Premium
Rotational Variance‐Based Data Augmentation in 3D Graph Convolutional Network
Author(s) -
Kim Jihoo,
Kim Yeji,
Lee Eok Kyun,
Chae Chong Hak,
Lee Kwangho,
Kim Won June,
Choi Insung S.
Publication year - 2021
Publication title -
chemistry – an asian journal
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 1.18
H-Index - 106
eISSN - 1861-471X
pISSN - 1861-4728
DOI - 10.1002/asia.202100789
Subject(s) - orientation (vector space) , graph , computer science , virtual screening , rotation (mathematics) , drug discovery , artificial intelligence , pattern recognition (psychology) , task (project management) , ligand (biochemistry) , data mining , chemistry , theoretical computer science , mathematics , engineering , biochemistry , receptor , geometry , systems engineering
Abstract This work proposes the data augmentation by molecular rotation, with consideration that the protein‐ligand binding events are rotation‐variant. As a proof‐of‐concept, known active (i. e., 1‐labeled) ligands to human β‐secretase 1 (BACE‐1) are rotated for the generation of 0‐labeled data, and the rotation‐dependent prediction accuracy of 3D graph convolutional network (3DGCN) is investigated after data augmentation. The data augmentation makes the orientation‐recognizing ability of 3DGCN improved significantly in the classification task for BACE‐1/ligand binding. Furthermore, the data‐augmented 3DGCN has a capability for predicting active ligands from a candidate dataset, via improved performance of orientation recognition, which would be applied to virtual drug screening and discovery.