TorchMD-Net 2.0: Fast Neural Network Potentials for Molecular Simulations

Pelaez, Raul P.; Simeon, Guillem; Galvelis, Raimondas; Mirarchi, Antonio; Eastman, Peter; Doerr, Stefan; Thölke, Philipp; Markland, Thomas E.; De Fabritiis, Gianni

doi:10.1021/acs.jctc.4c00253

Cited by 9 publications

(1 citation statement)

References 47 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…With three-body information, DimeNet++ reduces the MAE to 6.32 meV, and SphereNet further reaches 6.26 meV after adding the four-body information. Second, the addition of the equivariant frameworks, including PAINN, ET, and Equiformer, incorporate effectively the many-body information in message passing, showing the performance being close to, if not better than, those without equivariant representations but with four-body information (SphereNet). , Third, attention appears to be important for intensive properties including ε HOMO , ε LUMO , and Δε. , The lowest MAE occurs at ET (20.3 meV) and Equiformer (15.0 meV), and both have the attention mechanism.…”

Section: Resultsmentioning

confidence: 94%

Many-Body Function Corrected Neural Network with Atomic Attention (MBNN-att) for Molecular Property Prediction

Yang,

Xie,

Kang

et al. 2024

J. Chem. Theory Comput.

View full text Add to dashboard Cite

Recent years have seen a surge of machine learning (ML) in chemistry for predicting chemical properties, but a low-cost, general-purpose, and high-performance model, desirable to be accessible on central processing unit (CPU) devices, remains not available. For this purpose, here we introduce an atomic attention mechanism into many-body function corrected neural network (MBNN), namely, MBNN-att ML model, to predict both the extensive and intensive properties of molecules and materials. The MBNN-att uses explicit function descriptors as the inputs for the atom-based feed-forward neural network (NN). The output of the NN is designed to be a vector to implement the multihead selfattention mechanism. This vector is split into two parts: the atomic attention weight part and the many-body-function part. The final property is obtained by summing the products of each atomic attention weight and the corresponding many-body function. We show that MBNN-att performs well on all QM9 properties, i.e., errors on all properties, below chemical accuracy, and, in particular, achieves the top performance for the energy-related extensive properties. By systematically comparing with other explicit-functiontype descriptor ML models and the graph representation ML models, we demonstrate that the many-body-function framework and atomic attention mechanism are key ingredients for the high performance and the good transferability of MBNN-att in molecular property prediction.

show abstract

Section: Resultsmentioning

confidence: 94%

Many-Body Function Corrected Neural Network with Atomic Attention (MBNN-att) for Molecular Property Prediction

Yang,

Xie,

Kang

et al. 2024

J. Chem. Theory Comput.

View full text Add to dashboard Cite

show abstract

Recent Advances in Machine Learning‐Assisted Multiscale Design of Energy Materials

Mortazavi

2024

Advanced Energy Materials

View full text Add to dashboard Cite

This review highlights recent advances in machine learning (ML)‐assisted design of energy materials. Initially, ML algorithms were successfully applied to screen materials databases by establishing complex relationships between atomic structures and their resulting properties, thus accelerating the identification of candidates with desirable properties. Recently, the development of highly accurate ML interatomic potentials and generative models has not only improved the robust prediction of physical properties, but also significantly accelerated the discovery of materials. In the past couple of years, ML methods have enabled high‐precision first‐principles predictions of electronic and optical properties for large systems, providing unprecedented opportunities in materials science. Furthermore, ML‐assisted microstructure reconstruction and physics‐informed solutions for partial differential equations have facilitated the understanding of microstructure–property relationships. Most recently, the seamless integration of various ML platforms has led to the emergence of autonomous laboratories that combine quantum mechanical calculations, large language models, and experimental validations, fundamentally transforming the traditional approach to novel materials synthesis. While highlighting the aforementioned recent advances, existing challenges are also discussed. Ultimately, ML is expected to fully integrate atomic‐scale simulations, reverse engineering, process optimization, and device fabrication, empowering autonomous and generative energy system design. This will drive transformative innovations in energy conversion, storage, and harvesting technologies.

show abstract

SchNet_IIA: Potential Energy Surface Fitting by Interatomic Interactions Attention Based on Transfer Learning Analysis

Jiang,

Wang,

et al. 2024

J. Chem. Inf. Model.

View full text Add to dashboard Cite

TorchMD-Net 2.0: Fast Neural Network Potentials for Molecular Simulations

Cited by 9 publications

References 47 publications

Many-Body Function Corrected Neural Network with Atomic Attention (MBNN-att) for Molecular Property Prediction

Many-Body Function Corrected Neural Network with Atomic Attention (MBNN-att) for Molecular Property Prediction

Recent Advances in Machine Learning‐Assisted Multiscale Design of Energy Materials

SchNet_IIA: Potential Energy Surface Fitting by Interatomic Interactions Attention Based on Transfer Learning Analysis

Contact Info

Product

Resources

About