000623116 001__ 623116
000623116 005__ 20250919155014.0
000623116 0247_ $$2doi$$a10.1038/s41467-025-62237-4
000623116 037__ $$aPUBDB-2025-00603
000623116 082__ $$a500
000623116 1001_ $$0P:(DE-H253)PIP1106404$$aNeumann, Philipp$$b0
000623116 245__ $$aHigh Performance Data Integration for Large-Scale Analyses of Incomplete Omic Profiles Using Batch-Effect Reduction Trees (BERT)
000623116 260__ $$a[London]$$bSpringer Nature$$c2025
000623116 3367_ $$2DRIVER$$aarticle
000623116 3367_ $$2DataCite$$aOutput Types/Journal article
000623116 3367_ $$0PUB:(DE-HGF)16$$2PUB:(DE-HGF)$$aJournal Article$$bjournal$$mjournal$$s1758289723_110687
000623116 3367_ $$2BibTeX$$aARTICLE
000623116 3367_ $$2ORCID$$aJOURNAL_ARTICLE
000623116 3367_ $$00$$2EndNote$$aJournal Article
000623116 520__ $$aData from high-throughput technologies assessing global patterns of biomolecules (omic data), is often afflicted with missing values and with measurement-specific biases (batch-effects), that hinder the quantitative comparison of independently acquired datasets. This work introduces batch-effect reduction trees (BERT), a high-performance method for data integration of incomplete omic profiles.We characterize BERT on large-scale data integration tasks with up to 5000 datasets from simulated and experimental data of different quantification techniques and omic types (proteomics, transcriptomics, metabolomics) as well as other datatypes e.g., clinical data, emphasizing the broad scope of the algorithm. Compared to the only available method for integration of incomplete omic data, HarmonizR, our method1) retains up to five orders of magnitude more numeric values,2) leverages multi-core and distributed-memory systems for up to 11x runtime improvement3) considers covariates and reference measurements to account for severely imbalanced or sparsely distributed conditions (up to 2x improvement of average-silhouette-width).
000623116 536__ $$0G:(DE-HGF)POF4-623$$a623 - Data Management and Analysis (POF4-623)$$cPOF4-623$$fPOF IV$$x0
000623116 588__ $$aDataset connected to CrossRef, Journals: bib-pubdb1.desy.de
000623116 693__ $$0EXP:(DE-MLZ)NOSPEC-20140101$$5EXP:(DE-MLZ)NOSPEC-20140101$$eNo specific instrument$$x0
000623116 7001_ $$0P:(DE-H253)PIP1086181$$aSchumann, Yannis$$b1$$eCorresponding author
000623116 7001_ $$0P:(DE-HGF)0$$aSchlumbohm, Simon$$b2
000623116 7001_ $$0P:(DE-HGF)0$$aNeumann, Julia$$b3
000623116 773__ $$0PERI:(DE-600)2553671-0$$a10.1038/s41467-025-62237-4$$gVol. 16, no. 1, p. 7104$$n1$$p7104$$tNature Communications$$v16$$x2041-1723$$y2025
000623116 8564_ $$uhttps://bib-pubdb1.desy.de/record/623116/files/HTML-Approval_of_scientific_publication.html
000623116 8564_ $$uhttps://bib-pubdb1.desy.de/record/623116/files/PDF-Approval_of_scientific_publication.pdf
000623116 8564_ $$uhttps://bib-pubdb1.desy.de/record/623116/files/Schumann_et_al-2025-Nature_Communications.pdf$$yRestricted
000623116 8564_ $$uhttps://bib-pubdb1.desy.de/record/623116/files/Schumann_et_al-2025-Nature_Communications.pdf?subformat=pdfa$$xpdfa$$yRestricted
000623116 8767_ $$92025-07-31$$d2025-08-01$$eAPC$$jDEAL$$lSpringerNature$$v18.19
000623116 8767_ $$92025-07-31$$d2025-08-01$$ePayment fee$$jBestellt$$lSpringerNature$$v0.35$$zMPDL Gebühr
