GTAM: a molecular pretraining model with geometric triangle awareness.

Journal: Bioinformatics (Oxford, England)
PMID: 39177102

Abstract

MOTIVATION: Molecular representation learning is pivotal for advancing deep learning applications in quantum chemistry and drug discovery. Existing methods for molecular representation learning often fall short of fully capturing the intricate interactions within chemical bonds of 2D topological graphs and the multifaceted effects of 3D geometric conformations.

Authors

  • Xiaoyang Hou
    Key Laboratory of Intelligent Information Processing, Institute of Computing Technology, Beijing, 100049, China.
  • Tian Zhu
    Key Laboratory of Intelligent Information Processing, Institute of Computing Technology, Beijing, 100049, China.
  • Milong Ren
    Key Laboratory of Intelligent Information Processing, Institute of Computing Technology, Beijing, 100049, China.
  • Bo Duan
    Department of Otolaryngology-Head and Neck Surgery, Children's Hospital of Fudan University, Shanghai 201102, China.
  • Chunming Zhang
    Key Laboratory of Intelligent Information Processing, Institute of Computing Technology, Beijing, 100049, China.
  • Dongbo Bu
    Key Lab of Intelligent Information Process, Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China.
  • Shiwei Sun
    Department of Urology, Peking Union Medical College Hospital, Chinese Academy of Medical Sciences and Peking Union Medical College, Beijing, China.

Keywords

External Resources

Popular Topics
Recent Journals