{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,31]],"date-time":"2026-07-31T06:00:56Z","timestamp":1785477656290,"version":"3.56.0"},"reference-count":61,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2026,7,31]],"date-time":"2026-07-31T00:00:00Z","timestamp":1785456000000},"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. Bioinform."],"abstract":"<jats:p>\n                    Computational drug\u2013target interaction (DTI) prediction provides a scalable alternative to costly and time-consuming experimental screening, but its reliability is limited by the scarcity of experimentally verified negative interactions. In public DTI databases, most unobserved drug\u2013target pairs are unlabeled rather than true non-interactions. Randomly treating these unlabeled pairs as negatives can introduce label noise and reduce model reliability, particularly in cold-start scenarios involving unseen drugs or targets. To address this issue, we propose LNMGAT, a LapRLS-guided reliable pseudo-negative mining framework coupled with dual graph attention encoders. Instead of relying on experimentally confirmed negative labels or randomly sampled negatives, LNMGAT first applies Laplacian regularized least squares to drug and target similarity graphs to identify low-confidence unlabeled pairs as reliable pseudo-negatives. Drug and target representations are then learned separately on similarity-based k-nearest-neighbor graphs using graph attention networks, and their embeddings are concatenated for MLP-based interaction prediction. Across Yamanishi, Davis, KIBA, and BindingDB benchmarks, LNMGAT achieved the best AUPR in 10 of 16 evaluation settings and ranked within the top two in 14 of 16 settings. In the 12 cold-start settings, LNMGAT obtained the best AUPR in 9 cases, with absolute AUPR gains over the strongest baseline of up to 0.016 in pair cold-start prediction. External evaluation on DrugBank positive interactions and SwissDock-based molecular docking further provided database-level and\n                    <jats:italic>in silico<\/jats:italic>\n                    support for the plausibility of high-ranked predictions. Nevertheless, the biological validation in this study remains computational and database-based; no wet-lab binding assay was performed. LNMGAT therefore provides a competitive and interpretable framework for DTI prediction under negative-label uncertainty, while further experimental validation is required for its top-ranked candidates.\n                  <\/jats:p>","DOI":"10.3389\/fbinf.2026.1882476","type":"journal-article","created":{"date-parts":[[2026,7,31]],"date-time":"2026-07-31T05:39:34Z","timestamp":1785476374000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["LNMGAT: a laplacian regularized pseudo-negative mining graph attention network for robust drug\u2013target interaction prediction under multi-scenario cold-start settings"],"prefix":"10.3389","volume":"6","author":[{"given":"Shuai","family":"Guo","sequence":"first","affiliation":[{"name":"College of Computer and Information Engineering, Inner Mongolia Agricultural University","place":["Hohhot, China"]},{"name":"Inner Mongolia Autonomous Region Key Laboratory of Big Data Research and Application of Agriculture and Animal Husbandry","place":["Hohhot, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Weichi","family":"Liu","sequence":"additional","affiliation":[{"name":"College of Food Science and Engineering, Inner Mongolia Agricultural University","place":["Hohhot, China"]},{"name":"Key Laboratory of Dairy Biotechnology and Engineering, Ministry of Education, Inner Mongolia Agricultural University","place":["Hohhot, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jie","family":"Zou","sequence":"additional","affiliation":[{"name":"College of Computer and Information Engineering, Inner Mongolia Agricultural University","place":["Hohhot, China"]},{"name":"Inner Mongolia Autonomous Region Key Laboratory of Big Data Research and Application of Agriculture and Animal Husbandry","place":["Hohhot, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tao","family":"Ban","sequence":"additional","affiliation":[{"name":"College of Computer and Information Engineering, Inner Mongolia Agricultural University","place":["Hohhot, China"]},{"name":"Inner Mongolia Autonomous Region Key Laboratory of Big Data Research and Application of Agriculture and Animal Husbandry","place":["Hohhot, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Gaifang","family":"Dong","sequence":"additional","affiliation":[{"name":"College of Computer and Information Engineering, Inner Mongolia Agricultural University","place":["Hohhot, China"]},{"name":"Inner Mongolia Autonomous Region Key Laboratory of Big Data Research and Application of Agriculture and Animal Husbandry","place":["Hohhot, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2026,7,31]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","first-page":"3594","DOI":"10.1038\/s41598-023-30026-y","article-title":"Drug\u2013target interaction prediction based on protein features, using wrapper feature selection","volume":"13","author":"Abbasi Mesrabadi","year":"2023","journal-title":"Sci. Rep."