{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,26]],"date-time":"2026-08-26T06:30:47Z","timestamp":1787725847120,"version":"build-2784847793"},"reference-count":35,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2026,8,26]],"date-time":"2026-08-26T00:00:00Z","timestamp":1787702400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Immunol."],"abstract":"<jats:sec>\n                    <jats:title>Introduction<\/jats:title>\n                    <jats:p>\n                      Tyrosine kinase inhibitors targeting the c-KIT receptor are pivotal in the targeted therapy of malignancies such as gastrointestinal stromal tumors (GIST). The bioactivity of these inhibitors is typically quantified by the half-maximal inhibitory concentration (IC\n                      <jats:sub>50<\/jats:sub>\n                      ), making its accurate prediction a critical computational task for accelerating the discovery and optimization of anticancer lead compounds.\n                    <\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>\n                      To address this need, we propose HGATT\u2014a hybrid high activity aware framework integrating Graph Attention Network (GAT) and Transformer\u2014for high-accuracy half maximal inhibitory concentration (IC\n                      <jats:sub>50<\/jats:sub>\n                      ) prediction of c-KIT inhibitors. The model was trained on inhibitor data targeting c-KIT and related kinase families sourced from the BindingDB and ChEMBL databases. By extracting atom-level graph features, Morgan fingerprints, and physicochemical descriptors from SMILES strings, HGATT constructs a unified molecular representation that integrates both local structural and global information. Its architecture employs multidimensional graph attention mechanisms and gated residual modules to simultaneously capture atomic-level local structural features and macroscopic molecular properties. Stabilized training strategies, including gradient clipping, were adopted to enhance training efficiency and model robustness.\n                    <\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>On an independent test set, HGATT achieved a mean squared error (MSE) of 0.28 and a coefficient of determination (R\u00b2) of 0.57, corresponding to an approximate 44% reduction in MSE compared to the second-best baseline.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Discussion<\/jats:title>\n                    <jats:p>Experimental results demonstrate that HGATT outperforms not only individual graph neural network (GNN)- and machine learning-based models but also other related drug-target prediction methods and baseline regression approaches, exhibiting superior predictive accuracy.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.3389\/fimmu.2026.1929215","type":"journal-article","created":{"date-parts":[[2026,8,26]],"date-time":"2026-08-26T06:04:47Z","timestamp":1787724287000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["A hybrid high activity aware framework integrating graph attention network and transformer for half maximal inhibitory concentration prediction"],"prefix":"10.3389","volume":"17","author":[{"given":"Dingcheng","family":"Ban","sequence":"first","affiliation":[{"name":"School of Computer and Big Data Science, Jiujiang University","place":["Jiujiang, China"]},{"name":"Jiujiang Key Laboratory of Digital Technology, Jiujiang University","place":["Jiujiang, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lu","family":"Pan","sequence":"additional","affiliation":[{"name":"Institute of Management and Health (IMH) Swansea Business School, University of Wales Trinity Saint David","place":["Swansea, United Kingdom"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xueli","family":"Zhang","sequence":"additional","affiliation":[{"name":"Department of Medical Technology, Zhengzhou Railway Vocational and Technical College","place":["Zhengzhou, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Peng","family":"Xu","sequence":"additional","affiliation":[{"name":"Institute of computational science and technology, Guangzhou University","place":["Guangzhou, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Binbin","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Computer and Big Data Science, Jiujiang University","place":["Jiujiang, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tao","family":"Liu","sequence":"additional","affiliation":[{"name":"School of Computer and Big Data Science, Jiujiang University","place":["Jiujiang, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Deng","family":"Pan","sequence":"additional","affiliation":[{"name":"School of Computer and Big Data Science, Jiujiang University","place":["Jiujiang, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xianbin","family":"Li","sequence":"additional","affiliation":[{"name":"School of Computer and Big Data Science, Jiujiang University","place":["Jiujiang, China"]},{"name":"Jiujiang Key Laboratory of Digital Technology, Jiujiang