Joshua A. Rackers
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Joshua A. Rackers has a total of 43 co-authors. Here are the top co-authors by number of shared publications:
- Jay W. Ponder
Department of Chemistry, Washington University in St. Louis, St. Louis, Missouri 63130, USA
4 shared publications - William P. Bricker
Department of Chemical and Biological Engineering, University of New Mexico, Albuquerque, New Mexico
3 shared publications Alex J. Lee
Department of Chemical and Biological Engineering, University of New Mexico 3 , Albuquerque, New Mexico 87131, USA
2 shared publications- Ignacio Ema
Departamento de Química Física Aplicada, Facultad de Ciencias, Universidad Autónoma de Madrid, 28049 Madrid, Spain
2 shared publications Lucas Tecot
Department of Computer Science, University of California, Los Angeles, CA, United States of America
2 shared publicationsMario Geiger
Institute of Physics, Ecole Polytechnique Fédérale de Lausanne, Lausanne, Switzerland
2 shared publications
Latest Publications
- Top Cited Papers
- 2 April 2025
- Published by AIP Publishing in Applied Physics Reviews
- Vol. 12 (2)
On the design space between molecular mechanics and machine learning force fields
A force field as accurate as quantum mechanics (QMs) and as fast as molecular mechanics (MMs), 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 in this direction, where differentiable neural functions are parametrized to fit ab initio energies and 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—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 exploration and design of faster, albeit perhaps slightly less accurate MLFFs, in this review, we focus our attention on the technical design space (the speed-accuracy trade-off) between MM and ML force fields. After a brief review of the building blocks (from a machine learning-centric point of view) 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, and envision what the next generation of MLFF might look like.
- 2 April 2025
- Published by AIP Publishing in Applied Physics Reviews
- Vol. 12 (2)
Top Cited PapersOn the design space between molecular mechanics and machine learning force fields
A force field as accurate as quantum mechanics (QMs) and as fast as molecular mechanics (MMs), 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 in this direction, where differentiable neural functions are parametrized to fit ab initio energies and 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—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 exploration and design of faster, albeit perhaps slightly less accurate MLFFs, in this review, we focus our attention on the technical design space (the speed-accuracy trade-off) between MM and ML force fields. After a brief review of the building blocks (from a machine learning-centric point of view) 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, and envision what the next generation of MLFF might look like.
- Open Access
- 15 February 2024
- Published by Public Library of Science (PLoS) in PLOS ONE
- Vol. 19 (2) , e0297502
Building an ab initio solvated DNA model using Euclidean neural networks
Accurately modeling large biomolecules such as DNA from first principles is fundamentally challenging due to the steep computational scaling of ab initio quantum chemistry methods. This limitation becomes even more prominent when modeling biomolecules in solution due to the need to include large numbers of solvent molecules. We present a machine-learned electron density model based on a Euclidean neural network framework that includes a built-in understanding of equivariance to model explicitly solvated double-stranded DNA. By training the machine learning model using molecular fragments that sample the key DNA and solvent interactions, we show that the model predicts electron densities of arbitrary systems of solvated DNA accurately, resolves polarization effects that are neglected by classical force fields, and captures the physics of the DNA-solvent interaction at the ab initio level.
- 15 February 2024
- Published by Public Library of Science (PLoS) in PLOS ONE
- Vol. 19 (2) , e0297502
Open AccessBuilding an ab initio solvated DNA model using Euclidean neural networks
Accurately modeling large biomolecules such as DNA from first principles is fundamentally challenging due to the steep computational scaling of ab initio quantum chemistry methods. This limitation becomes even more prominent when modeling biomolecules in solution due to the need to include large numbers of solvent molecules. We present a machine-learned electron density model based on a Euclidean neural network framework that includes a built-in understanding of equivariance to model explicitly solvated double-stranded DNA. By training the machine learning model using molecular fragments that sample the key DNA and solvent interactions, we show that the model predicts electron densities of arbitrary systems of solvated DNA accurately, resolves polarization effects that are neglected by classical force fields, and captures the physics of the DNA-solvent interaction at the ab initio level.
