Research Topic

neural network

48 publications exploring this topic

2025

2025
cited3

Transferable Machine Learning Interatomic Potential for Pd-Catalyzed Cross-Coupling Reactions

Anstine D., Zubatyuk R., Gallegos L., Paton R., Wiest O., Nebgen B., Jones T., Gomes G., Tretiak S., Isayev O.

(2025)

Ml Potentials
Reactions Reactivity
Experiment Automation
Materials Informatics

Finding efficient substrate-catalyst combinations for palladium-catalyzed cross-coupling reactions remains a critical challenge in synthetic chemistry, with broad implications for pharmaceutical and materials manufacturing.

DOI
2025
cited47

AIMNet2: a neural network potential to meet your neutral, charged, organic, and elemental-organic needs

Anstine D. M., Zubatyuk R., Isayev O.

Chemical Science, 16, 10228–10244 (2025)

Ml Potentials

Machine learned interatomic potentials (MLIPs) are reshaping computational chemistry practices because of their ability to drastically exceed the accuracy-length/time scale tradeoff.

DOI
2025

Democratizing Reaction Kinetics through Machine Vision and Learning

Baumer M., Gallegos L., Anstine D., Kubaney A., Regio J., Isayev O., Bernhard S., Gomes G.

(2025)

Reactions Reactivity
Ml Potentials

Democratizing Reaction Kinetics through Machine Vision and Learning.

DOI
2025
cited1

Anticipating the Selectivity of Intramolecular Cyclization Reaction Pathways with Neural Network Potentials

Casetti N., Anstine D., Isayev O., Coley C. W.

Journal of Chemical Theory and Computation, 21, 10362–10372 (2025)

Reactions Reactivity

Anticipating the Selectivity of Intramolecular Cyclization Reaction Pathways with Neural Network Potentials.

DOI
2025

AIQM3: Targeting Coupled-Cluster Accuracy with Semi-Empirical Speed Across Seven Main Group Elements

Chen Y., Hou Y., Zubatyuk R., Isayev O., Dral P. O.

(2025)

Quantum Chemistry
Ml Potentials
Drug Discovery

The AIQM series methods are successful neural network-based models that target coupled-cluster accuracy while maintaining high robustness and transferability across various tasks by leveraging Δ-learning.

DOI
2025
cited1

AIMNet2‐NSE: A Transferable Reactive Neural Network Potential for Open‐Shell Chemistry

Kalita B., Zubatyuk R., Anstine D. M., Bergeler M., Settels V., Stork C., Spicher S., Isayev O.

Angewandte Chemie International Edition (2025)

Ml Potentials
Quantum Chemistry
Reactions Reactivity

Abstract Open‐shell systems such as radical intermediates are central to radical polymerization (RP), combustion, catalysis, and many other chemical and industrial processes, yet their accurate modeling presents significant computational challenges.

DOI
2025

AIMNet2‐NSE: A Transferable Reactive Neural Network Potential for Open‐Shell Chemistry

Kalita B., Zubatyuk R., Anstine D. M., Bergeler M., Settels V., Stork C., Spicher S., Isayev O.

Angewandte Chemie (2025)

Ml Potentials
Quantum Chemistry
Reactions Reactivity

Abstract Open‐shell systems such as radical intermediates are central to radical polymerization (RP), combustion, catalysis, and many other chemical and industrial processes, yet their accurate modeling presents significant computational challenges.

DOI
2025
cited2

Efficient Molecular Crystal Structure Prediction and Stability Assessment with AIMNet2 Neural Network Potentials

Nayal K. S., O’Connor D., Zubatyuk R., Anstine D. M., Yang Y., Tom R., Deng W., Tang K., Marom N., Isayev O.

Crystal Growth & Design, 25, 9092–9106 (2025)

Ml Potentials

Efficient Molecular Crystal Structure Prediction and Stability Assessment with AIMNet2 Neural Network Potentials.

DOI
2025

Scalable Low-Energy Molecular Conformer Generation with Quantum Mechanical Accuracy

Nikitin F., Anstine D. M., Zubatyuk R., Paliwal S. G., Isayev O.

(2025)

Ml Potentials
Generative Ai
Drug Discovery

Molecular geometry is crucial for biological activity and chemical reactivity; however, computational methods for generating 3D structures are limited by the vast scale of conformational space and the complexities of stereochemistry.

DOI
2025

Machine Learning-Accelerated Screening of Hydroquinone Analogs for Proton-Coupled Electron Transfer

Sarma R., Wang Y., Hebert D., Tran E., Shao C., Fu S., Cho I., Isayev O., Garcia-Bosch I.

(2025)

Ml Potentials
Quantum Chemistry
Reactions Reactivity

Proton-coupled electron transfer (PCET) mediated by hydroquinone and related molecules is key to natural and artificial energy conversion.

