000267539 001__ 267539
000267539 005__ 20240229154920.0
000267539 0247_ $$2doi$$a10.1371/journal.pone.0281618
000267539 0247_ $$2pmid$$apmid:36763605
000267539 0247_ $$2pmc$$apmc:PMC9916647
000267539 0247_ $$2altmetric$$aaltmetric:142374983
000267539 037__ $$aDKFZ-2023-00317
000267539 041__ $$aEnglish
000267539 082__ $$a610
000267539 1001_ $$00000-0001-5393-8180$$aMassi, Michela C$$b0
000267539 245__ $$aLearning high-order interactions for polygenic risk prediction.
000267539 260__ $$aSan Francisco, California, US$$bPLOS$$c2023
000267539 3367_ $$2DRIVER$$aarticle
000267539 3367_ $$2DataCite$$aOutput Types/Journal article
000267539 3367_ $$0PUB:(DE-HGF)16$$2PUB:(DE-HGF)$$aJournal Article$$bjournal$$mjournal$$s1677578969_27830
000267539 3367_ $$2BibTeX$$aARTICLE
000267539 3367_ $$2ORCID$$aJOURNAL_ARTICLE
000267539 3367_ $$00$$2EndNote$$aJournal Article
000267539 520__ $$aWithin the framework of precision medicine, the stratification of individual genetic susceptibility based on inherited DNA variation has paramount relevance. However, one of the most relevant pitfalls of traditional Polygenic Risk Scores (PRS) approaches is their inability to model complex high-order non-linear SNP-SNP interactions and their effect on the phenotype (e.g. epistasis). Indeed, they incur in a computational challenge as the number of possible interactions grows exponentially with the number of SNPs considered, affecting the statistical reliability of the model parameters as well. In this work, we address this issue by proposing a novel PRS approach, called High-order Interactions-aware Polygenic Risk Score (hiPRS), that incorporates high-order interactions in modeling polygenic risk. The latter combines an interaction search routine based on frequent itemsets mining and a novel interaction selection algorithm based on Mutual Information, to construct a simple and interpretable weighted model of user-specified dimensionality that can predict a given binary phenotype. Compared to traditional PRSs methods, hiPRS does not rely on GWAS summary statistics nor any external information. Moreover, hiPRS differs from Machine Learning-based approaches that can include complex interactions in that it provides a readable and interpretable model and it is able to control overfitting, even on small samples. In the present work we demonstrate through a comprehensive simulation study the superior performance of hiPRS w.r.t. state of the art methods, both in terms of scoring performance and interpretability of the resulting model. We also test hiPRS against small sample size, class imbalance and the presence of noise, showcasing its robustness to extreme experimental settings. Finally, we apply hiPRS to a case study on real data from DACHS cohort, defining an interaction-aware scoring model to predict mortality of stage II-III Colon-Rectal Cancer patients treated with oxaliplatin.
000267539 536__ $$0G:(DE-HGF)POF4-313$$a313 - Krebsrisikofaktoren und Prävention (POF4-313)$$cPOF4-313$$fPOF IV$$x0
000267539 588__ $$aDataset connected to CrossRef, PubMed, , Journals: inrepo02.dkfz.de
000267539 7001_ $$aFranco, Nicola R$$b1
000267539 7001_ $$00000-0001-8277-2802$$aManzoni, Andrea$$b2
000267539 7001_ $$aPaganoni, Anna Maria$$b3
000267539 7001_ $$0P:(DE-HGF)0$$aPark, Hanla A$$b4
000267539 7001_ $$0P:(DE-He78)6c5d058b7552d071a7fa4c5e943fff0f$$aHoffmeister, Michael$$b5$$udkfz
000267539 7001_ $$0P:(DE-He78)90d5535ff896e70eed81f4a4f6f22ae2$$aBrenner, Hermann$$b6$$udkfz
