{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,10]],"date-time":"2026-07-10T05:13:54Z","timestamp":1783660434304,"version":"3.55.0"},"reference-count":35,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2026,7,10]],"date-time":"2026-07-10T00:00:00Z","timestamp":1783641600000},"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. Pharmacol."],"abstract":"<jats:sec>\n                    <jats:title>Background<\/jats:title>\n                    <jats:p>Tuberculosis (TB) remains a global health crisis, with complex molecular mechanisms that are not fully understood. Traditional pathway analysis methods fail to capture the intricate non-linear relationships within biological networks.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>We developed a novel artificial intelligence framework integrating graph neural networks (GNNs), transformer architectures, and multimodal deep learning to decipher TB pathway mechanisms. Our approach constructs a comprehensive pathway-gene interaction network from three critical pathways (Tuberculosis hsa05152, Antigen processing hsa04612, and NF-\u03baB signaling hsa04064) and employs three interconnected models: (1) a Graph Convolutional Network for learning pathway-gene relationships, (2) a Transformer encoder for pathway activity prediction, and (3) a multimodal fusion model with attention mechanisms integrating transcriptomic, pathway, and clinical data. The framework was trained and validated on 467 clinical samples and 529 transcriptomic samples from five GEO datasets.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>\n                      The Transformer model achieved strong performance in pathway activity prediction (\n                      <jats:italic>R<\/jats:italic>\n                      <jats:sup>2<\/jats:sup>\n                      = 0.97, MSE = 0.014), demonstrating high accuracy in capturing pathway activation patterns. The multimodal fusion model achieved strong predictive performance (accuracy 88.2%, AUC-ROC 0.90) in clinical outcome prediction, with attention analysis revealing adaptive weighting of different data modalities. Network analysis identified 27 shared genes between Tuberculosis and Antigen processing pathways, and 18 shared genes between Tuberculosis and NF-\u03baB pathways, indicating coordinated immune regulation. Key pathway-gene interactions were identified, including critical roles of IFNG, TNF, IL1B, and NF-\u03baB signaling components.\n                    <\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>This study represents the first comprehensive application of GNNs and multimodal deep learning to TB pathway analysis. Our framework provides novel insights into TB pathogenesis, identifies potential therapeutic targets, and demonstrates the power of AI-driven approaches for understanding complex disease mechanisms. The interpretability of our models through attention mechanisms enables translation of computational findings into actionable biological insights, with significant implications for precision medicine and personalized TB treatment strategies.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.3389\/fphar.2026.1753893","type":"journal-article","created":{"date-parts":[[2026,7,10]],"date-time":"2026-07-10T04:25:50Z","timestamp":1783657550000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Deciphering tuberculosis pathway mechanisms via graph neural networks and multimodal deep learning: a comprehensive AI-driven framework for precision medicine"],"prefix":"10.3389","volume":"17","author":[{"given":"Yuanli","family":"Yang","sequence":"first","affiliation":[{"name":"The Third Department of Tuberculosis, Xi\u2019an Chest Hospital","place":["Xi\u2019an, Shaanxi, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Huanqing","family":"Liu","sequence":"additional","affiliation":[{"name":"Information Management Office, Northwestern Polytechnical University","place":["Xi\u2019an, Shaanxi, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qian","family":"Lei","sequence":"additional","affiliation":[{"name":"Department of Pharmacy, Xi\u2019an Chest Hospital","place":["Xi\u2019an, Shaanxi, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tingting","family":"Li","sequence":"additional","affiliation":[{"name":"Drug Clinical Trial Institution Office, Xi\u2019an Chest Hospital","place":["Xi\u2019an, Shaanxi, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2026,7,10]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","first-page":"1773","DOI":"10.1038\/s41591-022-01981-2","article-title":"Multimodal biomedical AI","volume":"28","author":"Acosta","year":"2022","journal-title":"Nat. Med."