{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,24]],"date-time":"2026-10-24T00:45:03Z","timestamp":1792802703011,"version":"4.5.0"},"reference-count":48,"publisher":"MDPI AG","issue":"13","license":[{"start":{"date-parts":[[2025,7,6]],"date-time":"2025-07-06T00:00:00Z","timestamp":1751760000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"National Research Foundation of Korea (NRF) grant funded by the Korean government (MSIT)","award":["2020R1A2C2005612"],"award-info":[{"award-number":["2020R1A2C2005612"]}]},{"name":"National Research Foundation of Korea (NRF) grant funded by the Korean government (MSIT)","award":["2022R1G1A1004613"],"award-info":[{"award-number":["2022R1G1A1004613"]}]},{"name":"Korean Big Data Station (K-BDS)","award":["2020R1A2C2005612"],"award-info":[{"award-number":["2020R1A2C2005612"]}]},{"name":"Korean Big Data Station (K-BDS)","award":["2022R1G1A1004613"],"award-info":[{"award-number":["2022R1G1A1004613"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Molecules"],"abstract":"<jats:p>Kinase is an enzyme responsible for cell signaling and other complex processes. Mutations or changes in kinase can cause cancer and other diseases in humans, including leukemia, neuroblastomas, glioblastomas, and more. Considering these concerns, inhibiting overexpressed or dysregulated kinases through small drug molecules is very important. In the past, many machine learning and deep learning approaches have been used to inhibit unregulated kinase enzymes. In this work, we employ a Graph Neural Network (GNN) to predict the inhibition activities of kinases. A separate Graph Convolution Network (GCN) and combined Graph Convolution and Graph Attention Network (GCN_GAT) are developed and trained on two large datasets (Kinase Datasets 1 and 2) consisting of small drug molecules against the targeted kinase using 10-fold cross-validation. Furthermore, a wide range of molecules are used as independent datasets on which the performance of the models is evaluated. On both independent kinase datasets, our model combining GCN and GAT provides the best evaluation and outperforms previous models in terms of accuracy, Matthews Correlation Coefficient (MCC), sensitivity, specificity, and precision. On the independent Kinase Dataset 1, the values of accuracy, MCC, sensitivity, specificity, and precision are 0.96, 0.89, 0.90, 0.98, and 0.91, respectively. Similarly, the performance of our model combining GCN and GAT on the independent Kinase Dataset 2 is 0.97, 0.90, 0.91, 0.99, and 0.92 in terms of accuracy, MCC, sensitivity, specificity, and precision, respectively.<\/jats:p>","DOI":"10.3390\/molecules30132871","type":"journal-article","created":{"date-parts":[[2025,7,7]],"date-time":"2025-07-07T04:43:37Z","timestamp":1751863417000},"page":"2871","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":13,"title":["Integrating Graph Convolution and Attention Mechanism for Kinase Inhibition Prediction"],"prefix":"10.3390","volume":"30","author":[{"given":"Hamza","family":"Zahid","sequence":"first","affiliation":[{"name":"Department of Electronics and Information Engineering, Jeonbuk National University, Jeonju 54896, Jeollabuk-do, Republic of Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1952-0001","authenticated-orcid":false,"given":"Kil To","family":"Chong","sequence":"additional","affiliation":[{"name":"Department of Electronics and Information Engineering, Jeonbuk National University, Jeonju 54896, Jeollabuk-do, Republic of Korea"},{"name":"Advances Electronics and Information Research Centre, Jeonbuk National University, Jeonju 54896, Jeollabuk-do, Republic of Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5678-3479","authenticated-orcid":false,"given":"Hilal","family":"Tayara","sequence":"additional","affiliation":[{"name":"School of International Engineering and Science, Jeonbuk National University, Jeonju 54896, Jeollabuk-do, Republic of Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2025,7,6]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"1163","DOI":"10.1007\/s00018-008-8539-7","article-title":"Therapeutic protein kinase inhibitors","volume":"66","author":"Grant","year":"2009","journal-title":"Cell. Mol. Life Sci."