{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,24]],"date-time":"2026-06-24T13:48:44Z","timestamp":1782308924362,"version":"3.54.5"},"reference-count":24,"publisher":"Oxford University Press (OUP)","issue":"6","license":[{"start":{"date-parts":[[2026,5,25]],"date-time":"2026-05-25T00:00:00Z","timestamp":1779667200000},"content-version":"vor","delay-in-days":4,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"National Science and Technology Major Project of China","award":["2023ZD0120903"],"award-info":[{"award-number":["2023ZD0120903"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62322112"],"award-info":[{"award-number":["62322112"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62402351"],"award-info":[{"award-number":["62402351"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Internal Research Grants of Macao Polytechnic University","award":["RP\/CAI-01\/2025"],"award-info":[{"award-number":["RP\/CAI-01\/2025"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026,6,1]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:sec>\n                    <jats:title>Motivation<\/jats:title>\n                    <jats:p>Accurately identifying compound\u2013protein interactions (CPIs) is critical for accelerating drug discovery. Recent deep learning methods have achieved impressive results, yet they primarily focus on local structures and neighborhood information, often overlooking high-order interaction patterns shared among similar molecules.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>In this paper, we propose HKD-CPI, a high-order knowledge-enhanced inductive framework designed to improve generalization to unseen compound\u2013protein pairs. Specifically, HKD-CPI introduces a molecular graph tokenization mechanism that aligns compound molecular graph features with token embeddings from sequence-pretrained large language models (LLMs), effectively infusing sequence-derived semantics into structural representations. To capture shared interaction patterns among functionally similar biomolecules, we construct a hypergraph-based representation to model high-order relationships between feature-similar compound\/protein groups and their binding partners. Furthermore, a knowledge distillation strategy is further adopted to transfer high-order interaction knowledge from the hypergraph to a lightweight student model, enabling efficient and robust CPI prediction. Extensive experiments demonstrate that HKD-CPI outperforms existing state-of-the-art methods in inductive CPI prediction tasks. In particular, it achieves an average improvement of 4.94% in AUROC and 3.64% in AUPRC over the best-performing baseline across five benchmark datasets.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Availability and implementation<\/jats:title>\n                    <jats:p>Our code and data are available at https:\/\/github.com\/Hezy618\/HKD-CPI.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1093\/bioinformatics\/btag290","type":"journal-article","created":{"date-parts":[[2026,5,19]],"date-time":"2026-05-19T11:33:44Z","timestamp":1779190424000},"source":"Crossref","is-referenced-by-count":0,"title":["HKD-CPI: high-order knowledge distillation enhanced inductive compound-protein interaction prediction"],"prefix":"10.1093","volume":"42","author":[{"given":"Zhongyu","family":"He","sequence":"first","affiliation":[{"name":"School of Informatics, Xiamen University , Xiamen, 361005,","place":["China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9885-1978","authenticated-orcid":false,"given":"Xiangrong","family":"Liu","sequence":"additional","affiliation":[{"name":"School of Informatics, Xiamen University , Xiamen, 361005,","place":["China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yinghui","family":"Jiang","sequence":"additional","affiliation":[{"name":"School of Informatics, Xiamen University , Xiamen, 361005,","place":["China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Junlin","family":"Xu","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Wuhan University of Science and Technology , Wuhan, Hubei 430065,","place":["China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuan","family":"Lin","sequence":"additional","affiliation":[{"name":"School of Economics, Innovation, and Technology, Kristiania University College , Bergen 5022,","place":["Norway"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8113-9367","authenticated-orcid":false,"given":"Shuting","family":"Jin","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Wuhan University of Science and Technology , Wuhan, Hubei 430065,","place":["China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1444-190X","authenticated-orcid":false,"given":"Leyi","family":"Wei","sequence":"additional","affiliation":[{"name":"Centre for Artificial Intelligence driven Drug Discovery, Faculty of Applied Science, Macao Polytechnic University , Macao SAR 999078,","place":["China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Youyu","family":"Wang","sequence":"additional","affiliation":[{"name":"Department of Thoracic Surgery, Sichuan Academy of Medical Sciences and Sichuan Provincial People\u2019s Hospital, University of Electronic Science and Technology of China , Chengdu, Sichuan Province 610072,","place":["China"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"286","published-online":{"date-parts":[[2026,5,21]]},"reference":[{"key":"2026062409130781800_btag290-B1","doi-asserted-by":"crossref","first-page":"126","DOI":"10.1038\/s42256-022-00605-1","article-title":"Interpretable bilinear attention network with domain adaptation improves drug\u2013target prediction","volume":"5","author":"Bai","year":"2023","journal-title":"Nat Mach Intell"},{"key":"2026062409130781800_btag290-B2","doi-asserted-by":"crossref","first-page":"e1005929","DOI":"10.1371\/journal.pcbi.1005929","article-title":"Representability of algebraic topology for biomolecules in machine learning based scoring and virtual screening","volume":"14","author":"Cang","year":"2018","journal-title":"PLoS