TranGRU: focusing on both the local and global information of molecules for molecular property prediction

Jing Jiang; Ruisheng Zhang; Jun Ma; Yunwu Liu; Enjie Yang; Shikang Du; Zhili Zhao; Yongna Yuan

doi:10.1007/s10489-022-04280-y

TranGRU: focusing on both the local and global information of molecules for molecular property prediction

Appl Intell (Dordr). 2023;53(12):15246-15260. doi: 10.1007/s10489-022-04280-y. Epub 2022 Nov 14.

Authors

Jing Jiang^{1

2}, Ruisheng Zhang¹, Jun Ma¹, Yunwu Liu¹, Enjie Yang¹, Shikang Du¹, Zhili Zhao¹, Yongna Yuan¹

Affiliations

¹ School of Information Science and Engineering, Lanzhou University, Tianshui Road, Lanzhou, 730000 Gansu China.
² Key Laboratory of China's Ethnic Languages and Information Technology of Ministry of Education, Northwest Minzu University, Baiyin Road, Lanzhou, 730030 Gansu China.

Abstract

Molecular property prediction is an essential but challenging task in drug discovery. The recurrent neural network (RNN) and Transformer are the mainstream methods for sequence modeling, and both have been successfully applied independently for molecular property prediction. As the local information and global information of molecules are very important for molecular properties, we aim to integrate the bi-directional gated recurrent unit (BiGRU) into the original Transformer encoder, together with self-attention to better capture local and global molecular information simultaneously. To this end, we propose the TranGRU approach, which encodes the local and global information of molecules by using the BiGRU and self-attention, respectively. Then, we use a gate mechanism to reasonably fuse the two molecular representations. In this way, we enhance the ability of the proposed model to encode both local and global molecular information. Compared to the baselines and state-of-the-art methods when treating each task as a single-task classification on Tox21, the proposed approach outperforms the baselines on 9 out of 12 tasks and state-of-the-art methods on 5 out of 12 tasks. TranGRU also obtains the best ROC-AUC scores on BBBP, FDA, LogP, and Tox21 (multitask classification) and has a comparable performance on ToxCast, BACE, and ecoli. On the whole, TranGRU achieves better performance for molecular property prediction. The source code is available in GitHub: https://github.com/Jiangjing0122/TranGRU.

Keywords: Fusion model; Global information; Local information; Molecular property prediction.

© The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature 2022. Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.