- Open Access
- 27 February 2023
- Published by IOP Publishing in Machine Learning: Science and Technology
- Vol. 4 (1) , 015027
A recipe for cracking the quantum scaling limit with machine learned electron densities
A long-standing goal of science is to accurately simulate large molecular systems using quantum mechanics. The poor scaling of current quantum chemistry algorithms on classical computers, however, imposes an effective limit of about a few dozen atoms on traditional electronic structure calculations. We present a machine learning (ML) method to break through this scaling limit for electron densities. We show that Euclidean neural networks can be trained to predict molecular electron densities from limited data. By learning the electron density, the model can be trained on small systems and make accurate predictions on large ones. In the context of water clusters, we show that an ML model trained on clusters of just 12 molecules contains all the information needed to make accurate electron density predictions on cluster sizes of 50 or more, beyond the scaling limit of current quantum chemistry methods.
- 27 February 2023
- Published by IOP Publishing in Machine Learning: Science and Technology
- Vol. 4 (1) , 015027
Open AccessA recipe for cracking the quantum scaling limit with machine learned electron densities
A long-standing goal of science is to accurately simulate large molecular systems using quantum mechanics. The poor scaling of current quantum chemistry algorithms on classical computers, however, imposes an effective limit of about a few dozen atoms on traditional electronic structure calculations. We present a machine learning (ML) method to break through this scaling limit for electron densities. We show that Euclidean neural networks can be trained to predict molecular electron densities from limited data. By learning the electron density, the model can be trained on small systems and make accurate predictions on large ones. In the context of water clusters, we show that an ML model trained on clusters of just 12 molecules contains all the information needed to make accurate electron density predictions on cluster sizes of 50 or more, beyond the scaling limit of current quantum chemistry methods.
- 4 January 2023
- Published by AIP Publishing
- Vol. 158 (1) , 014104
10.1063/5.0130668.1
The Hellmann–Feynman (HF) theorem provides a way to compute forces directly from the electron density, enabling efficient force calculations for large systems through machine learning (ML) models for the electron density. The main issue holding back the general acceptance of the HF approach for atom-centered basis sets is the well-known Pulay force which, if naively discarded, typically constitutes an error upward of 10 eV/Å in forces. In this work, we demonstrate that if a suitably augmented Gaussian basis set is used for density functional calculations, the Pulay force can be suppressed, and HF forces can be computed as accurately as analytical forces with state-of-the-art basis sets, allowing geometry optimization and molecular dynamics to be reliably performed with HF forces. Our results pave a clear path forward for the accurate and efficient simulation of large systems using ML densities and the HF theorem.
- 4 January 2023
- Published by AIP Publishing
- Vol. 158 (1) , 014104
10.1063/5.0130668.1
The Hellmann–Feynman (HF) theorem provides a way to compute forces directly from the electron density, enabling efficient force calculations for large systems through machine learning (ML) models for the electron density. The main issue holding back the general acceptance of the HF approach for atom-centered basis sets is the well-known Pulay force which, if naively discarded, typically constitutes an error upward of 10 eV/Å in forces. In this work, we demonstrate that if a suitably augmented Gaussian basis set is used for density functional calculations, the Pulay force can be suppressed, and HF forces can be computed as accurately as analytical forces with state-of-the-art basis sets, allowing geometry optimization and molecular dynamics to be reliably performed with HF forces. Our results pave a clear path forward for the accurate and efficient simulation of large systems using ML densities and the HF theorem.
- Open Access
- 4 January 2023
- Published by AIP Publishing in The Journal of Chemical Physics
- Vol. 158 (1) , 014104
Accurate Hellmann–Feynman forces from density functional calculations with augmented Gaussian basis sets
The Hellmann–Feynman (HF) theorem provides a way to compute forces directly from the electron density, enabling efficient force calculations for large systems through machine learning (ML) models for the electron density. The main issue holding back the general acceptance of the HF approach for atom-centered basis sets is the well-known Pulay force which, if naively discarded, typically constitutes an error upward of 10 eV/Å in forces. In this work, we demonstrate that if a suitably augmented Gaussian basis set is used for density functional calculations, the Pulay force can be suppressed, and HF forces can be computed as accurately as analytical forces with state-of-the-art basis sets, allowing geometry optimization and molecular dynamics to be reliably performed with HF forces. Our results pave a clear path forward for the accurate and efficient simulation of large systems using ML densities and the HF theorem.
