{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,25]],"date-time":"2026-05-25T15:04:23Z","timestamp":1779721463177,"version":"3.53.1"},"reference-count":51,"publisher":"Oxford University Press (OUP)","issue":"3","license":[{"start":{"date-parts":[[2026,5,25]],"date-time":"2026-05-25T00:00:00Z","timestamp":1779667200000},"content-version":"vor","delay-in-days":24,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62272192"],"award-info":[{"award-number":["62272192"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026,5,4]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>Protein phosphorylation governs cellular signaling, making accurate identification of kinase-specific sites essential for understanding regulatory and disease mechanisms. Although computational approaches have shown promise in inferring kinase specificity, most existing methods primarily rely on local sequence patterns and remain limited in their ability to capture broader contextual information. More critically, experimentally validated kinase\u2013substrate data are inherently scarce and highly imbalanced across kinase groups, substantially restricting the generalization performance of purely discriminative models, especially for underrepresented kinases. To address these challenges, we propose KSDiffusion, a unified framework for kinase-specific phosphorylation site prediction explicitly designed for data-limited and imbalanced regimes. KSDiffusion integrates a protein language model with task-aware conditional diffusion-based generative modeling. Specifically, an ESM-2-based encoder is employed to extract context-aware peptide representations enriched with evolutionary and structural information, while supervised contrastive learning further enhances kinase-specific discriminability in the embedding space. To alleviate data scarcity for rare kinase groups, we introduce a conditional diffusion model, termed KS-DiT, which generates biologically plausible and kinase-consistent synthetic representations that directly support downstream prediction. Comprehensive experiments across kinase groups spanning low-, medium-, and large-data regimes demonstrate that KSDiffusion consistently outperforms representative baseline methods. In particular, substantial improvements are achieved for data-scarce kinase groups, with AUC gains of up to $\\sim $15%, while maintaining competitive performance when sufficient training data are available. These results underscore the regime-dependent effectiveness of conditional diffusion-based augmentation and highlight the value of integrating protein language models with task-aware generative modeling for robust kinase-specific phosphorylation site prediction under realistic data constraints.<\/jats:p>","DOI":"10.1093\/bib\/bbag257","type":"journal-article","created":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T11:17:22Z","timestamp":1777893442000},"source":"Crossref","is-referenced-by-count":0,"title":["KSDiffusion: conditional diffusion for kinase-specific phosphorylation site prediction under data-limited and imbalanced regimes"],"prefix":"10.1093","volume":"27","author":[{"given":"Shi","family":"Qiu","sequence":"first","affiliation":[{"name":"College of Computer Science and Technology, Jilin University , 2699 Qianjin Street, Chaoyang District, Changchun 130012,","place":["China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chunguo","family":"Wu","sequence":"additional","affiliation":[{"name":"College of Computer Science and Technology, Jilin University , 2699 Qianjin Street, Chaoyang District, Changchun 130012,","place":["China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuxiang","family":"Ma","sequence":"additional","affiliation":[{"name":"College of Computer Science and Technology, Jilin University , 2699 Qianjin Street, Chaoyang District, Changchun 130012,","place":["China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Songye","family":"Gao","sequence":"additional","affiliation":[{"name":"College