{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,6]],"date-time":"2026-07-06T06:15:07Z","timestamp":1783318507839,"version":"3.54.6"},"reference-count":48,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2026,7,6]],"date-time":"2026-07-06T00:00:00Z","timestamp":1783296000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100001691","name":"Japan Society for the Promotion of Science","doi-asserted-by":"publisher","award":["JP23H03411"],"award-info":[{"award-number":["JP23H03411"]}],"id":[{"id":"10.13039\/501100001691","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Chem."],"abstract":"<jats:sec>\n                    <jats:title>Motivation<\/jats:title>\n                    <jats:p>Accurate drug\u2013target interaction (DTI) prediction remains difficult for underexplored drugs and targets, especially when available interaction evidence is sparse. Existing approaches often focus either on pairwise molecular representations or on heterogeneous biomedical graph topology, making it difficult to effectively integrate structure-derived representations with multi-relational contextual evidence.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Result<\/jats:title>\n                    <jats:p>We propose ColdstartMHDTI, a two-stage framework for heterogeneous-graph-based DTI prediction that integrates sequence-derived structural representations with local and global relational information. Specifically, drug SMILES and target sequences are encoded by pretrained transformer models, while one-hop heterogeneous relations are captured through self-supervised DistMult embeddings. These representations are then fused through a meta-path-guided module that models ordered meta-path instances and aggregates them with cross-attention for interaction scoring. Across two benchmark datasets, ColdstartMHDTI shows consistent improvements under warm-start and entity-disjoint settings, with particularly strong performance for underexplored drugs and targets. It also remains robust under more imbalanced evaluation protocols with 1:5 and 1:10 positive-to-negative ratios. In addition to standard classification performance, ColdstartMHDTI supports candidate prioritization for downstream screening and evidence-guided hypothesis generation. Case studies on ESR1, EGFR, and Parkinson\u2019s disease further demonstrate its practical utility, with the Parkinson\u2019s disease analysis additionally highlighting strong per-drug target ranking performance.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.3389\/fchem.2026.1846850","type":"journal-article","created":{"date-parts":[[2026,7,6]],"date-time":"2026-07-06T05:36:57Z","timestamp":1783316217000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["ColdstartMHDTI: integrating biomolecular pretraining and attention-based heterogeneous graph learning for drug\u2013target interaction prediction"],"prefix":"10.3389","volume":"14","author":[{"given":"Hongyang","family":"Yang","sequence":"first","affiliation":[{"name":"Department of Computer Science, University of Tsukuba","place":["Tsukuba, Japan"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiucai","family":"Ye","sequence":"additional","affiliation":[{"name":"Department of Computer Science, University of Tsukuba","place":["Tsukuba, Japan"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hui","family":"Han","sequence":"additional","affiliation":[{"name":"Department of Computer Science, University of Tsukuba","place":["Tsukuba, Japan"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tetsuya","family":"Sakurai","sequence":"additional","affiliation":[{"name":"Department of Computer Science, University of Tsukuba","place":["Tsukuba, Japan"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2026,7,6]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2209.01712","article-title":"ChemBERTa-2: towards chemical foundation models","author":"Ahmad","year":"2022","journal-title":"Preprint at arXiv"},{"key":"B2","doi-asserted-by":"publisher","first-page":"btae533","DOI":"10.1093\/bioinformatics\/btae533","article-title":"DTI-LM: language model powered drug-target interaction prediction","volume":"40","author":"Ahmed","year":"2024","journal-title":"Bioinformatics"},{"key":"B3","doi-asserted-by":"publisher","first-page":"2141","DOI":"10.1002\/mds.29637","article-title":"What is the parkinson pandemic?","volume":"38","author":"Albin","year":"2023","journal-title":"Mov. Disord."