Xu Han
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Xu Han has a total of 5 co-authors. Here are the top co-authors by number of shared publications:
- Guanqun Liu
College of mechanical and Electronic Engineering, Dalian Minzu University, Dalian 116600, China
1 shared publication - Jie Zhang
Beijing Huawei Digital Technologies Co., Ltd, Beijing, China
1 shared publication - Naifeng Wen
School of Electromechanical Engineering, Dalian Minzu University, Dalian, China
1 shared publication - Rubo Zhang
College of Mechanical and Electronic Engineering, Dalian Minzu University, Dalian, China
1 shared publication - Yating Fu
School of Mechanical and Electronic Engineering, Dalian Minzu University, Dalian, China
1 shared publication
Latest Publications
- Open Access
- 21 October 2022
- Published by Springer Nature in Journal of Cheminformatics
- Vol. 14 (1) , 1-13
A fingerprints based molecular property prediction method using the BERT model
Molecular property prediction (MPP) is vital in drug discovery and drug reposition. Deep learning-based MPP models capture molecular property-related features from various molecule representations. In this paper, we propose a molecule sequence embedding and prediction model facing with MPP task. We pre-trained a bi-directional encoder representations from Transformers (BERT) encoder to obtain the semantic representation of compound fingerprints, called Fingerprints-BERT (FP-BERT), in a self-supervised learning manner. Then, the encoded molecular representation by the FP-BERT is input to the convolutional neural network (CNN) to extract higher-level abstract features, and the predicted properties of the molecule are finally obtained through fully connected layer for distinct classification or regression MPP tasks. Comparison with the baselines shows that the proposed model achieves high prediction performance on all of the classification tasks and regression tasks.
- 21 October 2022
- Published by Springer Nature in Journal of Cheminformatics
- Vol. 14 (1) , 1-13
Open AccessA fingerprints based molecular property prediction method using the BERT model
Molecular property prediction (MPP) is vital in drug discovery and drug reposition. Deep learning-based MPP models capture molecular property-related features from various molecule representations. In this paper, we propose a molecule sequence embedding and prediction model facing with MPP task. We pre-trained a bi-directional encoder representations from Transformers (BERT) encoder to obtain the semantic representation of compound fingerprints, called Fingerprints-BERT (FP-BERT), in a self-supervised learning manner. Then, the encoded molecular representation by the FP-BERT is input to the convolutional neural network (CNN) to extract higher-level abstract features, and the predicted properties of the molecule are finally obtained through fully connected layer for distinct classification or regression MPP tasks. Comparison with the baselines shows that the proposed model achieves high prediction performance on all of the classification tasks and regression tasks.