Deep Learning Concepts in Molecular Biology

Prof. Markus Kollmann, University of Düsseldorf

June 25, 2018


The field of Artificial Intelligence has made significant progress over the past years by making use of Deep Neural Networks. The ability of Deep Neural Networks to carry out complex mappings in high dimensional spaces makes them extremely interesting for biological applications, e.g. for mapping genotypes to (molecular) phenotypes.

This talk gives an introduction to recent Deep Learning concepts that are interesting for Life Sciences, with special focus on the ‘Attention Mechanism’ — a key concept of Neural Machine Translation. State of the art results are presented by using Deep Neural networks for predicting DNA binding motifs, RNA secondary structure for given RNA sequence, and RNA sequence for given RNA secondary structure.


The talk took place on Monday, 25 June, 2018 at 6:30 pm at the DKFZ Communication Center, rooms K1/K2.