arXiv subjects

Michael S. Chen

Publications and source records attributed to Michael S. Chen.

12 recordsLinked to original sources

arXiv2026

Sampling Free Energy Landscapes of Ionic Colloidal Crystal Systems using Machine-Learned Proxy Collective Variables

Charged colloids coated with a polymer brush can be designed to preferentially self-assemble into different crystal structures by varying easy-to-tune experimental conditions. For a given set of conditions, we have observed in experiments and simulations a distribution of thermodynamically (meta)stable self-assembled crystal structures. Properly quantifying the free energy landscape of these colloidal systems is essential for rationally choosing conditions to preferentially target particular crystal structures. For some of the structures we have formed, standard crystalline order parameters are not able to differentiate between crystals or between crystals and amorphous aggregates. We show that local environment similarity descriptors are able to distinguish the relevant metastable states, but are too expensive for use in biased MD simulations. Here, we adopt an approach from machine-learned interaction potentials showing that SE(3)-equivariant transformer networks can serve as an efficient-to-evaluate machine-learned proxy. As a result, we can compute the relative free energies of accessible colloidal structures as a function of different experimentally-relevant physical knobs that can steer our system between two observed crystal types. As an example application, we then show how changing surface potentials of positive and negative colloids while maintaining the same attractive energy can shift which crystal structure is favored.

cond-mat.stat-mech↗

arXiv2026

Streamlining Analysis and Design of Two-Dimensional Electronic Spectroscopy using Machine Learning

Two-dimensional electronic spectroscopy (2DES) offers unique insights into the coupling between electronic and nuclear motion and dynamics, making it a key technique in diverse fields, including materials science and biology. Obtaining 2DES data requires a series of measurements that involve multiple pulses to construct the full picture -- a time-consuming task that often necessitates working with limited or noisy data. Here we introduce a machine-learning based framework that aims to maximize the data that can be extracted from 2DES experiments and provides guidance towards the selection of additional experiments. We design a Gaussian mixture model to learn the underlying spectral density of a system, allowing the extraction of reorganization energies and the extrapolation of the 2DES spectra to other time delays beyond those measured, and demonstrate how our framework can be used to select additional measurements to further improve the accuracy. We show that our approach yields accurate results on a variety of systems, including simulations ranging from photoactive yellow protein in the gas phase to Nile red in benzene to the anionic green fluorescent protein chromophore in water, and experiments on Nile blue in ethanol. Our work provides an efficient route to extract maximum insights from 2DES while incurring minimal experimental costs.

physics.chem-ph↗

arXiv2026

PACSim: A Flexible Simulation Framework for Polymer-Attenuated Coulombic Self-Assembly

Polymer-Attenuated Coulombic Self-Assembly (PACS) is a flexible experimental approach for generating crystals from simple colloidal building blocks. The central components are charged spherical particles coated with a polymer brush that prevents irreversible aggregation. Whether oppositely charged colloids crystallize, and which structures they form, depends on several factors, including colloid concentration, charge, and size, as well as the salt concentration of the solution. Molecular dynamics (MD) simulations are a powerful tool for predicting the outcomes of PACS assembly experiments and also provide particle-level insight into the assembly processes. Here, we present an open-source simulation framework, PACSim, that enables MD simulation studies of assembly by PACS across a range of experimentally relevant scenarios. PACSim is built on top of OpenMM, a flexible MD simulation framework that readily supports the implementation of different interaction potentials, as well as integration with other tools such as enhanced-sampling and machine-learning frameworks. We describe the motivation for PACSim, outline its features, report methodological advancements inspired by this framework, and provide examples of its use.

cond-mat.soft↗

arXiv2025

Two-dimensional electronic spectroscopy in the condensed phase using equivariant transformer accelerated molecular dynamics simulations

Two-dimensional electronic spectroscopy (2DES) provides rich information about how the electronic states of molecules, proteins, and solid-state materials interact with each other and their surrounding environment. Atomistic molecular dynamics simulations offer an appealing route to uncover how nuclear motions mediate electronic energy relaxation and their manifestation in electronic spectroscopies, but are computationally expensive. Here we show that, by using an equivariant transformer-based machine learning architecture trained with only ~2500 ground state and ~100 excited state electronic structure calculations, one can construct accurate machine-learned potential energy surfaces for both the ground-state electronic surface and excited-state energy gap. We demonstrate the utility of this approach for simulating the dynamics of Nile blue in ethanol, where we experimentally validate and decompose the simulated 2DES to establish the nuclear motions of the chromophore and the solvent that couple to the excited state, connecting the spectroscopic signals to their molecular origin.

