Advancing density functional tight-binding method for large organic molecules through equivariant neural networks

Physical Chemistry Chemical Physics, vol. 28, pp. 3949–3962

Abstract

Semi-empirical electronic structure methods have become valuable tools for studying complex (bio)molecular systems due to their balance between computational efficiency and accuracy. A key aspect of these methods is their parameterization, which not only governs the reliability of the results but also provides an opportunity to enhance their overall performance. In our previous work [J. Phys. Chem. Lett. 11, 16 (2021)], we improved the accuracy of the semi-empirical density functional tight-binding (DFTB) method for computing multiple properties of small molecules by developing the machine learning (ML) potential NN$_{\rm rep}$ to bridge the gap between electronic DFTB components and those of the hybrid DFT-PBE0 functional. To overcome the limitations of NN$_{\rm rep}$, we introduce the EquiDTB framework, which leverages physics-inspired equivariant neural networks (NN) to parameterize scalable and transferable $\Delta_{\rm TB}$ many-body potentials, replacing the standard pairwise repulsive potential in the DFTB method. This advancement extends the applicability of our ML-corrected DFTB approach to larger molecules and non-covalent systems, going beyond the chemical space represented in the training quantum-mechanical datasets. Indeed, the enhanced performance of EquiDTB over the standard TB methods (DFTB and GFN2-xTB) is demonstrated by the accurate computation of the atomic forces of equilibrium and non-equilibrium small molecular dimers, as well as their interaction energies. Moreover, EquiDTB can be effectively employed to explore the potential energy surfaces of large and flexible drug-like molecules---for example, to determine the minimum energy path between isomers, analyze structural transitions during dynamical simulations, compute vibrational modes, and investigate energetic rankings. Therefore, our work highlights that an optimal integration of an equivariant NN with QM datasets can advance the DFTB method to achieve DFT-PBE0 level accuracy with high computational efficiency, paving the way for more reliable (bio)molecular simulations.

Authors 7

1. Leonardo Rafael Medrano Sandonas

   Max Bergmann Zentrum für Biomaterialien · Technische Universität Dresden

   Affiliation as printed

   Institute for Materials Science and Max Bergmann Center of Biomaterials, TUD Dresden University of Technology, 01062 Dresden, Germany

2. Mirela Puleva

   University of Luxembourg

   Affiliation as printed

   Department of Physics and Materials Science, University of Luxembourg, L-1511 Luxembourg City, Luxembourg

   Institute for Advanced Studies, University of Luxembourg, Campus Belval, L-4365 Esch-sur-Alzette, Luxembourg

3. Zekiye Erarslan

   Max Bergmann Zentrum für Biomaterialien · Technische Universität Dresden

   Affiliation as printed

   Institute for Materials Science and Max Bergmann Center of Biomaterials, TUD Dresden University of Technology, 01062 Dresden, Germany

4. Ricardo Parra Payano

   National University of Engineering

   Affiliation as printed

   Universidad Nacional de Ingeniería, Av. Túpac Amaru 210, Rímac, Lima 15333, Peru

5. Martin Stöhr

   University of Luxembourg · SLAC National Accelerator Laboratory · Stanford University

   Affiliation as printed

   Department of Chemistry and The PULSE Institute, Stanford University, Stanford, CA-94305, USA

   Department of Physics and Materials Science, University of Luxembourg, L-1511 Luxembourg City, Luxembourg

   SLAC National Accelerator Laboratory, Menlo Park CA-94025, USA

6. Gianaurelio Cuniberti Aachen Cluster of Excellence CARE

   Max Bergmann Zentrum für Biomaterialien · Centre for Tactile Internet with Human-in-the-Loop · Climate-Neutral and Resource-Efficient Construction · Technische Universität Dresden · RWTH Aachen University

   Affiliation as printed

   Cluster of Excellence CARE, TU Dresden and RWTH Aachen, Germany

   Cluster of Excellence CeTI, TU Dresden, Germany

   Institute for Materials Science and Max Bergmann Center of Biomaterials, TUD Dresden University of Technology, 01062 Dresden, Germany

7. Alexandre Tkatchenko

   University of Luxembourg

   Affiliation as printed

   Department of Physics and Materials Science, University of Luxembourg, L-1511 Luxembourg City, Luxembourg

   Institute for Advanced Studies, University of Luxembourg, Campus Belval, L-4365 Esch-sur-Alzette, Luxembourg