{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,30]],"date-time":"2026-09-30T04:56:33Z","timestamp":1790744193164,"version":"4.1.0"},"reference-count":70,"publisher":"MDPI AG","issue":"19","license":[{"start":{"date-parts":[[2026,9,27]],"date-time":"2026-09-27T00:00:00Z","timestamp":1790467200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Molecules"],"abstract":"<jats:p>Accurate molecular property prediction underpins progress in drug discovery, medicinal chemistry, and molecular design and depends critically on the quality of the learned molecular representations. While Graph Neural Networks (GNNs) and Graph Transformers have advanced this field considerably, most existing approaches emphasize a single structural perspective and struggle to jointly capture local connectivity, higher-order substructures, explicit topology, and long-range dependencies in a single learning process. This work introduces Topology-Guided Multi-Level Graph Learning (TMGL), a unified framework that integrates topology-enhanced node encoding, motif-guided representation learning, a Multi-Scale Graph Isomorphism Network, topology-aware graph transformer attention, adaptive multi-scale feature fusion, and cross-level contrastive learning into a single end-to-end architecture. By coupling topology preservation and motif consistency objectives with hierarchical contrastive alignment across node-, motif-, and graph-level embeddings, TMGL enables these complementary structural views to interact directly rather than being combined post hoc. The framework was evaluated on seven MoleculeNet benchmark datasets spanning binary classification, multi-label classification, and regression tasks. TMGL achieved Receiver Operating Characteristic Area Under the Curve (ROC-AUC) scores of 0.937, 0.960, 0.962, and 0.723 on BACE, BBBP, ClinTox, and SIDER, respectively, and RMSE values of 0.611, 1.293, and 0.436 on ESOL, FreeSolv, and Lipophilicity, outperforming a broad set of state-of-the-art baselines on most classification benchmarks and on Lipophilicity, while remaining competitive on ESOL and FreeSolv. Ablation experiments confirmed that each architectural component contributes meaningfully to overall performance, and embedding visualizations further illustrated the discriminative, class-consistent structure of the learned representation space. These results demonstrate the value of jointly modeling complementary structural perspectives for molecular graph learning and highlight the potential of the TMGL framework for applications in computational chemistry and drug discovery.<\/jats:p>","DOI":"10.3390\/molecules31193436","type":"journal-article","created":{"date-parts":[[2026,9,28]],"date-time":"2026-09-28T11:35:59Z","timestamp":1790595359000},"page":"3436","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Topology-Guided Multi-Level Graph Learning: A Unified Framework for Molecular Property Prediction"],"prefix":"10.3390","volume":"31","author":[{"given":"Hasnain","family":"Ali","sequence":"first","affiliation":[{"name":"Abdus Salam School of Mathematical Sciences, Government College University, Lahore 54600, Pakistan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-5675-5322","authenticated-orcid":false,"given":"Momina","family":"Arshad","sequence":"additional","affiliation":[{"name":"Abdus Salam School of Mathematical Sciences, Government College University, Lahore 54600, Pakistan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Malik Ahsin","family":"Iqbal","sequence":"additional","affiliation":[{"name":"Abdus Salam School of Mathematical Sciences, Government College University, Lahore 54600, Pakistan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Motasem S.","family":"Alsawadi","sequence":"additional","affiliation":[{"name":"Institute of Next Generation Connectivity, King Abdulaziz City for Science and Technology (KACST), Riyadh 12354, Saudi Arabia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Fahad","family":"Alghannam","sequence":"additional","affiliation":[{"name":"Microelectronics and Semiconductors Institute, King Abdulaziz City for Science and Technology (KACST), Riyadh 12354, Saudi Arabia"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2026,9,27]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"106207","DOI":"10.1016\/j.neunet.2024.106207","article-title":"A comprehensive survey on deep graph representation learning","volume":"173","author":"Ju","year":"2024","journal-title":"Neural Netw."