Lixue Cheng
Research Subjects
Lixue Cheng has a total of 48 co-authors. Here are the top co-authors by number of shared publications:
- Thomas Francis Miller
Division of Chemistry and Chemical Engineering, California Institute of Technology , Pasadena, California 91125, USA
5 shared publications Jiace Sun
Division of Chemistry and Chemical Engineering, California Institute of Technology, Pasadena, California 91125, United States
3 shared publications- Adam Foster
Microsoft Research AI for Science, Cambridge, UK
2 shared publications - Frank Noé
Freie Universität Berlin
2 shared publications - Jan Hermann
Microsoft Research AI for Science
2 shared publications - Jiace Sun
Division of Engineering and Applied Science, California Institute of Technology, Pasadena, California 91125, USA
2 shared publications
Latest Publications
- Open Access
- 9 November 2026
- Published by Springer Nature in Nature Communications
SimPoly: Simulation of polymers with machine learning force fields derived from first principles
- 9 November 2026
- Published by Springer Nature in Nature Communications
Open AccessSimPoly: Simulation of polymers with machine learning force fields derived from first principles
- Open Access
- 21 August 2026
- Published by Springer Nature in Nature Communications
- Vol. 17 (1) , 9976
An ab initio foundation model of wavefunctions that accurately describes chemical bond breaking
Reliable description of bond breaking remains a major challenge for quantum chemistry due to the multireference character of the electronic structure in dissociating species. Multireference methods in particular suffer from large computational cost, which under the normal paradigm has to be paid anew for each system at a full price, ignoring commonalities in electronic structure across molecules. Quantum Monte Carlo with deep neural networks uniquely offers to exploit such commonalities by pretraining transferable wavefunction models, but all such attempts were so far limited in scope. Here, we bring this paradigm to fruition with Orbformer, a transferable wavefunction model pretrained on 22,000 equilibrium and dissociating structures that can be fine-tuned on unseen molecules reaching an accuracy–cost ratio rivalling classical multireference methods. On established benchmarks as well as more challenging bond dissociations and Diels–Alder reactions, Orbformer is the only method that consistently converges to chemical accuracy (1 kcal/mol). This work turns the idea of amortizing the cost of solving the Schrödinger equation over many molecules into a practical approach in quantum chemistry.
- 21 August 2026
- Published by Springer Nature in Nature Communications
- Vol. 17 (1) , 9976
Open AccessAn ab initio foundation model of wavefunctions that accurately describes chemical bond breaking
Reliable description of bond breaking remains a major challenge for quantum chemistry due to the multireference character of the electronic structure in dissociating species. Multireference methods in particular suffer from large computational cost, which under the normal paradigm has to be paid anew for each system at a full price, ignoring commonalities in electronic structure across molecules. Quantum Monte Carlo with deep neural networks uniquely offers to exploit such commonalities by pretraining transferable wavefunction models, but all such attempts were so far limited in scope. Here, we bring this paradigm to fruition with Orbformer, a transferable wavefunction model pretrained on 22,000 equilibrium and dissociating structures that can be fine-tuned on unseen molecules reaching an accuracy–cost ratio rivalling classical multireference methods. On established benchmarks as well as more challenging bond dissociations and Diels–Alder reactions, Orbformer is the only method that consistently converges to chemical accuracy (1 kcal/mol). This work turns the idea of amortizing the cost of solving the Schrödinger equation over many molecules into a practical approach in quantum chemistry.
- Open Access
- 23 January 2026
- Published by American Chemical Society (ACS) in Precision Chemistry
- Vol. 4 (5) , 612-621
Benchmarking Foundation Potentials against Quantum Chemistry Methods for Predicting Molecular Redox Potentials
Computational high-throughput virtual screening is essential for identifying redox-active molecules for sustainable applications, such as electrochemical carbon capture. A primary challenge in this approach is the high computational cost associated with accurate quantum chemistry calculations. Machine learning foundation potentials (FPs) trained on extensive density functional theory (DFT) calculations offer a computationally efficient alternative. Here, we benchmark the MACE-OMol-0 and UMA FPs against a hierarchy of DFT functionals for predicting experimental molecular redox potentials for both electron transfer (ET) and proton-coupled electron transfer (PCET) reactions. We find that these FPs achieve exceptional accuracy for PCET processes, rivaling their target DFT method. However, the performance is diminished for ET reactions, particularly for multielectron transfers involving reactive ions that are underrepresented in the OMol25 training data, revealing a key out-of-distribution limitation. To overcome this, we propose an optimal hybrid workflow that uses the FPs for efficient geometry optimization and thermochemical analysis, followed by a crucial single-point DFT energy refinement and an implicit solvation correction. This pragmatic approach provides a robust and scalable strategy for accelerating high-throughput virtual screening in sustainable chemistry.
