{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,30]],"date-time":"2026-06-30T01:45:37Z","timestamp":1782783937231,"version":"3.54.5"},"reference-count":48,"publisher":"MDPI AG","issue":"13","license":[{"start":{"date-parts":[[2026,6,29]],"date-time":"2026-06-29T00:00:00Z","timestamp":1782691200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IJMS"],"abstract":"<jats:p>Drug\u2013target affinity (DTA) prediction is a critical step in drug discovery and precision medicine. Although graph neural networks (GNNs) have achieved remarkable progress, existing graph pooling methods rely on fixed ratios, failing to adapt to the structural diversity of molecules and proteins, which leads to information loss or redundant feature retention. To address this issue, we propose the Adaptive Self-Attention Graph Pooling (ASAGPooling) mechanism, which introduces a learnable pooling ratio that dynamically adjusts node retention during training. Furthermore, we develop ASAG-DTA, a multi-modal framework that integrates GNNs with Transformers to jointly model molecular graphs, protein contact maps, SMILES sequences, and FASTA sequences. While ASAGPooling achieves competitive prediction accuracy (MSE = 0.186 on Davis), we acknowledge that it does not surpass the state-of-the-art DynHeter-DTA (MSE = 0.130), which incorporates a more complex dynamic heterogeneous graph architecture. Instead, the key contribution of ASAGPooling lies in its adaptability, interpretability, and computational efficiency. It can eliminate the need for manually tuned pooling ratios, enable direct visualization of retained key residues\/atoms, and reduce model complexity. This makes ASAG-DTA a practical lightweight alternative for large-scale virtual screening scenarios where computational resources are constrained.<\/jats:p>","DOI":"10.3390\/ijms27135861","type":"journal-article","created":{"date-parts":[[2026,6,30]],"date-time":"2026-06-30T00:55:11Z","timestamp":1782780911000},"page":"5861","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Adaptive Self-Attention Graph Pooling for Drug\u2013Target Affinity Prediction"],"prefix":"10.3390","volume":"27","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-5135-7638","authenticated-orcid":false,"given":"Changli","family":"Li","sequence":"first","affiliation":[{"name":"School of Artificial Intelligence, Nanjing University of Information Science & Technology, Nanjing 210044, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Guangyue","family":"Li","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence, Nanjing University of Information Science & Technology, Nanjing 210044, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2026,6,29]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"755","DOI":"10.1080\/17460441.2019.1623202","article-title":"Binding affinity in drug design: Experimental and computational techniques","volume":"14","author":"Kairys","year":"2019","journal-title":"Expert Opin. Drug Discov."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"87","DOI":"10.1038\/nrd.2015.18","article-title":"The drug-target residence time model: A 10-year retrospective","volume":"15","author":"Copeland","year":"2016","journal-title":"Nat. Rev. Drug Discov."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1016\/j.ab.2006.10.040","article-title":"Higher-throughput, label-free, real-time molecular interaction analysis","volume":"361","author":"Rich","year":"2006","journal-title":"Anal. Biochem."},{"key":"ref_4","doi-asserted-by":"crossref","unstructured":"Liao, J., Chen, H., Wei, L., and Wei, L. (2022). GSAML-DTA: An interpretable drug-target binding affinity prediction model based on graph neural networks with self-attention mechanism and mutual information. Comput. Biol. Med., 150.","DOI":"10.1016\/j.compbiomed.2022.106145"},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"455","DOI":"10.1002\/jcc.21334","article-title":"AutoDock Vina: Improving the speed and accuracy of docking with a new scoring function, efficient optimization, and multithreading","volume":"31","author":"Trott","year":"2010","journal-title":"J. Comput. Chem."