MultImp: Multiomics Generative Models for Data Imputation

Ji-Eun Park, Wancen Mu, Yining Jiao, Michael I Love, Marc Niethammer, Natalie Stanley

Abstract: In biomedical applications, patients are often prof iled with multiple technologies or assays to produce a multiomics or multiview biological dataset. A challenge in collecting these datasets is that there are often entire views or individual features missing, which can significantly limit the accuracy of downstream tasks, such as, predicting a patient phenotype. Here, we propose a multiview based deep generative adversarial data imputation model (MultImp). MultImp improves imputation quality and disease subtype classification accuracy in comparison to several baseline methods across two multiomics datasets. MultImp is now publicly available at https: //github.com/multimp/multimp.