{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,13]],"date-time":"2026-03-13T04:35:42Z","timestamp":1773376542728,"version":"3.50.1"},"reference-count":43,"publisher":"Oxford University Press (OUP)","issue":"2","license":[{"start":{"date-parts":[[2026,3,12]],"date-time":"2026-03-12T00:00:00Z","timestamp":1773273600000},"content-version":"vor","delay-in-days":11,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026,3,1]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>Accurate drug\u2013target affinity (DTA) prediction is critical for drug discovery and repurposing. However, existing models often struggle with generalizing to unseen drug\u2013target pairs, lack interpretability, and fail to integrate heterogeneous biological features effectively. To overcome these challenges, we introduce KANPM-DTA, a deep learning framework designed to capture richer biochemical interactions and improve prediction reliability. Specifically, an ESM-guided protein graph construction strategy incorporates evolutionary and structural information to overcome underexplored protein representations. A gated fusion mechanism was employed to integrate drug\u2013protein graph features, while linear attention captures cross-modal dependencies that enhance discriminative power. For the final affinity prediction, a Kolmogorov\u2013Arnold network was used, offering a stronger nonlinear approximation and improved interpretability. Comprehensive experiments on benchmark datasets demonstrate that KANPM-DTA significantly outperforms state-of-the-art methods. On the Davis, KIBA, Metz, and BindingDB datasets, we achieved significant performance improvements under warm setting, with MSE reductions of 6.42%, 4.86%, 4.44%, and 5.46%, CI increases of 0.45%, 0.34%, 0.48%, and 0.80%, and $r_{m}^{2}$ gains of 1.85%, 0.90%, 0.84%, and 1.05%, respectively. Moreover, a case study on the epidermal growth factor receptor further highlights the effectiveness of KANPM-DTA in predicting DTAs for unknown drug\u2013target pairs, emphasizing its potential for real-world applications in drug discovery. However, wet-lab validation is required to assess the applicability of the results.<\/jats:p>","DOI":"10.1093\/bib\/bbag112","type":"journal-article","created":{"date-parts":[[2026,2,21]],"date-time":"2026-02-21T12:33:41Z","timestamp":1771677221000},"source":"Crossref","is-referenced-by-count":0,"title":["KANPM-DTA: improving drug\u2013target affinity prediction with Kolmogorov\u2013Arnold networks and pretrained models"],"prefix":"10.1093","volume":"27","author":[{"ORCID":"https:\/\/orcid.org\/0009-0009-2609-8601","authenticated-orcid":false,"given":"M D Youshuf Khan","family":"Rakib","sequence":"first","affiliation":[{"name":"School of Computer Science and Engineering, Central South University , Changsha, 410083 Hunan ,","place":["China"]}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4333-3871","authenticated-orcid":false,"given":"Muhammad Habibulla","family":"Alamin","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Central South University , Changsha, 410083 Hunan ,","place":["China"]}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-4558-0634","authenticated-orcid":false,"given":"Jiamu","family":"Li","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Macau University of Science and Technology , Taipa, 999078 Macau ,","place":["China"]}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-0651-0721","authenticated-orcid":false,"given":"Sheikh Sohan","family":"Mamun","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Central South University , Changsha, 410083 Hunan ,","place":["China"]}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-1155-7832","authenticated-orcid":false,"given":"Kaleb Amsalu","family":"Gobena","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Central South University , Changsha, 410083 Hunan ,","place":["China"]}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7709-4234","authenticated-orcid":false,"given":"Shengbing","family":"Ren","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Central South University , Changsha, 410083 Hunan ,","place":["China"]}]}],"member":"286","published-online":{"date-parts":[[2026,3,12]]},"reference":[{"key":"2026031216243009600_ref1","doi-asserted-by":"crossref","first-page":"108435","DOI":"10.1016\/j.compbiomed.2024.108435","article-title":"Prediction of drug-target binding affinity based on deep learning models","volume":"174","author":"Zhang","year":"2024","journal-title":"Comput Biol Med"},{"key":"2026031216243009600_ref2","doi-asserted-by":"publisher","first-page":"449","DOI":"10.1186\/s12864-022-08648-9","article-title":"Sequence-based drug-target affinity prediction using weighted graph neural networks","volume":"23","author":"Jiang","year":"2022","journal-title":"BMC Genomics"},{"key":"2026031216243009600_ref3","doi-asserted-by":"publisher","first-page":"i821","DOI":"10.1093\/bioinformatics\/bty593","article-title":"DeepDTA: deep drug\u2013target binding affinity prediction","volume":"34","author":"\u00d6zt\u00fcrk","year":"2018","journal-title":"Bioinformatics"},{"key":"2026031216243009600_ref4","doi-asserted-by":"publisher","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":"2026031216243009600_ref5","doi-asserted-by":"publisher","DOI":"10.1093\/bib\/bbab506","article-title":"FusionDTA: attention-based feature polymerizer and knowledge distillation for drug-target binding affinity prediction","volume":"23","author":"Yuan","year":"2022","journal-title":"Briefings in Bioinformatics."},{"key":"2026031216243009600_ref6","doi-asserted-by":"publisher","first-page":"816","DOI":"10.1039\/d1sc05180f","article-title":"MGraphDTA: deep multiscale graph neural network for explainable drug\u2013target binding affinity prediction","volume":"13","author":"Yang","year":"2022","journal-title":"Chem Sci"},{"key":"2026031216243009600_ref7","doi-asserted-by":"crossref","first-page":"8326","DOI":"10.3390\/ijms24098326","article-title":"MSGNN-DTA: multi-scale topological feature fusion based on graph neural networks for drug\u2013target binding affinity prediction","volume":"24","author":"Wang","year":"2023","journal-title":"Int J Mol Sci"},{"key":"2026031216243009600_ref8","doi-asserted-by":"crossref","first-page":"5126","DOI":"10.3390\/ijms25105126","article-title":"Prediction of drug-target affinity using attention neural network","volume":"25","author":"Tang","year":"2024","journal-title":"Int J Mol Sci"},{"key":"2026031216243009600_ref9","doi-asserted-by":"publisher","first-page":"981","DOI":"10.1021\/acs.jcim.4c01828","article-title":"MMSG-DTA: a multimodal, multiscale model based on sequence and graph modalities for drug-target affinity prediction","volume":"65","author":"Xu","year":"2025","journal-title":"J Chem Inf Model"},{"key":"2026031216243009600_ref10","doi-asserted-by":"publisher","DOI":"10.1093\/bioinformatics\/btaf002","article-title":"Improving generalizability of drug\u2013target binding prediction by pre-trained multi-view molecular representations","volume":"41","author":"Ouyang","year":"2025","journal-title":"Bioinformatics"},{"key":"2026031216243009600_ref11","doi-asserted-by":"crossref","first-page":"67","DOI":"10.1038\/s41746-025-01464-x","article-title":"Dual modality feature fused neural network integrating binding site information for drug target affinity prediction","volume":"8","author":"He","year":"2025","journal-title":"NPJ Digit Med"},{"key":"2026031216243009600_ref12","doi-asserted-by":"publisher","first-page":"1123","DOI":"10.1126\/science.ade2574","article-title":"Evolutionary-scale prediction of atomic-level protein structure with a language model","volume":"379","author":"Lin","journal-title":"Science (American Association for the Advancement of Science)"},{"key":"2026031216243009600_ref13","article-title":"ChemBERTa-2: towards chemical foundation models","author":"Ahmad","year":"2022  5"},{"key":"2026031216243009600_ref14","volume-title":"ESM Cambrian: Revealing the Mysteries of Proteins with Unsupervised Learning","author":"ESM Team"},{"key":"2026031216243009600_ref15","doi-asserted-by":"publisher","DOI":"10.1093\/bioinformatics\/btaf011","article-title":"SP-DTI: Subpocket-informed transformer for drug\u2013target interaction prediction","volume":"41","author":"Liu","year":"2025","journal-title":"Bioinformatics"},{"key":"2026031216243009600_ref16","first-page":"35454","article-title":"Flexmol: a flexible toolkit for benchmarking molecular