- 23 January 2026
- Published by American Chemical Society (ACS) in Precision Chemistry
- Vol. 4 (5) , 612-621
Open AccessBenchmarking Foundation Potentials against Quantum Chemistry Methods for Predicting Molecular Redox Potentials
Computational high-throughput virtual screening is essential for identifying redox-active molecules for sustainable applications, such as electrochemical carbon capture. A primary challenge in this approach is the high computational cost associated with accurate quantum chemistry calculations. Machine learning foundation potentials (FPs) trained on extensive density functional theory (DFT) calculations offer a computationally efficient alternative. Here, we benchmark the MACE-OMol-0 and UMA FPs against a hierarchy of DFT functionals for predicting experimental molecular redox potentials for both electron transfer (ET) and proton-coupled electron transfer (PCET) reactions. We find that these FPs achieve exceptional accuracy for PCET processes, rivaling their target DFT method. However, the performance is diminished for ET reactions, particularly for multielectron transfers involving reactive ions that are underrepresented in the OMol25 training data, revealing a key out-of-distribution limitation. To overcome this, we propose an optimal hybrid workflow that uses the FPs for efficient geometry optimization and thermochemical analysis, followed by a crucial single-point DFT energy refinement and an implicit solvation correction. This pragmatic approach provides a robust and scalable strategy for accelerating high-throughput virtual screening in sustainable chemistry.
- 21 January 2025
- Published by AIP Publishing in The Journal of Chemical Physics
- Vol. 162 (3)
Highly accurate real-space electron densities with neural networks
Variational ab initio methods in quantum chemistry stand out among other methods in providing direct access to the wave function. This allows, in principle, straightforward extraction of any other observable of interest, besides the energy, but, in practice, this extraction is often technically difficult and computationally impractical. Here, we consider the electron density as a central observable in quantum chemistry and introduce a novel method to obtain accurate densities from real-space many-electron wave functions by representing the density with a neural network that captures known asymptotic properties and is trained from the wave function by score matching and noise-contrastive estimation. We use variational quantum Monte Carlo with deep-learning Ansätze to obtain highly accurate wave functions free of basis set errors and from them, using our novel method, correspondingly accurate electron densities, which we demonstrate by calculating dipole moments, nuclear forces, contact densities, and other density-based properties.
- 21 January 2025
- Published by AIP Publishing in The Journal of Chemical Physics
- Vol. 162 (3)
Highly accurate real-space electron densities with neural networks
Variational ab initio methods in quantum chemistry stand out among other methods in providing direct access to the wave function. This allows, in principle, straightforward extraction of any other observable of interest, besides the energy, but, in practice, this extraction is often technically difficult and computationally impractical. Here, we consider the electron density as a central observable in quantum chemistry and introduce a novel method to obtain accurate densities from real-space many-electron wave functions by representing the density with a neural network that captures known asymptotic properties and is trained from the wave function by score matching and noise-contrastive estimation. We use variational quantum Monte Carlo with deep-learning Ansätze to obtain highly accurate wave functions free of basis set errors and from them, using our novel method, correspondingly accurate electron densities, which we demonstrate by calculating dipole moments, nuclear forces, contact densities, and other density-based properties.
