000268866 001__ 268866
000268866 005__ 20240421003713.0
000268866 0247_ $$2doi$$a10.1038/s42256-023-00744-z
000268866 0247_ $$2altmetric$$aaltmetric:155785283
000268866 037__ $$aDZNE-2024-00365
000268866 082__ $$a004
000268866 1001_ $$0P:(DE-2719)9001044$$aLagemann, Kai$$b0$$eFirst author$$udzne
000268866 245__ $$aDeep learning of causal structures in high dimensions under data limitations
000268866 260__ $$a[London]$$bSpringer Nature Publishing$$c2023
000268866 3367_ $$2DRIVER$$aarticle
000268866 3367_ $$2DataCite$$aOutput Types/Journal article
000268866 3367_ $$0PUB:(DE-HGF)16$$2PUB:(DE-HGF)$$aJournal Article$$bjournal$$mjournal$$s1713172265_9657
000268866 3367_ $$2BibTeX$$aARTICLE
000268866 3367_ $$2ORCID$$aJOURNAL_ARTICLE
000268866 3367_ $$00$$2EndNote$$aJournal Article
000268866 520__ $$aCausal learning is a key challenge in scientific artificial intelligence as it allows researchers to go beyond purely correlative or predictive analyses towards learning underlying cause-and-effect relationships, which are important for scientific understanding as well as for a wide range of downstream tasks. Here, motivated by emerging biomedical questions, we propose a deep neural architecture for learning causal relationships between variables from a combination of high-dimensional data and prior causal knowledge. We combine convolutional and graph neural networks within a causal risk framework to provide an approach that is demonstrably effective under the conditions of high dimensionality, noise and data limitations that are characteristic of many applications, including in large-scale biology. In experiments, we find that the proposed learners can effectively identify novel causal relationships across thousands of variables. Results include extensive (linear and nonlinear) simulations (where the ground truth is known and can be directly compared against), as well as real biological examples where the models are applied to high-dimensional molecular data and their outputs compared against entirely unseen validation experiments. These results support the notion that deep learning approaches can be used to learn causal networks at large scale.
000268866 536__ $$0G:(DE-HGF)POF4-354$$a354 - Disease Prevention and Healthy Aging (POF4-354)$$cPOF4-354$$fPOF IV$$x0
000268866 588__ $$aDataset connected to CrossRef, Journals: pub.dzne.de
000268866 7001_ $$aLagemann, Christian$$b1
000268866 7001_ $$0P:(DE-2719)2812256$$aTaschler, Bernd$$b2
000268866 7001_ $$0P:(DE-2719)2811372$$aMukherjee, Sach$$b3$$eLast author$$udzne
000268866 773__ $$0PERI:(DE-600)2933875-X$$a10.1038/s42256-023-00744-z$$gVol. 5, no. 11, p. 1306 - 1316$$n11$$p1306 - 1316$$tNature machine intelligence$$v5$$x2522-5839$$y2023
000268866 8564_ $$uhttps://pub.dzne.de/record/268866/files/DZNE-2024-00365.pdf$$yOpenAccess
000268866 8564_ $$uhttps://pub.dzne.de/record/268866/files/DZNE-2024-00365.pdf?subformat=pdfa$$xpdfa$$yOpenAccess
000268866 909CO $$ooai:pub.dzne.de:268866$$pdnbdelivery$$pdriver$$pVDB$$popen_access$$popenaire
000268866 9101_ $$0I:(DE-588)1065079516$$6P:(DE-2719)9001044$$aDeutsches Zentrum für Neurodegenerative Erkrankungen$$b0$$kDZNE
000268866 9101_ $$0I:(DE-588)1065079516$$6P:(DE-2719)2812256$$aDeutsches Zentrum für Neurodegenerative Erkrankungen$$b2$$kDZNE
000268866 9101_ $$0I:(DE-588)1065079516$$6P:(DE-2719)2811372$$aDeutsches Zentrum für Neurodegenerative Erkrankungen$$b3$$kDZNE
000268866 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
000268866 915__ $$0StatID:(DE-HGF)0200$$2StatID$$aDBCoverage$$bSCOPUS$$d2023-08-29
000268866 915__ $$0StatID:(DE-HGF)0160$$2StatID$$aDBCoverage$$bEssential Science Indicators$$d2023-08-29
000268866 915__ $$0StatID:(DE-HGF)1160$$2StatID$$aDBCoverage$$bCurrent Contents - Engineering, Computing and Technology$$d2023-08-29
000268866 915__ $$0LIC:(DE-HGF)CCBY4$$2HGFVOC$$aCreative Commons Attribution CC BY 4.0
000268866 915__ $$0StatID:(DE-HGF)9920$$2StatID$$aIF >= 20$$bNAT MACH INTELL : 2022$$d2023-08-29
000268866 915__ $$0StatID:(DE-HGF)0100$$2StatID$$aJCR$$bNAT MACH INTELL : 2022$$d2023-08-29
000268866 915__ $$0StatID:(DE-HGF)0113$$2StatID$$aWoS$$bScience Citation Index Expanded$$d2023-08-29
000268866 915__ $$0StatID:(DE-HGF)3003$$2StatID$$aDEAL Nature$$d2023-08-29$$wger
000268866 915__ $$0StatID:(DE-HGF)0150$$2StatID$$aDBCoverage$$bWeb of Science Core Collection$$d2023-08-29
000268866 915__ $$0StatID:(DE-HGF)0510$$2StatID$$aOpenAccess
000268866 915__ $$0StatID:(DE-HGF)0300$$2StatID$$aDBCoverage$$bMedline$$d2023-08-29
000268866 915__ $$0StatID:(DE-HGF)0199$$2StatID$$aDBCoverage$$bClarivate Analytics Master Journal List$$d2023-08-29
000268866 9201_ $$0I:(DE-2719)1013030$$kAG Mukherjee$$lStatistics and Machine Learning$$x0
000268866 980__ $$ajournal
000268866 980__ $$aVDB
000268866 980__ $$aUNRESTRICTED
000268866 980__ $$aI:(DE-2719)1013030
000268866 9801_ $$aFullTexts