},{"key":"ref_2","doi-asserted-by":"crossref","unstructured":"Singha, M., Pu, L., Srivastava, G., Ni, X., Stanfield, B.A., Uche, I.K., Rider, P.J., Kousoulas, K.G., Ramanujam, J., and Brylinski, M. (2023). Unlocking the potential of kinase targets in cancer: Insights from CancerOmicsNet, an AI-driven approach to drug response prediction in cancer. Cancers, 15.","DOI":"10.3390\/cancers15164050"},{"key":"ref_3","doi-asserted-by":"crossref","unstructured":"Cicenas, J., Zalyte, E., Bairoch, A., and Gaudet, P. (2018). Kinases and cancer. Cancers, 10.","DOI":"10.3390\/cancers10030063"},{"key":"ref_4","first-page":"357027","article-title":"Imatinib: A breakthrough of targeted therapy in cancer","volume":"2014","author":"Iqbal","year":"2014","journal-title":"Chemother. Res. Pract."},{"key":"ref_5","doi-asserted-by":"crossref","unstructured":"Lien, S.T., Lin, T.E., Hsieh, J.H., Sung, T.Y., Chen, J.H., and Hsu, K.C. (2023). Establishment of extensive artificial intelligence models for kinase inhibitor prediction: Identification of novel PDGFRB inhibitors. Comput. Biol. Med., 156.","DOI":"10.1016\/j.compbiomed.2023.106722"},{"key":"ref_6","doi-asserted-by":"crossref","unstructured":"Shaker, B., Ahmad, S., Lee, J., Jung, C., and Na, D. (2021). In silico methods and tools for drug discovery. Comput. Biol. Med., 137.","DOI":"10.1016\/j.compbiomed.2021.104851"},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"146","DOI":"10.2174\/157340911795677602","article-title":"Molecular docking: A powerful approach for structure-based drug discovery","volume":"7","author":"Meng","year":"2011","journal-title":"Curr. Comput.-Aided Drug Des."},{"key":"ref_8","doi-asserted-by":"crossref","unstructured":"Hessler, G., and Baringhaus, K.H. (2018). Artificial intelligence in drug design. Molecules, 23.","DOI":"10.3390\/molecules23102520"},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"20585","DOI":"10.1109\/ACCESS.2019.2896961","article-title":"Deep belief network modeling for automatic liver segmentation","volume":"7","author":"Ahmad","year":"2019","journal-title":"IEEE Access"},{"key":"ref_10","doi-asserted-by":"crossref","unstructured":"Gagic, Z., Ruzic, D., Djokovic, N., Djikic, T., and Nikolic, K. (2020). In silico methods for design of kinase inhibitors as anticancer drugs. Front. Chem., 7.","DOI":"10.3389\/fchem.2019.00873"},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"8723","DOI":"10.1021\/acs.jmedchem.9b00855","article-title":"Deep learning enhancing kinome-wide polypharmacology profiling: Model construction and experiment validation","volume":"63","author":"Li","year":"2019","journal-title":"J. Med. Chem."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"4367","DOI":"10.1021\/acsomega.9b00298","article-title":"Multitask machine learning for classifying highly and weakly potent kinase inhibitors","volume":"4","author":"Bajorath","year":"2019","journal-title":"ACS Omega"},{"key":"ref_13","doi-asserted-by":"crossref","unstructured":"Hu, J., Allen, B.K., Stathias, V., Ayad, N.G., and Sch\u00fcrer, S.C. (2024). Kinome-Wide Virtual Screening by Multi-Task Deep Learning. Int. J. Mol. Sci., 25.","DOI":"10.3390\/ijms25052538"},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"5354","DOI":"10.1093\/bioinformatics\/btz519","article-title":"KinomeX: A web application for predicting kinome-wide polypharmacology effect of small molecules","volume":"35","author":"Li","year":"2019","journal-title":"Bioinformatics"},{"key":"ref_15","unstructured":"Fang, Z., Zhang, X., Zhao, A., Li, X., Chen, H., and Li, J. (2025). Recent Developments in GNNs for Drug Discovery. arXiv."},{"key":"ref_16","unstructured":"Zhang, O., Lin, H., Zhang, X., Wang, X., Wu, Z., Ye, Q., Zhao, W., Wang, J., Ying, K., and Kang, Y. (2025). Graph Neural Networks in Modern AI-aided Drug Discovery. arXiv."},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"5035","DOI":"10.1021\/acs.jcim.3c00554","article-title":"Evaluating the use of graph neural networks and transfer learning for oral bioavailability prediction","volume":"63","author":"Ng","year":"2023","journal-title":"J. Chem. Inf. Model."