loading..

NEWS

NEWS

More

RESEARCH

RESEARCH

More

AI4S (AI for Science) - AI in Materials Applications: The Yuqian Chen Team Makes Significant Progress in the Research of Efficient Equivariant Model-Based Machine Learning Interatomic Potentials

Recently, the research team led by Yuqian Chen at the School of Chemical Biology and Biotechnology and the School of Scientific Intelligence at Peking University, in collaboration with the National University of Singapore, developed a machine learning interatomic potential model named E2GNN based on an efficient equivariant model. Unlike traditional equivariant models that rely on complex high-order tensor representations,E2GNN encodes equivariant features using a concise scalar-vector representation and incorporates a global message-passing mechanism. This approach enables a more accurate description of long-range atomic interactions, achieving efficient and physically reasonable potential energy predictions. The related findings were published in the prestigious AI4M (AI for Materials) journalnpj Computational Materials (a top-tier journal in the Chinese Academy

Recently, the research team led by Yuqian Chen at the School of Chemical Biology and Biotechnology and the School of Scientific Intelligence at Peking University, in collaboration with the National University of Singapore, developed a machine learning interatomic potential model named E2GNN based on an efficient equivariant model. Unlike traditional equivariant models that rely on complex high-order tensor representations,E2GNN encodes equivariant features using a concise scalar-vector representation and incorporates a global message-passing mechanism. This approach enables a more accurate description of long-range atomic interactions, achieving efficient and physically reasonable potential energy predictions. The related findings were published in the prestigious AI4M (AI for Materials) journalnpj Computational Materials (a top-tier journal in the Chinese Academy

More+

Bo Zhang Lab has elucidated the mechanism of action of atypical cadherin FAT2, which is associated with ataxia/autism.

​Motor ability, as a core product of animal evolution, is an adaptive survival skill essential for sustaining life. The integrity of the motor system directly determines an individual’s success in food chain competition, predator avoidance, and access to reproductive opportunities. In vertebrates, the cadherin FAT family comprises a group of single-pass transmembrane cell adhesion molecules, consisting of four members: FAT1–4. Each FAT molecule possesses over 30 extracellular cadherin repeat domains along with related functional domains. Clinical studies have shown that mutations in the FAT2 gene are associated with motor coordination disorders and autism. Due to the large molecular weight and complex structure of these proteins, research on their functional mechanisms has long been hindered. Therefore, elucidating the molecular mechanism by which FAT2 regulates motor behavior provides a critical breakthrough for understanding the pathogenesis of motor disorders.

​Motor ability, as a core product of animal evolution, is an adaptive survival skill essential for sustaining life. The integrity of the motor system directly determines an individual’s success in food chain competition, predator avoidance, and access to reproductive opportunities. In vertebrates, the cadherin FAT family comprises a group of single-pass transmembrane cell adhesion molecules, consisting of four members: FAT1–4. Each FAT molecule possesses over 30 extracellular cadherin repeat domains along with related functional domains. Clinical studies have shown that mutations in the FAT2 gene are associated with motor coordination disorders and autism. Due to the large molecular weight and complex structure of these proteins, research on their functional mechanisms has long been hindered. Therefore, elucidating the molecular mechanism by which FAT2 regulates motor behavior provides a critical breakthrough for understanding the pathogenesis of motor disorders.

More+

Faculty

TEACHER

More

Contact Us

Contact Person: Ms. Lu

Tel: +86-755-2603-3049

Fax: +86-755-2603-3174

EMAIL: luyanan@pku.edu.cn

Address: Peking University Shenzhen Graduate School Building F 203, Xili University Town, Nanshan District, Shenzhen (518055)

Copyright © School of Chemical Biology and Biotechnology, Peking University Shenzhen Graduate School     ICP License No.: 粤ICP备12081285号

Public Network Security License No.: 44030502008554        Technical Support: its@pkusz.edu.cn