},{"key":"B4","doi-asserted-by":"publisher","first-page":"126","DOI":"10.1038\/s42256-022-00605-1","article-title":"Interpretable bilinear attention network with domain adaptation improves drug-target prediction","volume":"5","author":"Bai","year":"2023","journal-title":"Nat. Mach. Intell."},{"key":"B5","doi-asserted-by":"publisher","first-page":"85","DOI":"10.1186\/s13058-021-01462-3","article-title":"ESR1 mutation as an emerging clinical biomarker in metastatic hormone receptor-positive breast cancer","volume":"23","author":"Brett","year":"2021","journal-title":"Breast Cancer Res."},{"key":"B6","doi-asserted-by":"publisher","first-page":"366","DOI":"10.1038\/s41592-021-01101-x","article-title":"Sensitive protein alignments at tree-of-life scale using DIAMOND","volume":"18","author":"Buchfink","year":"2021","journal-title":"Nat. Methods."},{"key":"B7","doi-asserted-by":"publisher","first-page":"102824","DOI":"10.1016\/j.ctrv.2024.102824","article-title":"Advancements in fourth-generation EGFR TKIs in EGFR-mutant NSCLC: bridging biological insights and therapeutic development","volume":"130","author":"Corvaja","year":"2024","journal-title":"Cancer Treat. Rev."},{"key":"B8","doi-asserted-by":"publisher","first-page":"1308","DOI":"10.1158\/1541-7786.MCR-07-2159","article-title":"Mebendazole induces apoptosis via Bcl-2 inactivation in chemoresistant melanoma cells","volume":"6","author":"Doudican","year":"2008","journal-title":"Mol. Cancer Res."},{"key":"B9","article-title":"A Generalization of Transformer Networks to Graphs","author":"Dwivedi","year":"2021"},{"key":"B10","doi-asserted-by":"publisher","first-page":"3891","DOI":"10.1021\/acs.jcim.1c00203","article-title":"AutoDock vina 1.2.0: new docking methods, expanded force field, and python bindings","volume":"61","author":"Eberhardt","year":"2021","journal-title":"J. Chem. Inf. Model."},{"key":"B11","doi-asserted-by":"crossref","first-page":"2331","DOI":"10.1145\/3366423.3380297","article-title":"MAGNN: metapath aggregated graph neural network for heterogeneous graph embedding","volume-title":"Proceedings of the Web Conference 2020","author":"Fu","year":"2020"},{"key":"B12","doi-asserted-by":"publisher","first-page":"102527","DOI":"10.1016\/j.sbi.2023.102527","article-title":"Chemical language models for de novo drug design: challenges and opportunities","volume":"79","author":"Grisoni","year":"2023","journal-title":"Curr. Opin. Struct. Biol."},{"key":"B13","doi-asserted-by":"publisher","first-page":"549","DOI":"10.1016\/j.bmcl.2018.12.065","article-title":"Shape-based virtual screen for the discovery of novel CDK8 inhibitor chemotypes","volume":"29","author":"He","year":"2019","journal-title":"Bioorg. Med. Chem. Lett."},{"key":"B14","doi-asserted-by":"publisher","first-page":"e26726","DOI":"10.7554\/eLife.26726","article-title":"Systematic integration of biomedical knowledge prioritizes drugs for repurposing","volume":"6","author":"Himmelstein","year":"2017","journal-title":"eLife"},{"key":"B15","doi-asserted-by":"publisher","first-page":"682","DOI":"10.1038\/nchembio.118","article-title":"Network pharmacology: the next paradigm in drug discovery","volume":"4","author":"Hopkins","year":"2008","journal-title":"Nat. Chem. Biol."},{"key":"B16","doi-asserted-by":"publisher","first-page":"830","DOI":"10.1093\/bioinformatics\/btaa880","article-title":"MolTrans: molecular interaction transformer for drug-target interaction prediction","volume":"37","author":"Huang","year":"2021","journal-title":"Bioinformatics"},{"key":"B17","doi-asserted-by":"publisher","first-page":"108181","DOI":"10.1016\/j.compbiomed.2024.108181","article-title":"Multi-party collaborative drug discovery via federated learning","volume":"171","author":"Huang","year":"2024","journal-title":"Comput. Biol. Med."},{"key":"B18","doi-asserted-by":"publisher","first-page":"1937","DOI":"10.1001\/jama.299.16.1937","article-title":"Efficacy of current drugs against soil-transmitted helminth infections: systematic review and meta-analysis","volume":"299","author":"Keiser","year":"2008","journal-title":"JAMA"},{"key":"B19","doi-asserted-by":"publisher","first-page":"583","DOI":"10.1080\/01621459.1952.10483441","article-title":"Use of ranks in one-criterion variance analysis","volume":"47","author":"Kruskal","year":"1952","journal-title":"J. Am. Stat. Assoc."