MT-LLE: Multi-Task Locally Linear Embedding for Interpretable Disease Modeling from Longitudinal Omics Data
Sundous Hussein, Iain R. Konigsberg, Katerina J. Kechris, Russell Paul Bowler, Farnoush Banaei‐Kashani
This paper introduces MT-LLE, a multi-task manifold learning method that improves disease modeling from longitudinal omics data by integrating clinical labels and temporal progression, achieving better clinical structure and progression forecasting than standard methods.
bioRxiv · Aug 27, 2026 · PreprintBioinformatics