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"1129","DOI":"10.1016\/j.neuron.2018.08.011","article-title":"Molecular dynamics simulation for all","volume":"99","author":"Hollingsworth","year":"2018","journal-title":"Neuron"},{"key":"ref_7","first-page":"381","article-title":"Machine learning algorithms-a review","volume":"9","author":"Mahesh","year":"2020","journal-title":"Int. J. Sci. Res."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"255","DOI":"10.1126\/science.aaa8415","article-title":"Machine learning: Trends, perspectives, and prospects","volume":"349","author":"Jordan","year":"2015","journal-title":"Science"},{"key":"ref_9","doi-asserted-by":"crossref","unstructured":"Alzubi, J., Nayyar, A., and Kumar, A. (2018). Machine learning from theory to algorithms: An overview. J. Phys. Conf. Ser., 1142.","DOI":"10.1088\/1742-6596\/1142\/1\/012012"},{"key":"ref_10","doi-asserted-by":"crossref","unstructured":"Nascimento, A.C.A., Prudencio, R.B.C., and Costa, I.G. (2016). A multiple kernel learning algorithm for drug-target interaction prediction. BMC Bioinform., 17.","DOI":"10.1186\/s12859-016-0890-3"},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"24","DOI":"10.1186\/s13321-017-0209-z","article-title":"SimBoost: A read-across approach for predicting drug-target binding affinities using gradient boosting machines","volume":"9","author":"He","year":"2017","journal-title":"J. Cheminform."},{"key":"ref_12","doi-asserted-by":"crossref","unstructured":"Chang, C.H., Hung, C.L., and Tang, C.Y. (2019, January 18\u201321). A review of deep learning in computer-aided drug design. Proceedings of the 2019 IEEE International Conference on Bioinformatics and Biomedicine (BIBM), San Diego, CA, USA.","DOI":"10.1109\/BIBM47256.2019.8982968"},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"3","DOI":"10.1002\/minf.201501008","article-title":"Deep learning in drug discovery","volume":"35","author":"Gawehn","year":"2016","journal-title":"Mol. Inform."},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"2017","DOI":"10.1016\/j.drudis.2019.07.006","article-title":"Deep learning in drug discovery: Opportunities, challenges and future prospects","volume":"24","author":"Lavecchia","year":"2019","journal-title":"Drug Discov. Today"},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"i821","DOI":"10.1093\/bioinformatics\/bty593","article-title":"DeepDTA: Deep drug-target binding affinity prediction","volume":"34","author":"Ozkirimli","year":"2018","journal-title":"Bioinformatics"},{"key":"ref_16","doi-asserted-by":"crossref","unstructured":"\u00d6zt\u00fcrk, H., Ozkirimli, E., and \u00d6zg\u00fcr, A. (2019). WideDTA: Prediction of drug-target binding affinity. arXiv.","DOI":"10.1093\/bioinformatics\/bty593"},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"4406","DOI":"10.1093\/bioinformatics\/btaa524","article-title":"TransformerCPI: Improving compound-protein interaction prediction by sequence-based deep learning with self-attention mechanism and label reversal experiments","volume":"36","author":"Chen","year":"2020","journal-title":"Bioinformatics"},{"key":"ref_18","first-page":"6000","article-title":"Attention is all you need","volume":"30","author":"Vaswani","year":"2017","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref_19","doi-asserted-by":"crossref","unstructured":"Zhang, Z., Chen, L., Zhong, F., Wang, D., Jiang, J., Zhang, S., Jiang, H., Zheng, M., and Li, X. (2022). Graph neural network approaches for drug-target interactions. Curr. Opin. Struct. Biol., 73.","DOI":"10.1016\/j.sbi.2021.102327"},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"242","DOI":"10.1016\/j.neucom.2021.04.039","article-title":"Molecular generative graph neural networks for drug