Molecular property prediction provides an important computational basis for compound screening and drug development by estimating physicochemical characteristics and biological activities from molecular structures. Although deep learning has improved molecular modeling, existing methods often describe molecules through a limited structural view or combine multiple views without sufficiently exploiting their complementary relationships. In addition, graph-based approaches commonly concentrate on local atomic connectivity, making it difficult to represent chemically meaningful structural units that may strongly influence molecular properties. This paper develops MG-CMIF, a multi-granularity cross-modal framework for molecular property prediction. The proposed model describes each molecule from symbolic, topological, and spatial perspectives and learns an integrated representation through three key designs. First, hierarchical graph modeling combines detailed atomic interactions with substructure-level chemical patterns to enrich topology-oriented features. Second, interaction across molecular views enables information relevant to property prediction to be exchanged selectively rather than merged through shallow operations. Third, alignment-oriented training objectives encourage representations derived from the same molecule to preserve compatible chemical semantics during fusion. Experiments on multiple public benchmark datasets show that MG-CMIF achieves better prediction results than competitive methods in both classification and regression settings. Further ablation analyses confirm that hierarchical structural modeling and cross-view integration both contribute to the effectiveness of the proposed framework.
- Open Access
- Article
MG-CMIF: A Multi-Granularity Enhanced Cross-Modal Information Fusion Framework for Molecular Property Prediction
- Maoyuan Zang 1,2,
- Qun Liu 1,2,
- Rui Han 1,2,*,
- Xu Gong 3
Author Information
Received: 14 May 2026 | Revised: 17 Aug 2026 | Accepted: 31 Aug 2026 | Published: 07 Sep 2026
Abstract
Keywords
molecular property prediction | graph neural network | multi-modal learning | multi-granularity representation | self-supervised learning
References
- 1.
DiMasi, J.A.; Grabowski, H.G.; Hansen, R.W. Innovation in the Pharmaceutical Industry: New Estimates of R&D Costs. J. Health Econ. 2016, 47, 20–33.
- 2.
Liu, M.; Yang, Y.; Liu, Q.; et al. A Knowledge-Driven Self-Supervised Approach for Molecular Generation. IEEE/ACM Trans. Comput. Biol. Bioinform. 2024, 21, 1579–1590.
- 3.
Ocaña, A.; Pandiella, A.; Privat, C.; et al. Integrating Artificial Intelligence in Drug Discovery and Early Drug Development: A Transformative Approach. Biomark. Res. 2025, 13, 45.
- 4.
Liao, Q.; Zhang, Y.; Chu, Y.; et al. Application of Artificial Intelligence in Drug-Target Interactions Prediction: A Review. npj Biomed. Innov. 2025, 2, 1.
- 5.
Xia, Y.; Xiong, A.; Zhang, Z.; et al. A Comprehensive Review of Deep Learning-Based Approaches for Drug-Drug Interaction Prediction. Brief. Funct. Genomics 2025, 24, elae052.
- 6.
Gong, X.; Liu, Q.; Han, R.; et al. MIFS: An Adaptive Multipath Information Fused Self-Supervised Framework for Drug Discovery. Neural Netw. 2025, 184, 107088.
- 7.
Shao, Y.; Li, Y.; Wu, B. A Directional Attention Fusion and Multi-Head Spatial-Channel Attention Network for Facial Expression Recognition. J. Mach. Learn. Inf. Secur. 2025, 1, 7.
- 8.
Ye, W.; Li, J.; Cai, X. MfGNN: Multi-Scale Feature-Attentive Graph Neural Networks for Molecular Property Prediction. J. Comput. Chem. 2025, 46, e70011.
- 9.
Peng, J.; Wang, W.; He, Y.; et al. An Enhanced YOLOv8 Algorithm with C2f Parnet for Vehicle and Pedestrian Detection. J. Mach. Learn. Inf. Secur. 2026, 2, 17.
- 10.
Li, L.; Zhang, Y.; Wang, G.; et al. Kolmogorov-Arnold Graph Neural Networks for Molecular Property Prediction. Nat. Mach. Intell. 2025, 7, 1346–1354.
