Adrian E. Roitberg

Nonadiabatic molecular dynamics is essential for simulating photoinduced processes, but its application to large molecular systems is often limited by the cost of repeatedly evaluating excited-state energies, forces, and nonadiabatic couplings. Here, we present a GPU-accelerated implementation of trajectory surface hopping within PYSEQM (https://github.com/lanl/PYSEQM/), a PyTorch-based semiempirical quantum chemistry framework. The module combines semiempirical model Hamiltonians with configuration-interaction singles excited states and introduces the nonadiabatic coupling vectors and time-derivative couplings required for surface-hopping dynamics. The implementation further includes treatments of trivial crossings and electronic decoherence, providing a complete framework for propagating coupled electronic and nuclear dynamics. To improve GPU utilization, independent trajectories are propagated concurrently in batches. Benchmark calculations show that this strategy substantially increases aggregate simulation throughput as the batch size is increased for small molecules. We demonstrate the applicability of the method to large molecular systems by simulating the excited-state population dynamics of methyl- and tert-butyl-substituted molecular nanostar dendrimers, which contain dense manifolds of electronically excited states. These calculations show that semiempirical surface-hopping dynamics can be extended to molecular systems that remain challenging for conventional ab initio approaches. In addition, the differentiable PyTorch formulation provides a data-science route for optimizing semiempirical Hamiltonian parameters against reference excited-state properties and, ultimately, dynamical observables. PYSEQM therefore provides a platform for high-throughput nonadiabatic molecular dynamics and for the development of data-driven semiempirical models for photophysics and photochemistry.

Key objectives in conditional molecular generation include ensuring chemical validity, aligning generated molecules with target properties, promoting structural diversity, and enabling efficient sampling for discovery. Recent advances in computer vision introduced a range of new guidance strategies for generative models, many of which can be adapted to support these goals. In this work, we integrate state-of-the-art guidance methods─including classifier-free guidance, autoguidance, and model guidance─in a leading molecule generation framework built on an SE(3)-equivariant flow matching process. We propose a hybrid guidance strategy that separately guides continuous and discrete molecular modalities─operating on velocity fields and predicted denoising probabilities, respectively─while jointly optimizing their guidance scales via Bayesian optimization. Our implementation, benchmarked on the QM9 and QMe14S data sets, achieves new state-of-the-art performance in property alignment for de novo molecular generation. The generated molecules also exhibit high structural validity. Furthermore, we systematically compare the strengths and limitations of various guidance methods, offering insights into their broader applicability.

Machine Learning Interatomic Potentials (MLIPs), trained with Quantum Mechanics data, can model potential energy surfaces for molecular systems with very high accuracy and extreme speedups compared to reference quantum calculations, offering a powerful tool for studying complex chemical and biological systems. This work presents the LAMMPS-ANI interface, which scales our ANI neural network potential models for large systems, demonstrated with up to 100 million atoms across up to 128 NVIDIA A100 GPUs. The high performance of LAMMPS-ANI was achieved through a comprehensive code redesign, in-depth performance profiling, and advanced GPU performance optimizations. Our benchmarks show that ANI is 30 to 60 times faster than the state-of-the-art Allegro Model, emphasizing its speed and efficiency. We highlight our work in large-scale molecular dynamics using ANI potentials, presenting benchmark results for water boxes (up to 100 million atoms) and a solvated HIV capsid (44 million atoms). We also present results for accurately simulating complex reaction processes at unprecedented scales, such as methane combustion (300 thousand atoms) and early Earth chemistry experiment (228 thousand atoms) demonstrating the spontaneous formation of glycine.

Hybrid machine-learning/molecular-mechanics (ML/MM) methods extend the classical QM/MM paradigm by replacing the quantum description with neural network interatomic potentials trained to reproduce accurately quantum-mechanical (QM) results. By describing only the chemically active region with ML and the surrounding environment with molecular mechanics (MM), ML/MM models achieve near-QM/MM fidelity at a fraction of the computational cost, enabling routine simulation of reaction mechanisms, vibrational spectra, and binding free energies in complex biological or condensed-phase environments. The key challenge lies in coupling the ML and MM regions, a task addressed through three main strategies: (1) mechanical embedding (ME), where ML regions interact with fixed MM charges via classical electrostatics; (2) polarization-corrected mechanical embedding (PCME), where a vacuum-trained ML potential is supplemented post hoc with electrostatic corrections; and (3) environment-integrated embedding (EIE), where ML potentials are trained with explicit inclusion of MM-derived fields, enhancing accuracy but requiring specialized data. Since ML/MM builds on the scaffolding of QM/MM, most proposed coupling strategies rely heavily on electrostatics, polarization, and other physicochemical concepts, and the development and analysis of ML/MM schemes sits naturally at the intersection of physical chemistry and modern data science. This review surveys the conceptual foundations of ML/MM schemes, classifies existing implementations, and highlights key applications and open challenges, providing a critical snapshot of the current state-of-the-art and positioning ML/MM not merely as a computational alternative but as the natural evolution of QM/MM toward data-driven, scalable multiscale modeling.

