{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,20]],"date-time":"2026-03-20T09:49:45Z","timestamp":1774000185583,"version":"3.50.1"},"reference-count":43,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2026,3,20]],"date-time":"2026-03-20T00:00:00Z","timestamp":1773964800000},"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:sec>\n                    <jats:title>Introduction<\/jats:title>\n                    <jats:p>Computational drug repurposing has been widely explored using similarity-based methods, network diffusion, matrix factorization, deep learning, and graph neural networks (GNNs). However, recent heterogeneous GNN models, such as TxGNN and GAT-based models, demonstrate serious limitations for real-world biomedical applications, including poor generalization to sparsely annotated diseases, limited disease-level adaptation, and inability to effectively combine heterogeneous evidence from curated databases, multi-omics profiles, and unstructured biomedical literature.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>This article proposes a heterogeneous attention-based meta-learning graph neural network named HAMGNN, which employs three major innovations: (i) relation-sensitive multi-head attention to prioritize biologically significant interactions among heterogeneous edge types, (ii) a disease-focused meta-learning framework enabling rapid adaptation to newly observed or under-informed diseases, and (iii) a literature-enhanced knowledge graph construction pipeline encoding high-confidence, LLM-extracted therapeutic information. The model was tested on a large multimodal biomedical knowledge graph assembled from DrugBank, DisGeNET, and Hetionet, comprising more than 2.2 million edges, using a stringent disjoint disease-based (cold-start) evaluation protocol.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>HAMGNN achieved a receiver operating characteristic\u2013area under the curve (ROC\u2013AUC) of 0.98 and precision of 0.95, representing a 10%\u201315% improvement over TxGNN and GAT-GNN on unseen disease generalization. Translational applicability was demonstrated through Alzheimer\u2019s disease and Long COVID case studies, identifying clinically plausible repurposing candidates and disease-associated biomarker signatures via mechanistic pathways.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Discussion<\/jats:title>\n                    <jats:p>HAMGNN offers a generalized, biologically grounded, and unified framework for evidence-based drug repurposing and biomarker discovery in complex and emerging diseases.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.3389\/fbinf.2026.1755412","type":"journal-article","created":{"date-parts":[[2026,3,20]],"date-time":"2026-03-20T06:39:06Z","timestamp":1773988746000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Generative AI in drug repurposing and biomarker discovery: a multimodal approach"],"prefix":"10.3389","volume":"6","author":[{"given":"K.","family":"Saranya","sequence":"first","affiliation":[{"name":"Department of Computer Science & Engineering, Bannari Amman Institute of Technology","place":["Erode, Tamilnadu, India"]},{"name":"Centre for Advanced Analytics, Multimedia University","place":["Melaka, Malaysia"]}]},{"given":"Emerson Raja","family":"Joseph","sequence":"additional","affiliation":[{"name":"Faculty of Engineering and Technology Centre for Advanced Analytics, OE of Artificial Intelligence, Multimedia University","place":["Melaka, Malaysia"]}]},{"given":"Ts.","family":"Kalaiarasi","sequence":"additional","affiliation":[{"name":"Faculty of Information Science and Technology, Multimedia University","place":["Melaka, Malaysia"]}]},{"given":"M.","family":"Karthiga","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Engineering, Bannari Amman Institute of Technology","place":["Sathyamangalam, Tamilnadu, India"]}]}],"member":"1965","published-online":{"date-parts":[[2026,3,20]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","first-page":"991","DOI":"10.1080\/17460441.2021.1925281","article-title":"Artificial intelligence in early drug discovery enabling precision medicine","volume":"16","author":"Boniolo","year":"2021","journal-title":"Expert Opin. Drug Discov."},{"key":"B2","doi-asserted-by":"publisher","first-page":"3476","DOI":"10.1038\/s41467-019-11452-4","article-title":"Network-based approach to prediction and population-based validation of in silico drug repurposing","volume":"10","author":"Cheng","year":"2019","journal-title":"Nat. Commun."