- 11.
Weininger, D. SMILES, a Chemical Language and Information System. 1. Introduction to Methodology and Encoding Rules. J. Chem. Inf. Comput. Sci. 1988, 28, 31–36.
- 12.
Wang, Z.; Jiang, T.; Wang, J.; et al. Multi-Modal Representation Learning for Molecular Property Prediction: Sequence, Graph, Geometry. arXiv 2024, arXiv:2401.03369.
- 13.
Zhang, H.; Wu, J.; Liu, S.; et al. A Pre-Trained Multi-Representation Fusion Network for Molecular Property Prediction. Inf. Fusion 2024, 103, 102092.
- 14.
Zang, M.; Gong, X.; Han, R.; et al. CMIF: A Cross-Modal Information Fusion Approach for Molecular Property Prediction. In Proceedings of the International Joint Conference on Rough Sets, Chongqing, China, 11–13 May 2025; pp. 228–241.
- 15.
Zheng, S.; Yan, X.; Yang, Y.; et al. Identifying Structure-Property Relationships through SMILES Syntax Analysis with Self-Attention Mechanism. J. Chem. Inf. Model. 2019, 59, 914–923.
- 16.
Honda, S.; Shi, S.; Ueda, H.R. SMILES Transformer: Pre-Trained Molecular Fingerprint for Low Data Drug Discovery. arXiv 2019, arXiv:1911.04738.
- 17.
Wang, S.; Guo, Y.; Wang, Y.; et al. SMILES-BERT: Large Scale Unsupervised Pre-Training for Molecular Property Prediction. In Proceedings of the 10th ACM International Conference on Bioinformatics, Computational Biology and Health Informatics, Niagara Falls, NY, USA, 7–10 September 2019; pp. 429–436.
- 18.
Li, Z.; Jiang, M.; Wang, S.; et al. Deep Learning Methods for Molecular Representation and Property Prediction. Drug Discov. Today 2022, 27, 103373.
- 19.
Song, Y.; Zheng, S.; Niu, Z.; et al. Communicative Representation Learning on Attributed Molecular Graphs. In Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence, Yokohama, Japan, 7–15 January 2021; pp. 2831–2838.
- 20.
Ma, H.; Bian, Y.; Rong, Y.; et al. Cross-Dependent Graph Neural Networks for Molecular Property Prediction. Bioinformatics 2022, 38, 2003–2009.
- 21.
Fang, X.; Liu, L.; Lei, J.; et al. Geometry-Enhanced Molecular Representation Learning for Property Prediction. Nat. Mach. Intell. 2022, 4, 127–134.
- 22.
Ren, G.P.; Wu, K.J.; He, Y. Enhancing Molecular Representations via Graph Transformation Layers. J. Chem. Inf. Model. 2023, 63, 2679–2688.
- 23.
Son, Y.H.; Shin, D.H.; Kam, T.E. FTMMR: Fusion Transformer for Integrating Multiple Molecular Representations. IEEE J. Biomed. Health Inform. 2024, 28, 4361–4372.
- 24.
Wu, T.; Tang, Y.; Sun, Q.; et al. Molecular Joint Representation Learning via Multi-Modal Information of SMILES and Graphs. IEEE/ACM Trans. Comput. Biol. Bioinform. 2023, 20, 3044–3055.
- 25.
Guo, Z.; Yu, W.; Zhang, C.; et al. GraSeq: Graph and Sequence Fusion Learning for Molecular Property Prediction. In Proceedings of the 29th ACM International Conference on Information & Knowledge Management, Virtual Event, Ireland, 19–23 October 2020; pp. 435–443.
- 26.
Liu, S.; Wang, H.; Liu, W.; et al. Pre-Training Molecular Graph Representation with 3D Geometry. In Proceedings of the Tenth International Conference on Learning Representations, Virtual Event, 25–29 April 2022.
- 27.
Zhu, J.; Xia, Y.; Wu, L.; et al. Unified 2D and 3D Pre-Training of Molecular Representations. In Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, Washington, DC, USA, 14–18 August 2022; pp. 2626–2636.