physics.chem-ph↗

arXiv2024

On the design space between molecular mechanics and machine learning force fields

A force field as accurate as quantum mechanics (QM) and as fast as molecular mechanics (MM), with which one can simulate a biomolecular system efficiently enough and meaningfully enough to get quantitative insights, is among the most ardent dreams of biophysicists -- a dream, nevertheless, not to be fulfilled any time soon. Machine learning force fields (MLFFs) represent a meaningful endeavor towards this direction, where differentiable neural functions are parametrized to fit ab initio energies, and furthermore forces through automatic differentiation. We argue that, as of now, the utility of the MLFF models is no longer bottlenecked by accuracy but primarily by their speed (as well as stability and generalizability), as many recent variants, on limited chemical spaces, have long surpassed the chemical accuracy of $1$ kcal/mol -- the empirical threshold beyond which realistic chemical predictions are possible -- though still magnitudes slower than MM. Hoping to kindle explorations and designs of faster, albeit perhaps slightly less accurate MLFFs, in this review, we focus our attention on the design space (the speed-accuracy tradeoff) between MM and ML force fields. After a brief review of the building blocks of force fields of either kind, we discuss the desired properties and challenges now faced by the force field development community, survey the efforts to make MM force fields more accurate and ML force fields faster, envision what the next generation of MLFF might look like.

physics.chem-ph↗

arXiv2024

Accurate and efficient structure elucidation from routine one-dimensional NMR spectra using multitask machine learning

Rapid determination of molecular structures can greatly accelerate workflows across many chemical disciplines. However, elucidating structure using only one-dimensional (1D) NMR spectra, the most readily accessible data, remains an extremely challenging problem because of the combinatorial explosion of the number of possible molecules as the number of constituent atoms is increased. Here, we introduce a multitask machine learning framework that predicts the molecular structure (formula and connectivity) of an unknown compound solely based on its 1D 1H and/or 13C NMR spectra. First, we show how a transformer architecture can be constructed to efficiently solve the task, traditionally performed by chemists, of assembling large numbers of molecular fragments into molecular structures. Integrating this capability with a convolutional neural network (CNN), we build an end-to-end model for predicting structure from spectra that is fast and accurate. We demonstrate the effectiveness of this framework on molecules with up to 19 heavy (non-hydrogen) atoms, a size for which there are trillions of possible structures. Without relying on any prior chemical knowledge such as the molecular formula, we show that our approach predicts the exact molecule 69.6% of the time within the first 15 predictions, reducing the search space by up to 11 orders of magnitude.

physics.chem-ph↗

arXiv2024

Quantum Hardware-Enabled Molecular Dynamics via Transfer Learning

The ability to perform ab initio molecular dynamics simulations using potential energies calculated on quantum computers would allow virtually exact dynamics for chemical and biochemical systems, with substantial impacts on the fields of catalysis and biophysics. However, noisy hardware, the costs of computing gradients, and the number of qubits required to simulate large systems present major challenges to realizing the potential of dynamical simulations using quantum hardware. Here, we demonstrate that some of these issues can be mitigated by recent advances in machine learning. By combining transfer learning with techniques for building machine-learned potential energy surfaces, we propose a new path forward for molecular dynamics simulations on quantum hardware. We use transfer learning to reduce the number of energy evaluations that use quantum hardware by first training models on larger, less accurate classical datasets and then refining them on smaller, more accurate quantum datasets. We demonstrate this approach by training machine learning models to predict a molecule's potential energy using Behler-Parrinello neural networks. When successfully trained, the model enables energy gradient predictions necessary for dynamics simulations that cannot be readily obtained directly from quantum hardware. To reduce the quantum resources needed, the model is initially trained with data derived from low-cost techniques, such as Density Functional Theory, and subsequently refined with a smaller dataset obtained from the optimization of the Unitary Coupled Cluster ansatz. We show that this approach significantly reduces the size of the quantum training dataset while capturing the high accuracies needed for quantum chemistry simulations.

physics.chem-ph↗

arXiv2023

Elucidating the role of hydrogen bonding in the optical spectroscopy of the solvated green fluorescent protein chromophore: using machine learning to establish the importance of high-level electronic structure