000623116 9101_ $$0I:(DE-588b)2008985-5$$6P:(DE-H253)PIP1106404$$aDeutsches Elektronen-Synchrotron$$b0$$kDESY
000623116 9101_ $$0I:(DE-HGF)0$$6P:(DE-H253)PIP1106404$$aExternal Institute$$b0$$kExtern
000623116 9101_ $$0I:(DE-588b)2008985-5$$6P:(DE-H253)PIP1086181$$aDeutsches Elektronen-Synchrotron$$b1$$kDESY
000623116 9101_ $$0I:(DE-HGF)0$$6P:(DE-HGF)0$$a Helmut-Schmidt-Universität, Chair for High Performance Computing$$b2
000623116 9101_ $$0I:(DE-HGF)0$$6P:(DE-HGF)0$$aUniversitätsklinikum Hamburg-Eppendorf, UKE$$b3
000623116 9131_ $$0G:(DE-HGF)POF4-623$$1G:(DE-HGF)POF4-620$$2G:(DE-HGF)POF4-600$$3G:(DE-HGF)POF4$$4G:(DE-HGF)POF$$aDE-HGF$$bForschungsbereich Materie$$lMaterie und Technologie$$vData Management and Analysis$$x0
000623116 9141_ $$y2025
000623116 915pc $$0PC:(DE-HGF)0000$$2APC$$aAPC keys set
000623116 915pc $$0PC:(DE-HGF)0001$$2APC$$aLocal Funding
000623116 915pc $$0PC:(DE-HGF)0003$$2APC$$aDOAJ Journal
000623116 915pc $$0PC:(DE-HGF)0113$$2APC$$aDEAL: Springer Nature 2020
000623116 915__ $$0StatID:(DE-HGF)0100$$2StatID$$aJCR$$bNAT COMMUN : 2022$$d2025-01-02
000623116 915__ $$0StatID:(DE-HGF)0200$$2StatID$$aDBCoverage$$bSCOPUS$$d2025-01-02
000623116 915__ $$0StatID:(DE-HGF)0300$$2StatID$$aDBCoverage$$bMedline$$d2025-01-02
000623116 915__ $$0StatID:(DE-HGF)0501$$2StatID$$aDBCoverage$$bDOAJ Seal$$d2024-01-30T07:48:07Z
000623116 915__ $$0StatID:(DE-HGF)0500$$2StatID$$aDBCoverage$$bDOAJ$$d2024-01-30T07:48:07Z
000623116 915__ $$0StatID:(DE-HGF)0030$$2StatID$$aPeer Review$$bDOAJ : Peer review$$d2024-01-30T07:48:07Z
000623116 915__ $$0LIC:(DE-HGF)CCBYNV$$2V:(DE-HGF)$$aCreative Commons Attribution CC BY (No Version)$$bDOAJ$$d2024-01-30T07:48:07Z
000623116 915__ $$0StatID:(DE-HGF)0199$$2StatID$$aDBCoverage$$bClarivate Analytics Master Journal List$$d2025-01-02
000623116 915__ $$0StatID:(DE-HGF)1040$$2StatID$$aDBCoverage$$bZoological Record$$d2025-01-02
000623116 915__ $$0StatID:(DE-HGF)1060$$2StatID$$aDBCoverage$$bCurrent Contents - Agriculture, Biology and Environmental Sciences$$d2025-01-02
000623116 915__ $$0StatID:(DE-HGF)1150$$2StatID$$aDBCoverage$$bCurrent Contents - Physical, Chemical and Earth Sciences$$d2025-01-02
000623116 915__ $$0StatID:(DE-HGF)1050$$2StatID$$aDBCoverage$$bBIOSIS Previews$$d2025-01-02
000623116 915__ $$0StatID:(DE-HGF)0160$$2StatID$$aDBCoverage$$bEssential Science Indicators$$d2025-01-02
000623116 915__ $$0StatID:(DE-HGF)1030$$2StatID$$aDBCoverage$$bCurrent Contents - Life Sciences$$d2025-01-02
000623116 915__ $$0StatID:(DE-HGF)1190$$2StatID$$aDBCoverage$$bBiological Abstracts$$d2025-01-02
000623116 915__ $$0StatID:(DE-HGF)0113$$2StatID$$aWoS$$bScience Citation Index Expanded$$d2025-01-02
000623116 915__ $$0StatID:(DE-HGF)0150$$2StatID$$aDBCoverage$$bWeb of Science Core Collection$$d2025-01-02
000623116 915__ $$0StatID:(DE-HGF)9915$$2StatID$$aIF >= 15$$bNAT COMMUN : 2022$$d2025-01-02
000623116 915__ $$0StatID:(DE-HGF)0561$$2StatID$$aArticle Processing Charges$$d2025-01-02
000623116 915__ $$0StatID:(DE-HGF)0700$$2StatID$$aFees$$d2025-01-02
000623116 9201_ $$0I:(DE-H253)IT-20120731$$kIT$$lInformationstechnologie$$x0
000623116 980__ $$ajournal
000623116 980__ $$aEDITORS
000623116 980__ $$aVDBINPRINT
000623116 980__ $$aI:(DE-H253)IT-20120731
000623116 980__ $$aAPC
000623116 980__ $$aUNRESTRICTED
000623116 9801_ $$aAPC