},{"key":"B2","doi-asserted-by":"crossref","first-page":"417","DOI":"10.1109\/FLLM63129.2024.10852448","article-title":"Large language models in drug discovery: a comprehensive analysis of drug\u2013target interaction prediction","volume-title":"2024 2nd Int. Conf. on Foundation and Large Language Models (FLLM)","author":"AbuNasser","year":"2024"},{"key":"B3","volume-title":"Random-Forest Model for drug\u2013target Interaction Prediction via Kullback\u2013Leibler Divergence","author":"Ahn","year":"2024"},{"key":"B4","doi-asserted-by":"publisher","first-page":"1663","DOI":"10.3390\/molecules28041663","article-title":"Comparative studies on resampling techniques in machine learning and deep learning models for drug\u2013target interaction prediction","volume":"28","author":"Azlim Khan","year":"2023","journal-title":"Molecules"},{"key":"B5","volume-title":"Pgraphdta: Improving Drug Target Interaction Prediction Using Protein Language Models and Contact Maps","author":"Bal","year":"2023"},{"key":"B6","doi-asserted-by":"crossref","DOI":"10.7557\/18.6788","article-title":"FastDTI: drug-target interaction prediction using multimodality and transformers[C]","volume-title":"Proceedings of the Northern Lights Deep Learning Workshop 2023","author":"Boezer","year":"2023"},{"key":"B7","doi-asserted-by":"publisher","first-page":"W324","DOI":"10.1093\/nar\/gkae300","article-title":"SwissDock 2024: major enhancements for small-molecule docking with attracting cavities and AutoDock vina","volume":"52","author":"Bugnon","year":"2024","journal-title":"Nucleic Acids Research"},{"key":"B8","doi-asserted-by":"publisher","first-page":"e18224","DOI":"10.1111\/jcmm.18224","article-title":"NGCN: drug\u2013target interaction prediction by integrating information and feature learning from heterogeneous network","volume":"28","author":"Cao","year":"2024","journal-title":"J. Cell. Mol. Med."},{"key":"B9","doi-asserted-by":"crossref","DOI":"10.1371\/journal.pone.0043425","volume-title":"Prediction of disease-related Interactions Between Micrornas and Environmental Factors Based on a Semi-supervised Classifier","author":"Chen","year":"2012"},{"key":"B10","doi-asserted-by":"publisher","first-page":"e1004975","DOI":"10.1371\/journal.pcbi.1004975","article-title":"NLLSS: predicting synergistic drug combinations based on semi-supervised learning","volume":"12","author":"Chen","year":"2016","journal-title":"PLoS Computational Biology"},{"key":"B11","doi-asserted-by":"publisher","first-page":"7753","DOI":"10.3390\/ijms25147753","article-title":"Drug\u2013target interaction prediction based on an interactive inference network","volume":"25","author":"Chen","year":"2024","journal-title":"Int. J. Mol. Sci."},{"key":"B12","doi-asserted-by":"publisher","first-page":"120754","DOI":"10.1016\/j.eswa.2023.120754","article-title":"TripletMultiDTI: multimodal representation learning in drug-target interaction prediction with triplet loss function","volume":"232","author":"Dehghan","year":"2023","journal-title":"Expert Syst. Appl."},{"key":"B13","doi-asserted-by":"publisher","first-page":"vbag034","DOI":"10.1093\/bioadv\/vbag034","article-title":"Multi-DDA: drug\u2013disease association prediction using a hybrid graph convolutional network with multi-modal drug representations","volume":"6","author":"Dehghan","year":"2026","journal-title":"Bioinforma. Adv."},{"key":"B14","doi-asserted-by":"publisher","first-page":"306","DOI":"10.1007\/s12539-023-00557-z","article-title":"Deep learning-based modeling of drug\u2013target interaction prediction incorporating binding site information of proteins","volume":"15","author":"D\u2019Souza","year":"2023","journal-title":"Interdiscip. Sci. Comput. Life Sci."},{"key":"B15","volume-title":"A Comparison of Embedding Aggregation Strategies in drug\u2013target Interaction Prediction","year":"2024"},{"key":"B16","doi-asserted-by":"publisher","first-page":"239","DOI":"10.1016\/j.future.2024.07.014","article-title":"DeFuseDTI: interpretable drug target interaction prediction model with dual-branch encoder and multiview fusion","volume":"161","author":"Feng","year":"2024","journal-title":"Future Gener. Comput. Syst."