Hydrogen bonding interactions with chromophores in chemical and biological environments play a key role in determining their electronic absorption and relaxation processes, which are manifested in their linear and multidimensional optical spectra. For chromophores in the condensed phase, the large number of atoms needed to simulate the environment has traditionally prohibited the use of high-level excited-state electronic structure methods. By leveraging transfer learning, we show how to construct machine-learned models to accurately predict high-level excitation energies of a chromophore in solution from only 400 high-level calculations. We show that when the electronic excitations of the green fluorescent protein chromophore in water are treated using EOM-CCSD embedded in a DFT description of the solvent, the optical spectrum is correctly captured and that this improvement arises from correctly treating the coupling of the electronic transition to electric fields, which leads to a larger response upon hydrogen bonding between the chromophore and water.

physics.chem-ph↗

arXiv2022

Machine learning potentials from transfer learning of periodic correlated electronic structure methods: Application to liquid water with AFQMC, CCSD, and CCSD(T)

Obtaining the atomistic structure and dynamics of disordered condensed phase systems from first principles remains one of the forefront challenges of chemical theory. Here we exploit recent advances in periodic electronic structure to show that, by leveraging transfer learning starting from lower tier electronic structure methods, one can obtain machine learned potential energy surfaces for liquid water from the higher tier AFQMC, CCSD, and CCSD(T) approaches using $\le$200 energies. By performing both classical and path integral molecular dynamics simulations on these machine learned potential energy surfaces we uncover the interplay of dynamical electron correlation and nuclear quantum effects across the entire liquid range of water while providing a general strategy for efficiently utilizing periodic correlated electronic structure methods to explore disordered condensed phase systems.

physics.chem-ph↗

arXiv2022

Optically induced anisotropy in time-resolved scattering: Imaging molecular scale structure and dynamics in disordered media with experiment and theory

Time-resolved scattering experiments enable imaging of materials at the molecular scale with femtosecond time resolution. However, in disordered media they provide access to just one radial dimension thus limiting the study of orientational structure and dynamics. Here we introduce a rigorous and practical theoretical framework for predicting and interpreting experiments combining optically induced anisotropy and time-resolved scattering. Using impulsive nuclear Raman and ultrafast X-ray scattering experiments of chloroform and simulations, we demonstrate that this framework can accurately predict and elucidate both the spatial and temporal features of these experiments.

physics.chem-ph↗

arXiv2021

AENET-LAMMPS and AENET-TINKER: Interfaces for Accurate and Efficient Molecular Dynamics Simulations with Machine Learning Potentials

Machine learning potentials (MLPs) trained on data from quantum-mechanics based first-principles methods can approach the accuracy of the reference method at a fraction of the computational cost. To facilitate efficient MLP-based molecular dynamics (MD) and Monte Carlo (MC) simulations, an integration of the MLPs with sampling software is needed. Here we develop two interfaces that link the Atomic Energy Network (ænet) MLP package with the popular sampling packages TINKER and LAMMPS. The three packages, ænet, TINKER, and LAMMPS, are free and open-source software that enable, in combination, accurate simulations of large and complex systems with low computational cost that scales linearly with the number of atoms. Scaling tests show that the parallel efficiency of the ænet-TINKER interface is nearly optimal but is limited to shared-memory systems. The ænet-LAMMPS interface achieves excellent parallel efficiency on highly parallel distributed memory systems and benefits from the highly optimized neighbor list implemented in LAMMPS. We demonstrate the utility of the two MLP interfaces for two relevant example applications, the investigation of diffusion phenomena in liquid water and the equilibration of nanostructured amorphous battery materials.

cond-mat.mtrl-sci↗

arXiv2020

Exploiting machine learning to efficiently predict multidimensional optical spectra in complex environments

The excited state dynamics of chromophores in complex environments determine a range of vital biological and energy capture processes. Time-resolved, multidimensional optical spectroscopies provide a key tool to investigate these processes. Although theory has the potential to decode these spectra in terms of the electronic and atomistic dynamics, the need for large numbers of excited state electronic structure calculations severely limits first principles predictions of multidimensional optical spectra for chromophores in the condensed phase. Here, we leverage the locality of chromophore excitations to develop machine learning models to predict the excited state energy gap of chromophores in complex environments for efficiently constructing linear and multidimensional optical spectra. By analyzing the performance of these models, which span a hierarchy of physical approximations, across a range of chromophore-environment interaction strengths, we provide strategies for the construction of ML models that greatly accelerate the calculation of multidimensional optical spectra from first principles.

physics.chem-ph↗