},{"key":"B3","doi-asserted-by":"publisher","first-page":"e02448","DOI":"10.1002\/slct.202402448","article-title":"Transforming precision medicine through generative artificial intelligence: advanced architectures and tailored therapeutic design for patient-specific drug discovery","volume":"10","author":"Das","year":"2025","journal-title":"ChemistrySelect"},{"key":"B4","doi-asserted-by":"publisher","first-page":"1615523","DOI":"10.3389\/fneur.2025.1615523","article-title":"Harnessing artificial intelligence for brain disease: advances in diagnosis, drug discovery, and closed-loop therapeutics","volume":"16","author":"Fang","year":"2025","journal-title":"Front. Neurology"},{"key":"B5","first-page":"1126","article-title":"Model-agnostic meta-learning for fast adaptation of deep networks","volume-title":"Proceedings of the 34th international conference on machine learning (ICML)","author":"Finn","year":"2017"},{"key":"B6","article-title":"TxGNN: few-shot drug discovery via disease-centric heterogeneous graph learning","volume-title":"Advances in neural information processing systems (NeurIPS)","author":"Fu","year":"2022"},{"key":"B7","doi-asserted-by":"publisher","first-page":"1331062","DOI":"10.3389\/fphar.2024.1331062","article-title":"Generative artificial intelligence in drug discovery: basic framework, recent advances, challenges, and opportunities","volume":"15","author":"Gangwal","year":"2024","journal-title":"Front. Pharmacology"},{"key":"B8","doi-asserted-by":"crossref","DOI":"10.1016\/j.drudis.2025.104448","article-title":"Revolutionizing drug discovery: integrating artificial intelligence with quantitative systems pharmacology","volume-title":"Drug discovery today (Elsevier)","author":"Goryanin","year":"2025"},{"key":"B9","doi-asserted-by":"publisher","first-page":"573","DOI":"10.1038\/s41592-021-01209-0","article-title":"Domain-specific language model pretraining for biomedical natural language processing","volume":"18","author":"Gu","year":"2021","journal-title":"Nat. Methods"},{"key":"B10","doi-asserted-by":"publisher","first-page":"698","DOI":"10.1007\/s12539-024-00654-7","article-title":"Empowering graph neural network\u2013based computational drug repositioning with large language model\u2013inferred knowledge representation","volume":"17","author":"Gu","year":"","journal-title":"Interdiscip. Sciences: Computational Life Sci."},{"key":"B11","doi-asserted-by":"publisher","first-page":"109403","DOI":"10.1016\/j.compbiomed.2024.109403","article-title":"Deep multiple instance learning on heterogeneous graph for drug\u2013disease association prediction","volume":"184","author":"Gu","year":"","journal-title":"Comput. Biol. Med."},{"key":"B12","first-page":"1024","article-title":"Inductive representation learning on large graphs","volume-title":"Advances in neural information processing systems (NeurIPS)","author":"Hamilton","year":"2017"},{"key":"B13","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":"B14","doi-asserted-by":"publisher","first-page":"136","DOI":"10.1038\/s41746-020-00341-z","article-title":"Fusion of medical imaging and electronic health records using deep learning: a systematic review and implementation guidelines","volume":"3","author":"Huang","year":"2020","journal-title":"Npj Digit. Med."},{"key":"B15","doi-asserted-by":"publisher","first-page":"100610","DOI":"10.1016\/j.patter.2022.100610","article-title":"Meta-learning for drug discovery in rare diseases","volume":"3","author":"Huang","year":"2022","journal-title":"Patterns"},{"key":"B16","article-title":"Semi-supervised classification with graph convolutional networks","volume-title":"Proceedings of the international conference on learning representations (ICLR)","author":"Kipf","year":"2017"},{"key":"B17","doi-asserted-by":"crossref","DOI":"10.1002\/9781394269969","volume-title":"Multimodal data fusion for bioinformatics artificial intelligence","author":"Lilhore","year":"2025"},{"key":"B18","doi-asserted-by":"crossref","first-page":"489","DOI":"10.1002\/9781394280735.ch25","article-title":"Transform drug discovery and development with generative artificial intelligence","volume-title":"Generative artificial intelligence for biomedical and smart health informatics","author":"Lavecchia","year":"2025"},{"key":"B19","doi-asserted-by":"publisher","first-page":"1234","DOI":"10.1093\/bioinformatics\/btz682","article-title":"BioBERT: a pre-trained biomedical language representation model for biomedical text mining","volume":"36","author":"Lee","year":"2020","journal-title":"Bioinformatics"},{"key":"B20","doi-asserted-by":"publisher","first-page":"bbab488","DOI":"10.1093\/bib\/bbab488","article-title":"A review on machine learning principles for multi-omics data integration","volume":"23","author":"Li","year":"2022","journal-title":"Briefings Bioinforma."},{"key":"B21","doi-asserted-by":"publisher","first-page":"1445","DOI":"10.1021\/acs.molpharmaceut.5b00982","article-title":"Applications of deep learning in biomedicine","volume":"13","author":"Mamoshina","year":"2016","journal-title":"Mol. Pharm."},{"key":"B22","doi-asserted-by":"publisher","first-page":"1441","DOI":"10.3390\/biomedinformatics4020079","article-title":"Unlocking the future of drug development: generative AI, digital twins, and beyond","volume":"4","author":"Mariam","year":"2024","journal-title":"BioMedInformatics"},{"key":"B23","doi-asserted-by":"publisher","first-page":"1372","DOI":"10.1016\/j.csbj.2023.03.021","article-title":"Deep learning facilitates multi-data type analysis and predictive biomarker discovery in cancer precision medicine","volume":"21","author":"Mathema","year":"2023","journal-title":"Comput. Struct. Biotechnol. J."