},{"key":"B17","doi-asserted-by":"publisher","first-page":"141","DOI":"10.1002\/qub2.39","article-title":"GCARDTI: drug\u2013target interaction prediction based on a hybrid mechanism in drug SELFIES","volume":"12","author":"Feng","year":"2024","journal-title":"Quant. Biol."},{"key":"B18","doi-asserted-by":"publisher","first-page":"108339","DOI":"10.1016\/j.compbiomed.2024.108339","article-title":"GraphormerDTI: a graph transformer-based approach for drug-target interaction prediction","volume":"173","author":"Gao","year":"2024","journal-title":"Comput. Biol. Med."},{"key":"B19","article-title":"MT-ConBiFormer-GPT: multi-target molecular generation for low-data drug discovery via a contrastive BiFormer-GPT architecture and curriculum learning with cross-domain generalization","volume":"27","author":"Gharaghani","year":"2026","journal-title":"Briefings Bioinforma."},{"key":"B20","doi-asserted-by":"publisher","first-page":"123821","DOI":"10.1016\/j.eswa.2024.123821","article-title":"Flexible drug\u2013target interaction prediction with interactive information extraction and trade-off","volume":"249","author":"He","year":"2024","journal-title":"Expert Syst. Appl."},{"key":"B21","doi-asserted-by":"publisher","first-page":"10","DOI":"10.1016\/j.ymeth.2024.11.010","article-title":"Exploring drug-target interaction prediction on cold-start scenarios via meta-learning-based graph transformer","volume":"234","author":"He","year":"2025","journal-title":"Methods"},{"key":"B22","doi-asserted-by":"publisher","first-page":"110887","DOI":"10.1016\/j.patcog.2024.110887","article-title":"MMDG-DTI: drug\u2013target interaction prediction via multimodal feature fusion and domain generalization","volume":"157","author":"Hua","year":"2025","journal-title":"Pattern Recognit."},{"key":"B23","doi-asserted-by":"publisher","first-page":"14061","DOI":"10.3390\/ijms241814061","article-title":"A robust drug\u2013target interaction prediction framework with capsule network and transfer learning","volume":"24","author":"Huang","year":"2023","journal-title":"Int. J. Mol. Sci."},{"key":"B24","volume-title":"Drugagent: multi-agent large language model-based reasoning for drug-target Interaction Prediction","author":"Inoue","year":"2025"},{"key":"B25","doi-asserted-by":"publisher","first-page":"4070","DOI":"10.1021\/acs.jcim.3c00082","article-title":"Discovery of a novel DCAF1 ligand using a drug\u2013target interaction prediction model: generalizing machine learning to new drug targets","volume":"63","author":"Kimani","year":"2023","journal-title":"J. Chem. Inf. Model."},{"key":"B26","doi-asserted-by":"publisher","first-page":"35588","DOI":"10.1038\/s41598-025-01589-9","article-title":"A generative framework for enhancing drug target interaction prediction in drug discovery","volume":"15","author":"Kotkondawar","year":"2025","journal-title":"Sci. Rep."},{"key":"B27","doi-asserted-by":"crossref","DOI":"10.1101\/2024.10.14.618129","article-title":"A unified framework for drug\u2013target interaction prediction by semantic-guided meta-path method","author":"Li","year":"2024"},{"key":"B28","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1038\/s44385-024-00003-9","article-title":"Application of artificial intelligence in drug-target interactions prediction: a review","volume":"2","author":"Liao","year":"2025","journal-title":"Npj Biomedical Innovations"},{"key":"B29","doi-asserted-by":"publisher","first-page":"11818","DOI":"10.3390\/ijms252111818","article-title":"NFSA-DTI: a novel drug\u2013target interaction prediction model using neural fingerprint and self-attention mechanism","volume":"25","author":"Liu","year":"2024","journal-title":"Int. J. Mol. Sci."},{"key":"B30","doi-asserted-by":"publisher","first-page":"102778","DOI":"10.1016\/j.artmed.2024.102778","article-title":"SSLDTI: a novel method for drug-target interaction prediction based on self-supervised learning","volume":"149","author":"Liu","year":"2024","journal-title":"Artif. Intell. Med."},{"key":"B31","doi-asserted-by":"publisher","first-page":"btae693","DOI":"10.1093\/bioinformatics\/btae693","article-title":"Accurate and transferable drug\u2013target interaction prediction with DrugLAMP","volume":"40","author":"Luo","year":"2024","journal-title":"Bioinformatics"},{"key":"B32","volume-title":"Heterogeneous Networks in drug-target Interaction Prediction","author":"Molaee","year":"2025"},{"key":"B33","doi-asserted-by":"publisher","first-page":"103023","DOI":"10.1016\/j.artmed.2024.103023","article-title":"DMHGNN: double multi-view heterogeneous graph neural network framework for drug-target interaction prediction","volume":"159","author":"Ning","year":"2025","journal-title":"Artif. Intell. Med."