- Open Access
- 30 December 2024
- Published by American Chemical Society (ACS) in ChemRxiv
Machine Learning Approaches for Developing Potential Surfaces: Applications to OH-(H2O)n (n=1-3) Complexes
An approach for obtaining high-level ab initio potential surfaces is described. The approach takes advantage of machine learning strategies in a two-step process. In the first, the molecular-orbital based machine learning (MOB-ML) model uses Gaussian process regression to learn the correlation energy at the CCSD(T) level using the molecular orbitals obtained from Hartree-Fock calculations. In this work, the MOB-ML approach is expanded to use orbitals obtained using a smaller basis set, aug-cc-pVDZ, as features for learning the correlation energies at the complete basis set (CBS) limit. This approach is combined with the development of a neural-network potential, where the sampled geometries and energies that provide the training data for the potential are obtained using a diffusion Monte Carlo (DMC) calculation, which was run using the MOB-ML model. Protocols are developed to make full use of the structures that are obtained from the DMC calculation in the training process. These approaches are used to develop potentials for OH-(H2O) and H3O+(H2O), which are used for subsequent DMC calculations. The results of these calculations are compared to those performed using previously reported potentials. Overall, the results of the two sets of DMC calculations are in good agreement for these very floppy molecules. Potentials are also developed for OH-(H2O)2 and OH-(H2O)3, for which there are not available potential surfaces. The results of DMC calculations for these ions are compared to those for the correspondingOH-(H2O)2 and OH-(H2O)3 ions. It is found that the level of delocalization of the shared proton is similar for a hydroxide or hydronium ion bound to the same number of water molecules. This finding is consistent with the experimental observation that these sets of ions have similar spectra.
- 30 December 2024
- Published by American Chemical Society (ACS) in ChemRxiv
Open AccessMachine Learning Approaches for Developing Potential Surfaces: Applications to OH-(H2O)n (n=1-3) Complexes
An approach for obtaining high-level ab initio potential surfaces is described. The approach takes advantage of machine learning strategies in a two-step process. In the first, the molecular-orbital based machine learning (MOB-ML) model uses Gaussian process regression to learn the correlation energy at the CCSD(T) level using the molecular orbitals obtained from Hartree-Fock calculations. In this work, the MOB-ML approach is expanded to use orbitals obtained using a smaller basis set, aug-cc-pVDZ, as features for learning the correlation energies at the complete basis set (CBS) limit. This approach is combined with the development of a neural-network potential, where the sampled geometries and energies that provide the training data for the potential are obtained using a diffusion Monte Carlo (DMC) calculation, which was run using the MOB-ML model. Protocols are developed to make full use of the structures that are obtained from the DMC calculation in the training process. These approaches are used to develop potentials for OH-(H2O) and H3O+(H2O), which are used for subsequent DMC calculations. The results of these calculations are compared to those performed using previously reported potentials. Overall, the results of the two sets of DMC calculations are in good agreement for these very floppy molecules. Potentials are also developed for OH-(H2O)2 and OH-(H2O)3, for which there are not available potential surfaces. The results of DMC calculations for these ions are compared to those for the correspondingOH-(H2O)2 and OH-(H2O)3 ions. It is found that the level of delocalization of the shared proton is similar for a hydroxide or hydronium ion bound to the same number of water molecules. This finding is consistent with the experimental observation that these sets of ions have similar spectra.
- Open Access
- 6 March 2024
- Published by Springer Nature in Communications Physics
- Vol. 7 (1) , 1-9
Quantum approximate optimization via learning-based adaptive optimization
Combinatorial optimization problems are ubiquitous and computationally hard to solve in general. Quantum approximate optimization algorithm (QAOA), one of the most representative quantum-classical hybrid algorithms, is designed to solve combinatorial optimization problems by transforming the discrete optimization problem into a classical optimization problem over continuous circuit parameters. QAOA objective landscape is notorious for pervasive local minima, and its viability significantly relies on the efficacy of the classical optimizer. In this work, we design double adaptive-region Bayesian optimization (DARBO) for QAOA. Our numerical results demonstrate that the algorithm greatly outperforms conventional optimizers in terms of speed, accuracy, and stability. We also address the issues of measurement efficiency and the suppression of quantum noise by conducting the full optimization loop on a superconducting quantum processor as a proof of concept. This work helps to unlock the full power of QAOA and paves the way toward achieving quantum advantage in practical classical tasks.
