Journal Article

LEOPARD: missing view completion for multi-timepoint omics data via representation disentanglement and temporal knowledge transfer

Roden, Michael, Han, Siyu, Casale, Francesco Paolo, Prehn, Cornelia, Ge, Jianhong, Petrera, Agnese, Peters, Annette, Matullo, Giuseppe, Lin, Jiesheng, Shi, Mengya, Adamski, Jerzy, Cai, Na, Li, Ying, Suhre, Karsten, Hauck, Stefanie M., Wang-Sattler, Rui, Yu, Shixiang, Harada, Makoto, Sam, Flora, Gieger, Christian, Herder, Christian

2025

Overview

Longitudinal multi-view omics data offer unique insights into the temporal dynamics of individual-level physiology, which provides opportunities to advance personalized healthcare. However, the common occurrence of incomplete views makes extrapolation tasks difficult, and there is a lack of tailored methods for this critical issue. Here, we introduce LEOPARD, an innovative approach specifically designed to complete missing views in multi-timepoint omics data. By disentangling longitudinal omics data into content and temporal representations, LEOPARD transfers the temporal knowledge to the omics-specific content, thereby completing missing views. The effectiveness of LEOPARD is validated on four real-world omics datasets constructed with data from the MGH COVID study and the KORA cohort, spanning periods from 3 days to 14 years. Compared to conventional imputation methods, such as missForest, PMM, GLMM, and cGAN, LEOPARD yields the most robust results across the benchmark datasets. LEOPARD-imputed data also achieve the highest agreement with observed data in our analyses for age-associated metabolites detection, estimated glomerular filtration rate-associated proteins identification, and chronic kidney disease prediction. Our work takes the first step toward a generalized treatment of missing views in longitudinal omics data, enabling comprehensive exploration of temporal dynamics and providing valuable insights into personalized healthcare. Missing modality challenges longitudinal omics studies. Here, the authors introduce LEOPARD, a pioneering neural network that uses style transfer to re-entangle omics data, enabling robust imputation and unlocking fresh insights into predictive healthcare and biological temporal dynamics.

• Publisher: Nature Publishing Group UK,Nature Publishing Group,Nature Portfolio
• Subject: 631/114/1305 / 692/4017 / Case studies / Computational Biology / COVID-19 - metabolism / COVID-19 - virology / Customization / Datasets / Glomerular filtration rate / Health care / Humanities and Social Sciences / Humans / Kidney diseases / Knowledge / Knowledge representation / Longitudinal Studies / Metabolites / Missing data / multidisciplinary / Multiomics - methods / Neural networks / Robustness / Science / Science (multidisciplinary) / Statistical power