Graph Neural Networks for Drug–Target Interaction Prediction with Structure–Sequence Co-Embedding
International Journal of Computational and Biological Sciences · 31.12.2025 · 2 (02) · 279-286
DOI: 10.66238/ijcbs33 ↗Kurz gefasst
Fachartikel in der Zeitschrift International Journal of Computational and Biological Sciences, online erschienen am 31.12.2025. Verfasst von Tao Lin. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-ND 4.0).
Abstract (Originalsprache)
The identification of interactions between drug candidates and target proteins is a pivotal step in the drug discovery pipeline, traditionally characterized by high costs and substantial attrition rates. While experimental high-throughput screening remains the gold standard, its prohibitory expense has catalyzed the development of computational approaches. This paper introduces a novel deep learning framework that leverages Graph Neural Networks (GNNs) for molecular graph representation and Convolutional Neural Networks (CNNs) for protein sequence encoding, integrated via a unique structure-sequence co-embedding mechanism. Unlike conventional methods that rely on simplified SMILES strings or rigid structure docking, our approach captures the topological complexity of small molecules and the local residue patterns of protein targets simultaneously. We propose a cross-modal attention layer that fuses these distinct data modalities to predict binding affinities with high precision. Extensive experiments on benchmark datasets, including Davis and KIBA, demonstrate that our model outperforms state-of-the-art baselines in terms of Concordance Index (CI) and Mean Squared Error (MSE). The results underscore the efficacy of combining structural graph interactions with sequential biological data to mitigate the cold-start problem in pharmacology.
Zitieren
APA
Lin, T. (2025). Graph Neural Networks for Drug–Target Interaction Prediction with Structure–Sequence Co-Embedding. International Journal of Computational and Biological Sciences, 2(02), 279-286. https://doi.org/10.66238/ijcbs33
Vancouver
Lin T. Graph Neural Networks for Drug–Target Interaction Prediction with Structure–Sequence Co-Embedding. International Journal of Computational and Biological Sciences. 2025;2(02):279-286. doi:10.66238/ijcbs33
BibTeX
@article{Lin2025,
author = {Lin, Tao},
title = {Graph Neural Networks for Drug–Target Interaction Prediction with Structure–Sequence Co-Embedding},
journal = {International Journal of Computational and Biological Sciences},
year = {2025},
volume = {2},
number = {02},
pages = {279--286},
doi = {10.66238/ijcbs33}
}
EUVIMED