- 6 March 2024
- Published by Springer Nature in Communications Physics
- Vol. 7 (1) , 1-9
Open AccessQuantum approximate optimization via learning-based adaptive optimization
Combinatorial optimization problems are ubiquitous and computationally hard to solve in general. Quantum approximate optimization algorithm (QAOA), one of the most representative quantum-classical hybrid algorithms, is designed to solve combinatorial optimization problems by transforming the discrete optimization problem into a classical optimization problem over continuous circuit parameters. QAOA objective landscape is notorious for pervasive local minima, and its viability significantly relies on the efficacy of the classical optimizer. In this work, we design double adaptive-region Bayesian optimization (DARBO) for QAOA. Our numerical results demonstrate that the algorithm greatly outperforms conventional optimizers in terms of speed, accuracy, and stability. We also address the issues of measurement efficiency and the suppression of quantum noise by conducting the full optimization loop on a superconducting quantum processor as a proof of concept. This work helps to unlock the full power of QAOA and paves the way toward achieving quantum advantage in practical classical tasks.
- 3 January 2024
- Published by American Chemical Society (ACS) in Journal of Chemical Theory and Computation
- Vol. 20 (2) , 695-707
Toward Chemical Accuracy with Shallow Quantum Circuits: A Clifford-Based Hamiltonian Engineering Approach
Achieving chemical accuracy with shallow quantum circuits is a significant challenge in quantum computational chemistry, particularly for near-term quantum devices. In this work, we present a Clifford-based Hamiltonian engineering algorithm, namely CHEM, that addresses the trade-off between circuit depth and accuracy. Based on a variational quantum eigensolver and hardware-efficient ansatz, our method designs the Clifford-based Hamiltonian transformation that (1) ensures a set of initial circuit parameters corresponding to the Hartree-Fock energy can be generated, (2) effectively maximizes the initial energy gradient with respect to circuit parameters, (3) imposes negligible overhead for classical processing and does not require additional quantum resources, and (4) is compatible with any circuit topology. We demonstrate the efficacy of our approach using a quantum hardware emulator, achieving chemical accuracy for systems as large as 12 qubits with fewer than 30 two-qubit gates. Our Clifford-based Hamiltonian engineering approach offers a promising avenue for practical quantum computational chemistry on near-term quantum devices.
- 3 January 2024
- Published by American Chemical Society (ACS) in Journal of Chemical Theory and Computation
- Vol. 20 (2) , 695-707
Toward Chemical Accuracy with Shallow Quantum Circuits: A Clifford-Based Hamiltonian Engineering Approach
Achieving chemical accuracy with shallow quantum circuits is a significant challenge in quantum computational chemistry, particularly for near-term quantum devices. In this work, we present a Clifford-based Hamiltonian engineering algorithm, namely CHEM, that addresses the trade-off between circuit depth and accuracy. Based on a variational quantum eigensolver and hardware-efficient ansatz, our method designs the Clifford-based Hamiltonian transformation that (1) ensures a set of initial circuit parameters corresponding to the Hartree-Fock energy can be generated, (2) effectively maximizes the initial energy gradient with respect to circuit parameters, (3) imposes negligible overhead for classical processing and does not require additional quantum resources, and (4) is compatible with any circuit topology. We demonstrate the efficacy of our approach using a quantum hardware emulator, achieving chemical accuracy for systems as large as 12 qubits with fewer than 30 two-qubit gates. Our Clifford-based Hamiltonian engineering approach offers a promising avenue for practical quantum computational chemistry on near-term quantum devices.
- Open Access
- 21 October 2022
- Published by AIP Publishing in The Journal of Chemical Physics
- Vol. 157 (15) , 154105
Molecular-orbital-based machine learning for open-shell and multi-reference systems with kernel addition Gaussian process regression
We introduce a novel machine learning strategy, kernel addition Gaussian process regression (KA-GPR), in molecular-orbital-based machine learning (MOB-ML) to learn the total correlation energies of general electronic structure theories for closed- and open-shell systems by introducing a machine learning strategy. The learning efficiency of MOB-ML(KA-GPR) is the same as the original MOB-ML method for the smallest criegee molecule, which is a closed-shell molecule with multi-reference characters. In addition, the prediction accuracies of different small free radicals could reach the chemical accuracy of 1 kcal/mol by training on one example structure. Accurate potential energy surfaces for the H10 chain (closed-shell) and water OH bond dissociation (open-shell) could also be generated by MOB-ML(KA-GPR). To explore the breadth of chemical systems that KA-GPR can describe, we further apply MOB-ML to accurately predict the large benchmark datasets for closed- (QM9, QM7b-T, and GDB-13-T) and open-shell (QMSpin) molecules.
