An unsupervised learning approach to identify novel signatures of health and disease from multimodal data.
Ilan ShomoronyElizabeth T CirulliLei HuangLori A NapierRobyn R HeisterMichael HicksIsaac V CohenHung-Chun YuChristine Leon SwisherNatalie M Schenker-AhmedWeizhong LiKaren E NelsonPamila BrarAndrew M KahnTimothy D SpectorC Thomas CaskeyJ Craig VenterDavid S KarowEwen F KirknessNaisha ShahPublished in: Genome medicine (2020)
Our methodology and results demonstrate the potential of multimodal data integration, from the identification of novel biomarker signatures to a data-driven stratification of individuals into disease subtypes and stages-an essential step towards personalized, preventative health risk assessment.