},{"key":"B2","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1412.6980","article-title":"A method for stochastic optimization","volume":"1412","author":"Adam","year":"2014","journal-title":"arXiv Preprint arXiv:1412.6980"},{"key":"B3","doi-asserted-by":"publisher","first-page":"354","DOI":"10.1038\/s41588-021-00782-6","article-title":"Base-resolution models of transcription-factor binding reveal soft motif syntax","volume":"53","author":"Avsec","year":"2021","journal-title":"Nat. Genet."},{"key":"B4","doi-asserted-by":"publisher","first-page":"1607","DOI":"10.48550\/arXiv.1607.06450","article-title":"Layer normalization","author":"Ba","year":"2016","journal-title":"arXiv Preprint"},{"key":"B5","doi-asserted-by":"publisher","first-page":"2348","DOI":"10.4049\/jimmunol.1801303","article-title":"Mycobacterium tuberculosis inhibits autocrine type I IFN signaling to increase intracellular survival","volume":"202","author":"Banks","year":"2019","journal-title":"J. Immunol."},{"key":"B6","doi-asserted-by":"publisher","first-page":"108","DOI":"10.1038\/nature08460","article-title":"Systematic RNA interference reveals that oncogenic KRAS-driven cancers require TBK1","volume":"462","author":"Barbie","year":"2009","journal-title":"Nature"},{"key":"B7","doi-asserted-by":"publisher","first-page":"973","DOI":"10.1038\/nature09247","article-title":"An interferon-inducible neutrophil-driven blood transcriptional signature in human tuberculosis","volume":"466","author":"Berry","year":"2010","journal-title":"Nature"},{"key":"B8","doi-asserted-by":"publisher","first-page":"691","DOI":"10.1038\/nri.2017.69","article-title":"Heterogeneity in tuberculosis","volume":"17","author":"Cadena","year":"2017","journal-title":"Nat. Rev. Immunol."},{"key":"B9","doi-asserted-by":"publisher","first-page":"20170387","DOI":"10.1098\/rsif.2017.0387","article-title":"Opportunities and obstacles for deep learning in biology and medicine","volume":"15","author":"Ching","year":"2018","journal-title":"J. R. Soc. Interface"},{"key":"B10","doi-asserted-by":"publisher","first-page":"88","DOI":"10.1111\/imr.12269","article-title":"The human immune response to tuberculosis and its treatment: a view from the blood","volume":"264","author":"Cliff","year":"2015","journal-title":"Immunol. Rev."},{"key":"B11","doi-asserted-by":"publisher","first-page":"291","DOI":"10.1016\/S2213-2600(17)30079-6","article-title":"The epidemiology, pathogenesis, transmission, diagnosis, and management of multidrug-resistant, extensively drug-resistant, and incurable tuberculosis","volume":"5","author":"Dheda","year":"2017","journal-title":"Lancet Respir. Med."},{"key":"B12","doi-asserted-by":"publisher","first-page":"e92973","DOI":"10.1172\/jci.insight.92973","article-title":"Interleukin-17 limits hypoxia-inducible factor 1\u03b1 and development of hypoxic granulomas during tuberculosis","volume":"2","author":"Domingo-Gonzalez","year":"2017","journal-title":"JCI Insight"},{"key":"B13","first-page":"448","volume-title":"Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate shift[C]\/\/International Conference on Machine Learning","author":"Ioffe","year":"2015"},{"key":"B14","doi-asserted-by":"publisher","first-page":"249","DOI":"10.1093\/biostatistics\/4.2.249","article-title":"Exploration, normalization, and summaries of high density oligonucleotide array probe level data","volume":"4","author":"Irizarry","year":"2003","journal-title":"Biostatistics"},{"key":"B15","doi-asserted-by":"publisher","first-page":"583","DOI":"10.1038\/s41586-021-03819-2","article-title":"Highly accurate protein structure prediction with AlphaFold","volume":"596","author":"Jumper","year":"2021","journal-title":"Nature"},{"key":"B16","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1609.02907","article-title":"Semi-supervised classification with graph convolutional networks","author":"Kipf","year":"2016","journal-title":"arXiv Preprint arXiv:1609.02907"},{"key":"B17","doi-asserted-by":"publisher","first-page":"882","DOI":"10.1093\/bioinformatics\/bts034","article-title":"The sva package for removing batch effects and other unwanted variation in high-throughput experiments","volume":"28","author":"Leek","year":"2012","journal-title":"Bioinformatics"},{"key":"B18","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1608.03983","article-title":"Sgdr: stochastic gradient descent with warm restarts","author":"Loshchilov","year":"2016","journal-title":"arXiv Preprint arXiv:1608.03983"},{"key":"B19","doi-asserted-by":"publisher","first-page":"550","DOI":"10.1186\/s13059-014-0550-8","article-title":"Moderated estimation of fold change and dispersion for RNA-Seq data with DESeq2","volume":"15","author":"Love","year":"2014","journal-title":"Genome Biol."