973489875]
  Time-Aware Conditional Synthesis (TACS) is a novel approach to conditional generation on diffusion models. It integrates adaptively controlled plug-and-play "online" guidance into a diffusion model, driving samples toward the desired properties.
  arXiv  Detail & Related papers  (2024-11-01T12:59:25Z)
• Transition Path Sampling with Improved Off-Policy Training of Diffusion Path Samplers [10.210248065533133]
  We introduce a novel approach that trains diffusion path samplers (DPS) to address the transition path sampling problem.<n>We reformulate the problem as an amortized sampling from the transition path distribution by minimizing the log-variance divergence between the path distribution induced by DPS and the transition path distribution.<n>We extensively evaluate our approach, termed TPS-DPS, on a synthetic system, small peptide, and challenging fast-folding proteins, demonstrating that it produces more realistic and diverse transition pathways than existing baselines.
  arXiv  Detail & Related papers  (2024-05-30T11:32:42Z)
• Learning and Controlling Silicon Dopant Transitions in Graphene using Scanning Transmission Electron Microscopy [58.51812955462815]
  We introduce a machine learning approach to determine the transition dynamics of silicon atoms on a single layer of carbon atoms. The data samples are processed and filtered to produce symbolic representations, which we use to train a neural network to predict transition probabilities. These learned transition dynamics are then leveraged to guide a single silicon atom throughout the lattice to pre-determined target destinations.
  arXiv  Detail & Related papers  (2023-11-21T21:51:00Z)
• Message-Passing Neural Quantum States for the Homogeneous Electron Gas [41.94295877935867]
  We introduce a message-passing-neural-network-based wave function Ansatz to simulate extended, strongly interacting fermions in continuous space. We demonstrate its accuracy by simulating the ground state of the homogeneous electron gas in three spatial dimensions.
  arXiv  Detail & Related papers  (2023-05-12T04:12:04Z)
• Enhanced Sampling of Configuration and Path Space in a Generalized Ensemble by Shooting Point Exchange [71.49868712710743]
  We propose a new approach to simulate rare events caused by transitions between long-lived states. The scheme substantially enhances the efficiency of the transition path sampling simulations. It yields information on thermodynamics, kinetics and reaction coordinates of molecular processes without distorting their dynamics.
  arXiv  Detail & Related papers  (2023-02-17T08:41:31Z)
• Stochastic Optimal Control for Collective Variable Free Sampling of Molecular Transition Paths [60.254555533113674]
  We consider the problem of sampling transition paths between two given metastable states of a molecular system. We propose a machine learning method for sampling said transitions.
  arXiv  Detail & Related papers  (2022-06-27T14:01:06Z)
• Accurate Machine Learned Quantum-Mechanical Force Fields for Biomolecular Simulations [51.68332623405432]
  Molecular dynamics (MD) simulations allow atomistic insights into chemical and biological processes. Recently, machine learned force fields (MLFFs) emerged as an alternative means to execute MD simulations. This work proposes a general approach to constructing accurate MLFFs for large-scale molecular simulations.
  arXiv  Detail & Related papers  (2022-05-17T13:08:28Z)
• Generative methods for sampling transition paths in molecular dynamics [0.0]
  Simulating transition paths linking one metastable state to another one is difficult by direct numerical methods. We explore two approaches to more efficiently generate transition paths: sampling methods based on generative models such as variational autoencoders, and importance sampling methods based on reinforcement learning.
  arXiv  Detail & Related papers  (2022-05-05T17:50:10Z)
• Sampling Rare Conformational Transitions with a Quantum Computer [0.0]
  We introduce a machine learning algorithm and MD simulations implemented on a classical computer with adiabatic quantum computing. We derive a rigorous low-resolution representation of the system's dynamics, based on a small set of molecular configurations. Our results provide a new paradigm for MD simulations to integrate machine learning and quantum computing.
  arXiv  Detail & Related papers  (2022-01-27T19:46:06Z)
• Accelerated Simulations of Molecular Systems through Learning of their Effective Dynamics [4.276697874428501]
  We present a novel framework to advance simulation by up to three orders of magnitude. LED learns the effective dynamics of molecular systems. We demonstrate the effectiveness of LED in the M"ueller-Brown potential, the Trp Cage protein, and the alanine dipeptide.
  arXiv  Detail & Related papers  (2021-02-17T15:15:37Z)
• Ultrafast viscosity measurement with ballistic optical tweezers [55.41644538483948]
  Noninvasive viscosity measurements require integration times of seconds. We demonstrate a four orders-of-magnitude improvement in speed, down to twenty microseconds. We achieve this using the instantaneous velocity of a trapped particle in an optical tweezer.
  arXiv  Detail & Related papers  (2020-06-29T00:09:40Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.