Andreas Zamanos
National and Kapodistrian University of Athens
SHORT BIO
RESEARCH INTERESTS
Andreas' research interests include machine learning, structural biology, biophysics, computer vision, graph theory, and computational geometry. Andreas is primarily interested in applying machine learning techniques to cryo-electron microscopy and protein structure analysis, aiming to advance our understanding of biological systems by developing innovative algorithms and models.
PhD research on "Self-supervised Learning for Generalizable Particle Picking in Cryo-EM Micrographs"
Abstract: Cryo-EMMAE is a self-supervised method designed to overcome the need for manually annotated cryo-EM data. cryo-EMMAE leverages the representation space of a masked autoencoder to pick particle pixels through clustering of the MAE latent representation. Evaluation across different datasets demonstrates that cryo-EMMAE outperforms state-of-the-art supervised methods in terms of generalization.