- 4 January 2023
- Published by AIP Publishing in The Journal of Chemical Physics
- Vol. 158 (1) , 014104
Open AccessAccurate Hellmann–Feynman forces from density functional calculations with augmented Gaussian basis sets
The Hellmann–Feynman (HF) theorem provides a way to compute forces directly from the electron density, enabling efficient force calculations for large systems through machine learning (ML) models for the electron density. The main issue holding back the general acceptance of the HF approach for atom-centered basis sets is the well-known Pulay force which, if naively discarded, typically constitutes an error upward of 10 eV/Å in forces. In this work, we demonstrate that if a suitably augmented Gaussian basis set is used for density functional calculations, the Pulay force can be suppressed, and HF forces can be computed as accurately as analytical forces with state-of-the-art basis sets, allowing geometry optimization and molecular dynamics to be reliably performed with HF forces. Our results pave a clear path forward for the accurate and efficient simulation of large systems using ML densities and the HF theorem.
- Open Access
Hierarchical Learning in Euclidean Neural Networks
Equivariant machine learning methods have shown wide success at 3D learning applications in recent years. These models explicitly build in the reflection, translation and rotation symmetries of Euclidean space and have facilitated large advances in accuracy and data efficiency for a range of applications in the physical sciences. An outstanding question for equivariant models is why they achieve such larger-than-expected advances in these applications. To probe this question, we examine the role of higher order (non-scalar) features in Euclidean Neural Networks (\texttt{e3nn}). We focus on the previously studied application of \texttt{e3nn} to the problem of electron density prediction, which allows for a variety of non-scalar outputs, and examine whether the nature of the output (scalar $l=0$, vector $l=1$, or higher order $l>1$) is relevant to the effectiveness of non-scalar hidden features in the network. Further, we examine the behavior of non-scalar features throughout training, finding a natural hierarchy of features by $l$, reminiscent of a multipole expansion. We aim for our work to ultimately inform design principles and choices of domain applications for {\tt e3nn} networks.Open AccessHierarchical Learning in Euclidean Neural Networks
Equivariant machine learning methods have shown wide success at 3D learning applications in recent years. These models explicitly build in the reflection, translation and rotation symmetries of Euclidean space and have facilitated large advances in accuracy and data efficiency for a range of applications in the physical sciences. An outstanding question for equivariant models is why they achieve such larger-than-expected advances in these applications. To probe this question, we examine the role of higher order (non-scalar) features in Euclidean Neural Networks (\texttt{e3nn}). We focus on the previously studied application of \texttt{e3nn} to the problem of electron density prediction, which allows for a variety of non-scalar outputs, and examine whether the nature of the output (scalar $l=0$, vector $l=1$, or higher order $l>1$) is relevant to the effectiveness of non-scalar hidden features in the network. Further, we examine the behavior of non-scalar features throughout training, finding a natural hierarchy of features by $l$, reminiscent of a multipole expansion. We aim for our work to ultimately inform design principles and choices of domain applications for {\tt e3nn} networks. - 27 September 2022
- Published by American Chemical Society (ACS) in The Journal of Physical Chemistry B
- Vol. 126 (39) , 7579-7594
Classical Exchange Polarization: An Anisotropic Variable Polarizability Model
Polarizability, or the tendency of the electron distribution to distort under an electric field, often depends on the local chemical environment. For example, the polarizability of a chloride ion is larger in gas phase compared to a chloride ion solvated in water. This effect is due to the restriction the Pauli exclusion principle places on the allowed electron states. Because no two electrons can occupy the same state, when a highly polarizable atom comes in close contact with other atoms or molecules, the space of allowed states can dramatically decrease. This constraint suggests that an accurate molecular mechanics polarizability model should depend on the radial distance between neighboring atoms. This paper introduces a variable polarizability model within the framework of the HIPPO (Hydrogen-like Intermolecular Polarizable Potential) force field, by damping the polarizability as a function of the orbital overlap of two atoms. This effectively captures the quantum mechanical exchange polarization effects, without explicit utilization of antisymmetrized wave functions. We show that the variable polarizability model remarkably improves the two-body polarization energies and three-body energies of ion-ion and ion-water systems. Under this model, no manual tuning of atomic polarizabilities for monatomic ions is required; the gas-phase polarizability can be used because an appropriate damping function is able to correct the polarizability at short range.