- 21 October 2022
- Published by AIP Publishing in The Journal of Chemical Physics
- Vol. 157 (15) , 154105
Open AccessMolecular-orbital-based machine learning for open-shell and multi-reference systems with kernel addition Gaussian process regression
We introduce a novel machine learning strategy, kernel addition Gaussian process regression (KA-GPR), in molecular-orbital-based machine learning (MOB-ML) to learn the total correlation energies of general electronic structure theories for closed- and open-shell systems by introducing a machine learning strategy. The learning efficiency of MOB-ML(KA-GPR) is the same as the original MOB-ML method for the smallest criegee molecule, which is a closed-shell molecule with multi-reference characters. In addition, the prediction accuracies of different small free radicals could reach the chemical accuracy of 1 kcal/mol by training on one example structure. Accurate potential energy surfaces for the H10 chain (closed-shell) and water OH bond dissociation (open-shell) could also be generated by MOB-ML(KA-GPR). To explore the breadth of chemical systems that KA-GPR can describe, we further apply MOB-ML to accurately predict the large benchmark datasets for closed- (QM9, QM7b-T, and GDB-13-T) and open-shell (QMSpin) molecules.
- Open Access
- 8 September 2022
- Published by AIP Publishing in The Journal of Chemical Physics
- Vol. 157 (10) , 104109
Molecular dipole moment learning via rotationally equivariant derivative kernels in molecular-orbital-based machine learning
This study extends the accurate and transferable molecular-orbital-based machine learning (MOB-ML) approach to modeling the contribution of electron correlation to dipole moments at the cost of Hartree–Fock computations. A MOB pairwise decomposition of the correlation part of the dipole moment is applied, and these pair dipole moments could be further regressed as a universal function of MOs. The dipole MOB features consist of the energy MOB features and their responses to electric fields. An interpretable and rotationally equivariant derivative kernel for Gaussian process regression (GPR) is introduced to learn the dipole moment more efficiently. The proposed problem setup, feature design, and ML algorithm are shown to provide highly accurate models for both dipole moments and energies on water and 14 small molecules. To demonstrate the ability of MOB-ML to function as generalized density-matrix functionals for molecular dipole moments and energies of organic molecules, we further apply the proposed MOB-ML approach to train and test the molecules from the QM9 dataset. The application of local scalable GPR with Gaussian mixture model unsupervised clustering GPR scales up MOB-ML to a large-data regime while retaining the prediction accuracy. In addition, compared with the literature results, MOB-ML provides the best test mean absolute errors of 4.21 mD and 0.045 kcal/mol for dipole moment and energy models, respectively, when training on 110 000 QM9 molecules. The excellent transferability of the resulting QM9 models is also illustrated by the accurate predictions for four different series of peptides.
- 8 September 2022
- Published by AIP Publishing in The Journal of Chemical Physics
- Vol. 157 (10) , 104109
Open AccessMolecular dipole moment learning via rotationally equivariant derivative kernels in molecular-orbital-based machine learning
This study extends the accurate and transferable molecular-orbital-based machine learning (MOB-ML) approach to modeling the contribution of electron correlation to dipole moments at the cost of Hartree–Fock computations. A MOB pairwise decomposition of the correlation part of the dipole moment is applied, and these pair dipole moments could be further regressed as a universal function of MOs. The dipole MOB features consist of the energy MOB features and their responses to electric fields. An interpretable and rotationally equivariant derivative kernel for Gaussian process regression (GPR) is introduced to learn the dipole moment more efficiently. The proposed problem setup, feature design, and ML algorithm are shown to provide highly accurate models for both dipole moments and energies on water and 14 small molecules. To demonstrate the ability of MOB-ML to function as generalized density-matrix functionals for molecular dipole moments and energies of organic molecules, we further apply the proposed MOB-ML approach to train and test the molecules from the QM9 dataset. The application of local scalable GPR with Gaussian mixture model unsupervised clustering GPR scales up MOB-ML to a large-data regime while retaining the prediction accuracy. In addition, compared with the literature results, MOB-ML provides the best test mean absolute errors of 4.21 mD and 0.045 kcal/mol for dipole moment and energy models, respectively, when training on 110 000 QM9 molecules. The excellent transferability of the resulting QM9 models is also illustrated by the accurate predictions for four different series of peptides.