discovery","volume":"450","author":"Bongini","year":"2021","journal-title":"Neurocomputing"},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"1382","DOI":"10.1016\/j.drudis.2021.02.011","article-title":"Graph neural networks for automated de novo drug design","volume":"26","author":"Xiong","year":"2021","journal-title":"Drug Discov. Today"},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"1140","DOI":"10.1093\/bioinformatics\/btaa921","article-title":"GraphDTA: Predicting drug-target binding affinity with graph neural networks","volume":"37","author":"Nguyen","year":"2021","journal-title":"Bioinformatics"},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"20701","DOI":"10.1039\/D0RA02297G","article-title":"Drug-target affinity prediction using graph neural network and contact maps","volume":"10","author":"Jiang","year":"2020","journal-title":"RSC Adv."},{"key":"ref_24","unstructured":"Gao, H., and Ji, S. (2019, January 9\u201315). Graph U-Nets. Proceedings of the 36th International Conference on Machine Learning, Long Beach, CA, USA."},{"key":"ref_25","first-page":"4800","article-title":"Hierarchical graph representation learning with differentiable pooling","volume":"31","author":"Ying","year":"2018","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref_26","unstructured":"Lee, J., Lee, I., and Kang, J. (2019, January 9\u201315). Self-attention graph pooling. Proceedings of the 36th International Conference on Machine Learning, Long Beach, CA, USA."},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"583","DOI":"10.1038\/s41586-021-03819-2","article-title":"Highly accurate protein structure prediction with AlphaFold","volume":"596","author":"Jumper","year":"2021","journal-title":"Nature"},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"223","DOI":"10.1186\/s12943-024-02140-6","article-title":"Artificial intelligence alphafold model for molecular biology and drug discovery: A machine-learning-driven informatics investigation","volume":"23","author":"Guo","year":"2024","journal-title":"Mol. Cancer"},{"key":"ref_29","doi-asserted-by":"crossref","unstructured":"Rives, A., Meier, J., Sercu, T., Goyal, S., Lin, Z., Liu, J., Guo, D., Ott, M., Zitnick, C.L., and Ma, J. (2021). Biological structure and function emerge from scaling unsupervised learning to 250 million protein sequences. Proc. Natl. Acad. Sci. USA, 118.","DOI":"10.1073\/pnas.2016239118"},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"7112","DOI":"10.1109\/TPAMI.2021.3095381","article-title":"ProtTrans: Toward understanding the language of life through self-supervised learning","volume":"44","author":"Elnaggar","year":"2021","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"316","DOI":"10.1016\/j.csbj.2025.12.033","article-title":"Machine learning for drug-target interaction prediction: A comprehensive review of models, challenges, and computational strategies","volume":"31","author":"Ahmad","year":"2026","journal-title":"Comput. Struct. Biotechnol. J."},{"key":"ref_32","doi-asserted-by":"crossref","unstructured":"Debnath, K., Rana, P., and Ghosh, P. (2025). A survey on deep learning for drug-target binding. Brief. Bioinform., 26.","DOI":"10.1093\/bib\/bbaf491"},{"key":"ref_33","doi-asserted-by":"crossref","first-page":"691","DOI":"10.1016\/j.omtn.2023.02.019","article-title":"Artificial intelligence for drug discovery: Resources, methods, and applications","volume":"31","author":"Chen","year":"2024","journal-title":"Mol. Ther. Nucleic Acids"},{"key":"ref_34","doi-asserted-by":"crossref","first-page":"1046","DOI":"10.1038\/nbt.1990","article-title":"Comprehensive analysis of kinase inhibitor selectivity","volume":"29","author":"Davis","year":"2011","journal-title":"Nat. Biotechnol."},{"key":"ref_35","doi-asserted-by":"crossref","first-page":"735","DOI":"10.1021\/ci400709d","article-title":"Making sense of large-scale kinase inhibitor bioactivity data sets: A comparative and integrative analysis","volume":"54","author":"Tang","year":"2014","journal-title":"J. Chem. Inf. Model."