DOI
2025
cited4

Including Physics-Informed Atomization Constraints in Neural Networks for Reactive Chemistry

Zhang S., Chigaev M., Isayev O., Messerly R. A., Lubbers N.

Journal of Chemical Information and Modeling, 65, 4367–4380 (2025)

Including Physics-Informed Atomization Constraints in Neural Networks for Reactive Chemistry.

DOI

2024

2024
cited17

AIMNet2: A Neural Network Potential to Meet your Neutral, Charged, Organic, and Elemental-Organic Needs

Anstine D., Zubatyuk R., Isayev O.

(2024)

Ml Potentials
Quantum Chemistry

Machine learned interatomic potentials (MLIPs) are reshaping computational chemistry practices because of their ability to drastically exceed the accuracy-length/time scale tradeoff.

DOI
2024
cited17

AIMNet2: A Neural Network Potential to Meet your Neutral, Charged, Organic, and Elemental-Organic Needs

Anstine D., Zubatyuk R., Isayev O.

(2024)

Ml Potentials

Machine learned interatomic potentials (MLIPs) are reshaping computational chemistry practices because of their ability to drastically exceed the accuracy-length/time scale tradeoff.

DOI
2024
cited8

ANI/EFP: Modeling Long-Range Interactions in ANI Neural Network with Effective Fragment Potentials

Haghiri S., Viquez Rojas C., Bhat S., Isayev O., Slipchenko L.

Journal of Chemical Theory and Computation, 20, 9138–9147 (2024)

ANI/EFP: Modeling Long-Range Interactions in ANI Neural Network with Effective Fragment Potentials.

DOI
2024
cited2

Accurate Ring Strain Energy Predictions with Machine Learning and Application in Strain-Promoted Reactions

Liu Z., Vinskus J., Fu Y., Liu P., Noonan K., Isayev O.

(2024)

Ml Potentials
Experiment Automation
Reactions Reactivity

Ring strain energy (RSE) is crucial for understanding molecular reactivity.

DOI

2023

2023
cited27

AIMNet2: A Neural Network Potential to Meet your Neutral, Charged, Organic, and Elemental-Organic Needs

Anstine D., Zubatyuk R., Isayev O.

(2023)

Ml Potentials

Machine learned interatomic potentials (MLIPs) are reshaping computational chemistry practices because of their ability to drastically exceed the accuracy-length/time scale tradeoff.

DOI
2023

The Challenge of Balancing Model Sensitivity and Robustness in Predicting Yields: A Benchmarking Study of Amide Coupling Reactions

Liu Z., Moroz Y. S., Isayev O.

(2023)

Reactions Reactivity
Experiment Automation

Accurate prediction of reaction yield is the holy grail for computer-assisted synthesis, but current models have failed to generalize to large literature datasets.

DOI

2022

2022

Prediction of Protein pKa with Representation Learning

Gokcan H., Isayev O.

(2022)

Ml Potentials

The behavior of proteins is closely related to the protonation states of the residues.

DOI
2022

Prediction of Protein pKa with Representation Learning

Gokcan H., Isayev O.

(2022)

Ml Potentials

The behavior of proteins is closely related to the protonation states of the residues.

DOI
2022
cited74

Generative and reinforcement learning approaches for the automated de novo design of bioactive compounds

Korshunova M., Huang N., Capuzzi S., Radchenko D. S., Savych O., Moroz Y. S., Wells C. I., Willson T. M., Tropsha A., Isayev O.

Communications Chemistry, 5 (2022)

Generative Ai
Drug Discovery
Experiment Automation

AbstractDeep generative neural networks have been used increasingly in computational chemistry for de novo design of molecules with desired properties.

DOI
2022

Auto3D: Automatic Generation of the Low-energy 3D Structures with ANI Neural Network Potentials

Liu Z., Zubatiuk T., Roitberg A., Isayev O.

(2022)

Ml Potentials
Reactions Reactivity

Computational programs accelerate the chemical discovery processes but often need proper 3-dimensional molecular information as part of the input.

DOI
2022

Auto3D: Automatic Generation of the Low-energy 3D Structures with ANI Neural Network Potentials

Liu Z., Zubatiuk T., Roitberg A., Isayev O.

(2022)

Ml Potentials
Reactions Reactivity

Computational programs accelerate the chemical discovery processes but often need proper 3-dimensional molecular information as part of the input.

DOI

2021

2021
cited11

Active Learning in Bayesian Neural Networks for Bandgap Predictions of Novel Van der Waals Heterostructures

Fronzi M., Isayev O., Winkler D. A., Shapter J. G., Ellis A. V., Sherrell P. C., Shepelin N. A., Corletto A., Ford M. J.

Advanced Intelligent Systems, 3 (2021)

Experiment Automation

The bandgap is one of the most fundamental properties of condensed matter.