University","place":["Jiujiang, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2026,8,26]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","DOI":"10.1016\/j.bbcan.2021.188631","article-title":"A holistic view on c-Kit in cancer: Structure, signaling, pathophysiology and its inhibitors","volume":"1876","author":"Pathania","year":"2021","journal-title":"Biochim Biophys Acta (BBA) - Rev Cancer"},{"key":"B2","article-title":"Targeted therapy for hereditary cancer syndromes: neurofibromatosis type 1, neurofibromatosis type 2, and Gorlin syndrome","volume":"18","author":"Agarwal","year":"2014","journal-title":"Discov Med"},{"key":"B3","doi-asserted-by":"publisher","DOI":"10.3390\/ijms18030643","article-title":"Oleanolic acid alters multiple cell signaling pathways: Implication in cancer prevention and therapy","volume":"18","author":"\u017diberna","year":"2017","journal-title":"Int J Mol Sci"},{"key":"B4","doi-asserted-by":"publisher","DOI":"10.3390\/molecules28093906","article-title":"Past, present, and future perspectives on computer-aided drug design methodologies","volume":"28","author":"Bassani","year":"2023","journal-title":"Molecules"},{"key":"B5","doi-asserted-by":"publisher","DOI":"10.2174\/0115680266258467231107102643","article-title":"Recent trends in computer-aided drug design for anti-cancer drug discovery","volume":"23","author":"Razia","year":"2023","journal-title":"Curr Top Med Chem"},{"key":"B6","doi-asserted-by":"publisher","first-page":"995","DOI":"10.2174\/1568026621666210521164545","article-title":"Application of in silico methods in the design of drugs for neurodegenerative diseases","volume":"21","author":"Haider","year":"2021","journal-title":"Curr Top Med Chem"},{"key":"B7","doi-asserted-by":"publisher","first-page":"41","DOI":"10.1007\/s11030-015-9635-x","article-title":"In silico exploration of c-KIT inhibitors by pharmaco-informatics methodology: Pharmacophore modeling, 3D QSAR, docking studies, and virtual screening","volume":"20","author":"Chaudhari","year":"2016","journal-title":"Mol Divers"},{"key":"B8","doi-asserted-by":"publisher","DOI":"10.3390\/ijms21218232","article-title":"Molecular modeling study of c-KIT\/PDGFR\u03b1 dual inhibitors for the treatment of gastrointestinal stromal tumors","volume":"21","author":"Keretsu","year":"2020","journal-title":"Int J Mol Sci"},{"key":"B9","doi-asserted-by":"publisher","DOI":"10.1007\/s00894-011-1304-0","article-title":"Receptor-guided 3D-QSAR approach for the discovery of c-kit tyrosine kinase inhibitors","volume":"18","author":"Almerico","year":"2012","journal-title":"J Mol Model"},{"key":"B10","doi-asserted-by":"publisher","DOI":"10.1109\/tcbb.2023.3262821","article-title":"SGNet: Sequence-based convolution and ligand graph network for protein binding affinity prediction","volume":"20","author":"Chen","year":"2023","journal-title":"IEEE\/ACM Trans Comput Biol Bioinform"},{"key":"B11","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2025.108001","article-title":"Prediction of cancer drug response based on heterogeneous graph neural networks and multi-omics data","volume":"193","author":"Zhang","year":"2025","journal-title":"Neural Netw"},{"key":"B12","doi-asserted-by":"publisher","first-page":"1097","DOI":"10.1186\/s12967-024-05893-2","article-title":"Discovery of novel VEGFR2 inhibitors against non-small cell lung cancer based on fingerprint-enhanced graph attention convolutional network","volume":"22","author":"Wang","year":"2024","journal-title":"J Transl Med"},{"key":"B13","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijbiomac.2024.137060","article-title":"Predicting variable-length ACE inhibitory peptides based on graph convolutional network","volume":"282","author":"Rong","year":"2024","journal-title":"Int J Biol Macromol"},{"key":"B14","doi-asserted-by":"publisher","DOI":"10.1021\/acsomega.9b04162","article-title":"graphDelta: MPNN scoring function for the affinity prediction of protein-ligand complexes","volume":"5","author":"Karlov","year":"2020","journal-title":"ACS Omega"},{"key":"B15","doi-asserted-by":"publisher","DOI":"10.1038\/s41401-025-01644-1","article-title":"AI-enhanced virtual screening approach to hit identification for GluN1\/GluN3A NMDA receptor","volume":"47","author":"Ji","year":"2025","journal-title":"Acta Pharmacol Sin"},{"key":"B16","doi-asserted-by":"publisher","DOI":"10.1021\/acs.jcim.4c00863","article-title":"MolPipeline: A Python package for processing molecules with RDKit in Scikit-learn","volume":"64","author":"Sieg","year":"2024","journal-title":"J Chem Inf Model"},{"key":"B17","doi-asserted-by":"publisher","DOI":"10.1016\/j.compbiolchem.2023.107861","article-title":"Physicochemical properties, drug likeness, ADMET, DFT studies, and in vitro antioxidant activity of oxindole derivatives","volume":"104","author":"Ahmad","year":"2023","journal-title":"Comput Biol Chem"},{"key":"B18","doi-asserted-by":"publisher","DOI":"10.1021\/acs.jpcb.4c01875","article-title":"Utility of the Morgan fingerprint in structure-based virtual ligand