Can machine learning be useful in the molecular and biomedical sciences?
Staff - Faculty of Informatics
Date: / -
USI Lugano Campus, room SI-003, Informatics building (Via G. Buffi 13)
Simon Olsson, Freie Universität Berlin, Germany
In this talk I will to motivate and outline some general problems and opportunities for machine learning in molecular and biomedical sciences. I will then give three different examples of how we have used three different branches of machine learning in the molecular sciences to target very different albeit all challenging problems[1,2,3]. Finally, I will discuss future directions and outstanding problems.
 Olsson S*, Noé F* ”Dynamic Graphical Models of Molecular Kinetics” PNAS (2019)
 Wang L, Olsson S, Wehmeyer C, Perez A, Charron N, De Fabritiis G, Noé F*, Clementi C*. ”Machine Learning of coarse-grained Molecular Dynamics Force Fields” ACS Central Science (2019)
 Noé F*†, Olsson S†, Köhler J†, Wu H. ”Boltzmann Generators - Sampling Equilibrium States of Many-Body Systems with Deep Learning”
Simon Olsson is a graduate of Biochemistry (MSc) and Bioinformatics (PhD) from the University of Copenhagen, Denmark. Olsson was awarded a prestigious independent postdoctoral research grant from the Danish Council for Independent Research to join ETH Zürich and IRB Bellinzona as a postdoctoral researcher. Since spring 2016 Olsson has been a Dahlem Research School Fellow and later a Fellow of the Alexander von Humboldt foundation at the Freie Universität Berlin, Germany.
Host: Prof. Rolf Krause (ICS), Dr. Andrea Cavalli (IRB)