MFECL-DTI: Multiscale Feature Extraction and Cross-Branch Contrastive Learning for Drug–Target Interaction Prediction
Main Article Content
Keywords
drug–target interaction prediction, multimodal learning, self-supervised contrastive learning, adaptive gated fusion, graph neural networks
Abstract
Accurate drug–target interaction prediction plays an important role in drug discovery and repositioning. However, existing methods often struggle to fully exploit the complementary information between molecular structures and sequence representations. To address this issue, we propose MFECL-DTI, a dual-branch prediction framework integrating graph-based structural encoding, multiscale sequence feature extraction, cross-branch contrastive learning, and adaptive gated fusion. Specifically, the graph branch employs residual graph convolutional networks to extract structural features from drug molecular graphs and protein contact graphs, while the sequence branch combines multiscale convolutional neural networks with a Transformer to capture local patterns and contextual dependencies. Furthermore, a bidirectional contrastive learning mechanism is introduced to align the representations of the same drug–target pair across different branches. An adaptive gating mechanism then dynamically integrates complementary features for interaction prediction. Experiments on BioSNAP, DrugBank, and C.elegans achieve AUROC values of 0.925, 0.915, and 0.994, respectively, with corresponding AUPRC values of 0.927, 0.913, and 0.994. Comparative and ablation experiments demonstrate the effectiveness of the proposed framework in improving DTI prediction performance.
References
- [1]Shi W, Yang H, Xie L, et al. A review of machine learning-based methods for predicting drug-target interactions. Health Information Science and Systems. 2024; 12: 30.
- [2]Yamanishi Y, Araki M, Gutteridge A, et al. Prediction of drug–target interaction networks from the integration of chemical and genomic spaces. Bioinformatics. 2008; 24(13): i232–i240.
- [3]Öztürk H, Özgür A, Ozkirimli E. DeepDTA: deep drug–target binding affinity prediction. Bioinformatics. 2018; 34(17): i821–i829.
- [4]Nguyen T, Le H, Quinn T P, et al. GraphDTA: predicting drug–target binding affinity with graph neural networks. Bioinformatics. 2021; 37(8): 1140–1147.
- [5]Huang K, Xiao C, Glass L M, et al. MolTrans: Molecular Interaction Transformer for drug–target interaction prediction. Bioinformatics. 2021; 37(6): 830–836.
- [6]Bai P, Miljković F, John B, et al. Interpretable bilinear attention network with domain adaptation improves drug–target prediction. Nature Machine Intelligence. 2023; 5: 126–136.
- [7]Kipf T N, Welling M. Semi-Supervised Classification with Graph Convolutional Networks. International Conference on Learning Representations, 2017.
- [8]Lin Z, Akin H, Rao R, et al. Evolutionary-scale prediction of atomic-level protein structure with a language model. Science. 2023; 379(6637): 1123–1130.
- [9]Luo Z, Wu W, Sun Q, et al. Accurate and transferable drug-target interaction prediction with DrugLAMP. Bioinformatics. 2024; 40(12): btae693.
- [10]Cao Z, Xie J, Xu J, et al. Cross-Modal Interaction-Aware Progressive Fusion Network for Drug-Target Interaction Prediction. Journal of Chemical Information and Modeling. 2025; 65(19): 10713–10726.
- [11]Peng J, Liu X, Zhou X, et al. DBCA-DTI: A dual-branch multimodal framework based on bidirectional adaptive gated cross-attention mechanism for drug-target interaction prediction. Knowledge-Based Systems. 2026; 338: 115463.
- [12]Yun G H, Park J H, Cho Y R. TriDTI: tri-modal representation learning with cross-modal alignment for drug-target interaction prediction. Briefings in Bioinformatics. 2026; 27(1): bbag034.
- [13]Vaswani A, Shazeer N, Parmar N, et al. Attention Is All You Need. Advances in Neural Information Processing Systems. 2017; 30.
- [14]Tian Z, Yu Y, Ni F, et al. Drug-target interaction prediction with collaborative contrastive learning and adaptive self-paced sampling strategy. BMC Biology. 2024; 22: 216.
- [15]Chen L, Tan X, Wang D, et al. TransformerCPI: improving compound-protein interaction prediction by sequence-based deep learning with self-attention mechanism and label reversal experiments. Bioinformatics. 2020; 36(16): 4406–4414.
- [16]Zhao Q, Zhao H, Zheng K, et al. HyperAttentionDTI: improving drug-protein interaction prediction by sequence-based deep learning with attention mechanism. Bioinformatics. 2022; 38(3): 655–662.
- [17]Bian J, Zhang X, Zhang X, et al. MCANet: shared-weight-based MultiheadCrossAttention network for drug-target interaction prediction. Briefings in Bioinformatics. 2023; 24(2): bbad082.
- [18]Peng L, Liu X, Yang L, et al. BINDTI: A Bi-Directional Intention Network for Drug-Target Interaction Identification Based on Attention Mechanisms. IEEE Journal of Biomedical and Health Informatics. 2025; 29(3): 1602–1612.
- [19]Peng L, Liu X, Chen M, et al. MGNDTI: A Drug-Target Interaction Prediction Framework Based on Multimodal Representation Learning and the Gating Mechanism. Journal of Chemical Information and Modeling. 2024; 64(16): 6684–6698.
- [20]Hua Y, Feng Z, Song X, et al. MMDG-DTI: Drug-target interaction prediction via multimodal feature fusion and domain generalization. Pattern Recognition. 2025; 157: 110887.
- [21]Wei Z, Zheng X, Li C, et al. DACMF-DTI: Dual attention embedded cross-modality fusion for drug-target interaction prediction. Knowledge-Based Systems. 2025; 326: 114063.
