Post doc position in machine learning for cryogenic electron microscopy at the School of Engineering Sciences at KTH Royal Institute of Technology. This position is part of a joint collaboration between the two largest research programs in Sweden, WASP and the SciLifeLab and Wallenberg National Program for Data-Driven Life Science (DDLS), with the ultimate goal of solving ground-breaking research questions across disciplines.
Single-particle cryogenic electron microscopy (cryo-EM) is a tomographic method for computationally recovering the 3D structure of a biomolecule from electron microscope imaging data, which is having profound impact on structural biology in general, and drug design in particular. Current 3D reconstruction methods only work for quite rigid biomolecules but these molecules often have inherent flexibility that is of interest in structural biology as changes in the atomic structure are crucial in determining function. This postdoctoral research project will focus on developing data-driven priors of atomic models using domain-adapted neural networks trained on simulations obtained from molecular dynamics. These priors will then be used to estimate entire atomic model trajectories given cryo-EM data.