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"34","DOI":"10.1038\/s42004-023-00825-5","article-title":"Hierarchical molecular graph self-supervised learning for property prediction","volume":"6","author":"Zang","year":"2023","journal-title":"Commun. Chem."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"bbab430","DOI":"10.1093\/bib\/bbab430","article-title":"Artificial intelligence in drug discovery: Applications and techniques","volume":"23","author":"Deng","year":"2022","journal-title":"Brief. Bioinform."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"3370","DOI":"10.1021\/acs.jcim.9b00237","article-title":"Analyzing learned molecular representations for property prediction","volume":"59","author":"Yang","year":"2019","journal-title":"J. Chem. Inf. Model."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"21830","DOI":"10.1021\/acs.est.5c04614","article-title":"Multiscale-Information-Embedded Universal Toxicity Prediction Framework","volume":"59","author":"Wu","year":"2025","journal-title":"Environ. Sci. Technol."},{"key":"ref_6","doi-asserted-by":"crossref","unstructured":"Gangwal, A., Ansari, A., Ahmad, I., Azad, A.K., Kumarasamy, V., Subramaniyan, V., and Wong, L.S. (2024). Generative artificial intelligence in drug discovery: Basic framework, recent advances, challenges, and opportunities. Front. Pharmacol., 15.","DOI":"10.3389\/fphar.2024.1331062"},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"93","DOI":"10.1186\/s13321-021-00570-8","article-title":"Chemical toxicity prediction based on semi-supervised learning and graph convolutional neural network","volume":"13","author":"Chen","year":"2021","journal-title":"J. Cheminform."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"15","DOI":"10.1186\/s13321-020-0414-z","article-title":"A self-attention based message passing neural network for predicting molecular lipophilicity and aqueous solubility","volume":"12","author":"Tang","year":"2020","journal-title":"J. Cheminform."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"5975","DOI":"10.1007\/s10462-022-10306-1","article-title":"Deep learning in drug discovery: An integrative review and future challenges","volume":"56","author":"Askr","year":"2023","journal-title":"Artif. Intell. Rev."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"57","DOI":"10.1016\/j.aiopen.2021.01.001","article-title":"Graph neural networks: A review of methods and applications","volume":"1","author":"Zhou","year":"2020","journal-title":"AI Open"},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"10001","DOI":"10.1021\/acs.chemrev.5c00461","article-title":"Graph neural networks in modern AI-aided drug discovery","volume":"125","author":"Zhang","year":"2025","journal-title":"Chem. Rev."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1186\/s40649-019-0069-y","article-title":"Graph convolutional networks: A comprehensive review","volume":"6","author":"Zhang","year":"2019","journal-title":"Comput. Soc. Netw."},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3433000","article-title":"Network representation learning: From preprocessing, feature extraction to node embedding","volume":"55","author":"Zhou","year":"2022","journal-title":"ACM Comput. Surv. (CSUR)"},{"key":"ref_14","unstructured":"Alon, U., and Yahav, E. (2020). On the bottleneck of graph neural networks and its practical implications. arXiv."},{"key":"ref_15","unstructured":"Cai, D., and Lam, W. (2020, January 7\u201312). Graph transformer for graph-to-sequence learning. Proceedings of the AAAI Conference on Artificial Intelligence, New York, NY, USA."},{"key":"ref_16","doi-asserted-by":"crossref","unstructured":"Zhu, Q., Zhang, L., Xu, Q., Liu, K., Long, C., and Wang, X. (2025, January 10\u201314). Hhgt: Hierarchical heterogeneous graph transformer for heterogeneous graph representation learning. Proceedings of the Eighteenth ACM International Conference on Web Search and Data Mining, Hannover, Germany.","DOI":"10.1145\/3701551.3703511"},{"key":"ref_17","first-page":"12559","article-title":"Self-supervised graph transformer on large-scale molecular data","volume":"33","author":"Rong","year":"2020","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref_18","doi-asserted-by":"crossref","unstructured":"Wang, Y., Chen, S., Chen, G., Shurberg, E., Liu, H., and Hong, P. (2023). Motif-based graph representation learning with application to chemical molecules. Informatics, 10.","DOI":"10.3390\/informatics10010008"},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"108506","DOI":"10.1016\/j.jmgm.2023.108506","article-title":"MD-GNN: A mechanism-data-driven graph neural network for molecular properties prediction and new material discovery","volume":"123","author":"Chen","year":"2023","journal-title":"J. Mol. Graph. Model."