DOI
2021
cited1

Prediction of Protein pKa with Representation Learning

Gokcan H., Isayev O.

(2021)

Ml Potentials

The behavior of proteins is closely related to the protonation states of the residues.

DOI
2021
cited1

Prediction of Protein pKa with Representation Learning

Gokcan H., Isayev O.

(2021)

Ml Potentials

The behavior of proteins is closely related to the protonation states of the residues.

DOI
2021
cited6

A Bag of Tricks for Automated De Novo Design of Molecules with the Desired Properties: Application to EGFR Inhibitor Discovery

Korshunova M., Huang N., Capuzzi S., Radchenko D. S., Savych O., Moroz Y. S., Wells C., Willson T. M., Tropsha A., Isayev O.

(2021)

Generative Ai
Drug Discovery
Experiment Automation

Deep generative neural networks have been used increasingly in computational chemistry for de novo design of molecules with desired properties.

DOI
2021
cited115

Artificial intelligence-enhanced quantum chemical method with broad applicability

Zheng P., Zubatyuk R., Wu W., Isayev O., Dral P. O.

Nature Communications, 12 (2021)

Quantum Chemistry
Ml Potentials

Abstract High-level quantum mechanical (QM) calculations are indispensable for accurate explanation of natural phenomena on the atomistic level.

DOI
2021
cited25

Machine learned Hückel theory: Interfacing physics and deep neural networks

Zubatiuk T., Nebgen B., Lubbers N., Smith J. S., Zubatyuk R., Zhou G., Koh C., Barros K., Isayev O., Tretiak S.

The Journal of Chemical Physics, 154 (2021)

Quantum Chemistry

The Hückel Hamiltonian is an incredibly simple tight-binding model known for its ability to capture qualitative physics phenomena arising from electron interactions in molecules and materials.

DOI
2021
cited94

Teaching a neural network to attach and detach electrons from molecules

Zubatyuk R., Smith J. S., Nebgen B. T., Tretiak S., Isayev O.

Nature Communications, 12 (2021)

Ml Potentials
Reactions Reactivity
Drug Discovery
Quantum Chemistry

Abstract 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.

DOI
2021
cited3

Teaching a Neural Network to Attach and Detach Electrons from Molecules

Zubatyuk R., Smith J., Nebgen B. T., Tretiak S., Isayev O.

(2021)

Ml Potentials
Reactions Reactivity
Drug Discovery
Quantum Chemistry

Physics-inspired Artificial Intelligence (AI) is at the forefront of methods development in molecular modeling and computational chemistry.

DOI

2020

2020
cited259

TorchANI: A Free and Open Source PyTorch-Based Deep Learning Implementation of the ANI Neural Network Potentials

Gao X., Ramezanghorbani F., Isayev O., Smith J. S., Roitberg A. E.

Journal of Chemical Information and Modeling, 60, 3408–3415 (2020)

Ml Potentials

TorchANI: A Free and Open Source PyTorch-Based Deep Learning Implementation of the ANI Neural Network Potentials.

DOI
2020
cited2

TorchANI: A Free and Open Source PyTorch Based Deep Learning Implementation of the ANI Neural Network Potentials

Gao X., Ramezanghorbani F., Isayev O., Smith J., Roitberg A.

(2020)

Ml Potentials

This paper presents TorchANI, a PyTorch based software for training/inferenceof ANI (ANAKIN-ME) deep learning models to obtain potential energy surfaces andother physical properties of molecular systems.

DOI
2020

DRACON: Disconnected Graph Neural Network for Atom Mapping in Chemical Reactions

Nikitin F., Isayev O., Strijov V.

(2020)

Reactions Reactivity

Machine learning solved many challenging problems in computer-assisted synthesis prediction (CASP).

DOI
2020

DRACON: Disconnected Graph Neural Network for Atom Mapping in Chemical Reactions

Nikitin F., Isayev O., Strijov V.

(2020)

Reactions Reactivity

Machine learning solved many challenging problems in computer-assisted synthesis prediction (CASP).

DOI
2020
cited7

DRACON: Disconnected Graph Neural Network for Atom Mapping in Chemical Reactions

Nikitin F., Isayev O., Strijov V.

(2020)

Reactions Reactivity

Machine learning solved many challenging problems in computer-assisted synthesis prediction (CASP).

DOI
2020
cited9

DRACON: disconnected graph neural network for atom mapping in chemical reactions

Nikitin F., Isayev O., Strijov V.

Physical Chemistry Chemical Physics, 22, 26478–26486 (2020)

Reactions Reactivity

We formulate a reaction prediction problem in terms of node-classification in a disconnected graph of source molecules and generalize a graph convolution neural network for disconnected graphs.