of Computer Science and Technology, Jilin University , 2699 Qianjin Street, Chaoyang District, Changchun 130012,","place":["China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Limin","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Big Data and Artificial Intelligence, Guangdong University of Finance and Economics , 21 Luntou Road, Haizhu District, Guangzhou 510320,","place":["China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yanchun","family":"Liang","sequence":"additional","affiliation":[{"name":"School of Computer Science, Zhuhai College of Science and Technology , Anji East Road, Jinwan District, Zhuhai 519041,","place":["China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaohu","family":"Shi","sequence":"additional","affiliation":[{"name":"College of Computer Science and Technology, Jilin University , 2699 Qianjin Street, Chaoyang District, Changchun 130012,","place":["China"]},{"name":"School of Big Data and Artificial Intelligence, Guangdong University of Finance and Economics , 21 Luntou Road, Haizhu District, Guangzhou 510320,","place":["China"]},{"name":"School of Computer Science, Zhuhai College of Science and Technology , Anji East Road, Jinwan District, Zhuhai 519041,","place":["China"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"286","published-online":{"date-parts":[[2026,5,25]]},"reference":[{"key":"2026052510364277800_ref1","doi-asserted-by":"crossref","first-page":"327","DOI":"10.1016\/j.tibs.2018.02.010","article-title":"The cellular response to transcription-blocking DNA damage","volume":"43","author":"Gregersen","year":"2018","journal-title":"Trends Biochem Sci"},{"key":"2026052510364277800_ref2","doi-asserted-by":"publisher","first-page":"1912","DOI":"10.1126\/science.1075762","article-title":"The protein kinase complement of the human genome","volume":"298","author":"Manning","year":"2002","journal-title":"Science"},{"key":"2026052510364277800_ref3","doi-asserted-by":"crossref","first-page":"D261","DOI":"10.1093\/nar\/gkr1122","article-title":"PhosphoSitePlus: a comprehensive resource for investigating the structure and function of experimentally determined post-translational modifications in man and mouse","volume":"40","author":"Hornbeck","year":"2012","journal-title":"Nucleic Acids Res"},{"key":"2026052510364277800_ref4","doi-asserted-by":"crossref","first-page":"5691","DOI":"10.1039\/D1CS00991E","article-title":"Dissecting the role of protein phosphorylation: a chemical biology toolbox","volume":"51","author":"Bilbrough","year":"2022","journal-title":"Chem Soc Rev"},{"key":"2026052510364277800_ref5","doi-asserted-by":"publisher","first-page":"189","DOI":"10.1016\/j.tcb.2019.12.009","article-title":"RIPK1 kinase-dependent death: a symphony of phosphorylation events","volume":"30","author":"Delanghe","year":"2020","journal-title":"Trends Cell Biol"},{"key":"2026052510364277800_ref6","doi-asserted-by":"crossref","first-page":"597","DOI":"10.1016\/j.gpb.2020.09.003","article-title":"Phosphoproteomics reveals the AMPK substrate network in response to DNA damage and histone acetylation","volume":"20","author":"Jiang","year":"2022","journal-title":"Genomics Proteomics Bioinformatics"},{"key":"2026052510364277800_ref7","doi-asserted-by":"publisher","volume":"40","journal-title":"EBioMedicine","DOI":"10.1016\/j.ebiom.2018.12.039"},{"key":"2026052510364277800_ref8","doi-asserted-by":"publisher","first-page":"1211","DOI":"10.1039\/C0CS00020E","article-title":"Chemical approaches towards unravelling kinase-mediated signalling pathways","volume":"40","author":"Hodgson","year":"2011","journal-title":"Chem Soc Rev"},{"key":"2026052510364277800_ref9","doi-asserted-by":"publisher","first-page":"685","DOI":"10.1016\/j.tibs.2018.06.008","article-title":"Control of inflammasome activation by phosphorylation","volume":"43","author":"Gong","year":"2018","journal-title":"Trends Biochem Sci"},{"key":"2026052510364277800_ref10","doi-asserted-by":"publisher","first-page":"309","DOI":"10.1016\/j.apsb.2020.09.007","article-title":"Phosphorylation