Deep learning-based latent space analysis for cancer omics

• PhD

Deep learning methods are being used to identify lower dimensional latent spaces underlying complex disease datasets. Interpretation of the latent dimensions is possible using different approaches, but there is much room to improve understanding best practice.

The goal of this project is to explore and refine the use of deep learning methods to analyse and interpret latent spaces of complex cancer omics data.

The Papenfuss Lab develops and applies mathematical, statistical and computational methods to analyze and make sense of complex molecular and clinical data from cohorts of patients with cancer.

Our overarching goal is to enable insights into cancer evolution, including initiation, progression, therapy response and outcome.