Deep learning representations of human Immune Health for precision immunology
Matthew Lee, Jaesik Kim, Matei Ionita, Michelle L. McKeague, Jonghyun Lee, Yonghyun Nam, Chang-Uk Jeong, Akira Nair, Edmore T Moyo, Irene Khavin, Keving Wang, Shwetank, Divij Mathew, Victoria Fang, Benjamin A. Fensterheim, , E. John Wherry
The paper develops MAESTRO, a self-supervised deep learning framework to transform immune profiles into embeddings capturing immune health, enabling clinical prediction and precision immunotherapy.
bioRxiv · Jul 20, 2026 · PreprintImmunology