screening","volume":"128","author":"Zhou","year":"2024","journal-title":"J Phys Chem B"},{"key":"B19","doi-asserted-by":"publisher","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":"B20","doi-asserted-by":"publisher","DOI":"10.1093\/nar\/gkv1072","article-title":"BindingDB in 2015: A public database for medicinal chemistry, computational chemistry and systems pharmacology","volume":"44","author":"Gilson","year":"2016","journal-title":"Nucleic Acids Res"},{"key":"B21","doi-asserted-by":"publisher","DOI":"10.1016\/j.cellsig.2013.05.016","article-title":"The tyrosine kinase CSK associates with FLT3 and c-Kit receptors and regulates downstream signaling","volume":"25","author":"Kazi","year":"2013","journal-title":"Cell Signal"},{"key":"B22","doi-asserted-by":"publisher","first-page":"89","DOI":"10.1007\/s10143-014-0579-x","article-title":"Immunohistochemical expression of receptor tyrosine kinase PDGFR-\u03b1, c-Met, and EGFR in skull base chordoma","volume":"38","author":"Akhavan-Sigari","year":"2015","journal-title":"Neurosurg Rev"},{"key":"B23","doi-asserted-by":"publisher","DOI":"10.1111\/vco.12344","article-title":"Expression of receptor tyrosine kinase targets PDGFR-\u03b2, VEGFR2 and KIT in canine transitional cell carcinoma","volume":"16","author":"Walters","year":"2018","journal-title":"Vet Comp Oncol"},{"key":"B24","doi-asserted-by":"publisher","DOI":"10.1074\/jbc.M110.166702","article-title":"A CSF-1 receptor phosphotyrosine 559 signaling pathway regulates receptor ubiquitination and tyrosine phosphorylation","volume":"286","author":"Xiong","year":"2011","journal-title":"J Biol Chem"},{"key":"B25","doi-asserted-by":"publisher","DOI":"10.2174\/1381612043384394","article-title":"Flt3 receptor tyrosine kinase as a drug target in leukemia","volume":"10","author":"Schmidt-Arras","year":"2004","journal-title":"Curr Pharm Des"},{"key":"B26","doi-asserted-by":"publisher","DOI":"10.1109\/tcyb.2018.2883970","article-title":"Graph convolutional network hashing","volume":"50","author":"Zhou","year":"2020","journal-title":"IEEE Trans Cybern"},{"key":"B27","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2022.07.014","article-title":"MRGAT: Multi-relational graph attention network for knowledge graph completion","volume":"154","author":"Dai","year":"2022","journal-title":"Neural Netw"},{"key":"B28","doi-asserted-by":"publisher","DOI":"10.1016\/j.crstbi.2023.100122","article-title":"SAGESDA: Multi-GraphSAGE networks for predicting SnoRNA-disease associations","volume":"7","author":"Momanyi","year":"2024","journal-title":"Curr Res Struct Biol"},{"key":"B29","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2025.3550281","article-title":"Deformable graph transformer","volume":"47","author":"Park","year":"2025","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"B30","doi-asserted-by":"publisher","DOI":"10.3389\/frai.2024.1401810","article-title":"Automatic text classification of drug-induced liver injury using document-term matrix and XGBoost","volume":"7","author":"Chen","year":"2024","journal-title":"Front Artif Intell"},{"key":"B31","doi-asserted-by":"publisher","DOI":"10.1093\/bib\/bbad002","article-title":"A review on longitudinal data analysis with random forest","volume":"24","author":"Hu","year":"2023","journal-title":"Brief Bioinform"},{"key":"B32","doi-asserted-by":"publisher","first-page":"41","DOI":"10.21873\/cgp.20063","article-title":"Applications of support vector machine (SVM) learning in cancer genomics","volume":"15","author":"Huang","year":"2018","journal-title":"Cancer Genomics Proteomics"},{"key":"B33","doi-asserted-by":"publisher","DOI":"10.1016\/j.compbiomed.2023.107317","article-title":"PredDRBP-MLP: Prediction of DNA-binding proteins and RNA-binding proteins by multilayer perceptron","volume":"164","author":"Arican","year":"2023","journal-title":"Comput Biol Med"},{"key":"B34","doi-asserted-by":"publisher","DOI":"10.1101\/2023.03.16.532916","article-title":"TorchLens: A Python package for extracting and visualizing hidden activations of PyTorch models","volume":"18","author":"Taylor","year":"2023","journal-title":"bioRxiv"},{"key":"B35","doi-asserted-by":"publisher","DOI":"10.1111\/biom.13169","article-title":"Approximation of bias and mean-squared error in two-sample Mendelian randomization analyses","volume":"76","author":"Deng","year":"2020","journal-title":"Biometrics"}],"container-title":["Frontiers in Immunology"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fimmu.2026.1929215\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,26]],"date-time":"2026-08-26T06:04:47Z","timestamp":1787724287000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fimmu.2026.1929215\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8,26]]},"references-count":35,"alternative-id":["10.3389\/fimmu.2026.1929215"],"URL":"https:\/\/doi.org\/10.3389\/fimmu.2026.1929215","relation":{},"ISSN":["1664-3224"],"issn-type":[{"value":"1664-3224","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,8,26]]},"article-number":"1929215"}}