Interatomic potentials derived with Machine Learning algorithms such as Deep-Neural Networks (DNNs), achieve the accuracy of high-fidelity quantum mechanical (QM) methods in areas traditionally dominated by empirical force fields and allow performing massive simulations. Most DNN potentials were parametrized for neutral molecules or closed-shell ions due to architectural limitations. In this work, we propose an improved machine learning framework for simulating open-shell anions and cations. We introduce the AIMNet-NSE (Neural Spin Equilibration) architecture, which can predict molecular energies for an arbitrary combination of molecular charge and spin multiplicity with errors of about 2–3 kcal/mol and spin-charges with error errors ~0.01e for small and medium-sized organic molecules, compared to the reference QM simulations. The AIMNet-NSE model allows to fully bypass QM calculations and derive the ionization potential, electron affinity, and conceptual Density Functional Theory quantities like electronegativity, hardness, and condensed Fukui functions. We show that these descriptors, along with learned atomic representations, could be used to model chemical reactivity through an example of regioselectivity in electrophilic aromatic substitution reactions.more » « less
- Award ID(s):
- NSF-PAR ID:
- Publisher / Repository:
- Nature Publishing Group
- Date Published:
- Journal Name:
- Nature Communications
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
Density functional theory (DFT) has been applied to modeling molecular interactions in water for over three decades. The ubiquity of water in chemical and biological processes demands a unified understanding of its physics, from the single molecule to the thermodynamic limit and everything in between. Recent advances in the development of data-driven and machine-learning potentials have accelerated simulation of water and aqueous systems with DFT accuracy. However, anomalous properties of water in the condensed phase, where a rigorous treatment of both local and non-local many-body (MB) interactions is in order, are often unsatisfactory or partially missing in DFT models of water. In this review, we discuss the modeling of water and aqueous systems based on DFT and provide a comprehensive description of a general theoretical/computational framework for the development of data-driven many-body potentials from DFT reference data. This framework, coined MB-DFT, readily enables efficient many-body molecular dynamics (MD) simulations of small molecules, in both gas and condensed phases, while preserving the accuracy of the underlying DFT model. Theoretical considerations are emphasized, including the role that the delocalization error plays in MB-DFT potentials of water and the possibility to elevate DFT and MB-DFT to near-chemical-accuracy through a density-corrected formalism. The development of the MB-DFT framework is described in detail, along with its application in MB-MD simulations and recent extension to the modeling of reactive processes in solution within a quantum mechanics/MB molecular mechanics (QM/MB-MM) scheme, using water as a prototypical solvent. Finally, we identify open challenges and discuss future directions for MB-DFT and QM/MB-MM simulations in condensed phases.more » « less
AQME, automated quantum mechanical environments, is a free and open‐source Python package for the rapid deployment of automated workflows using cheminformatics and quantum chemistry. AQME workflows integrate tasks performed across multiple computational chemistry packages and data formats, preserving all computational protocols, data, and metadata for machine and human users to access and reuse. AQME has a modular structure of independent modules that can be implemented in any sequence, allowing the users to use all or only the desired parts of the program. The code has been developed for researchers with basic familiarity with the Python programming language. The CSEARCH module interfaces to molecular mechanics and semi‐empirical QM (SQM) conformer generation tools (e.g., RDKit and Conformer–Rotamer Ensemble Sampling Tool, CREST) starting from various initial structure formats. The CMIN module enables geometry refinement with SQM and neural network potentials, such as ANI. The QPREP module interfaces with multiple QM programs, such as Gaussian, ORCA, and PySCF. The QCORR module processes QM results, storing structural, energetic, and property data while also enabling automated error handling (i.e., convergence errors, wrong number of imaginary frequencies, isomerization, etc.) and job resubmission. The QDESCP module provides easy access to QM ensemble‐averaged molecular descriptors and computed properties, such as NMR spectra. Overall, AQME provides automated, transparent, and reproducible workflows to produce, analyze and archive computational chemistry results. SMILES inputs can be used, and many aspects of tedious human manipulation can be avoided. Installation and execution on Windows, macOS, and Linux platforms have been tested, and the code has been developed to support access through Jupyter Notebooks, the command line, and job submission (e.g., Slurm) scripts. Examples of pre‐configured workflows are available in various formats, and hands‐on video tutorials illustrate their use.
