1165 København K
Tlf: 21 17 95 65 (man-fre kl. 9-15)
Seminar — At this AI Seminar, Simon Rasmussen will talk about using variational autoencoders for unsupervised learning of metagenomics data and discuss how we apply such methods for integration of multi-omics data.
Date & Time:
SCIENCE AI Centre and Department of Computer Science. Contact: Wouter Boomsma, email@example.com and Francois Lauze, firstname.lastname@example.org
Simon Rasmussen, Associate Professor, PhD, Novo Nordisk Foundation Center for Protein Research, Faculty of Health and Medical Sciences, University of Copenhagen.
Deep learning has revolutionized several scientific fields and is changing our society. Data sets within life sciences are at the same time rapidly increasing in size with cohorts comprising hundreds of thousands and even millions. For example, national and international efforts (e.g. gnomAD and TopMed) are generating human genetic variation data from thousands to hundreds of thousands of individuals. Additionally, to study complex human disease there is a move towards generating matching multi-omics datasets such as genomics, proteomics, metabolomics and microbiomics to measure the human system as detailed as possible. Based on such datasets and the unique position that Denmark has with extensive registry and electronic patient journal data, we are now more than ever in a position to empower scientific discoveries for academia, clinic and industry. However, the sheer amount of data measured poses challenges of how to analyse and integrate the datasets as well as how to understand the relationships that exist between these in human health and disease. Here I will talk about using variational autoencoders for unsupervised learning of metagenomics data and discuss how we apply such methods for integration of multi-omics data. Ultimately, we will use these approaches to stratify patients, extract mechanistic knowledge and to develop predictors of human disease.
This seminar is a part of the AI Seminar Series organised by SCIENCE AI Centre. The series highlights advances and challenges in research within Machine Learning, Data Science, and Artificial Intelligence. Like the AI Centre itself, the seminar series has a broad scope, covering both new methodological contributions, ground-breaking applications, and impacts on society.