Project 2: Machine Learning and Causal Inference to Optimize Genomic Interventions using Disease State Representations

Project description

The human genome contains a torrent of information that gives clues not only about human origin, evolution, biological function, but also diseases. The goal of my project aims at developing novel machine learning techniques to better understand the complex genomic data and also other forms of data that can represent patient diseases. Towards this goal, we may be able to reveal more about disease mechanisms and therapy outcomes, which therefore shed new lights on the findings for personalized medicine and healthcare for each patient.

Secondments

1. Including network models in the search for patient state representations
   Host: University of Liege
2. Deep Learning for patient state representation
   Host: Pharmatics

Activities

• Member of the MLFPM team that participated in the EU vs Virus hackaton

Publications

• Bowen Fan, Juliane Klatt, Michael M. Moor, Latasha A. Daniels, Swiss Pediatric Sepsis Study, Lazaro N. Sanchez-Pinto, Philipp K. A. Agyeman, Luregn J. Schlapbach, and Karsten M. Borgwardt. Prediction of recovery from multiple organ dysfunction syndrome in pediatric sepsis patients. International Conference on Intelligent Systems for Molecular Biology (ISMB 2022) and Bioinformatics 2022, 38 (Supplement_1): i101–i108. https://doi.org/10.1093/bioinformatics/btac229

Preprints

• Dexiong Chen, Bowen Fan, Carlos Oliver, and Karsten Borgwardt. (2022). Unsupervised Manifold Alignment with Joint Multidimensional Scaling. arXiv:2207.02968; doi:https://doi.org/10.48550/arXiv.2207.02968