- 28.
Tang, X.; Tran, A.; Tan, J.; et al. MolLM: A Unified Language Model for Integrating Biomedical Text with 2D and 3D Molecular Representations. Bioinformatics 2024, 40 (Suppl. 1), i357–i368.
- 29.
Li, J.; Zhang, Z.; Lei, Z.; et al. MoLA: Molecular Multimodal Layerwise Adaptive Network for Molecular Property Prediction. Knowl. Based Syst. 2026, 338, 115563.
- 30.
Sun, S.; Wang, P.; He, Y.; et al. Multimodal Cross-Attention Molecular Property Prediction for Text, Sequence, Graph, and Geometry. ACS Omega 2025, 10, 56225–56239.
- 31.
Zhang, Z.; Liu, Q.; Wang, H.; et al. Motif-Based Graph Self-Supervised Learning for Molecular Property Prediction. In Proceedings of the Advances in Neural Information Processing Systems (NeurIPS 2021), Virtual Event, 6–14 December 2021; pp. 15870–15882.
- 32.
Zang, X.; Zhao, X.; Tang, B. Hierarchical Molecular Graph Self-Supervised Learning for Property Prediction. Commun. Chem. 2023, 6, 34.
- 33.
Jiang, J.; Zhang, R.; Zhao, Z.; et al. MultiGran-SMILES: Multi-Granularity SMILES Learning for Molecular Property Prediction. Bioinformatics 2022, 38, 4573–4580.
- 34.
Zhang, R.; Wang, X.; Liu, K.; et al. M2Mol: Multi-View Multi-Granularity Molecular Representation Learning for Property Prediction. In Proceedings of the 29th International Conference on Database Systems for Advanced Applications, Gifu, Japan, 2–5 July 2024; pp. 264–274.
- 35.
Cho, K.; van Merriënboer, B.; Gulcehre, C.; et al. Learning Phrase Representations Using RNN Encoder–Decoder for Statistical Machine Translation. In Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing, Doha, Qatar, 25–29 October 2014; pp. 1724–1734.
- 36.
Lee, J.; Lee, I.; Kang, J. Self-Attention Graph Pooling. In Proceedings of the 36th International Conference on Machine Learning, Long Beach, CA, USA, 9–15 June 2019; pp. 3734–3743.
- 37.
Brody, S.; Alon, U.; Yahav, E. How Attentive Are Graph Attention Networks? In Proceedings of the Tenth International Conference on Learning Representations, Virtual Event, 25–29 April 2022.
- 38.
Wu, Z.; Ramsundar, B.; Feinberg, E.N.; et al. MoleculeNet: A Benchmark for Molecular Machine Learning. Chem. Sci. 2018, 9, 513–530.
- 39.
Xu, Z.; Wang, S.; Zhu, F.; et al. Seq2seq Fingerprint: An Unsupervised Deep Molecular Embedding for Drug Discovery. In Proceedings of the 8th ACM International Conference on Bioinformatics, Computational Biology and Health Informatics, Boston, MA, USA, 20–23 August 2017; pp. 285–294.
- 40.
Stärk, H.; Beaini, D.; Corso, G.; et al. 3D Infomax Improves GNNs for Molecular Property Prediction. In Proceedings of the 39th International Conference on Machine Learning, Baltimore, MD, USA, 17–23 July 2022; pp. 20479–20502.
- 41.
van der Maaten, L.; Hinton, G. Visualizing Data Using t-SNE. J. Mach. Learn. Res. 2008, 9, 2579–2605.
- 42.
Heberle, H.; Zhao, L.; Schmidt, S.; et al. XSMILES: Interactive Visualization for Molecules, SMILES and XAI Attribution Scores. J. Cheminform. 2023, 15, 2.
This work is licensed under a Creative Commons Attribution 4.0 International License.
Suite 4002 Level 4, 447 Collins Street, Melbourne, Victoria 3000, Australia
General Inquiries: info@sciltp.com