Next Article in Journal
Dynamic m6A Modification Landscape During the Egg Laying Process of Chickens
Previous Article in Journal
Effective Dose Reduction of Emamectin Benzoate Through Inhibition of Bx-SDR3 in Pine Wood Nematode Management
Previous Article in Special Issue
Development of a Robust Read-Across Model for the Prediction of Biological Potency of Novel Peroxisome Proliferator-Activated Receptor Delta Agonists
 
 
Font Type:
Arial Georgia Verdana
Font Size:
Aa Aa Aa
Line Spacing:
Column Width:
Background:
Article

Graph and Multi-Level Sequence Fusion Learning for Predicting the Molecular Activity of BACE-1 Inhibitors

by
Shaohua Zheng
1,
Changwang Zhang
1,
Youjia Chen
1 and
Meimei Chen
2,*
1
College of Physics and Information Engineering, Fuzhou University, Fuzhou 350108, China
2
College of Traditional Chinese Medicine, Fujian University of Traditional Chinese Medicine, Fuzhou 350122, China
*
Author to whom correspondence should be addressed.
Int. J. Mol. Sci. 2025, 26(4), 1681; https://doi.org/10.3390/ijms26041681
Submission received: 7 January 2025 / Revised: 12 February 2025 / Accepted: 14 February 2025 / Published: 16 February 2025
(This article belongs to the Special Issue Cheminformatics in Drug Discovery and Material Design)

Abstract

The development of BACE-1 (β-site amyloid precursor protein cleaving enzyme 1) inhibitors is a crucial focus in exploring early treatments for Alzheimer’s disease (AD). Recently, graph neural networks (GNNs) have demonstrated significant advantages in predicting molecular activity. However, their reliance on graph structures alone often neglects explicit sequence-level semantic information. To address this limitation, we proposed a Graph and multi-level Sequence Fusion Learning (GSFL) model for predicting the molecular activity of BACE-1 inhibitors. Firstly, molecular graph structures generated from SMILES strings were encoded using GNNs with an atomic-level characteristic attention mechanism. Next, substrings at functional group, ion level, and atomic level substrings were extracted from SMILES strings and encoded using a BiLSTM–Transformer framework equipped with a hierarchical attention mechanism. Finally, these features were fused to predict the activity of BACE-1 inhibitors. A dataset of 1548 compounds with BACE-1 activity measurements was curated from the ChEMBL database. In the classification experiment, the model achieved an accuracy of 0.941 on the training set and 0.877 on the test set. For the test set, it delivered a sensitivity of 0.852, a specificity of 0.894, a MCC of 0.744, an F1-score of 0.872, a PRC of 0.869, and an AUC of 0.915. Compared to traditional computer-aided drug design methods and other machine learning algorithms, the proposed model can effectively improve the accuracy of the molecular activity prediction of BACE-1 inhibitors and has a potential application value.
Keywords: Alzheimer’s disease; BACE-1 inhibitor; molecular activity prediction; graph neural network; fusion learning Alzheimer’s disease; BACE-1 inhibitor; molecular activity prediction; graph neural network; fusion learning

Share and Cite

MDPI and ACS Style

Zheng, S.; Zhang, C.; Chen, Y.; Chen, M. Graph and Multi-Level Sequence Fusion Learning for Predicting the Molecular Activity of BACE-1 Inhibitors. Int. J. Mol. Sci. 2025, 26, 1681. https://doi.org/10.3390/ijms26041681

AMA Style

Zheng S, Zhang C, Chen Y, Chen M. Graph and Multi-Level Sequence Fusion Learning for Predicting the Molecular Activity of BACE-1 Inhibitors. International Journal of Molecular Sciences. 2025; 26(4):1681. https://doi.org/10.3390/ijms26041681

Chicago/Turabian Style

Zheng, Shaohua, Changwang Zhang, Youjia Chen, and Meimei Chen. 2025. "Graph and Multi-Level Sequence Fusion Learning for Predicting the Molecular Activity of BACE-1 Inhibitors" International Journal of Molecular Sciences 26, no. 4: 1681. https://doi.org/10.3390/ijms26041681

APA Style

Zheng, S., Zhang, C., Chen, Y., & Chen, M. (2025). Graph and Multi-Level Sequence Fusion Learning for Predicting the Molecular Activity of BACE-1 Inhibitors. International Journal of Molecular Sciences, 26(4), 1681. https://doi.org/10.3390/ijms26041681

Note that from the first issue of 2016, this journal uses article numbers instead of page numbers. See further details here.

Article Metrics

Back to TopTop