Comput. Biol"},{"key":"2026062409130781800_btag290-B3","doi-asserted-by":"publisher","author":"Chithrananda","year":"2020","DOI":"10.48550\/arXiv.2010.09885"},{"key":"2026062409130781800_btag290-B4","doi-asserted-by":"publisher","first-page":"1350","DOI":"10.1016\/j.drudis.2022.02.023","article-title":"Compound-protein interaction prediction by deep learning: databases, descriptors and models","volume":"27","author":"Du","year":"2022","journal-title":"Drug Discov Today"},{"key":"2026062409130781800_btag290-B5","doi-asserted-by":"publisher","first-page":"3558","DOI":"10.1609\/aaai.v33i01.33013558","article-title":"Hypergraph neural networks","volume":"33","author":"Feng","year":"2019","journal-title":"AAAI"},{"key":"2026062409130781800_btag290-B6","doi-asserted-by":"crossref","first-page":"D1045","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":"2026062409130781800_btag290-B7","doi-asserted-by":"publisher","first-page":"2541","DOI":"10.1038\/s41467-025-57536-9","article-title":"GraphBAN: an inductive graph-based approach for enhanced prediction of compound-protein interactions","volume":"16","author":"Hadipour","year":"2025","journal-title":"Nat Commun"},{"key":"2026062409130781800_btag290-B8","doi-asserted-by":"publisher","first-page":"17368","DOI":"10.1609\/aaai.v39i16.33909","article-title":"R-DTI: drug target interaction prediction based on second-order relevance exploration","volume":"39","author":"Hua","year":"2025","journal-title":"AAAI"},{"key":"2026062409130781800_btag290-B9","doi-asserted-by":"crossref","first-page":"i221","DOI":"10.1093\/bioinformatics\/btv256","article-title":"Improving compound-protein interaction prediction by building up highly credible negative samples","volume":"31","author":"Liu","year":"2015","journal-title":"Bioinformatics"},{"key":"2026062409130781800_btag290-B10","author":"Loshchilov"},{"key":"2026062409130781800_btag290-B11","first-page":"4878","article-title":"Graphformercpi: rethinking graph transformer for compound\u2013protein interaction and drug\u2013target binding affinity prediction with spherical message passing","volume":"63","author":"Ma","year":"2023","journal-title":"J Chem Inf Model"},{"key":"2026062409130781800_btag290-B12","volume-title":"Findings of the Association for Computational Linguistics","year":"2025"},{"key":"2026062409130781800_btag290-B13","author":"Murakumo","year":"2023"},{"key":"2026062409130781800_btag290-B14","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":"2026062409130781800_btag290-B15","doi-asserted-by":"publisher","first-page":"e2016239118","DOI":"10.1073\/pnas.2016239118","article-title":"Biological structure and function emerge from scaling unsupervised learning to 250 million protein sequences","volume":"118","author":"Rives","year":"2021","journal-title":"Proc Natl Acad Sci USA"},{"key":"2026062409130781800_btag290-B16","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":"2026062409130781800_btag290-B17","doi-asserted-by":"publisher","first-page":"e4594","DOI":"10.1002\/pro.4594","article-title":"PrePCI: a structure- and chemical similarity-informed database of predicted protein compound interactions","volume":"32","author":"Trudeau","year":"2023","journal-title":"Protein Sci"},{"key":"2026062409130781800_btag290-B18","author":"Wang","year":"2024"},{"key":"2026062409130781800_btag290-B19","doi-asserted-by":"publisher","first-page":"310","DOI":"10.1609\/aaai.v38i1.27784","article-title":"PSC-CPI: multi-scale protein sequence-structure contrasting for efficient and generalizable compound-protein interaction prediction","volume":"38","author":"Wu","year":"2024","journal-title":"AAAI"},{"key":"2026062409130781800_btag290-B20","doi-asserted-by":"publisher","first-page":"611","DOI":"10.1016\/j.str.2024.02.004","article-title":"Heterogeneous sampled subgraph neural networks with knowledge distillation to enhance double-blind compound-protein interaction prediction","volume":"32","author":"Xia","year":"2024","journal-title":"Structure"},{"key":"2026062409130781800_btag290-B21","doi-asserted-by":"publisher","first-page":"6107","DOI":"10.24963\/ijcai.2024\/675","author":"Xiang","year":"2024"},{"key":"2026062409130781800_btag290-B22","doi-asserted-by":"publisher","first-page":"108756","DOI":"10.1016\/j.isci.2023.108756","article-title":"FOTF-CPI: a compound-protein interaction prediction transformer based on the fusion of optimal transport fragments","volume":"27","author":"Yin","year":"2024","journal-title":"iScience"},{"key":"2026062409130781800_btag290-B23","doi-asserted-by":"publisher","first-page":"1565","DOI":"10.1109\/TCBB.2024.3404889","article-title":"ParaCPI: a parallel graph convolutional network for compound-protein interaction prediction","volume":"21","author":"Zhang","year":"2024","journal-title":"IEEE\/ACM Trans Comput Biol Bioinform"},{"key":"2026062409130781800_btag290-B24","article-title":"BioSNAP datasets: Stanford Biomedical Network Dataset Collection","volume-title":"Stanford Biomedical Network Dataset Collection","author":"Zitnik","year":"2018"}],"container-title":["Bioinformatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/bioinformatics\/advance-article-pdf\/doi\/10.1093\/bioinformatics\/btag290\/68380108\/btag290.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/42\/6\/btag290\/68380108\/btag290.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/42\/6\/btag290\/68380108\/btag290.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,24]],"date-time":"2026-06-24T13:13:14Z","timestamp":1782306794000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article\/doi\/10.1093\/bioinformatics\/btag290\/8692432"}},"subtitle":[],"editor":[{"given":"Jianlin","family":"Cheng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"editor"}]}],"short-title":[],"issued":{"date-parts":[[2026,5,21]]},"references-count":24,"journal-issue":{"issue":"6","published-print":{"date-parts":[[2026,6,1]]}},"URL":"https:\/\/doi.org\/10.1093\/bioinformatics\/btag290","relation":{},"ISSN":["1367-4803","1367-4811"],"issn-type":[{"value":"1367-4803","type":"print"},{"value":"1367-4811","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2026,6]]},"published":{"date-parts":[[2026,5,21]]},"article-number":"btag290"}}