},{"key":"B20","doi-asserted-by":"publisher","first-page":"655","DOI":"10.1109\/TCBB.2021.3088614","article-title":"IMCHGAN: inductive matrix completion with heterogeneous graph attention networks for drug-target interactions prediction","volume":"19","author":"Li","year":"2022","journal-title":"IEEE\/ACM Trans. Comput. Biol. Bioinform."},{"key":"B21","doi-asserted-by":"publisher","first-page":"bbac578","DOI":"10.1093\/bib\/bbac578","article-title":"Metapath-aggregated heterogeneous graph neural network for drug-target interaction prediction","volume":"24","author":"Li","year":"2023","journal-title":"Brief. Bioinform."},{"key":"B22","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","year":"2023","journal-title":"Science"},{"key":"B23","doi-asserted-by":"publisher","first-page":"W159","DOI":"10.1093\/nar\/gkac394","article-title":"CB-Dock2: improved protein-ligand blind docking by integrating cavity detection, docking and homologous template fitting","volume":"50","author":"Liu","year":"2022","journal-title":"Nucleic Acids Res."},{"key":"B24","doi-asserted-by":"publisher","first-page":"4174","DOI":"10.1039\/d2sc06860e","article-title":"Discovery of a photoactivatable dimerized STING agonist based on the benzo[b]selenophene scaffold","volume":"14","author":"Liu","year":"2023","journal-title":"Chem. Sci."},{"key":"B25","doi-asserted-by":"publisher","first-page":"573","DOI":"10.1038\/s41467-017-00680-8","article-title":"A network integration approach for drug-target interaction prediction and computational drug repositioning from heterogeneous information","volume":"8","author":"Luo","year":"2017","journal-title":"Nat. Commun."},{"key":"B26","first-page":"2963","article-title":"Mebendazole elicits a potent antitumor effect on human cancer cell lines both in vitro and in vivo","volume":"8","author":"Mukhopadhyay","year":"2002","journal-title":"Clin. Cancer Res."},{"key":"B27","doi-asserted-by":"publisher","first-page":"1140","DOI":"10.1093\/bioinformatics\/btaa921","article-title":"GraphDTA: predicting drug-target binding affinity with graph neural networks","volume":"37","author":"Nguyen","year":"2021","journal-title":"Bioinformatics"},{"key":"B28","doi-asserted-by":"publisher","first-page":"988","DOI":"10.1021\/acs.jmedchem.3c01093","article-title":"Discovery of novel aminobutanoic acid-based ASCT2 inhibitors for the treatment of non-small-cell lung cancer","volume":"67","author":"Qin","year":"2024","journal-title":"J. Med. Chem."},{"key":"B29","article-title":"A review of large language models and autonomous agents in chemistry","author":"Ramos","year":"2024"},{"key":"B30","doi-asserted-by":"publisher","first-page":"8339","DOI":"10.1021\/acs.jmedchem.3c00136","article-title":"Targeting the estrogen receptor for the treatment of breast cancer: recent advances and challenges","volume":"66","author":"Rej","year":"2023","journal-title":"J. Med. Chem."},{"key":"B31","doi-asserted-by":"publisher","first-page":"742","DOI":"10.1021\/ci100050t","article-title":"Extended-connectivity fingerprints","volume":"50","author":"Rogers","year":"2010","journal-title":"J. Chem. Inf. Model."},{"key":"B32","doi-asserted-by":"publisher","first-page":"6391","DOI":"10.3390\/jcm13216391","article-title":"EGFR-targeted therapies: a literature review","volume":"13","author":"Sha","year":"2024","journal-title":"J. Clin. Med."},{"key":"B33","doi-asserted-by":"publisher","first-page":"bbac059","DOI":"10.1093\/bib\/bbac059","article-title":"Multiview network embedding for drug-target interactions prediction by consistent and complementary information preserving","volume":"23","author":"Shang","year":"2022","journal-title":"Brief. Bioinform."},{"key":"B34","doi-asserted-by":"publisher","first-page":"e2220778120","DOI":"10.1073\/pnas.2220778120","article-title":"Contrastive learning in protein language space predicts interactions between drugs and protein targets","volume":"120","author":"Singh","year":"2023","journal-title":"Proc. Natl. Acad. Sci. U. S. A."},{"key":"B35","doi-asserted-by":"publisher","first-page":"216","DOI":"10.1186\/s12915-024-02012-x","article-title":"Drug-target interaction prediction with collaborative contrastive learning and adaptive self-paced sampling strategy","volume":"22","author":"Tian","year":"2024","journal-title":"BMC Biol."},{"key":"B36","doi-asserted-by":"publisher","first-page":"1282","DOI":"10.1016\/j.bmcl.2019.04.009","article-title":"Discovery of an EGFR tyrosine kinase inhibitor from ilex latifolia in breast cancer therapy","volume":"29","author":"Wang","year":"2019","journal-title":"Bioorg. Med. Chem. Lett."