In this work we introduce TorchANI-Amber, an interface for routine molecular dynamics simulations of biomolecular systems using ANI-style machine learning potentials. TochANI-Amber incorporates the ANI neural network potentials into the Amber software suite, supporting Amber's two engines: sander and pmemd. In addition to implementing all published ANI models, the interface is extensible to other energy predicting potentials through a simple mechanism requiring no knowledge of Amber's codebase. To illustrate this versatility, we implement extensions to the AIMNet2 and Nutmeg potentials. The interface is integrated with Amber's neighborlists, and it also supports an optimized CUDA implementation for computing the ANI models' feature vectors, enabling simulations of systems with hundreds of thousands of atoms at the neural network's level of theory (approaching DFT accuracy). The interface is designed so that all amber capabilities can be used with ANI potentials instead of force fields. To evaluate the energy conservation, stability, and performance of the ANI potentials as used through the interface, we run MD simulations on different biomolecular systems, including ubiquitin and Trp-cage proteins in explicit solvent. Additionally, we demonstrate the use of these potentials in the context of enhanced sampling techniques, such as temperature replica-exchange molecular dynamics.

In this work, we introduce TorchANI 2.0, a significantly improved version of the free and open source TorchANI software package for training and evaluation of ANI (ANAKIN-ME) deep learning models. TorchANI 2.0 builds upon the foundation of its predecessor, while addressing its limitations and introducing new features. These changes greatly enhance its extensibility, performance, and suitability as a framework for developing models ready for molecular dynamics applications. These improvements include the introduction of a modular system to add arbitrary pairwise potentials to models, CUDA-accelerated optimization for faster and more memory-efficient calculation of local atomic features, and a batched system for better performance of network ensembles, among others. Our benchmarks demonstrate that TorchANI 2.0 achieves significant speedup over previous versions in both training and inference, and the library enhancements allow users to train physically constrained models that better represent important qualities of chemical systems. We demonstrate this by introducing three new ANI models that incorporate these features and evaluating their capabilities.

In this work we introduce TorchANI-Amber, an interface for routine molecular dy- namics simulations of biomolecular systems using ANI-style machine learning poten- tials. TochANI-Amber incorporates the ANI neural network potentials into the Amber software suite, supporting Amber’s two engines: sander and pmemd. In addition to implementing all published ANI models, the interface is extensible to other energy predicting potentials through a simple mechanism requiring no knowledge of Amber’s codebase. To illustrate this versatility, we implement extensions to the AIMNet2 and Nutmeg potentials. The interface is integrated with Amber’s neighborlists, and it also supports an optimized CUDA implementation for computing the ANI models’ feature vectors, enabling simulations of systems with hundreds of thousands of atoms at the neural network’s level of theory (approaching DFT accuracy). The interface is designed so that all amber capabilities can be used with ANI potentials instead of force fields. To evaluate the energy conservation, stability, and performance of the ANI potentials as used through the interface, we run MD simulations on different biomolecular systems, including ubiquitin and Trp-cage proteins in explicit solvent. Additionally, we demon- strate the use of these potentials in the context of enhanced sampling techniques, such as temperature replica-exchange molecular dynamics.

In this work we introduce TorchANI 2.0, a significantly improved version of the free and open source TorchANI software package for training and evaluation of ANI (ANAKIN-ME) deep learning models. TorchANI 2.0 builds upon the foundation of its predecessor, while addressing its limitations and introducing new features. These changes greatly enhance its extensibility, performance, and suitability as a framework for developing models ready for molecular dynamics applications. These improvements include the introduction of a modular system to add arbitrary pairwise potentials to models, CUDA-accelerated optimization for faster and more memory-efficient calculation of local atomic features, and a batched system for better performance of network ensembles, among others. Our benchmarks demonstrate that TorchANI 2.0 achieves significant speedup over previous versions in both training and inference, and the library enhancements allow users to train physically constrained models that better represent important qualities of chemical systems. We demonstrate this by introducing three new ANI models that incorporate these features and evaluating their capabilities

Amber is a molecular dynamics (MD) software package first conceived by Peter Kollman, his lab and collaborators to simulate biomolecular systems. The pmemd module is available as a serial version for central processing units (CPUs), NVIDIA and Advanced Micro Devices (AMD) graphics processing unit (GPU) versions as well as Message Passing Interface (MPI) parallel versions. Advanced capabilities include thermodynamic integration, replica exchange MD and accelerated MD methods. A brief update to the software and recently added capabilities is described in this Application Note.