},{"key":"B34","doi-asserted-by":"publisher","first-page":"27177","DOI":"10.1007\/s10489-023-04977-8","article-title":"CSDTI: an interpretable cross-attention network with GNN-based drug molecule aggregation for drug-target interaction prediction: Y. Pan et al","volume":"53","author":"Pan","year":"2023","journal-title":"Appl. Intell."},{"key":"B35","doi-asserted-by":"publisher","first-page":"6684","DOI":"10.1021\/acs.jcim.4c00957","article-title":"MGNDTI: a drug-target interaction prediction framework based on multimodal representation learning and the gating mechanism","volume":"64","author":"Peng","year":"2024","journal-title":"J. Chem. Inf. Model."},{"key":"B36","doi-asserted-by":"publisher","first-page":"18","DOI":"10.1186\/s13321-025-00952-2","article-title":"Barlow twins deep neural network for advanced 1D drug\u2013target interaction prediction","volume":"17","author":"Schuh","year":"2025","journal-title":"J. Cheminformatics"},{"key":"B37","doi-asserted-by":"crossref","first-page":"170","DOI":"10.1080\/10255842.2023.2282951","article-title":"Enhancing drug discovery in schizophrenia: a deep learning approach for accurate drug\u2013target interaction prediction \u2013 DrugSchizoNet","volume":"28","author":"Sherine Glory","year":"2025","journal-title":"Comput. Methods Biomechanics Biomed. Eng."},{"key":"B38","doi-asserted-by":"publisher","first-page":"bbad474","DOI":"10.1093\/bib\/bbad474","article-title":"AMGDTI: drug\u2013target interaction prediction based on adaptive meta-graph learning in heterogeneous network","volume":"25","author":"Su","year":"2023","journal-title":"Briefings Bioinforma."},{"key":"B39","doi-asserted-by":"crossref","DOI":"10.9781\/ijimai.2022.11.002","volume-title":"Drug Target Interaction Prediction Using Machine Learning Techniques \u2013 a Review","author":"Suruliandi","year":"2024"},{"key":"B40","first-page":"157","article-title":"Improving drug-target interaction prediction using enhanced feature selection","volume-title":"2024 15th Int. Conf. on Information and Knowledge Technology (IKT)","author":"Taheri","year":"2024"},{"key":"B41","doi-asserted-by":"publisher","first-page":"44","DOI":"10.1186\/s13321-020-00447-2","article-title":"DTiGEMS+: drug\u2013target interaction prediction using graph embedding, graph mining, and similarity-based techniques","volume":"12","author":"Thafar","year":"2020","journal-title":"J. Cheminformatics"},{"key":"B42","doi-asserted-by":"publisher","first-page":"18104","DOI":"10.1038\/s41598-024-69186-w","article-title":"Drug\u2013target interaction prediction through fine-grained selection and bidirectional random walk methodology","volume":"14","author":"Wang","year":"2024","journal-title":"Sci. Rep."},{"key":"B43","doi-asserted-by":"publisher","first-page":"644","DOI":"10.3390\/biom12050644","article-title":"Multi-transdti: transformer for drug\u2013target interaction prediction based on simple universal dictionaries with multi-view strategy","volume":"12","author":"Wang","year":"2022","journal-title":"Biomolecules"},{"key":"B44","doi-asserted-by":"publisher","first-page":"568","DOI":"10.1007\/s12539-024-00608-z","article-title":"CHL-DTI: a novel high\u2013low order information convergence framework for effective drug\u2013target interaction prediction","volume":"16","author":"Wang","year":"2024","journal-title":"Interdiscip. Sci. Comput. Life Sci."},{"key":"B45","doi-asserted-by":"publisher","first-page":"S6","DOI":"10.1186\/1752-0509-4-S2-S6","article-title":"Semi-supervised drug-protein interaction prediction from heterogeneous biological spaces","volume":"4","author":"Xia","year":"2010","journal-title":"BMC Systems Biology"},{"key":"B46","doi-asserted-by":"publisher","first-page":"125264","DOI":"10.1016\/j.eswa.2024.125264","article-title":"A pseudo-label supervised graph fusion attention network for drug\u2013target interaction prediction","volume":"259","author":"Xie","year":"2025","journal-title":"Expert Syst. Appl."