},{"key":"ref_18","doi-asserted-by":"crossref","unstructured":"Li, W., Ma, W., Yang, M., and Tang, X. (2024). Drug repurposing based on the DTD-GNN graph neural network: Revealing the relationships among drugs, targets and diseases. BMC Genom., 25.","DOI":"10.1186\/s12864-024-10499-5"},{"key":"ref_19","unstructured":"Fey, M., and Lenssen, J.E. (2019). Fast graph representation learning with PyTorch Geometric. arXiv."},{"key":"ref_20","first-page":"17","article-title":"An analysis of early stopping and dropout regularization in deep learning","volume":"5","author":"Sitaula","year":"2017","journal-title":"Int. J. Concept. Comput. Inf. Technol."},{"key":"ref_21","unstructured":"Mahsereci, M., Balles, L., Lassner, C., and Hennig, P. (2017). Early stopping without a validation set. arXiv."},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"107723","DOI":"10.1016\/j.phrs.2025.107723","article-title":"Properties of FDA-approved small molecule protein kinase inhibitors: A 2025 update","volume":"216","author":"Roskoski","year":"2025","journal-title":"Pharmacol. Res."},{"key":"ref_23","doi-asserted-by":"crossref","unstructured":"Rehman, M.U., Hussain, I., Tayara, H., and Chong, K.T. (2024). A graph neural network approach for predicting drug susceptibility in the human microbiome. Comput. Biol. Med., 179.","DOI":"10.1016\/j.compbiomed.2024.108729"},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"66","DOI":"10.1186\/s13321-024-00865-6","article-title":"PUResNetV2. 0: A deep learning model leveraging sparse representation for improved ligand binding site prediction","volume":"16","author":"Jeevan","year":"2024","journal-title":"J. Cheminform."},{"key":"ref_25","first-page":"9240","article-title":"GNNExplainer: Generating explanations for graph neural networks","volume":"32","author":"Ying","year":"2019","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref_26","unstructured":"Amara, K., Ying, R., Zhang, Z., Han, Z., Shan, Y., Brandes, U., Schemm, S., and Zhang, C. (2022). Graphframex: Towards systematic evaluation of explainability methods for graph neural networks. arXiv."},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"D930","DOI":"10.1093\/nar\/gky1075","article-title":"ChEMBL: Towards direct deposition of bioassay data","volume":"47","author":"Mendez","year":"2019","journal-title":"Nucleic Acids Res."},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"D1102","DOI":"10.1093\/nar\/gky1033","article-title":"PubChem 2019 update: Improved access to chemical data","volume":"47","author":"Kim","year":"2019","journal-title":"Nucleic Acids Res."},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"340","DOI":"10.2174\/1568026613666131127160819","article-title":"Seeding collaborations to advance kinase science with the GSK Published Kinase Inhibitor Set (PKIS)","volume":"14","author":"Drewry","year":"2014","journal-title":"Curr. Top. Med. Chem."},{"key":"ref_30","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_31","doi-asserted-by":"crossref","first-page":"474","DOI":"10.1021\/acs.jmedchem.6b01611","article-title":"Profiling prediction of kinase inhibitors: Toward the virtual assay","volume":"60","author":"Merget","year":"2017","journal-title":"J. Med. Chem."},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"1654","DOI":"10.1021\/acs.jcim.6b00122","article-title":"Unprecedently large-scale kinase inhibitor set enabling the accurate prediction of compound\u2013kinase activities: A way toward selective promiscuity by design?","volume":"56","author":"Papadatos","year":"2016","journal-title":"J. Chem. Inf. Model."},{"key":"ref_33","first-page":"5281","article-title":"RDKit: A software suite for cheminformatics, computational chemistry, and predictive modeling","volume":"8","author":"Landrum","year":"2013","journal-title":"Greg Landrum"},{"key":"ref_34","doi-asserted-by":"crossref","first-page":"26","DOI":"10.1145\/1656274.1656280","article-title":"KNIME-the Konstanz information miner: Version 2.0 and beyond","volume":"11","author":"Berthold","year":"2009","journal-title":"ACM SIGKDD Explor. Newsl."},{"key":"ref_35","doi-asserted-by":"crossref","unstructured":"Ahmad, W., Tayara, H., Shim, H., and Chong, K.T. (2024). SolPredictor: Predicting Solubility with Residual Gated Graph Neural Network. Int. J. Mol. Sci., 25.","DOI":"10.3390\/ijms25020715"},{"key":"ref_36","doi-asserted-by":"crossref","first-page":"31","DOI":"10.1021\/ci00057a005","article-title":"SMILES, a chemical language and information system. 