{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,26]],"date-time":"2026-02-26T16:06:59Z","timestamp":1772122019451,"version":"3.50.1"},"reference-count":36,"publisher":"MDPI AG","issue":"2","license":[{"start":{"date-parts":[[2020,2,14]],"date-time":"2020-02-14T00:00:00Z","timestamp":1581638400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100002241","name":"Japan Science and Technology Agency","doi-asserted-by":"publisher","award":["Research Complex program"],"award-info":[{"award-number":["Research Complex program"]}],"id":[{"id":"10.13039\/501100002241","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Biomolecules"],"abstract":"<jats:p>Gene network estimation is a method key to understanding a fundamental cellular system from high throughput omics data. However, the existing gene network analysis relies on having a sufficient number of samples and is required to handle a huge number of nodes and estimated edges, which remain difficult to interpret, especially in discovering the clinically relevant portions of the network. Here, we propose a novel method to extract a biomedically significant subnetwork using a Bayesian network, a type of unsupervised machine learning method that can be used as an explainable and interpretable artificial intelligence algorithm. Our method quantifies sample specific networks using our proposed Edge Contribution value (ECv) based on the estimated system, which realizes condition-specific subnetwork extraction using a limited number of samples. We applied this method to the Epithelial-Mesenchymal Transition (EMT) data set that is related to the process of metastasis and thus prognosis in cancer biology. We established our method-driven EMT network representing putative gene interactions. Furthermore, we found that the sample-specific ECv patterns of this EMT network can characterize the survival of lung cancer patients. These results show that our method unveils the explainable network differences in biological and clinical features through artificial intelligence technology.<\/jats:p>","DOI":"10.3390\/biom10020306","type":"journal-article","created":{"date-parts":[[2020,2,21]],"date-time":"2020-02-21T10:49:16Z","timestamp":1582282156000},"page":"306","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":21,"title":["System-Based Differential Gene Network Analysis for Characterizing a Sample-Specific Subnetwork"],"prefix":"10.3390","volume":"10","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1460-8354","authenticated-orcid":false,"given":"Yoshihisa","family":"Tanaka","sequence":"first","affiliation":[{"name":"Graduate School of Pharmaceutical Sciences, Kyoto University, Kyoto 606-8507, Japan"},{"name":"RIKEN Cluster for Science, Technology and Innovation Hub, Medical Sciences Innovation Hub Program, Kanagawa 230-0045, Japan"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3483-9712","authenticated-orcid":false,"given":"Yoshinori","family":"Tamada","sequence":"additional","affiliation":[{"name":"Graduate School of Medicine, Kyoto University, Kyoto 606-8507, Japan"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7411-2193","authenticated-orcid":false,"given":"Marie","family":"Ikeguchi","sequence":"additional","affiliation":[{"name":"Graduate School of Medicine, Kyoto University, Kyoto 606-8507, Japan"}]},{"given":"Fumiyoshi","family":"Yamashita","sequence":"additional","affiliation":[{"name":"Graduate School of Pharmaceutical Sciences, Kyoto University, Kyoto 606-8507, Japan"}]},{"given":"Yasushi","family":"Okuno","sequence":"additional","affiliation":[{"name":"RIKEN Cluster for Science, Technology and Innovation Hub, Medical Sciences Innovation Hub Program, Kanagawa 230-0045, Japan"},{"name":"Graduate School of Medicine, Kyoto University, Kyoto 606-8507, Japan"}]}],"member":"1968","published-online":{"date-parts":[[2020,2,14]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"256","DOI":"10.1016\/j.drudis.2012.11.001","article-title":"Biological network inference for drug discovery","volume":"18","author":"Lecca","year":"2013","journal-title":"Drug Discov. Today"},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"10614","DOI":"10.1073\/pnas.93.20.10614","article-title":"Parallel human genome analysis: microarray-based expression monitoring of 1000 genes","volume":"93","author":"Schena","year":"1996","journal-title":"Proc. Natl. Acad. Sci. USA"},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"3158","DOI":"10.1186\/gb-2013-14-9-r95","article-title":"Comprehensive evaluation of differential gene expression analysis methods for RNA-seq data","volume":"14","author":"Rapaport","year":"2013","journal-title":"Genome Biol."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"44","DOI":"10.1038\/nprot.2008.211","article-title":"Systematic and integrative analysis of large gene lists using DAVID Bioinformatics Resources","volume":"4","author":"Huang","year":"2009","journal-title":"Nat. Protoc."