000267539 7001_ $$0P:(DE-He78)c259d6cc99edf5c7bc7ce22c7f87c253$$aChang-Claude, Jenny$$b7$$udkfz
000267539 7001_ $$00000-0003-0165-1983$$aIeva, Francesca$$b8
000267539 7001_ $$00000-0002-2470-0189$$aZunino, Paolo$$b9
000267539 773__ $$0PERI:(DE-600)2267670-3$$a10.1371/journal.pone.0281618$$gVol. 18, no. 2, p. e0281618 -$$n2$$pe0281618 -$$tPLOS ONE$$v18$$x1932-6203$$y2023
000267539 909CO $$ooai:inrepo02.dkfz.de:267539$$pVDB
000267539 9101_ $$0I:(DE-588b)2036810-0$$6P:(DE-HGF)0$$aDeutsches Krebsforschungszentrum$$b4$$kDKFZ
000267539 9101_ $$0I:(DE-588b)2036810-0$$6P:(DE-He78)6c5d058b7552d071a7fa4c5e943fff0f$$aDeutsches Krebsforschungszentrum$$b5$$kDKFZ
000267539 9101_ $$0I:(DE-588b)2036810-0$$6P:(DE-He78)90d5535ff896e70eed81f4a4f6f22ae2$$aDeutsches Krebsforschungszentrum$$b6$$kDKFZ
000267539 9101_ $$0I:(DE-588b)2036810-0$$6P:(DE-He78)c259d6cc99edf5c7bc7ce22c7f87c253$$aDeutsches Krebsforschungszentrum$$b7$$kDKFZ
000267539 9131_ $$0G:(DE-HGF)POF4-313$$1G:(DE-HGF)POF4-310$$2G:(DE-HGF)POF4-300$$3G:(DE-HGF)POF4$$4G:(DE-HGF)POF$$aDE-HGF$$bGesundheit$$lKrebsforschung$$vKrebsrisikofaktoren und Prävention$$x0
000267539 9141_ $$y2023
000267539 915__ $$0StatID:(DE-HGF)0501$$2StatID$$aDBCoverage$$bDOAJ Seal$$d2022-04-12T10:14:32Z
000267539 915__ $$0StatID:(DE-HGF)0500$$2StatID$$aDBCoverage$$bDOAJ$$d2022-04-12T10:14:32Z
000267539 915__ $$0LIC:(DE-HGF)CCBYNV$$2V:(DE-HGF)$$aCreative Commons Attribution CC BY (No Version)$$bDOAJ$$d2022-04-12T10:14:32Z
000267539 915__ $$0StatID:(DE-HGF)1190$$2StatID$$aDBCoverage$$bBiological Abstracts$$d2022-11-16
000267539 915__ $$0StatID:(DE-HGF)0113$$2StatID$$aWoS$$bScience Citation Index Expanded$$d2022-11-16
000267539 915__ $$0StatID:(DE-HGF)0160$$2StatID$$aDBCoverage$$bEssential Science Indicators$$d2022-11-16
000267539 915__ $$0StatID:(DE-HGF)0561$$2StatID$$aArticle Processing Charges$$d2022-11-16
000267539 915__ $$0StatID:(DE-HGF)0700$$2StatID$$aFees$$d2022-11-16
000267539 915__ $$0StatID:(DE-HGF)0200$$2StatID$$aDBCoverage$$bSCOPUS$$d2023-10-25
000267539 915__ $$0StatID:(DE-HGF)0300$$2StatID$$aDBCoverage$$bMedline$$d2023-10-25
000267539 915__ $$0StatID:(DE-HGF)0320$$2StatID$$aDBCoverage$$bPubMed Central$$d2023-10-25
000267539 915__ $$0StatID:(DE-HGF)0030$$2StatID$$aPeer Review$$bDOAJ : Anonymous peer review$$d2022-04-12T10:14:32Z
000267539 915__ $$0StatID:(DE-HGF)0600$$2StatID$$aDBCoverage$$bEbsco Academic Search$$d2023-10-25
000267539 915__ $$0StatID:(DE-HGF)0030$$2StatID$$aPeer Review$$bASC$$d2023-10-25
000267539 915__ $$0StatID:(DE-HGF)0199$$2StatID$$aDBCoverage$$bClarivate Analytics Master Journal List$$d2023-10-25
000267539 915__ $$0StatID:(DE-HGF)1050$$2StatID$$aDBCoverage$$bBIOSIS Previews$$d2023-10-25
000267539 915__ $$0StatID:(DE-HGF)0150$$2StatID$$aDBCoverage$$bWeb of Science Core Collection$$d2023-10-25
000267539 915__ $$0StatID:(DE-HGF)1040$$2StatID$$aDBCoverage$$bZoological Record$$d2023-10-25
000267539 9201_ $$0I:(DE-He78)C020-20160331$$kC020$$lC020 Epidemiologie von Krebs$$x0
000267539 9201_ $$0I:(DE-He78)C070-20160331$$kC070$$lC070 Klinische Epidemiologie und Alternf.$$x1
000267539 9201_ $$0I:(DE-He78)C120-20160331$$kC120$$lPräventive Onkologie$$x2
000267539 9201_ $$0I:(DE-He78)HD01-20160331$$kHD01$$lDKTK HD zentral$$x3
000267539 980__ $$ajournal
000267539 980__ $$aVDB
000267539 980__ $$aI:(DE-He78)C020-20160331
000267539 980__ $$aI:(DE-He78)C070-20160331
000267539 980__ $$aI:(DE-He78)C120-20160331
000267539 980__ $$aI:(DE-He78)HD01-20160331
000267539 980__ $$aUNRESTRICTED