- 27 September 2022
- Published by American Chemical Society (ACS) in The Journal of Physical Chemistry B
- Vol. 126 (39) , 7579-7594
Classical Exchange Polarization: An Anisotropic Variable Polarizability Model
Polarizability, or the tendency of the electron distribution to distort under an electric field, often depends on the local chemical environment. For example, the polarizability of a chloride ion is larger in gas phase compared to a chloride ion solvated in water. This effect is due to the restriction the Pauli exclusion principle places on the allowed electron states. Because no two electrons can occupy the same state, when a highly polarizable atom comes in close contact with other atoms or molecules, the space of allowed states can dramatically decrease. This constraint suggests that an accurate molecular mechanics polarizability model should depend on the radial distance between neighboring atoms. This paper introduces a variable polarizability model within the framework of the HIPPO (Hydrogen-like Intermolecular Polarizable Potential) force field, by damping the polarizability as a function of the orbital overlap of two atoms. This effectively captures the quantum mechanical exchange polarization effects, without explicit utilization of antisymmetrized wave functions. We show that the variable polarizability model remarkably improves the two-body polarization energies and three-body energies of ion-ion and ion-water systems. Under this model, no manual tuning of atomic polarizabilities for monatomic ions is required; the gas-phase polarizability can be used because an appropriate damping function is able to correct the polarizability at short range.
- Open Access
Cracking the Quantum Scaling Limit with Machine Learned Electron Densities
A long-standing goal of science is to accurately solve the Schr\"odinger equation for large molecular systems. The poor scaling of current quantum chemistry algorithms on classical computers imposes an effective limit of about a few dozen atoms for which we can calculate molecular electronic structure. We present a machine learning (ML) method to break through this scaling limit and make quantum chemistry calculations of very large systems possible. We show that Euclidean Neural Networks can be trained to predict the electron density with high fidelity from limited data. Learning the electron density allows us to train a machine learning model on small systems and make accurate predictions on large ones. We show that this ML electron density model can break through the quantum scaling limit and calculate the electron density of systems of thousands of atoms with quantum accuracy.
Open AccessCracking the Quantum Scaling Limit with Machine Learned Electron Densities
A long-standing goal of science is to accurately solve the Schr\"odinger equation for large molecular systems. The poor scaling of current quantum chemistry algorithms on classical computers imposes an effective limit of about a few dozen atoms for which we can calculate molecular electronic structure. We present a machine learning (ML) method to break through this scaling limit and make quantum chemistry calculations of very large systems possible. We show that Euclidean Neural Networks can be trained to predict the electron density with high fidelity from limited data. Learning the electron density allows us to train a machine learning model on small systems and make accurate predictions on large ones. We show that this ML electron density model can break through the quantum scaling limit and calculate the electron density of systems of thousands of atoms with quantum accuracy.
- 16 December 2021
- Published by American Chemical Society (ACS) in Journal of Chemical Theory and Computation
- Vol. 18 (1) , 580-594
Water in an External Electric Field: Comparing Charge Distribution Methods Using ReaxFF Simulations
The growing interest in the effects of external electric fields on reactive processes requires predictive methods that can reach longer length and time scales than quantum mechanical simulations. Recently, many studies have included electric fields in ReaxFF, a widely used reactive molecular dynamics method. In the case of modeling an external electric field, the charge distribution method used in ReaxFF is critical. The most common charge distribution method used in previous studies of electric fields is the charge equilibration (QEq) method, which assumes that the system is a contiguous conductor and that charge transfer can occur across any distance. In contrast, many systems of interest are insulators or semiconductors, and long-distance charge transfer should not occur in response to a small difference in potential. This study focuses on the limitations of the QEq method in the context of water in an external electric field. We demonstrate that QEq can predict unphysical charge distributions and exhibits properties that do not converge as a function of system size. Furthermore, we show that electric fields within the recently developed atom-condensed Kohn-Sham density functional theory (DFT) approximated to the second-order (ACKS2) approach address the major limitations of electric fields in QEq. With ACKS2, we observe more physical charge distributions and properties that converge as a function of system size. We do not suggest that ACKS2 is perfect in all circumstances but rather show specific cases where it addresses the major shortcomings of QEq in the context of an external electric field.