},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"bbad305","DOI":"10.1093\/bib\/bbad305","article-title":"HimGNN: A novel hierarchical molecular graph representation learning framework for property prediction","volume":"24","author":"Han","year":"2023","journal-title":"Brief. Bioinform."},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"10561","DOI":"10.1021\/acs.jcim.5c01339","article-title":"Molecular Property Prediction Based on Improved Graph Transformer Network and Multitask Joint Learning Strategy","volume":"65","author":"Zhao","year":"2025","journal-title":"J. Chem. Inf. Model."},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"85","DOI":"10.1186\/s13321-024-00880-7","article-title":"Enhancing molecular property prediction with auxiliary learning and task-specific adaptation","volume":"16","author":"Dey","year":"2024","journal-title":"J. Cheminform."},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"531","DOI":"10.1561\/2200000076","article-title":"Graph kernels: State-of-the-art and future challenges","volume":"13","author":"Borgwardt","year":"2020","journal-title":"Found. Trends Mach. Learn."},{"key":"ref_24","unstructured":"Borgwardt, K.M., and Kriegel, H.P. (2005, January 28\u201330). Shortest-path kernels on graphs. Proceedings of the Fifth IEEE International Conference on Data Mining (ICDM\u201905), Houston, TX, USA."},{"key":"ref_25","first-page":"2539","article-title":"Weisfeiler-lehman graph kernels","volume":"12","author":"Shervashidze","year":"2011","journal-title":"J. Mach. Learn. Res."},{"key":"ref_26","unstructured":"Kipf, T.N., and Welling, M. (2016). Semi-supervised classification with graph convolutional networks. arXiv."},{"key":"ref_27","first-page":"1025","article-title":"Inductive representation learning on large graphs","volume":"30","author":"Hamilton","year":"2017","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref_28","unstructured":"Veli\u010dkovi\u0107, P., Cucurull, G., Casanova, A., Romero, A., Lio, P., and Bengio, Y. (May, January 30). Graph attention networks. Proceedings of the International Conference on Learning Representations, Vancouver, BC, Canada."},{"key":"ref_29","unstructured":"Xu, K., Hu, W., Leskovec, J., and Jegelka, S. (2018). How powerful are graph neural networks?. arXiv."},{"key":"ref_30","first-page":"28877","article-title":"Do transformers really perform badly for graph representation?","volume":"34","author":"Ying","year":"2021","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref_31","first-page":"14501","article-title":"Recipe for a general, powerful, scalable graph transformer","volume":"35","author":"Galkin","year":"2022","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"824","DOI":"10.1126\/science.298.5594.824","article-title":"Network motifs: Simple building blocks of complex networks","volume":"298","author":"Milo","year":"2002","journal-title":"Science"},{"key":"ref_33","unstructured":"Jin, W., Barzilay, R., and Jaakkola, T. (2020, January 13\u201318). Hierarchical generation of molecular graphs using structural motifs. Proceedings of the International Conference on Machine Learning, PMLR, Virtual."},{"key":"ref_34","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3787204","article-title":"Atom-motif contrastive transformer for molecular property prediction","volume":"17","author":"Yu","year":"2026","journal-title":"ACM Trans. Intell. Syst. Technol."},{"key":"ref_35","doi-asserted-by":"crossref","first-page":"657","DOI":"10.1109\/TPAMI.2022.3154319","article-title":"Improving graph neural network expressivity via subgraph isomorphism counting","volume":"45","author":"Bouritsas","year":"2022","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref_36","doi-asserted-by":"crossref","first-page":"107246","DOI":"10.1016\/j.compbiomed.2023.107246","article-title":"GCNfold: A novel lightweight model with valid extractors for RNA secondary structure prediction","volume":"164","author":"Yang","year":"2023","journal-title":"Comput. Biol. Med."