This article is categorized under:
Data Science > Chemoinformatics
Data Science > Computer Algorithms and Programming
Software > Quantum Chemistry
The high cost of ab initio molecular dynamics (AIMD) simulations to model complex physical and chemical systems limits its ability to address many key questions. However, new machine learning‐based representations of complex potential energy surfaces have been introduced in recent years to circumvent computationally demanding AIMD simulations while retaining the same level of accuracy. As these machine learning methods gain in popularity over the next decade, it is important to address the appropriate way to develop and integrate them with well‐established simulation methods. This paper details the parameterization and training, using accurate electronic structure calculations, of artificial neural network potentials (NNPs) to model the intermolecular interactions in a hydrogen clathrate hydrate, wherein hydrogen molecules are confined inside the cavities of the 3D crystalline framework of hydrogen‐bonded water molecules. This new NNP is used in conjunction with new path‐integral based enhanced sampling methods, for inclusion of nuclear quantum effects and promotion of free energy barrier crossing, in order to determine properties that are important for understanding the diffusion of hydrogen gas in the clathrate system. These simulations demonstrate the influence of cage occupancy on the free energy barriers that determine the diffusivity of hydrogen gas through the network of large cages.
Maximum diversification of data is a central theme in building generalized and accurate machine learning (ML) models. In chemistry, ML has been used to develop models for predicting molecular properties, for example quantum mechanics (QM) calculated potential energy surfaces and atomic charge models. The ANI-1x and ANI-1ccx ML-based general-purpose potentials for organic molecules were developed through active learning; an automated data diversification process. Here, we describe the ANI-1x and ANI-1ccx data sets. To demonstrate data diversity, we visualize it with a dimensionality reduction scheme, and contrast against existing data sets. The ANI-1x data set contains multiple QM properties from 5 M density functional theory calculations, while the ANI-1ccx data set contains 500 k data points obtained with an accurate CCSD(T)/CBS extrapolation. Approximately 14 million CPU core-hours were expended to generate this data. Multiple QM calculated properties for the chemical elements C, H, N, and O are provided: energies, atomic forces, multipole moments, atomic charges, etc. We provide this data to the community to aid research and development of ML models for chemistry.
The potential energy of molecular species and their conformers can be computed with a wide range of computational chemistry methods, from molecular mechanics to ab initio quantum chemistry. However, the proper choice of the computational approach based on computational cost and reliability of calculated energies is a dilemma, especially for large molecules. This dilemma is proved to be even more problematic for studies that require hundreds and thousands of calculations, such as drug discovery. On the other hand, driven by their pattern recognition capabilities, neural networks started to gain popularity in the computational chemistry community. During the last decade, many neural network potentials have been developed to predict a variety of chemical information of different systems. Neural network potentials are proved to predict chemical properties with accuracy comparable to quantum mechanical approaches but with the cost approaching molecular mechanics calculations. As a result, the development of more reliable, transferable, and extensible neural network potentials became an attractive field of study for researchers. In this review, we outlined an overview of the status of current neural network potentials and strategies to improve their accuracy. We provide recent examples of studies that prove the applicability of these potentials. We also discuss the capabilities and shortcomings of the current models and the challenges and future aspects of their development and applications. It is expected that this review would provide guidance for the development of neural network potentials and the exploitation of their applicability.
This article is categorized under:
Data Science > Artificial Intelligence/Machine Learning
Molecular and Statistical Mechanics > Molecular Interactions
Software > Molecular Modeling