},{"key":"B47","article-title":"GENNDTI: Drug\u2013target interaction prediction using graph neural network enhanced by router nodes","author":"Yang","year":"","journal-title":"IEEE J. Biomed. Health Inf"},{"key":"B48","doi-asserted-by":"publisher","first-page":"btae147","DOI":"10.1093\/bioinformatics\/btae147","article-title":"MINDG: a drug\u2013target interaction prediction method based on an integrated learning algorithm","volume":"40","author":"Yang","year":"","journal-title":"Bioinformatics"},{"key":"B49","doi-asserted-by":"publisher","first-page":"558","DOI":"10.1007\/s11427-023-2569-7","article-title":"Predicting Lactobacillus delbrueckii subsp. bulgaricus-Streptococcus thermophilus interactions based on a highly accurate semi-supervised learning method","volume":"68","author":"Yang","year":"2025","journal-title":"Sci. China Life Sci."},{"key":"B50","doi-asserted-by":"publisher","first-page":"107199","DOI":"10.1016\/j.compbiomed.2023.107199","article-title":"Semi-supervised heterogeneous graph contrastive learning for drug\u2013target interaction prediction","volume":"163","author":"Yao","year":"2023","journal-title":"Comput. Biol. Med."},{"key":"B51","doi-asserted-by":"publisher","first-page":"bbac272","DOI":"10.1093\/bib\/bbac272","article-title":"AttentionSiteDTI: an interpretable graph-based model for drug\u2013target interaction prediction using NLP sentence-level relation classification","volume":"23","author":"Yazdani-Jahromi","year":"2022","journal-title":"Briefings Bioinforma."},{"key":"B52","doi-asserted-by":"publisher","first-page":"124289","DOI":"10.1016\/j.eswa.2024.124289","article-title":"Drug\u2013target interaction prediction based on improved heterogeneous graph representation learning and feature projection classification","volume":"252","author":"Yu","year":"2024","journal-title":"Expert Syst. Appl."},{"key":"B53","doi-asserted-by":"publisher","first-page":"141","DOI":"10.1186\/s12859-024-05753-2","article-title":"CAT-DTI: cross-attention and transformer network with domain adaptation for drug-target interaction prediction","volume":"25","author":"Zeng","year":"2024","journal-title":"BMC Bioinforma."},{"key":"B54","doi-asserted-by":"publisher","first-page":"2994","DOI":"10.1039\/d5dd00311c","article-title":"MAARDTI: a multi-perspective attention aggregation model for the prediction of drug\u2013target interactions","volume":"4","author":"Zhan","year":"2025","journal-title":"Digit. Discov."},{"key":"B55","doi-asserted-by":"publisher","first-page":"283","DOI":"10.1016\/j.future.2024.05.054","article-title":"A heterogeneous graph neural network with automatic discovery of effective metapaths for drug\u2013target interaction prediction","volume":"160","author":"Zhang","year":"2024","journal-title":"Future Gener. Comput. Syst."},{"key":"B56","volume-title":"A Cross-Field Fusion Strategy for Drug\u2013Target Interaction Prediction","author":"Zhang","year":"2024"},{"key":"B57","volume-title":"DeepMGT-DTI: transformer network incorporating multilayer graph information for drug\u2013target interaction prediction","author":"Zhang","year":""},{"key":"B58","article-title":"Escaping the drug-bias trap: using debiasing design to improve interpretability and generalization of drug-target interaction prediction","author":"Zhang","year":"2025","journal-title":"IEEE Trans. Comput. Biol. Bioinforma"},{"key":"B59","doi-asserted-by":"publisher","first-page":"bbaf342","DOI":"10.1093\/bib\/bbaf342","article-title":"NASNet-DTI: accurate drug\u2013target interaction prediction using heterogeneous graphs and node adaptation","volume":"26","author":"Zhong","year":"2025","journal-title":"Briefings Bioinforma."},{"key":"B60","doi-asserted-by":"publisher","first-page":"1558","DOI":"10.1049\/cit2.12194","article-title":"Associative learning mechanism for drug\u2013target interaction prediction","volume":"8","author":"Zhu","year":"2023","journal-title":"CAAI Trans. Intell. Technol."},{"key":"B61","doi-asserted-by":"crossref","first-page":"136","DOI":"10.1016\/j.ymeth.2024.01.018","article-title":"GSL-DTI: graph structure learning network for drug-target interaction prediction","volume":"223","author":"Zixuan","year":"2024","journal-title":"Methods"}],"container-title":["Frontiers in Bioinformatics"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fbinf.2026.1882476\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,31]],"date-time":"2026-07-31T05:39:38Z","timestamp":1785476378000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fbinf.2026.1882476\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7,31]]},"references-count":61,"alternative-id":["10.3389\/fbinf.2026.1882476"],"URL":"https:\/\/doi.org\/10.3389\/fbinf.2026.1882476","relation":{},"ISSN":["2673-7647"],"issn-type":[{"value":"2673-7647","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,7,31]]},"article-number":"1882476"}}