},{"key":"B37","doi-asserted-by":"publisher","first-page":"101336","DOI":"10.1016\/j.jpha.2025.101336","article-title":"DHGT-DTI: advancing drug-target interaction prediction through a dual-view heterogeneous network with GraphSAGE and graph transformer","volume":"15","author":"Wang","year":"2025","journal-title":"J. Pharm. Anal."},{"key":"B38","doi-asserted-by":"publisher","first-page":"4588","DOI":"10.1021\/acs.jmedchem.0c02044","article-title":"Structure-enabled discovery of novel macrocyclic inhibitors targeting glutaminase 1 allosteric binding site","volume":"64","author":"Xu","year":"2021","journal-title":"J. Med. Chem."},{"key":"B39","doi-asserted-by":"publisher","first-page":"i232","DOI":"10.1093\/bioinformatics\/btn162","article-title":"Prediction of drug-target interaction networks from the integration of chemical and genomic spaces","volume":"24","author":"Yamanishi","year":"2008","journal-title":"Bioinformatics"},{"key":"B40","doi-asserted-by":"publisher","first-page":"i246","DOI":"10.1093\/bioinformatics\/btq176","article-title":"Drug-target interaction prediction from chemical, genomic and pharmacological data in an integrated framework","volume":"26","author":"Yamanishi","year":"2010","journal-title":"Bioinformatics"},{"key":"B41","article-title":"Embedding Entities and Relations for Learning and Inference in Knowledge Bases","author":"Yang","year":"2015"},{"key":"B42","doi-asserted-by":"publisher","first-page":"6775","DOI":"10.1038\/s41467-021-27137-3","article-title":"A unified drug-target interaction prediction framework based on knowledge graph and recommendation system","volume":"12","author":"Ye","year":"2021","journal-title":"Nat. Commun."},{"key":"B43","doi-asserted-by":"publisher","first-page":"114846","DOI":"10.1016\/j.ejmech.2022.114846","article-title":"The SAR and action mechanisms of autophagy inhibitors that eliminate drug resistance","volume":"244","author":"Ye","year":"2022","journal-title":"Eur. J. Med. Chem."},{"key":"B44","doi-asserted-by":"publisher","first-page":"67","DOI":"10.1186\/s13321-024-00862-9","article-title":"An end-to-end method for predicting compound-protein interactions based on simplified homogeneous graph convolutional network and pre-trained language model","volume":"16","author":"Zhang","year":"2024","journal-title":"J. Cheminform."},{"key":"B45","doi-asserted-by":"publisher","first-page":"btae594","DOI":"10.1093\/bioinformatics\/btae594","article-title":"PocketDTA: an advanced multimodal architecture for enhanced prediction of drug-target affinity from 3D structural data of target binding pockets","volume":"40","author":"Zhao","year":"2024","journal-title":"Bioinformatics"},{"key":"B46","doi-asserted-by":"publisher","first-page":"6436","DOI":"10.1038\/s41467-025-61745-7","article-title":"ColdstartCPI: induced-fit theory-guided DTI predictive model with improved generalization performance","volume":"16","author":"Zhao","year":"2025","journal-title":"Nat. Commun."},{"key":"B47","doi-asserted-by":"publisher","first-page":"114860","DOI":"10.1016\/j.ejmech.2022.114860","article-title":"Discovery of novel hydroxyamidine based indoleamine 2,3-dioxygenase 1 (IDO1) and thioredoxin reductase 1 (TrxR1) dual inhibitors","volume":"245","author":"Zhou","year":"2023","journal-title":"Eur. J. Med. Chem."},{"key":"B48","doi-asserted-by":"publisher","first-page":"140125","DOI":"10.1016\/j.molstruc.2024.140125","article-title":"Discovery of novel thiophene[2,3-d]pyrimidine-thiazole derivative as promising MNK inhibitor to treat breast cancer","volume":"1321","author":"Zhu","year":"2025","journal-title":"J. Mol. Struct."}],"container-title":["Frontiers in Chemistry"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fchem.2026.1846850\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,6]],"date-time":"2026-07-06T05:36:58Z","timestamp":1783316218000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fchem.2026.1846850\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7,6]]},"references-count":48,"alternative-id":["10.3389\/fchem.2026.1846850"],"URL":"https:\/\/doi.org\/10.3389\/fchem.2026.1846850","relation":{},"ISSN":["2296-2646"],"issn-type":[{"value":"2296-2646","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,7,6]]},"article-number":"1846850"}}