New Algorithms to Generate Permutationally Invariant Polynomials and Fundamental Invariants for Potential Energy Surface Fitting

Journal of Chemical Theory and Computation, Journal Year: 2025, Volume and Issue: unknown

Published: Jan. 22, 2025

Symmetric functions, such as Permutationally Invariant Polynomials (PIPs) and Fundamental Invariants (FIs), are effective concise descriptors for incorporating permutation symmetry into neural network (NN) potential energy surface (PES) fitting. The traditional algorithm generating symmetric polynomials has a factorial time complexity of N!, where N is the number identical atoms, posing significant challenge to applying NN PESs larger systems, particularly with more than 10 atoms. Herein, we report new which only linear It can tremendously accelerate generation process molecular systems. proposed based on graph connectivity analysis following action set permutational group. For instance, in case calculating invariant 15-atom molecule, tropolone, our approximately 2 million times faster previous method. efficiency be further enhanced increasing size making FI-NN approach feasible systems over atoms high demands.

Language: Английский

---

MOLPIPx: An end-to-end differentiable package for permutationally invariant polynomials in Python and Rust

The Journal of Chemical Physics, Journal Year: 2025, Volume and Issue: 162(8)

Published: Feb. 28, 2025

In this work, we present MOLPIPx, a versatile library designed to seamlessly integrate permutationally invariant polynomials with modern machine learning frameworks, enabling the efficient development of linear models, neural networks, and Gaussian process models. These methodologies are widely employed for parameterizing potential energy surfaces across diverse molecular systems. MOLPIPx leverages two powerful automatic differentiation engines—JAX EnzymeAD-Rust—to facilitate computation gradients higher-order derivatives, which essential tasks such as force field dynamic simulations. is available at https://github.com/ChemAI-Lab/molpipx.

Language: Английский

---

Targeted Transferable Machine-Learned Potential for Linear Alkanes Trained on C₁₄H₃₀ and Tested for C₄H₁₀ to C₃₀H₆₂

Journal of Chemical Theory and Computation, Journal Year: 2025, Volume and Issue: unknown

Published: March 27, 2025

Given the great importance of linear alkanes in fundamental and applied research, an accurate machine-learned potential (MLP) would be a major advance computational modeling these hydrocarbons. Recently, we reported novel, many-body permutationally invariant model that was trained specifically for 44-atom hydrocarbon C14H30 on roughly 250,000 B3LYP energies (Qu, C.; Houston, P. L.; Allison, T.; Schneider, B. I.; Bowman, J. M. Chem. Theory Comput. 2024, 20, 9339–9353). Here, demonstrate accuracy transferability this ranging from butane C4H10 up to C30H62. Unlike other approaches aim universal applicability, present approach is targeted alkanes. The mean absolute error (MAE) energy ranges 0.26 kcal/mol rises 0.73 C30H62 over range 80 600 These values are unprecedented transferable potentials indicate high performance potential. conformational barriers shown excellent agreement with high-level ab initio calculations pentane, largest alkane which such have been reported. Vibrational power spectra molecular dynamics presented briefly discussed. Finally, evaluation time vary linearly number atoms.

Language: Английский

---

The evolution of machine learning potentials for molecules, reactions and materials

Chemical Society Reviews, Journal Year: 2025, Volume and Issue: unknown

Published: Jan. 1, 2025

This review offers a comprehensive overview of the development machine learning potentials for molecules, reactions, and materials over past two decades, evolving from traditional models to state-of-the-art.

Language: Английский

---

A perspective marking 20 years of using permutationally invariant polynomials for molecular potentials

The Journal of Chemical Physics, Journal Year: 2025, Volume and Issue: 162(18)

Published: May 13, 2025

This Perspective is focused on permutationally invariant polynomials (PIPs). Since their introduction in 2004 and first use developing a fully potential for the highly fluxional cation CH5+, PIPs have found widespread machine learned potentials (MLPs) isolated molecules, chemical reactions, clusters, condensed phase, materials. More than 100 been reported using PIPs. The popularity of MLPs stems from fundamental property being with respect to permutations like atoms; this energy surfaces. achieved global descriptors and, thus, without an atom-centered approach (which manifestly invariant). used directly linear regression fitting electronic energies gradients complex landscapes reactions numerous product channels. also as inputs neural network Gaussian process methods many-body (atom-centered, water monomer, etc.) applications, notably gold standard water. Here, we focus progress usage since 2018, when last review was done by our group.

Language: Английский

---

Dynamics Calculations of the Flexibility and Vibrational Spectrum of the Linear Alkane C₁₄H₃₀, Based on Machine-Learned Potentials

The Journal of Physical Chemistry A, Journal Year: 2024, Volume and Issue: unknown

Published: Dec. 3, 2024

Hydrocarbons are the central feedstock of fuels, solvents, lubricants, and starting materials for many synthetic materials, thus physical properties hydrocarbons have received intense study. Among these, molecular flexibility power infrared spectroscopies focus this paper. These examined linear alkane C14H30 using dynamics (MD) calculations recent machine-learned potentials. All MD microcanonical start at global minimum. The radius gyration, number gauche bond conformations distributions all C–C distances reported as a function total internal energy time. compared to spectra double harmonic stationary points. Spectral features smoothly track structural differences, measured by in molecule. Preliminary quantum local mode model CH-stretch presented satisfactorily capture anharmonic effects.

Language: Английский

---