regulates cullin-based ubiquitination in tumorigenesis","volume":"11","author":"Chen","year":"2021","journal-title":"Acta Pharm Sin B"},{"key":"2026052510364277800_ref11","doi-asserted-by":"publisher","first-page":"133","DOI":"10.1016\/j.sbi.2017.12.008","article-title":"Evolution, dynamics and dysregulation of kinase signalling","volume":"48","author":"Ochoa","year":"2018","journal-title":"Curr Opin Struct Biol"},{"key":"2026052510364277800_ref12","doi-asserted-by":"publisher","volume":"7","journal-title":"PLoS One","DOI":"10.1371\/journal.pone.0034370"},{"key":"2026052510364277800_ref13","doi-asserted-by":"publisher","first-page":"D460","DOI":"10.1093\/nar\/gkab1080","article-title":"dbAMP 2.0: updated resource for antimicrobial peptides with an enhanced scanning method for genomic and proteomic data","volume":"50","author":"Jhong","year":"2022","journal-title":"Nucleic Acids Res"},{"key":"2026052510364277800_ref14","doi-asserted-by":"publisher","first-page":"286","DOI":"10.1186\/s12859-021-03965-4","article-title":"Incorporating support vector machine with sequential minimal optimization to identify anticancer peptides","volume":"22","author":"Yu","year":"2021","journal-title":"BMC Bioinformatics"},{"key":"2026052510364277800_ref15","doi-asserted-by":"publisher","first-page":"2386","DOI":"10.1093\/bioinformatics\/bty977","article-title":"Capsule network for protein post-translational modification site prediction","volume":"35","author":"Wang","year":"2019","journal-title":"Bioinformatics"},{"key":"2026052510364277800_ref16","doi-asserted-by":"publisher","first-page":"1443","DOI":"10.1016\/j.bbrc.2004.11.001","article-title":"GPS: a novel group-based phosphorylation predicting and scoring method","volume":"325","author":"Zhou","year":"2004","journal-title":"Biochem Biophys Res Commun"},{"key":"2026052510364277800_ref17","doi-asserted-by":"publisher","first-page":"6862","DOI":"10.1038\/s41598-017-07199-4","article-title":"Phosphopredict: a bioinformatics tool for prediction of human kinase-specific phosphorylation substrates and sites by integrating heterogeneous feature selection","volume":"7","author":"Song","year":"2017","journal-title":"Sci Rep"},{"key":"2026052510364277800_ref18","doi-asserted-by":"publisher","first-page":"637","DOI":"10.1038\/s41586-023-06510-w","article-title":"Clustering predicted structures at the scale of the known protein universe","volume":"622","author":"Barrio-Hernandez","year":"2023","journal-title":"Nature"},{"key":"2026052510364277800_ref19","doi-asserted-by":"publisher","volume":"24","journal-title":"Brief Bioinform","DOI":"10.1093\/bib\/bbac599"},{"key":"2026052510364277800_ref20","volume-title":"Computational Prediction of Kinase-Substrate Interactions with Scansite 3 and the Enrichment of Well-Known Protein-Protein Interaction Networks with Novel and Relevant Interactors."},{"key":"2026052510364277800_ref21","doi-asserted-by":"crossref","first-page":"3635","DOI":"10.1093\/nar\/gkg584","article-title":"Scansite 2.0: proteome-wide prediction of cell signaling interactions using short sequence motifs","volume":"31","author":"Obenauer","year":"2003","journal-title":"Nucleic Acids Res"},{"key":"2026052510364277800_ref22","doi-asserted-by":"crossref","first-page":"D1015","DOI":"10.1093\/nar\/gkm812","article-title":"Phosphat: a database of phosphorylation sites in Arabidopsis thaliana and a plant-specific phosphorylation site predictor","volume":"36","author":"Heazlewood","year":"2007","journal-title":"Nucleic Acids Res"},{"key":"2026052510364277800_ref23","doi-asserted-by":"publisher","first-page":"116","DOI":"10.1002\/pmic.200800285","article-title":"NetPhosBac - a predictor for Ser\/Thr phosphorylation sites in bacterial proteins","volume":"9","author":"Miller","year":"2009","journal-title":"Proteomics"},{"key":"2026052510364277800_ref24","doi-asserted-by":"crossref","first-page":"1598","DOI":"10.1074\/mcp.M700574-MCP200","article-title":"GPS 