000271138 001__ 271138
000271138 005__ 20240816121456.0
000271138 0247_ $$2doi$$a10.56553/popets-2024-0062
000271138 037__ $$aDZNE-2024-01006
000271138 082__ $$a004
000271138 1001_ $$aChen, Dingfan$$b0
000271138 245__ $$aTowards Biologically Plausible and Private Gene Expression Data Generation
000271138 260__ $$aWarsaw, Poland$$bDe Gruyter Open$$c2024
000271138 3367_ $$2DRIVER$$aarticle
000271138 3367_ $$2DataCite$$aOutput Types/Journal article
000271138 3367_ $$0PUB:(DE-HGF)16$$2PUB:(DE-HGF)$$aJournal Article$$bjournal$$mjournal$$s1723718977_26248
000271138 3367_ $$2BibTeX$$aARTICLE
000271138 3367_ $$2ORCID$$aJOURNAL_ARTICLE
000271138 3367_ $$00$$2EndNote$$aJournal Article
000271138 520__ $$aGenerative models trained with Differential Privacy (DP) are becoming increasingly prominent in the creation of synthetic data for downstream applications. Existing literature, however, primarily focuses on basic benchmarking datasets and tends to report promising results only for elementary metrics and relatively simple data distributions. In this paper, we initiate a systematic analysis of how DP generative models perform in their natural application scenarios, specifically focusing on real-world gene expression data. We conduct a comprehensive analysis of five representative DP generation methods, examining them from various angles, such as downstream utility, statistical properties, and biological plausibility. Our extensive evaluation illuminates the unique characteristics of each DP generation method, offering critical insights into the strengths and weaknesses of each approach, and uncovering intriguing possibilities for future developments. Perhaps surprisingly, our analysis reveals that most methods are capable of achieving seemingly reasonable downstream utility, according to the standard evaluation metrics considered in existing literature. Nevertheless, we find that none of the DP methods are able to accurately capture the biological characteristics of the real dataset. This observation suggests a potential over-optimistic assessment of current methodologies in this field and underscores a pressing need for future enhancements in model design.
000271138 536__ $$0G:(DE-HGF)POF4-354$$a354 - Disease Prevention and Healthy Aging (POF4-354)$$cPOF4-354$$fPOF IV$$x0
000271138 588__ $$aDataset connected to CrossRef, Journals: pub.dzne.de
000271138 7001_ $$0P:(DE-2719)9002070$$aOestreich, Marie$$b1$$udzne
000271138 7001_ $$aAfonja, Tejumade$$b2
000271138 7001_ $$aKerkouche, Raouf$$b3
000271138 7001_ $$0P:(DE-2719)2812750$$aBecker, Matthias$$b4$$udzne
000271138 7001_ $$aFritz, Mario$$b5
000271138 773__ $$0PERI:(DE-600)2877594-6$$a10.56553/popets-2024-0062$$gVol. 2024, no. 2, p. 531 - 554$$n2$$p531 - 554$$tProceedings on privacy enhancing technologies$$v2024$$x2299-0984$$y2024
000271138 8564_ $$uhttps://pub.dzne.de/record/271138/files/DZNE-2024-01006.pdf$$yOpenAccess
000271138 8564_ $$uhttps://pub.dzne.de/record/271138/files/DZNE-2024-01006.pdf?subformat=pdfa$$xpdfa$$yOpenAccess
000271138 909CO $$ooai:pub.dzne.de:271138$$popenaire$$popen_access$$pVDB$$pdriver$$pdnbdelivery
000271138 9101_ $$0I:(DE-588)1065079516$$6P:(DE-2719)9002070$$aDeutsches Zentrum für Neurodegenerative Erkrankungen$$b1$$kDZNE
000271138 9101_ $$0I:(DE-588)1065079516$$6P:(DE-2719)2812750$$aDeutsches Zentrum für Neurodegenerative Erkrankungen$$b4$$kDZNE
000271138 9131_ $$0G:(DE-HGF)POF4-354$$1G:(DE-HGF)POF4-350$$2G:(DE-HGF)POF4-300$$3G:(DE-HGF)POF4$$4G:(DE-HGF)POF$$aDE-HGF$$bGesundheit$$lNeurodegenerative Diseases$$vDisease Prevention and Healthy Aging$$x0
000271138 9141_ $$y2024
000271138 915__ $$0StatID:(DE-HGF)0510$$2StatID$$aOpenAccess
000271138 915__ $$0StatID:(DE-HGF)0300$$2StatID$$aDBCoverage$$bMedline$$d2023-09-02
000271138 915__ $$0LIC:(DE-HGF)CCBY4$$2HGFVOC$$aCreative Commons Attribution CC BY 4.0
000271138 9201_ $$0I:(DE-2719)1013038$$kAG Schultze$$lClinical Single Cell Omics (CSCO) / Systems Medicine$$x0
000271138 9201_ $$0I:(DE-2719)5000079$$kAG Becker$$lModular High Performance Computing and Artificial Intelligence$$x1
000271138 980__ $$ajournal
000271138 980__ $$aVDB
000271138 980__ $$aUNRESTRICTED
000271138 980__ $$aI:(DE-2719)1013038
000271138 980__ $$aI:(DE-2719)5000079
000271138 9801_ $$aFullTexts