},{"key":"ref_5","doi-asserted-by":"crossref","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":"Aravind","year":"2005","journal-title":"Proc. Natl. Acad. Sci. USA"},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"267","DOI":"10.1038\/ng1180","article-title":"PGC-1\u03b1-responsive genes involved in oxidative phosphorylation are coordinately downregulated in human diabetes","volume":"34","author":"Mootha","year":"2003","journal-title":"Nat. Genet."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"55","DOI":"10.1016\/j.compbiomed.2014.02.011","article-title":"A review on the computational approaches for gene regulatory network construction","volume":"48","author":"Chai","year":"2014","journal-title":"Comput. Biol. Med."},{"key":"ref_8","first-page":"615","article-title":"Mutation Consequences and Pathway Analysis Working Group of the International Cancer Genome Consortium. Pathway and network analysis of cancer genomes","volume":"12","author":"Creixell","year":"2015","journal-title":"Nat. Method"},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"147","DOI":"10.1016\/j.cels.2016.02.014","article-title":"Cross-disciplinary network comparison: Matchmaking between hairballs","volume":"2","author":"Yan","year":"2016","journal-title":"Cell Syst."},{"key":"ref_10","doi-asserted-by":"crossref","unstructured":"Margolin, A.A., Nemenman, I., Basso, K., Wiggins, C., Stolovitzky, G., Dalla Favera, R., and Califano, A. (2006). ARACNE: an algorithm for the reconstruction of gene regulatory networks in a mammalian cellular context. BMC Bioinform., 7.","DOI":"10.1186\/1471-2105-7-S1-S7"},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"221","DOI":"10.1007\/s10456-009-9142-8","article-title":"Analysis of PPAR\u03b1-dependent and PPAR\u03b1-independent transcript regulation following fenofibrate treatment of human endothelial cells","volume":"12","author":"Araki","year":"2009","journal-title":"Angiogenesis"},{"key":"ref_12","doi-asserted-by":"crossref","unstructured":"Wang, L., Hurley, D., Watkins, W., Araki, H., Tamada, Y., Muthukaruppan, A., Ranjard, L., Derkac, E., Imoto, S., and Miyano, S. (2012). Cell cycle gene networks are associated with melanoma prognosis. PLoS ONE, 7.","DOI":"10.1371\/journal.pone.0034247"},{"key":"ref_13","doi-asserted-by":"crossref","unstructured":"Affara, M., Sanders, D., Araki, H., Tamada, Y., Dunmore, B.J., Humphreys, S., Imoto, S., Savoie, C., Miyano, S., and Kuhara, S. (2013). Vasohibin-1 is identified as a master-regulator of endothelial cell apoptosis using gene network analysis. BMC Genomics, 14.","DOI":"10.1186\/1471-2164-14-23"},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"1013","DOI":"10.1007\/s00018-017-2679-6","article-title":"Differential gene regulatory networks in development and disease","volume":"75","author":"Singh","year":"2018","journal-title":"Cell Mol. Life Sci."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"683","DOI":"10.1109\/TCBB.2010.68","article-title":"Estimating genome-wide gene networks using nonparametric Bayesian network models on massively parallel computers","volume":"8","author":"Tamada","year":"2011","journal-title":"IEEE\/ACM Trans. Comput. Biol. Bioinform."},{"key":"ref_16","doi-asserted-by":"crossref","unstructured":"Shimamura, T., Imoto, S., Shimada, Y., Hosono, Y., Niida, A., Nagasaki, M., Yamaguchi, R., Takahashi, T., and Miyano, S. (2011). A novel network profiling analysis reveals system changes in epithelial-mesenchymal transition. PLoS ONE, 6.","DOI":"10.1371\/journal.pone.0020804"},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"189","DOI":"10.1186\/s12967-015-0546-5","article-title":"Unravelling personalized dysfunctional gene network of complex diseases based on differential network model","volume":"13","author":"Yu","year":"2015","journal-title":"J. Transl. Med."},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"226","DOI":"10.1016\/j.isci.2019.03.021","article-title":"Estimating sample-specific regulatory networks","volume":"14","author":"Kuijjer","year":"2019","journal-title":"iScience"},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"20","DOI":"10.1186\/2049-3002-2-20","article-title":"Metabolic and transcriptional profiling reveals pyruvate dehydrogenase kinase 4 as a mediator of epithelial-mesenchymal transition and drug resistance in tumor cells","volume":"2","author":"Sun","year":"2014","journal-title":"Cancer Metab."},{"key":"ref_20","doi-asserted-by":"crossref","unstructured":"Cancer Genome Atlas Research Network (2014). Comprehensive molecular profiling of lung adenocarcinoma. Nature, 511, 543\u2013550.","DOI":"10.1038\/nature13385"},{"key":"ref_21","first-page":"175","article-title":"Estimation of genetic networks and functional structures between genes by using Bayesian networks and nonparametric regression","volume":"7","author":"Imoto","year":"2002","journal-title":"Pac. Symp. Biocomput."},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"2224","DOI":"10.1093\/carcin\/bgu127","article-title":"Lung adenocarcinoma subtypes definable by lung development-related miRNA expression profiles in association with clinicopathologic features","volume":"35","author":"Arima","year":"2014","journal-title":"Carcinogenesis"},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"1575","DOI":"10.1158\/0008-5472.CAN-16-0512","article-title":"Bayesian network inference modeling identifies TRIB1 as a novel regulator of cell-cycle progression and survival in cancer cells","volume":"77","author":"Gendelman","year":"2017","journal-title":"Cancer Res."},{"key":"ref_24","doi-asserted-by":"crossref","unstructured":"Goldman, M., Craft, B., Hastie, M., Repe\u010dka, K., McDade, F., Kamath, A., Banerjee, A., Luo, Y., Rogers, D., and Brooks, A.N. (2019). The UCSC Xena platform for public and private cancer genomics data visualization and interpretation. bioRxiv, 326470.","DOI":"10.1101\/326470"},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"e47","DOI":"10.1093\/nar\/gkv007","article-title":"limma powers differential expression analyses for RNA-sequencing and microarray studies","volume":"43","author":"Ritchie","year":"2015","journal-title":"Nucleic Acids Res."},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"289","DOI":"10.1111\/j.2517-6161.1995.tb02031.x","article-title":"Controlling the False Discovery Rate: A Practical and Powerful Approach to Multiple Testing","volume":"57","author":"Benjamini","year":"1995","journal-title":"J. R. Stat. Soc. B"},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"523","DOI":"10.1093\/bioinformatics\/btt703","article-title":"Causal analysis approaches in Ingenuity Pathway Analysis","volume":"30","author":"Green","year":"2014","journal-title":"Bioinformatics"},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"e71","DOI":"10.1093\/nar\/gkv1507","article-title":"TCGAbiolinks: an R\/Bioconductor package for integrative analysis of TCGA data","volume":"44","author":"Colaprico","year":"2016","journal-title":"Nucleic Acids Res."},{"key":"ref_29","doi-asserted-by":"crossref","unstructured":"Mounir, M., Lucchetta, M., Silva, T.C., Olsen, C., Bontempi, G., Chen, X., Noushmehr, H., Colaprico, A., and Papaleo, E. (2019). New functionalities in the TCGAbiolinks package for the study and integration of cancer data from GDC and GTEx. PLoS Comput. Biol., 15.","DOI":"10.1371\/journal.pcbi.1006701"},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"2498","DOI":"10.1101\/gr.1239303","article-title":"Cytoscape: A software environment for integrated models of biomolecular interaction networks","volume":"13","author":"Shannon","year":"2003","journal-title":"Genome Res."},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"6","DOI":"10.1186\/s40169-015-0048-3","article-title":"EMT and tumor metastasis","volume":"4","author":"Heerboth","year":"2015","journal-title":"Clin. Transl. Med."},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"1216","DOI":"10.1126\/science.1176009","article-title":"The extracellular matrix: Not just pretty fibrils","volume":"326","author":"Hynes","year":"2009","journal-title":"Science"},{"key":"ref_33","doi-asserted-by":"crossref","first-page":"388","DOI":"10.4161\/cbt.12.5.15957","article-title":"Heparan sulfate D-glucosaminyl 3-O-sulfotransferase-3B1, a novel epithelial-mesenchymal transition inducer in pancreatic cancer","volume":"12","author":"Song","year":"2011","journal-title":"Cancer Biol. Ther."},{"key":"ref_34","doi-asserted-by":"crossref","first-page":"916","DOI":"10.1158\/1078-0432.CCR-17-1347","article-title":"FAM198B is associated with prolonged survival and inhibits metastasis in lung adenocarcinoma via blockage of ERK-mediated MMP-1 expression","volume":"24","author":"Hsu","year":"2018","journal-title":"Clin. Cancer Res."},{"key":"ref_35","doi-asserted-by":"crossref","first-page":"20636","DOI":"10.18632\/oncotarget.4114","article-title":"Insulin-like growth factor binding protein 5 (IGFBP5) functions as a tumor suppressor in human melanoma cells","volume":"6","author":"Wang","year":"2015","journal-title":"Oncotarget"},{"key":"ref_36","doi-asserted-by":"crossref","first-page":"368","DOI":"10.1002\/dvdy.24557","article-title":"Role of the extracellular matrix in cancer-associated epithelial to mesenchymal transition phenomenon","volume":"247","author":"Tzanakakis","year":"2018","journal-title":"Dev. Dyn."}],"container-title":["Biomolecules"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2218-273X\/10\/2\/306\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T08:58:01Z","timestamp":1760173081000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2218-273X\/10\/2\/306"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,2,14]]},"references-count":36,"journal-issue":{"issue":"2","published-online":{"date-parts":[[2020,2]]}},"alternative-id":["biom10020306"],"URL":"https:\/\/doi.org\/10.3390\/biom10020306","relation":{},"ISSN":["2218-273X"],"issn-type":[{"value":"2218-273X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020,2,14]]}}}