EUVIMEDEUVIMED entdecken
Crossref

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

Zheng-Xin Yang, Xin-Tian Xie iD, Pei-Lin Kang iD, Zhen-Xiong Wang, Cheng Shang iD, Zhi-Pan Liu iD

Journal of Chemical Theory and Computation · 13.08.2024 · 20 (15) · 6717-6727

DOI: 10.1021/acs.jctc.4c00660 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of Chemical Theory and Computation, online erschienen am 22.07.2024. Verfasst von Zheng-Xin Yang und 5 weiteren Autor:innen. Beteiligte Einrichtung: Collaborative Innovation Center of Chemistry for Energy Material, Shanghai Key Laboratory of Molecular Catalysis and Innovative Materials, Key Labora…. Die Arbeit wurde bisher 15-mal zitiert (Crossref) und nennt 57 Literaturangaben. Gefördert von: National Key Research and Development Program of China, Tencent, Fundamental Research Funds for the Central Universities.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

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 self-attention 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-function-type 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.

Autor:innen und Institutionen

  • Collaborative Innovation Center of Chemistry for Energy Material, Shanghai Key Laboratory of Molecular Catalysis and Innovative Materials, Key Laboratory of Computational Physical Science, Department of Chemistry, Fudan…
  • Shanghai Qi Zhi Institution, Shanghai 200030, China.
  • Key Laboratory of Synthetic and Self-Assembly Chemistry for Organic Functional Molecules, Shanghai Institute of Organic Chemistry, Chinese Academy of Sciences, Shanghai 200032, China.

ORCID-Profile: Xin-Tian Xie, Pei-Lin Kang, Cheng Shang, Zhi-Pan Liu

Förderung

  • National Key Research and Development Program of China
  • Tencent
  • Fundamental Research Funds for the Central Universities
  • National Natural Science Foundation of China

Zitieren

APA

Yang, Z. X., Xie, X. T., Kang, P. L., Wang, Z. X., Shang, C., & Liu, Z. P. (2024). Many-Body Function Corrected Neural Network with Atomic Attention (MBNN-att) for Molecular Property Prediction. Journal of Chemical Theory and Computation, 20(15), 6717-6727. https://doi.org/10.1021/acs.jctc.4c00660

Vancouver

Yang ZX, Xie XT, Kang PL, Wang ZX, Shang C, Liu ZP. Many-Body Function Corrected Neural Network with Atomic Attention (MBNN-att) for Molecular Property Prediction. Journal of Chemical Theory and Computation. 2024;20(15):6717-6727. doi:10.1021/acs.jctc.4c00660

BibTeX
@article{Yang2024,
  author = {Yang, Zheng-Xin and Xie, Xin-Tian and Kang, Pei-Lin and Wang, Zhen-Xiong and Shang, Cheng and Liu, Zhi-Pan},
  title = {Many-Body Function Corrected Neural Network with Atomic Attention (MBNN-att) for Molecular Property Prediction},
  journal = {Journal of Chemical Theory and Computation},
  year = {2024},
  volume = {20},
  number = {15},
  pages = {6717--6727},
  doi = {10.1021/acs.jctc.4c00660}
}
Kostenlos starten →