An official website of the United States government
Rapid computational exploration of the free energy landscape of biological molecules remains an active area of research due to the difficulty of sampling rare state transitions in molecular dynamics (MD) simulations. In recent years, an increasing number of studies have exploited machine learning (ML) models to enhance and analyze MD simulations. Notably, unsupervised models that extract kinetic information from a set of parallel trajectories have been proposed including the variational approach for Markov processes (VAMP), VAMPNets, and time-lagged variational autoencoders (TVAE). In this work, we propose a combination of adaptive sampling with active learning of kinetic models to accelerate the discovery of the conformational landscape of biomolecules. In particular, we introduce and compare several techniques that combine kinetic models with two adaptive sampling regimes (least counts and multiagent reinforcement learning- based adaptive sampling) to enhance the exploration of conformational ensembles without introducing biasing forces. Moreover, inspired by the active learning approach of uncertainty-based sampling, we also present MaxEnt VAMPNet. This technique consists of restarting simulations from the microstates that maximize the Shannon entropy of a VAMPNet trained to perform the soft discretization of metastable states. By running simulations on two test systems, the WLALL pentapeptide and the villin headpiece subdomain, we empirically demonstrate that MaxEnt VAMPNet results in faster exploration of conformational landscapes compared with the baseline and other proposed methods.
more »
« less
Adaptive Sampling Methods for Molecular Dynamics in the Era of Machine Learning
Molecular dynamics (MD) simulations are fundamental computational tools for the study of proteins and their free energy landscapes. However, sampling protein conformational changes through MD simulations is challenging due to the relatively long time scales of these processes. Many enhanced sampling approaches have emerged to tackle this problem, including biased sampling and path-sampling methods. In this Perspective, we focus on adaptive sampling algorithms. These techniques differ from other approaches because the thermodynamic ensemble is preserved and the sampling is enhanced solely by restarting MD trajectories at particularly chosen seeds rather than introducing biasing forces. We begin our treatment with an overview of theoretically transparent methods, where we discuss principles and guidelines for adaptive sampling. Then, we present a brief summary of select methods that have been applied to realistic systems in the past. Finally, we discuss recent advances in adaptive sampling methodology powered by deep learning techniques, as well as their shortcomings.
more »
« less
- Award ID(s):
- 1845606
- PAR ID:
- 10507114
- Publisher / Repository:
- American Chemical Society
- Date Published:
- Journal Name:
- The Journal of Physical Chemistry B
- Volume:
- 127
- Issue:
- 50
- ISSN:
- 1520-6106
- Page Range / eLocation ID:
- 10669 to 10681
- Subject(s) / Keyword(s):
- Molecular Simulations Markov State Models Adaptive Sampling Enhanced Sampling
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
Abstract Electron paramagnetic resonance (EPR) has become a powerful probe of conformational heterogeneity and dynamics of biomolecules. In this Review, we discuss different computational modeling techniques that enrich the interpretation of EPR measurements of dynamics or distance restraints. A variety of spin labels are surveyed to provide a background for the discussion of modeling tools. Molecular dynamics (MD) simulations of models containing spin labels provide dynamical properties of biomolecules and their labels. These simulations can be used to predict EPR spectra, sample stable conformations and sample rotameric preferences of label sidechains. For molecular motions longer than milliseconds, enhanced sampling strategies and de novo prediction software incorporating or validated by EPR measurements are able to efficiently refine or predict protein conformations, respectively. To sample large‐amplitude conformational transition, a coarse‐grained or an atomistic weighted ensemble (WE) strategy can be guided with EPR insights. Looking forward, we anticipate an integrative strategy for efficient sampling of alternate conformations by de novo predictions, followed by validations by systematic EPR measurements and MD simulations. Continuous pathways between alternate states can be further sampled by WE‐MD including all intermediate states.more » « less
-
Molecular dynamics (MD) is the method of choice for understanding the structure, function, and interactions of molecules. However, MD simulations are limited by the strong metastability of many molecules, which traps them in a single conformation basin for an extended amount of time. Enhanced sampling techniques, such as metadynamics and replica exchange, have been developed to overcome this limitation and accelerate the exploration of complex free energy landscapes. In this paper, we propose Vendi Sampling, a replica-based algorithm for increasing the efficiency and efficacy of the exploration of molecular conformation spaces. In Vendi sampling, replicas are simulated in parallel and coupled via a global statistical measure, the Vendi Score, to enhance diversity. Vendi sampling allows for the recovery of unbiased sampling statistics and dramatically improves sampling efficiency. We demonstrate the effectiveness of Vendi sampling in improving molecular dynamics simulations by showing significant improvements in coverage and mixing between metastable states and convergence of free energy estimates for four common benchmarks, including Alanine Dipeptide and Chignolin.more » « less
-
Abstract Molecular simulations are an important tool for research in physics, chemistry, and biology. The capabilities of simulations can be greatly expanded by providing access to advanced sampling methods and techniques that permit calculation of the relevant underlying free energy landscapes. In this sense, software that can be seamlessly adapted to a broad range of complex systems is essential. Building on past efforts to provide open-source community-supported software for advanced sampling, we introduce PySAGES, a Python implementation of the Software Suite for Advanced General Ensemble Simulations (SSAGES) that provides full GPU support for massively parallel applications of enhanced sampling methods such as adaptive biasing forces, harmonic bias, or forward flux sampling in the context of molecular dynamics simulations. By providing an intuitive interface that facilitates the management of a system’s configuration, the inclusion of new collective variables, and the implementation of sophisticated free energy-based sampling methods, the PySAGES library serves as a general platform for the development and implementation of emerging simulation techniques. The capabilities, core features, and computational performance of this tool are demonstrated with clear and concise examples pertaining to different classes of molecular systems. We anticipate that PySAGES will provide the scientific community with a robust and easily accessible platform to accelerate simulations, improve sampling, and enable facile estimation of free energies for a wide range of materials and processes.more » « less
-
Molecular dynamics (MD) simulations generate valuable all-atom resolution trajectories of complex systems, but analyzing this high-dimensional data as well as reaching practical timescales, even with powerful supercomputers, remain open problems. As such, many specialized sampling and reaction coordinate construction methods exist that alleviate these problems. However, these methods typically don't work directly on all atomic coordinates, and still require previous knowledge of the important distinguishing features of the system, known as order parameters (OPs). Here we present AMINO, an automated method that generates such OPs by screening through a very large dictionary of OPs, such as all heavy atom contacts in a biomolecule. AMINO uses ideas from information theory to learn OPs that can then serve as an input for designing a reaction coordinate which can then be used in many enhanced sampling methods. Here we outline its key theoretical underpinnings, and apply it to systems of increasing complexity. Our applications include a problem of tremendous pharmaceutical and engineering relevance, namely, calculating the binding affinity of a protein–ligand system when all that is known is the structure of the bound system. Our calculations are performed in a human-free fashion, obtaining very accurate results compared to long unbiased MD simulations on the Anton supercomputer, but in orders of magnitude less computer time. We thus expect AMINO to be useful for the calculation of thermodynamics and kinetics in the study of diverse molecular systems.more » « less
- Free Publicly Accessible Full Text
-
Accepted Manuscript1.0
- Journal Article:
- https://doi.org/10.1021/acs.jpcb.3c04843
