Tora3D: an autoregressive torsion angle prediction model for molecular 3D conformation generation

Journal of Cheminformatics

Research

Zimei Zhang¹  Mingyue Zheng²  Xiaochu Tong³  Gang Wang³  Xiaojie Lu³  Xiangtai Kong³  Xutong Li³  Shengkun Ni³  RunZe Zhang³  Dingyan Wang⁴  Kaiyang Cheng⁵  Lin Ni⁵  Qun Ren⁵  Li Luo⁶  Rui Li⁷ 

[1] Division of Life Science and Medicine, University of Science and Technology of China, 230026, Hefei, Anhui, China;Drug Discovery and Design Center, State Key Laboratory of Drug Research, Shanghai Institute of Materia Medica, Chinese Academy of Sciences, 555 Zuchongzhi Road, 201203, Shanghai, China;Division of Life Science and Medicine, University of Science and Technology of China, 230026, Hefei, Anhui, China;Drug Discovery and Design Center, State Key Laboratory of Drug Research, Shanghai Institute of Materia Medica, Chinese Academy of Sciences, 555 Zuchongzhi Road, 201203, Shanghai, China;University of Chinese Academy of Sciences, No.19A Yuquan Road, 100049, Beijing, China;Nanjing University of Chinese Medicine, 138 Xianlin Road, 210023, Nanjing, China;Drug Discovery and Design Center, State Key Laboratory of Drug Research, Shanghai Institute of Materia Medica, Chinese Academy of Sciences, 555 Zuchongzhi Road, 201203, Shanghai, China;University of Chinese Academy of Sciences, No.19A Yuquan Road, 100049, Beijing, China;Lingang Laboratory, 200031, Shanghai, China;Nanjing University of Chinese Medicine, 138 Xianlin Road, 210023, Nanjing, China;Drug Discovery and Design Center, State Key Laboratory of Drug Research, Shanghai Institute of Materia Medica, Chinese Academy of Sciences, 555 Zuchongzhi Road, 201203, Shanghai, China;Precision Pharmacy & Drug Development Center, Department of Pharmacy, Tangdu Hospital, Fourth Military Medical University, 710038, Xi’an, China;School of Pharmacy, China Pharmaceutical University, 639 Longmian Road, 211198, Nanjing, China;Drug Discovery and Design Center, State Key Laboratory of Drug Research, Shanghai Institute of Materia Medica, Chinese Academy of Sciences, 555 Zuchongzhi Road, 201203, Shanghai, China;

关键词: Conformations generation;    Autoregressive;    Transformer;    Deep learning;    Small molecules;   

DOI  :  10.1186/s13321-023-00726-8

 received in 2023-01-12, accepted in 2023-05-20,  发布年份 2023

来源: Springer

【 摘 要 】

Three-dimensional (3D) conformations of a small molecule profoundly affect its binding to the target of interest, the resulting biological effects, and its disposition in living organisms, but it is challenging to accurately characterize the conformational ensemble experimentally. Here, we proposed an autoregressive torsion angle prediction model Tora3D for molecular 3D conformer generation. Rather than directly predicting the conformations in an end-to-end way, Tora3D predicts a set of torsion angles of rotatable bonds by an interpretable autoregressive method and reconstructs the 3D conformations from them, which keeps structural validity during reconstruction. Another advancement of our method over other conformational generation methods is the ability to use energy to guide the conformation generation. In addition, we propose a new message-passing mechanism that applies the Transformer to the graph to solve the difficulty of remote message passing. Tora3D shows superior performance to prior computational models in the trade-off between accuracy and efficiency, and ensures conformational validity, accuracy, and diversity in an interpretable way. Overall, Tora3D can be used for the quick generation of diverse molecular conformations and 3D-based molecular representation, contributing to a wide range of downstream drug design tasks.Graphical Abstract

【 授权许可】

CC BY   
© The Author(s) 2023

【 图 表 】

Fig. 1

Fig. 3

Fig. 5

Fig. 4

Fig. 2

Fig. 2

Fig. 2

Fig. 1

Fig. 5

Fig. 3

12888_2023_4935_Article_IEq1.gif

Fig. 3

Fig. 2

Fig. 2

Fig. 5

Fig. 3

Fig. 3

Fig. 1

Fig. 3

Fig. 2

Fig. 2

Fig. 1

Fig. 3

Fig. 6

Fig. 5

Fig. 1

Fig. 5

Fig. 7

Fig. 1

40517_2023_259_Article_IEq82.gif

40517_2023_259_Article_IEq79.gif

40517_2023_259_Article_IEq78.gif

40517_2023_259_Article_IEq77.gif

40517_2023_259_Article_IEq76.gif

Fig. 3

40517_2023_259_Article_IEq73.gif

40517_2023_259_Article_IEq72.gif

40517_2023_259_Article_IEq71.gif

40517_2023_259_Article_IEq56.gif

40517_2023_259_Article_IEq54.gif

40517_2023_259_Article_IEq53.gif

40517_2023_259_Article_IEq86.gif

40517_2023_259_Article_IEq52.gif

Fig. 4

40517_2023_259_Article_IEq51.gif

40517_2023_259_Article_IEq90.gif

40517_2023_259_Article_IEq89.gif

40517_2023_259_Article_IEq48.gif

40517_2023_259_Article_IEq85.gif

40517_2023_259_Article_IEq84.gif

40517_2023_259_Article_IEq46.gif

40517_2023_259_Article_IEq45.gif

Fig. 2

Fig. 1

40517_2023_259_Article_IEq42.gif

40517_2023_259_Article_IEq41.gif

Fig. 1

40517_2023_259_Article_IEq36.gif

40517_2023_259_Article_IEq35.gif

40517_2023_259_Article_IEq32.gif

40517_2023_259_Article_IEq31.gif

40517_2023_259_Article_IEq30.gif

Fig. 1

40517_2023_259_Article_IEq28.gif

Fig. 2

Fig. 1

42004_2023_919_Article_IEq176.gif

42004_2023_919_Article_IEq175.gif

Fig. 5

Fig. 8

Fig. 1

42004_2023_919_Article_IEq168.gif

13011_2023_540_Article_IEq40.gif

40517_2023_259_Article_IEq17.gif

Fig. 2

Fig. 1

13011_2023_540_Article_IEq1.gif

Fig. 10

41116_2023_37_Article_IEq287.gif

41116_2023_37_Article_IEq271.gif

41116_2023_37_Article_IEq251.gif