1. Introduction to methodology and encoding rules","volume":"28","author":"Weininger","year":"1988","journal-title":"J. Chem. Inf. Comput. Sci."},{"key":"ref_37","doi-asserted-by":"crossref","first-page":"2647","DOI":"10.1007\/s00204-024-03756-9","article-title":"Harnessing machine learning to predict cytochrome P450 inhibition through molecular properties","volume":"98","author":"Zahid","year":"2024","journal-title":"Arch. Toxicol."},{"key":"ref_38","doi-asserted-by":"crossref","first-page":"225","DOI":"10.1007\/s00204-024-03888-y","article-title":"Possum: Identification and interpretation of potassium ion inhibitors using probabilistic feature vectors","volume":"99","author":"Hassan","year":"2025","journal-title":"Arch. Toxicol."},{"key":"ref_39","doi-asserted-by":"crossref","unstructured":"Chicco, D., T\u00f6tsch, N., and Jurman, G. (2021). The Matthews correlation coefficient (MCC) is more reliable than balanced accuracy, bookmaker informedness, and markedness in two-class confusion matrix evaluation. BioData Min., 14.","DOI":"10.1186\/s13040-021-00244-z"},{"key":"ref_40","doi-asserted-by":"crossref","first-page":"2940","DOI":"10.1109\/TVCG.2018.2865940","article-title":"Node-link or adjacency matrices: Old question, new insights","volume":"25","author":"Okoe","year":"2018","journal-title":"IEEE Trans. Vis. Comput. Graph."},{"key":"ref_41","doi-asserted-by":"crossref","first-page":"61","DOI":"10.1109\/TNN.2008.2005605","article-title":"The graph neural network model","volume":"20","author":"Scarselli","year":"2008","journal-title":"IEEE Trans. Neural Netw."},{"key":"ref_42","unstructured":"Kipf, T.N., and Welling, M. (2016). Semi-supervised classification with graph convolutional networks. arXiv."},{"key":"ref_43","doi-asserted-by":"crossref","first-page":"1140","DOI":"10.1093\/bioinformatics\/btaa921","article-title":"GraphDTA: Predicting drug\u2013target binding affinity with graph neural networks","volume":"37","author":"Nguyen","year":"2021","journal-title":"Bioinformatics"},{"key":"ref_44","doi-asserted-by":"crossref","first-page":"2708","DOI":"10.1109\/TNNLS.2022.3190922","article-title":"Understanding pooling in graph neural networks","volume":"35","author":"Grattarola","year":"2022","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"key":"ref_45","unstructured":"Veli\u010dkovi\u0107, P., Cucurull, G., Casanova, A., Romero, A., Lio, P., and Bengio, Y. (2017). Graph attention networks. arXiv."},{"key":"ref_46","doi-asserted-by":"crossref","first-page":"3049","DOI":"10.1016\/j.apsb.2022.02.002","article-title":"Why 90% of clinical drug development fails and how to improve it?","volume":"12","author":"Sun","year":"2022","journal-title":"Acta Pharm. Sin. B"},{"key":"ref_47","doi-asserted-by":"crossref","first-page":"262","DOI":"10.1038\/s41392-023-01469-6","article-title":"Adverse effects of tyrosine kinase inhibitors in cancer therapy: Pathophysiology, mechanisms and clinical management","volume":"8","author":"Sharma","year":"2023","journal-title":"Signal Transduct. Target. Ther."},{"key":"ref_48","unstructured":"Purushotham, S., and Tripathy, B. (2011). Evaluation of classifier models using stratified tenfold cross validation techniques. Global Trends in Information Systems and Software Applications, Proceedings of the 4th International Conference on Computing and Communication Systems, Vellore, TN, India, 9\u201311 December 2011, Springer."}],"container-title":["Molecules"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1420-3049\/30\/13\/2871\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,9]],"date-time":"2025-10-09T18:05:24Z","timestamp":1760033124000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1420-3049\/30\/13\/2871"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,7,6]]},"references-count":48,"journal-issue":{"issue":"13","published-online":{"date-parts":[[2025,7]]}},"alternative-id":["molecules30132871"],"URL":"https:\/\/doi.org\/10.3390\/molecules30132871","relation":{},"ISSN":["1420-3049"],"issn-type":[{"value":"1420-3049","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,7,6]]}}}