},{"key":"ref_37","unstructured":"Zhang, S., Liu, Y., and Xie, L. (2022). Physics-aware graph neural network for accurate RNA 3D structure prediction. arXiv."},{"key":"ref_38","doi-asserted-by":"crossref","unstructured":"Liu, Z., Luo, F., and Du, B. (2021, January 2\u20139). RNA secondary structure representation network for RNA-proteins binding prediction. Proceedings of the AAAI Conference on Artificial Intelligence, Virtual Event.","DOI":"10.1609\/aaai.v35i1.16112"},{"key":"ref_39","doi-asserted-by":"crossref","first-page":"btaf515","DOI":"10.1093\/bioinformatics\/btaf515","article-title":"Graph neural network and diffusion model for modeling RNA interatomic interactions","volume":"41","author":"Justyna","year":"2025","journal-title":"Bioinformatics"},{"key":"ref_40","first-page":"5812","article-title":"Graph contrastive learning with augmentations","volume":"33","author":"You","year":"2020","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref_41","unstructured":"Veli\u010dkovi\u0107, P., Fedus, W., Hamilton, W.L., Li\u00f2, P., Bengio, Y., and Hjelm, R.D. (2018). Deep graph infomax. arXiv."},{"key":"ref_42","doi-asserted-by":"crossref","unstructured":"Qiu, J., Chen, Q., Dong, Y., Zhang, J., Yang, H., Ding, M., Wang, K., and Tang, J. (2020, January 6\u201310). Gcc: Graph contrastive coding for graph neural network pre-training. Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, Virtual Event.","DOI":"10.1145\/3394486.3403168"},{"key":"ref_43","unstructured":"Sun, F.Y., Hoffmann, J., Verma, V., and Tang, J. (2019). Infograph: Unsupervised and semi-supervised graph-level representation learning via mutual information maximization. arXiv."},{"key":"ref_44","unstructured":"Hu, W., Liu, B., Gomes, J., Zitnik, M., Liang, P., Pande, V., and Leskovec, J. (2019). Strategies for pre-training graph neural networks. arXiv."},{"key":"ref_45","unstructured":"Hassani, K., and Khasahmadi, A.H. (2020, January 13\u201318). Contrastive multi-view representation learning on graphs. Proceedings of the International Conference on Machine Learning, PMLR, Virtual."},{"key":"ref_46","first-page":"30414","article-title":"Infogcl: Information-aware graph contrastive learning","volume":"34","author":"Xu","year":"2021","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref_47","doi-asserted-by":"crossref","first-page":"btae574","DOI":"10.1093\/bioinformatics\/btae574","article-title":"Chain-aware graph neural networks for molecular property prediction","volume":"40","author":"Wang","year":"2024","journal-title":"Bioinformatics"},{"key":"ref_48","unstructured":"Chen, Y., Li, Z., Wan, Z., Yu, H., and Wei, X. (2023). CTAGE: Curvature-Based Topology-Aware Graph Embedding for Learning Molecular Representations. arXiv."},{"key":"ref_49","unstructured":"Korkmaz, A.S., Coskunuzer, S., and Uddin, M.J. (2025). Cross-View Topology-Aware Graph Representation Learning. arXiv."},{"key":"ref_50","first-page":"992","article-title":"Schnet: A continuous-filter convolutional neural network for modeling quantum interactions","volume":"30","author":"Kindermans","year":"2017","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref_51","doi-asserted-by":"crossref","first-page":"513","DOI":"10.1039\/C7SC02664A","article-title":"MoleculeNet: A benchmark for molecular machine learning","volume":"9","author":"Wu","year":"2018","journal-title":"Chem. Sci."},{"key":"ref_52","doi-asserted-by":"crossref","unstructured":"Hou, Z., Liu, X., Cen, Y., Dong, Y., Yang, H., Wang, C., and Tang, J. (2022, January 14\u201318). Graphmae: Self-supervised masked graph autoencoders. Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, Washington, DC, USA.","DOI":"10.1145\/3534678.3539321"},{"key":"ref_53","doi-asserted-by":"crossref","first-page":"542","DOI":"10.1038\/s42256-023-00654-0","article-title":"Knowledge graph-enhanced molecular contrastive learning with functional prompt","volume":"5","author":"Fang","year":"2023","journal-title":"Nat. Mach. Intell."},{"key":"ref_54","first-page":"24","article-title":"H2o automl: Scalable automatic machine learning","volume":"2020","author":"LeDell","year":"2020","journal-title":"AutoML Workshop ICML"},{"key":"ref_55","unstructured":"Wu, F., Radev, D., and Li, S.Z. (2021). Molformer: Motif-based transformer on 3d heterogeneous molecular graphs. arXiv."