DOI
2020
cited7

Teaching a Neural Network to Attach and Detach Electrons from Molecules

Zubatyuk R., Smith J., Nebgen B. T., Tretiak S., Isayev O.

(2020)

Ml Potentials
Reactions Reactivity
Drug Discovery
Quantum Chemistry

Physics-inspired Artificial Intelligence (AI) is at the forefront of methods development in molecular modeling and computational chemistry.

DOI

2019

2019
cited531

Approaching coupled cluster accuracy with a general-purpose neural network potential through transfer learning

Smith J. S., Nebgen B. T., Zubatyuk R., Lubbers N., Devereux C., Barros K., Tretiak S., Isayev O., Roitberg A. E.

Nature Communications, 10 (2019)

Quantum Chemistry
Ml Potentials

Abstract Computational modeling of chemical and biological systems at atomic resolution is a crucial tool in the chemist’s toolset.

DOI
2019
cited5

Approaching coupled cluster accuracy with a general-purpose neural network potential through transfer learning

S Smith J., Nebgen B. T., Zubatyuk R., Lubbers N., Devereux C., Barros K., Tretiak S., Isayev O., Roitberg A.

(2019)

Quantum Chemistry
Ml Potentials

Computational modeling of chemical and biological systems at atomic resolution is a crucial tool in the chemist's toolset.

DOI
2019
cited5

Approaching coupled cluster accuracy with a general-purpose neural network potential through transfer learning

S Smith J., Nebgen B. T., Zubatyuk R., Lubbers N., Devereux C., Barros K., Tretiak S., Isayev O., Roitberg A.

(2019)

Quantum Chemistry
Ml Potentials

Computational modeling of chemical and biological systems at atomic resolution is a crucial tool in the chemist's toolset.

DOI
2019
cited227

Accurate and transferable multitask prediction of chemical properties with an atoms-in-molecules neural network

Zubatyuk R., Smith J. S., Leszczynski J., Isayev O.

Science Advances, 5 (2019)

We introduce a modular, chemically inspired deep neural network model for prediction of several atomic and molecular properties.

DOI

2018

2018
cited100

Transferable Dynamic Molecular Charge Assignment Using Deep Neural Networks

Nebgen B., Lubbers N., Smith J. S., Sifain A. E., Lokhov A., Isayev O., Roitberg A. E., Barros K., Tretiak S.

Journal of Chemical Theory and Computation, 14, 4687–4698 (2018)

Transferable Dynamic Molecular Charge Assignment Using Deep Neural Networks.

DOI
2018

Discovering a Transferable Charge Assignment Model Using Machine Learning

Sifain A. E., Lubbers N., Nebgen B. T., Smith J. S., Lokhov A. Y., Isayev O., Roitberg A. E., Barros K., Tretiak S.

(2018)

Partial atomic charge assignment is of immense practical value to force field parametrization, molecular docking, and cheminformatics.

DOI
2018
cited2

Accurate and Transferable Multitask Prediction of Chemical Properties with an Atoms-in-Molecule Neural Network

Zubatyuk R., Smith J. S., Leszczynski J., Isayev O.

(2018)

Ml Potentials

Atomic and molecular properties could be evaluated from the fundamental Schrodinger’s equation and therefore represent different modalities of the same quantum phenomena.

DOI
2018
cited2

Accurate and Transferable Multitask Prediction of Chemical Properties with an Atoms-in-Molecule Neural Network

Zubatyuk R., Smith J. S., Leszczynski J., Isayev O.

(2018)

Ml Potentials

Atomic and molecular properties could be evaluated from the fundamental Schrodinger’s equation and therefore represent different modalities of the same quantum phenomena.

DOI
2018

Accurate and Transferable Multitask Prediction of Chemical Properties with an Atoms-in-Molecule Neural Network

Zubatyuk R., Smith J. S., Leszczynski J., Isayev O.

(2018)

Ml Potentials

Atomic and molecular properties could be evaluated from the fundamental Schrodinger’s equation and therefore represent different modalities of the same quantum phenomena.

DOI

2017

2017
cited269

ANI-1, A data set of 20 million calculated off-equilibrium conformations for organic molecules

Smith J. S., Isayev O., Roitberg A. E.

Scientific Data, 4 (2017)

Ml Potentials
Quantum Chemistry

AbstractOne of the grand challenges in modern theoretical chemistry is designing and implementing approximations that expedite ab initio methods without loss of accuracy.

DOI
2017
cited1243

ANI-1: an extensible neural network potential with DFT accuracy at force field computational cost

Smith J. S., Isayev O., Roitberg A. E.

Chemical Science, 8, 3192–3203 (2017)

Ml Potentials
Quantum Chemistry

We demonstrate how a deep neural network (NN) trained on a data set of quantum mechanical (QM) DFT calculated energies can learn an accurate and transferable atomistic potential for organic molecules containing H, C, N, and O atoms.

DOI