},{"key":"B20","doi-asserted-by":"publisher","first-page":"2334","DOI":"10.1007\/s00018-003-3020-0","article-title":"Regulation of macrophage activation","volume":"60","author":"Ma","year":"2003","journal-title":"Cell Mol. Life Sci."},{"key":"B21","doi-asserted-by":"publisher","first-page":"278","DOI":"10.3389\/fphys.2013.00278","article-title":"Methods and approaches in the topology-based analysis of biological pathways","volume":"4","author":"Mitrea","year":"2013","journal-title":"Front. Physiol."},{"key":"B22","doi-asserted-by":"publisher","first-page":"16076","DOI":"10.1038\/nrdp.2016.76","volume":"2","author":"Pai","year":"2016","journal-title":"Tuberc. Nat. Rev. Dis. Prim."},{"key":"B23","doi-asserted-by":"publisher","first-page":"2284","DOI":"10.3389\/fmicb.2017.02284","article-title":"The macrophage: a disputed fortress in the battle against Mycobacterium tuberculosis","volume":"8","author":"Queval","year":"2017","journal-title":"Front. Microbiol."},{"key":"B24","doi-asserted-by":"publisher","first-page":"31","DOI":"10.1038\/s41591-021-01614-0","article-title":"AI in health and medicine","volume":"28","author":"Rajpurkar","year":"2022","journal-title":"Nat. Med."},{"key":"B25","doi-asserted-by":"publisher","first-page":"3706","DOI":"10.4049\/jimmunol.0802297","article-title":"Synergy between individual TNF-dependent functions determines granuloma performance for controlling Mycobacterium tuberculosis infection","volume":"182","author":"Ray","year":"2009","journal-title":"J. Immunol."},{"key":"B26","doi-asserted-by":"publisher","first-page":"482","DOI":"10.1038\/s41596-018-0103-9","article-title":"Pathway enrichment analysis and visualization of omics data using g:Profiler, GSEA, cytoscape and EnrichmentMap","volume":"14","author":"Reimand","year":"2019","journal-title":"Nat. Protoc."},{"key":"B27","doi-asserted-by":"publisher","first-page":"93","DOI":"10.1038\/s43246-022-00315-6","article-title":"Graph neural networks for materials science and chemistry","volume":"3","author":"Reiser","year":"2022","journal-title":"Commun. Mater"},{"key":"B28","doi-asserted-by":"publisher","first-page":"950","DOI":"10.1038\/s42003-025-08337-9","article-title":"Human alveolar macrophage response to mycobacterium tuberculosis: immune characteristics underlying large inter-individual variability","volume":"8","author":"Sadee","year":"2025","journal-title":"Commun. Biol."},{"key":"B29","doi-asserted-by":"publisher","first-page":"15545","DOI":"10.1073\/pnas.0506580102","article-title":"Gene set enrichment analysis: a knowledge-based approach for interpreting genome-wide expression profiles","volume":"102","author":"Subramanian","year":"2005","journal-title":"Proc. Natl. Acad. Sci. U. S. A."},{"key":"B30","doi-asserted-by":"publisher","first-page":"1177932219899051","DOI":"10.1177\/1177932219899051","article-title":"Multi-omics data integration, interpretation, and its application","volume":"14","author":"Subramanian","year":"2020","journal-title":"Bioinform Biol. Insights"},{"key":"B31","doi-asserted-by":"publisher","first-page":"225","DOI":"10.1186\/1471-2105-6-225","article-title":"Pathway level analysis of gene expression using singular value decomposition","volume":"6","author":"Tomfohr","year":"2005","journal-title":"BMC Bioinforma."},{"key":"B32","doi-asserted-by":"publisher","first-page":"24","DOI":"10.48550\/arXiv.1706.03762","article-title":"Attention is all you need","volume":"30","author":"Vaswani","year":"2017","journal-title":"Adv. Neural Information Processing Systems"},{"key":"B33","doi-asserted-by":"publisher","first-page":"1686","DOI":"10.21105\/joss.01686","article-title":"Welcome to the tidyverse","volume":"4","author":"Wickham","year":"2019","journal-title":"J. Open Source Softw."},{"key":"B34","volume-title":"Global Tuberculosis Report 2023","year":"2023"},{"key":"B35","doi-asserted-by":"publisher","first-page":"71","DOI":"10.1016\/j.inffus.2018.09.012","article-title":"Machine learning for integrating data in biology and medicine: principles, practice, and opportunities","volume":"50","author":"Zitnik","year":"2019","journal-title":"Inf. Fusion"}],"container-title":["Frontiers in Pharmacology"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fphar.2026.1753893\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,10]],"date-time":"2026-07-10T04:25:53Z","timestamp":1783657553000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fphar.2026.1753893\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7,10]]},"references-count":35,"alternative-id":["10.3389\/fphar.2026.1753893"],"URL":"https:\/\/doi.org\/10.3389\/fphar.2026.1753893","relation":{},"ISSN":["1663-9812"],"issn-type":[{"value":"1663-9812","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,7,10]]},"article-number":"1753893"}}