- 16 December 2021
- Published by American Chemical Society (ACS) in Journal of Chemical Theory and Computation
- Vol. 18 (1) , 580-594
Water in an External Electric Field: Comparing Charge Distribution Methods Using ReaxFF Simulations
The growing interest in the effects of external electric fields on reactive processes requires predictive methods that can reach longer length and time scales than quantum mechanical simulations. Recently, many studies have included electric fields in ReaxFF, a widely used reactive molecular dynamics method. In the case of modeling an external electric field, the charge distribution method used in ReaxFF is critical. The most common charge distribution method used in previous studies of electric fields is the charge equilibration (QEq) method, which assumes that the system is a contiguous conductor and that charge transfer can occur across any distance. In contrast, many systems of interest are insulators or semiconductors, and long-distance charge transfer should not occur in response to a small difference in potential. This study focuses on the limitations of the QEq method in the context of water in an external electric field. We demonstrate that QEq can predict unphysical charge distributions and exhibits properties that do not converge as a function of system size. Furthermore, we show that electric fields within the recently developed atom-condensed Kohn-Sham density functional theory (DFT) approximated to the second-order (ACKS2) approach address the major limitations of electric fields in QEq. With ACKS2, we observe more physical charge distributions and properties that converge as a function of system size. We do not suggest that ACKS2 is perfect in all circumstances but rather show specific cases where it addresses the major shortcomings of QEq in the context of an external electric field.
- 26 October 2021
- Published by American Chemical Society (ACS) in Journal of Chemical Theory and Computation
- Vol. 17 (11) , 7056-7084
Polarizable Water Potential Derived from a Model Electron Density
A new empirical potential for efficient, large scale molecular dynamics simulation of water is presented. The HIPPO (Hydrogen-like Intermolecular Polarizable POtential) force field is based upon the model electron density of a hydrogen-like atom. This framework is used to derive and parametrize individual terms describing charge penetration damped permanent electrostatics, damped polarization, charge transfer, anisotropic Pauli repulsion, and damped dispersion interactions. Initial parameter values were fit to Symmetry Adapted Perturbation Theory (SAPT) energy components for ten water dimer configurations, as well as the radial and angular dependence of the canonical dimer. The SAPT-based parameters were then systematically refined to extend the treatment to water bulk phases. The final HIPPO water model provides a balanced representation of a wide variety of properties of gas phase clusters, liquid water, and ice polymorphs, across a range of temperatures and pressures. This water potential yields a rationalization of water structure, dynamics, and thermodynamics explicitly correlated with an ab initio energy decomposition, while providing a level of accuracy comparable or superior to previous polarizable atomic multipole force fields. The HIPPO water model serves as a cornerstone around which similarly detailed physics-based models can be developed for additional molecular species.
- 26 October 2021
- Published by American Chemical Society (ACS) in Journal of Chemical Theory and Computation
- Vol. 17 (11) , 7056-7084
Polarizable Water Potential Derived from a Model Electron Density
A new empirical potential for efficient, large scale molecular dynamics simulation of water is presented. The HIPPO (Hydrogen-like Intermolecular Polarizable POtential) force field is based upon the model electron density of a hydrogen-like atom. This framework is used to derive and parametrize individual terms describing charge penetration damped permanent electrostatics, damped polarization, charge transfer, anisotropic Pauli repulsion, and damped dispersion interactions. Initial parameter values were fit to Symmetry Adapted Perturbation Theory (SAPT) energy components for ten water dimer configurations, as well as the radial and angular dependence of the canonical dimer. The SAPT-based parameters were then systematically refined to extend the treatment to water bulk phases. The final HIPPO water model provides a balanced representation of a wide variety of properties of gas phase clusters, liquid water, and ice polymorphs, across a range of temperatures and pressures. This water potential yields a rationalization of water structure, dynamics, and thermodynamics explicitly correlated with an ab initio energy decomposition, while providing a level of accuracy comparable or superior to previous polarizable atomic multipole force fields. The HIPPO water model serves as a cornerstone around which similarly detailed physics-based models can be developed for additional molecular species.