relational learning","volume":"37","author":"Sizhe Liu","year":"2024","journal-title":"Adv Neural Inf Proces Syst"},{"key":"2026031216243009600_ref17","first-page":"1123","article-title":"KAN: Kolmogorov-Arnold networks","volume":"379","author":"Liu","year":"2023","journal-title":"Science"},{"key":"2026031216243009600_ref18","doi-asserted-by":"crossref","first-page":"533","DOI":"10.1038\/323533a0","article-title":"Learning representations by back-propagating errors","volume":"323","author":"Rumelhart","year":"1986","journal-title":"Nature"},{"key":"2026031216243009600_ref19","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":"2026031216243009600_ref20","doi-asserted-by":"publisher","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":"2026031216243009600_ref21","doi-asserted-by":"publisher","first-page":"200","DOI":"10.1038\/nchembio.530","article-title":"Navigating the kinome","volume":"7","author":"Metz","year":"2011","journal-title":"Nat Chem Biol"},{"key":"2026031216243009600_ref22","doi-asserted-by":"publisher","first-page":"D198","DOI":"10.1093\/nar\/gkl999","article-title":"BindingDB: a web-accessible database of experimentally determined protein\u2013ligand binding affinities","volume":"35","author":"Liu","year":"2007","journal-title":"Nucleic Acids Res"},{"key":"2026031216243009600_ref23","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":"2026031216243009600_ref24","article-title":"Attention is all you need","volume":"30","author":"Vaswani","year":"2017","journal-title":"Adv Neural Inf Proces Syst"},{"key":"2026031216243009600_ref25","article-title":"LINKER: learning interactions between functional groups and residues with chemical knowledge-enhanced reasoning and explainability","author":"Pham","year":"2025  3"},{"key":"2026031216243009600_ref26","doi-asserted-by":"publisher","first-page":"243","DOI":"10.1007\/978-981-97-5692-6_22","article-title":"MFFDTA: a multimodal feature fusion framework for drug-target affinity prediction","volume-title":"International Conference on Intelligent Computing","author":"Wang","year":"2024"},{"key":"2026031216243009600_ref27","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":"Computational Social Networks"},{"key":"2026031216243009600_ref28","article-title":"Graph attention networks","volume-title":"International conference on learning representations","author":"Veli\u010dkovi\u0107"},{"key":"2026031216243009600_ref29","doi-asserted-by":"crossref","first-page":"361","DOI":"10.1002\/(SICI)1097-0258(19960229)15:4<361::AID-SIM168>3.0.CO;2-4","article-title":"Multivariable prognostic models: Issues in developing models, evaluating assumptions and adequacy, and measuring and reducing errors","volume":"15","author":"Harrell","year":"1996","journal-title":"Stat Med"},{"key":"2026031216243009600_ref30","doi-asserted-by":"publisher","first-page":"1071","DOI":"10.1002\/jcc.23231","article-title":"Some case studies on application of \u201crm2\u201d metrics for judging quality of quantitative structure\u2013activity relationship predictions: emphasis on scaling of response data","volume":"34","author":"Roy","year":"2013","journal-title":"J Comput Chem"},{"key":"2026031216243009600_ref31","doi-asserted-by":"crossref","first-page":"107621","DOI":"10.1016\/j.compbiomed.2023.107621","article-title":"Drug\u2013target affinity prediction method based on multi-scale information interaction and graph optimization","volume":"167","author":"Zhu","year":"2023","journal-title":"Comput Biol Med"},{"key":"2026031216243009600_ref32","doi-asserted-by":"crossref","first-page":"107512","DOI":"10.1016\/j.compbiomed.2023.107512","article-title":"GPCNDTA: prediction of drug-target binding affinity through cross-attention networks augmented with graph features and pharmacophores","volume":"166","author":"Zhang","year":"2023","journal-title":"Comput Biol Med"},{"key":"2026031216243009600_ref33","doi-asserted-by":"publisher","first-page":"2398","DOI":"10.1109\/TCBBIO.2025.3541634","article-title":"LLMDTA: improving cold-start prediction in drug-target affinity with biological LLM","volume":"22","author":"Tang","year":"2025","journal-title":"IEEE Trans Comput Biol