},{"key":"ref_36","doi-asserted-by":"crossref","unstructured":"Li, C., and Li, G. (2025). DynHeter-DTA: Dynamic Heterogeneous Graph Representation for Drug-Target Binding Affinity Prediction. Int. J. Mol. Sci., 26.","DOI":"10.3390\/ijms26031223"},{"key":"ref_37","doi-asserted-by":"crossref","first-page":"18193","DOI":"10.1021\/acs.est.3c02198","article-title":"Count-based Morgan fingerprint: A more efficient and interpretable molecular representation in developing machine learning-based predictive regression models for water contaminants\u2019 activities and properties","volume":"57","author":"Zhong","year":"2023","journal-title":"Environ. Sci. Technol."},{"key":"ref_38","doi-asserted-by":"crossref","unstructured":"Skwark, M.J., Raimondi, D., Michel, M., and Elofsson, A. (2014). Improved contact predictions using the recognition of protein-like contact patterns. PLoS Comput. Biol., 10.","DOI":"10.1371\/journal.pcbi.1003889"},{"key":"ref_39","unstructured":"Fey, M., and Lenssen, J.E. (2019). Fast graph representation learning with PyTorch Geometric. arXiv."},{"key":"ref_40","first-page":"8024","article-title":"Pytorch: An imperative style, high-performance deep learning library","volume":"32","author":"Paszke","year":"2019","journal-title":"NeurIPS"},{"key":"ref_41","doi-asserted-by":"crossref","first-page":"btd355","DOI":"10.1093\/bioinformatics\/btad355","article-title":"NHGNN-DTA: A node-adaptive hybrid graph neural network for interpretable drug-target binding affinity prediction","volume":"39","author":"He","year":"2023","journal-title":"Bioinformatics"},{"key":"ref_42","doi-asserted-by":"crossref","unstructured":"Zhang, Y., Hu, Y., Han, N., Yang, A., Liu, X., and Cai, H. (2023). A survey of drug-target interaction and affinity prediction methods via graph neural networks. Comput. Biol. Med., 163.","DOI":"10.1016\/j.compbiomed.2023.107136"},{"key":"ref_43","doi-asserted-by":"crossref","first-page":"48","DOI":"10.1186\/s13321-018-0302-y","article-title":"Life beyond the Tanimoto coefficient: Similarity measures for interaction fingerprints","volume":"10","author":"Bajusz","year":"2018","journal-title":"J. Cheminform."},{"key":"ref_44","doi-asserted-by":"crossref","first-page":"109522","DOI":"10.1109\/ACCESS.2021.3100408","article-title":"Sequence alignment using machine learning-based needleman-wunsch algorithm","volume":"9","author":"Amer","year":"2021","journal-title":"IEEE Access"},{"key":"ref_45","doi-asserted-by":"crossref","first-page":"11","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_46","unstructured":"Veli\u010dkovi\u0107, P., Cucurull, G., Casanova, A., Romero, A., Lio, P., and Bengio, Y. (2017). Graph attention networks. arXiv."},{"key":"ref_47","unstructured":"Brody, S., Alon, U., and Yahav, E. (2022, January 25\u201329). How attentive are graph attention networks?. Proceedings of the International Conference on Learning Representations, Virtual."},{"key":"ref_48","unstructured":"Xu, K., Hu, W., Leskovec, J., and Jegelka, S. (2019, January 6\u20139). How powerful are graph neural networks?. Proceedings of the International Conference on Learning Representations, New Orleans, LA, USA."}],"container-title":["International Journal of Molecular Sciences"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1422-0067\/27\/13\/5861\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,30]],"date-time":"2026-06-30T01:17:32Z","timestamp":1782782252000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1422-0067\/27\/13\/5861"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6,29]]},"references-count":48,"journal-issue":{"issue":"13","published-online":{"date-parts":[[2026,7]]}},"alternative-id":["ijms27135861"],"URL":"https:\/\/doi.org\/10.3390\/ijms27135861","relation":{},"ISSN":["1422-0067"],"issn-type":[{"value":"1422-0067","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,6,29]]}}}