2.0, a tool to predict kinase-specific phosphorylation sites in hierarchy","volume":"7","author":"Xue","year":"2008","journal-title":"Mol Cell Proteomics"},{"key":"2026052510364277800_ref25","doi-asserted-by":"publisher","first-page":"bbad090","DOI":"10.1093\/bib\/bbad090","article-title":"Protein phosphorylation database and prediction tools","volume":"24","author":"Zhao","year":"2023","journal-title":"Brief Bioinform"},{"key":"2026052510364277800_ref26","doi-asserted-by":"crossref","first-page":"W226","DOI":"10.1093\/nar\/gki471","article-title":"KinasePhos: a web tool for identifying protein kinase-specific phosphorylation sites","volume":"33","author":"Huang","year":"2005","journal-title":"Nucleic Acids Res"},{"key":"2026052510364277800_ref27","doi-asserted-by":"publisher","first-page":"W588","DOI":"10.1093\/nar\/gkm322","article-title":"KinasePhos 2.0: a web server for identifying protein kinase-specific phosphorylation sites based on sequences and coupling patterns","volume":"35","author":"Wong","year":"2007","journal-title":"Nucleic Acids Res"},{"key":"2026052510364277800_ref28","doi-asserted-by":"crossref","first-page":"228","DOI":"10.1016\/j.gpb.2022.06.004","article-title":"KinasePhos 3.0: redesign and expansion of the prediction on kinase-specific phosphorylation sites","volume":"21","author":"Ma","year":"2023","journal-title":"Genomics Proteomics Bioinformatics"},{"key":"2026052510364277800_ref29","doi-asserted-by":"publisher","first-page":"W243","DOI":"10.1093\/nar\/gkad383","article-title":"GPS 6.0: an updated server for prediction of kinase-specific phosphorylation sites in proteins","volume":"51","author":"Chen","year":"2023","journal-title":"Nucleic Acids Res"},{"key":"2026052510364277800_ref30","doi-asserted-by":"publisher","first-page":"btae033","DOI":"10.1093\/bioinformatics\/btae033","article-title":"Using explainable machine learning to uncover the kinase\u2013substrate interaction landscape","volume":"40","author":"Zhou","year":"2024","journal-title":"Bioinformatics"},{"key":"2026052510364277800_ref31","doi-asserted-by":"publisher","first-page":"btad046","DOI":"10.1093\/bioinformatics\/btad046","article-title":"Phosformer: an explainable transformer model for protein kinase-specific phosphorylation predictions","volume":"39","author":"Zhou","year":"2023","journal-title":"Bioinformatics"},{"key":"2026052510364277800_ref32","doi-asserted-by":"publisher","first-page":"D433","DOI":"10.1093\/nar\/gky1159","article-title":"15 years of phosphositeplus$\\circledR $: integrating post-translationally modified sites, disease variants and isoforms","volume":"47","author":"Hornbeck","year":"2019","journal-title":"Nucleic Acids Res"},{"key":"2026052510364277800_ref33","doi-asserted-by":"publisher","first-page":"3150","DOI":"10.1093\/bioinformatics\/bts565","article-title":"CD-HIT: accelerated for clustering the next-generation sequencing data","volume":"28","author":"Limin","year":"2012","journal-title":"Bioinformatics"},{"key":"2026052510364277800_ref34","volume-title":"UniProtKB\/Swiss-Prot, the Manually Annotated Section of the UniProt KnowledgeBase: How to Use the Entry View."},{"key":"2026052510364277800_ref35","volume-title":"UniProtKB\/Swiss-Prot: the Manually Annotated Section of the UniProt KnowledgeBase."},{"key":"2026052510364277800_ref36","doi-asserted-by":"publisher","first-page":"e28782","DOI":"10.1371\/journal.pone.0028782","article-title":"ProKinO: an ontology for integrative analysis of protein kinases in cancer","volume":"6","author":"Gosal","year":"2011","journal-title":"PLoS One"},{"key":"2026052510364277800_ref37","doi-asserted-by":"publisher","first-page":"383","DOI":"10.1146\/annurev-orgpsych-032414-111335","article-title":"ESM 2.0: state of the art and future potential of experience sampling methods in organizational research","volume":"2","author":"Beal","year":"2015","journal-title":"Annu Rev Organ Psychol Organ Behav"},{"key":"2026052510364277800_ref38","doi-asserted-by":"publisher","first-page":"bbad534","DOI":"10.1093\/bib\/bbad534","article-title":"Interpretable feature extraction and dimensionality reduction in ESM2 for protein localization prediction","volume":"25","author":"Luo","year":"2024","journal-title":"Brief Bioinform"},{"key":"2026052510364277800_ref39","doi-asserted-by":"publisher","volume-title":"Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics","DOI":"10.18653\/v1\/2020.acl-main.240"},{"key":"2026052510364277800_ref40","doi-asserted-by":"publisher","journal-title":"Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing","DOI":"10.18653\/v1\/2021.emnlp-main.230"},{"key":"2026052510364277800_ref41","first-page":"18661","article-title":"Supervised contrastive learning","volume":"33","author":"Khosla","year":"2020","journal-title":"Adv Neural Inf Proces Syst"},{"key":"2026052510364277800_ref42","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume":"33","author":"Ho","year":"2020","journal-title":"Adv Neural Inf Proces Syst"},{"key":"2026052510364277800_ref43","volume-title":"Proceedings of the 38th International Conference on Machine Learning"},{"key":"2026052510364277800_ref44","doi-asserted-by":"publisher","journal-title":"Proceedings of the 2021 IEEE\/CVF International Conference on Computer Vision","DOI":"10.1109\/ICCV48922.2021.01410"},{"key":"2026052510364277800_ref45","first-page":"17383","article-title":"Semi-implicit denoising diffusion models (SIDDMS)","volume":"36","author":"Gong","year":"2023","journal-title":"Adv Neural Inf Proces Syst"},{"key":"2026052510364277800_ref46","doi-asserted-by":"publisher","first-page":"77","DOI":"10.1023\/A:1019956318069","article-title":"A perspective view and survey of meta-learning","volume":"18","author":"Vilalta","year":"2002","journal-title":"Artif Intell Rev"},{"key":"2026052510364277800_ref47","doi-asserted-by":"publisher","volume":"44","journal-title":"IEEE Trans Pattern Anal Mach Intell","DOI":"10.1109\/TPAMI.2021.3079209"},{"key":"2026052510364277800_ref48","doi-asserted-by":"publisher","volume-title":"Proceedings of the 2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition","DOI":"10.1109\/CVPR42600.2020.00078"},{"key":"2026052510364277800_ref49","first-page":"4356","article-title":"How should pre-trained language models be fine-tuned towards adversarial robustness?","volume":"34","author":"Dong","year":"2021","journal-title":"Adv Neural Inf Proces Syst"},{"key":"2026052510364277800_ref50","doi-asserted-by":"crossref","first-page":"e1637","DOI":"10.1002\/wcms.1637","article-title":"Efficient and enhanced sampling of drug-like chemical space for virtual screening and molecular design using modern machine learning methods","volume":"13","author":"Goel","year":"2022","journal-title":"Wiley Interdiscip Rev Comput Mol Sci"},{"key":"2026052510364277800_ref51","doi-asserted-by":"crossref","first-page":"381","DOI":"10.1111\/j.1547-5069.1999.tb00524.x","article-title":"A classification scheme for outcome indicators","volume":"31","author":"Jennings","year":"1999","journal-title":"J Nurs Scholarsh"}],"container-title":["Briefings in Bioinformatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/bib\/article-pdf\/27\/3\/bbag257\/68381917\/bbag257.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bib\/article-pdf\/27\/3\/bbag257\/68381917\/bbag257.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,25]],"date-time":"2026-05-25T14:36:52Z","timestamp":1779719812000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/bib\/article\/doi\/10.1093\/bib\/bbag257\/8692747"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,5]]},"references-count":51,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2026,5,4]]}},"URL":"https:\/\/doi.org\/10.1093\/bib\/bbag257","relation":{},"ISSN":["1467-5463","1477-4054"],"issn-type":[{"value":"1467-5463","type":"print"},{"value":"1477-4054","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2026,5]]},"published":{"date-parts":[[2026,5]]},"article-number":"bbag257"}}