- 20 July 2022
- Published by American Chemical Society (ACS) in Journal of Chemical Theory and Computation
- Vol. 18 (8) , 4826-4835
Accurate Molecular-Orbital-Based Machine Learning Energies via Unsupervised Clustering of Chemical Space
We introduce an unsupervised clustering algorithm to improve training efficiency and accuracy in predicting energies using molecular-orbital-based machine learning (MOB-ML). This work determines clusters via the Gaussian mixture model (GMM) in an entirely automatic manner and simplifies an earlier supervised clustering approach [J. Chem. Theory Comput. 2019, 15, 6668] by eliminating both the necessity for user-specified parameters and the training of an additional classifier. Unsupervised clustering results from GMM have the advantages of accurately reproducing chemically intuitive groupings of frontier molecular orbitals and exhibiting improved performance with an increasing number of training examples. The resulting clusters from supervised or unsupervised clustering are further combined with scalable Gaussian process regression (GPR) or linear regression (LR) to learn molecular energies accurately by generating a local regression model in each cluster. Among all four combinations of regressors and clustering methods, GMM combined with scalable exact GPR (GMM/GPR) is the most efficient training protocol for MOB-ML. The numerical tests of molecular energy learning on thermalized data sets of drug-like molecules demonstrate the improved accuracy, transferability, and learning efficiency of GMM/GPR over other training protocols for MOB-ML, i.e., supervised regression clustering combined with GPR (RC/GPR) and GPR without clustering. GMM/GPR also provides the best molecular energy predictions compared with ones from the literature on the same benchmark data sets. With a lower scaling, GMM/GPR has a 10.4-fold speedup in wall-clock training time compared with scalable exact GPR with a training size of 6500 QM7b-T molecules.
- 20 July 2022
- Published by American Chemical Society (ACS) in Journal of Chemical Theory and Computation
- Vol. 18 (8) , 4826-4835
Accurate Molecular-Orbital-Based Machine Learning Energies via Unsupervised Clustering of Chemical Space
We introduce an unsupervised clustering algorithm to improve training efficiency and accuracy in predicting energies using molecular-orbital-based machine learning (MOB-ML). This work determines clusters via the Gaussian mixture model (GMM) in an entirely automatic manner and simplifies an earlier supervised clustering approach [J. Chem. Theory Comput. 2019, 15, 6668] by eliminating both the necessity for user-specified parameters and the training of an additional classifier. Unsupervised clustering results from GMM have the advantages of accurately reproducing chemically intuitive groupings of frontier molecular orbitals and exhibiting improved performance with an increasing number of training examples. The resulting clusters from supervised or unsupervised clustering are further combined with scalable Gaussian process regression (GPR) or linear regression (LR) to learn molecular energies accurately by generating a local regression model in each cluster. Among all four combinations of regressors and clustering methods, GMM combined with scalable exact GPR (GMM/GPR) is the most efficient training protocol for MOB-ML. The numerical tests of molecular energy learning on thermalized data sets of drug-like molecules demonstrate the improved accuracy, transferability, and learning efficiency of GMM/GPR over other training protocols for MOB-ML, i.e., supervised regression clustering combined with GPR (RC/GPR) and GPR without clustering. GMM/GPR also provides the best molecular energy predictions compared with ones from the literature on the same benchmark data sets. With a lower scaling, GMM/GPR has a 10.4-fold speedup in wall-clock training time compared with scalable exact GPR with a training size of 6500 QM7b-T molecules.