Bioinform"},{"key":"2026031216243009600_ref34","doi-asserted-by":"crossref","first-page":"124647","DOI":"10.1016\/j.eswa.2024.124647","article-title":"Drug\u2013target binding affinity prediction model based on multi-scale diffusion and interactive learning","volume":"255","author":"Zhu","year":"2024","journal-title":"Expert Syst Appl"},{"key":"2026031216243009600_ref35","first-page":"8071","article-title":"MMFA-DTA: multimodal feature attention fusion network for drug-target affinity prediction for drug repurposing against SARS-CoV-2","volume":"20","author":"Chen","year":"2024","journal-title":"J Chem Theory Comput"},{"key":"2026031216243009600_ref36","doi-asserted-by":"publisher","first-page":"5021","DOI":"10.1038\/s41467-025-59917-6","article-title":"DeepDTAGen: a multitask deep learning framework for drug-target affinity prediction and target-aware drugs generation","volume":"16","author":"Shah","year":"2025","journal-title":"Nat Commun"},{"key":"2026031216243009600_ref37","doi-asserted-by":"crossref","first-page":"142030","DOI":"10.1016\/j.molstruc.2025.142030","article-title":"Synthesis, EGFR and VEGFR-2 inhibitors, crystal structure, DFT analysis, molecular docking study of $\\beta $-enaminonitrile incorporating 1H-benzo [f]-chromene-2-carbonitrile","volume":"1336","author":"Al-Dies","year":"2025","journal-title":"J Mol Struct"},{"key":"2026031216243009600_ref38","doi-asserted-by":"crossref","first-page":"1148171","DOI":"10.3389\/fphar.2023.1148171","article-title":"To explore the effect of kaempferol on non-small cell lung cancer based on network pharmacology and molecular docking","volume":"14","author":"Zhang","year":"2023","journal-title":"Front Pharmacol"},{"key":"2026031216243009600_ref39","doi-asserted-by":"crossref","first-page":"1711","DOI":"10.3390\/cancers16091711","article-title":"The role of phytonutrient kaempferol in the prevention of gastrointestinal cancers: recent trends and future perspectives","volume":"16","author":"Singh","year":"2024","journal-title":"Cancers"},{"key":"2026031216243009600_ref43","doi-asserted-by":"publisher","first-page":"e0155264","DOI":"10.1371\/journal.pone.0155264","article-title":"Kaempferol inhibits pancreatic cancer cell growth and migration through the blockade of EGFR-related pathway in vitro","volume":"11","author":"Lee","year":"2016","journal-title":"PLoS One"},{"key":"2026031216243009600_ref40","doi-asserted-by":"publisher","first-page":"231","DOI":"10.1007\/s10735-023-10127-8","article-title":"EGF-receptor phosphorylation and downstream signaling are activated by genistein during subacute liver damage","volume":"54","author":"Ayala-Calvillo","year":"2023","journal-title":"J Mol Histol"},{"key":"2026031216243009600_ref41","doi-asserted-by":"publisher","first-page":"3678","DOI":"10.18632\/aging.204702","article-title":"Genistein exerts anti-colorectal cancer actions: clinical reports, computational and validated findings","volume":"15","author":"Liu","year":"2023","journal-title":"Aging (Albany NY)"},{"key":"2026031216243009600_ref42","doi-asserted-by":"publisher","first-page":"e0304425","DOI":"10.1371\/journal.pone.0304425","article-title":"In-silico discovery of common molecular signatures for which SARS-CoV-2 infections and lung diseases stimulate each other, and drug repurposing","volume":"19","author":"Alamin","year":"2024","journal-title":"PLoS One"}],"container-title":["Briefings in Bioinformatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/bib\/article-pdf\/27\/2\/bbag112\/67318653\/bbag112.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bib\/article-pdf\/27\/2\/bbag112\/67318653\/bbag112.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,12]],"date-time":"2026-03-12T20:24:43Z","timestamp":1773347083000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/bib\/article\/doi\/10.1093\/bib\/bbag112\/8516647"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,1]]},"references-count":43,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2026,3,1]]}},"URL":"https:\/\/doi.org\/10.1093\/bib\/bbag112","relation":{},"ISSN":["1467-5463","1477-4054"],"issn-type":[{"value":"1467-5463","type":"print"},{"value":"1477-4054","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2026,3]]},"published":{"date-parts":[[2026,3,1]]},"article-number":"bbag112"}}