},{"key":"B24","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1201\/9781003539483-1","article-title":"Drug discovery and development with generative artificial intelligence","volume-title":"Generative Intelligence in Healthcare","author":"Ogidi","year":"2025"},{"key":"B25","doi-asserted-by":"publisher","first-page":"37","DOI":"10.1016\/j.drudis.2024.103992","article-title":"Unlocking the potential of generative artificial intelligence in drug discovery","author":"Romanelli","year":"2024","journal-title":"Appl. Generative"},{"key":"B26","first-page":"593","article-title":"Modeling relational data with graph convolutional networks","volume-title":"Proceedings of the European semantic web conference (ESWC)","author":"Schlichtkrull","year":"2018"},{"key":"B27","doi-asserted-by":"publisher","first-page":"172","DOI":"10.1038\/s41586-023-06291-2","article-title":"Large language models encode clinical knowledge","volume":"620","author":"Singhal","year":"2023","journal-title":"Nature"},{"key":"B28","doi-asserted-by":"publisher","first-page":"495","DOI":"10.1038\/s41576-020-0211-8","article-title":"Multi-omics data integration, interpretation, and application","volume":"21","author":"Subramanian","year":"2020","journal-title":"Nat. Rev. Genet."},{"key":"B29","article-title":"Graph attention networks","volume-title":"Proceedings of the international conference on learning representations (ICLR)","author":"Veli\u010dkovi\u0107","year":"2018"},{"key":"B30","first-page":"145","article-title":"Review on multi-modal AI models to integrate imaging and omics data","author":"Vincenzo","year":"2024"},{"key":"B31","doi-asserted-by":"publisher","first-page":"100011","DOI":"10.1016\/j.ccwv.2025.100011","article-title":"Artificial intelligence and multi-omics in drug discovery: a deep learning-powered revolution","volume":"1","author":"Vora","year":"2025","journal-title":"Cure and Care"},{"key":"B32","doi-asserted-by":"publisher","first-page":"i357","DOI":"10.1093\/bioinformatics\/btad270","article-title":"Few-shot learning for drug discovery","volume":"39","author":"Wang","year":"2023","journal-title":"Bioinformatics"},{"key":"B33","first-page":"80","article-title":"AI-Driven drug discovery and repurposing for neurodegenerative disorders","volume-title":"Machine learning for neurodegenerative disorders","author":"Yingngam","year":"2024"},{"key":"B34","doi-asserted-by":"publisher","first-page":"bbac586","DOI":"10.1093\/bib\/bbac586","article-title":"Heterogeneous graph learning for drug discovery","volume":"24","author":"Yu","year":"2023","journal-title":"Briefings Bioinforma."},{"key":"B35","doi-asserted-by":"publisher","first-page":"100794","DOI":"10.1016\/j.xcrm.2022.100794","article-title":"Deep generative molecular design reshapes drug discovery","volume":"3","author":"Zeng","year":"","journal-title":"Cell Rep. Med."},{"key":"B36","doi-asserted-by":"publisher","first-page":"44","DOI":"10.1038\/s42256-021-00425-x","article-title":"Repurposing open data to discover therapeutics for COVID-19 using knowledge graph learning","volume":"4","author":"Zeng","year":"","journal-title":"Nat. Mach. Intell."},{"key":"B37","doi-asserted-by":"publisher","first-page":"243","DOI":"10.1038\/s41573-022-00547-9","article-title":"Interpretable deep learning for drug discovery and development","volume":"22","author":"Zeng","year":"2023","journal-title":"Nat. Rev. Drug Discov."},{"key":"B38","doi-asserted-by":"publisher","first-page":"1205144","DOI":"10.3389\/fphar.2023.1205144","article-title":"Artificial intelligence\u2013driven drug repurposing: advances, challenges, and future perspectives","volume":"14","author":"Zhang","year":"2023","journal-title":"Front. Pharmacol."},{"key":"B39","doi-asserted-by":"publisher","first-page":"45","DOI":"10.1038\/s41591-024-03434-4","article-title":"Artificial intelligence in drug development","volume":"31","author":"Zhang","year":"2025","journal-title":"Nat. Medicine"},{"key":"B40","article-title":"Disease-aware graph learning for drug repurposing","volume-title":"Bioinformatics","author":"Zhao","year":"2024"},{"key":"B41","doi-asserted-by":"publisher","first-page":"1038","DOI":"10.1038\/s41587-019-0224-x","article-title":"Deep learning enables rapid identification of potent DDR1 kinase inhibitors","volume":"37","author":"Zhavoronkov","year":"2019","journal-title":"Nat. Biotechnol."},{"key":"B42","doi-asserted-by":"publisher","first-page":"4212","DOI":"10.1038\/ncomms5212","article-title":"Human symptoms\u2013disease network","volume":"5","author":"Zhou","year":"2014","journal-title":"Nat. Commun."},{"key":"B43","doi-asserted-by":"publisher","first-page":"i457","DOI":"10.1093\/bioinformatics\/bty294","article-title":"Modeling polypharmacy side effects with graph convolutional networks","volume":"34","author":"Zitnik","year":"2018","journal-title":"Bioinformatics"}],"container-title":["Frontiers in Bioinformatics"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fbinf.2026.1755412\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,20]],"date-time":"2026-03-20T06:39:08Z","timestamp":1773988748000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fbinf.2026.1755412\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,20]]},"references-count":43,"alternative-id":["10.3389\/fbinf.2026.1755412"],"URL":"https:\/\/doi.org\/10.3389\/fbinf.2026.1755412","relation":{},"ISSN":["2673-7647"],"issn-type":[{"value":"2673-7647","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,3,20]]},"article-number":"1755412"}}