},{"key":"ref_56","first-page":"15870","article-title":"Motif-based graph self-supervised learning for molecular property prediction","volume":"34","author":"Zhang","year":"2021","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref_57","doi-asserted-by":"crossref","first-page":"bbaf629","DOI":"10.1093\/bib\/bbaf629","article-title":"ProtoMol: Enhancing molecular property prediction via prototype-guided multimodal learning","volume":"26","author":"Wang","year":"2025","journal-title":"Brief. Bioinform."},{"key":"ref_58","doi-asserted-by":"crossref","first-page":"286","DOI":"10.1038\/s42004-025-01683-z","article-title":"MolGraph-xLSTM as a graph-based dual-level xLSTM framework for enhanced molecular representation and interpretability","volume":"8","author":"Sun","year":"2025","journal-title":"Commun. Chem."},{"key":"ref_59","unstructured":"Oord, A.v.d., Li, Y., and Vinyals, O. (2018). Representation learning with contrastive predictive coding. arXiv."},{"key":"ref_60","unstructured":"Snell, J., Swersky, K., and Zemel, R. (2017). Prototypical networks for few-shot learning. Adv. Neural Inf. Process. Syst., 30."},{"key":"ref_61","unstructured":"Lee, J., Lee, I., and Kang, J. (2019, January 9\u201315). Self-attention graph pooling. Proceedings of the International Conference on Machine Learning, PMLR, Long Beach, CA, USA."},{"key":"ref_62","unstructured":"Loshchilov, I., and Hutter, F. (2017). Decoupled weight decay regularization. arXiv."},{"key":"ref_63","first-page":"1929","article-title":"Dropout: A Simple Way to Prevent Neural Networks from Overfitting","volume":"15","author":"Srivastava","year":"2014","journal-title":"J. Mach. Learn. Res."},{"key":"ref_64","doi-asserted-by":"crossref","first-page":"1686","DOI":"10.1021\/ci300124c","article-title":"A Bayesian approach to in silico blood-brain barrier penetration modeling","volume":"52","author":"Martins","year":"2012","journal-title":"J. Chem. Inf. Model."},{"key":"ref_65","doi-asserted-by":"crossref","first-page":"1936","DOI":"10.1021\/acs.jcim.6b00290","article-title":"Computational modeling of \u03b2-secretase 1 (BACE-1) inhibitors using ligand based approaches","volume":"56","author":"Subramanian","year":"2016","journal-title":"J. Chem. Inf. Model."},{"key":"ref_66","doi-asserted-by":"crossref","first-page":"1294","DOI":"10.1016\/j.chembiol.2016.07.023","article-title":"A data-driven approach to predicting successes and failures of clinical trials","volume":"23","author":"Gayvert","year":"2016","journal-title":"Cell Chem. Biol."},{"key":"ref_67","doi-asserted-by":"crossref","first-page":"D1075","DOI":"10.1093\/nar\/gkv1075","article-title":"The SIDER database of drugs and side effects","volume":"44","author":"Kuhn","year":"2016","journal-title":"Nucleic Acids Res."},{"key":"ref_68","doi-asserted-by":"crossref","first-page":"1000","DOI":"10.1021\/ci034243x","article-title":"ESOL: Estimating aqueous solubility directly from molecular structure","volume":"44","author":"Delaney","year":"2004","journal-title":"J. Chem. Inf. Comput. Sci."},{"key":"ref_69","doi-asserted-by":"crossref","first-page":"711","DOI":"10.1007\/s10822-014-9747-x","article-title":"FreeSolv: A database of experimental and calculated hydration free energies, with input files","volume":"28","author":"Mobley","year":"2014","journal-title":"J. Comput. Aided Mol. Des."},{"key":"ref_70","doi-asserted-by":"crossref","first-page":"D1100","DOI":"10.1093\/nar\/gkr777","article-title":"ChEMBL: A large-scale bioactivity database for drug discovery","volume":"40","author":"Gaulton","year":"2012","journal-title":"Nucleic Acids Res."}],"container-title":["Molecules"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1420-3049\/31\/19\/3436\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,30]],"date-time":"2026-09-30T04:15:05Z","timestamp":1790741705000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1420-3049\/31\/19\/3436"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,9,27]]},"references-count":70,"journal-issue":{"issue":"19","published-online":{"date-parts":[[2026,10]]}},"alternative-id":["molecules31193436"],"URL":"https:\/\/doi.org\/10.3390\/molecules31193436","relation":{},"ISSN":["1420-3049"],"issn-type":[{"value":"1420-3049","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,9,27]]}}}