RT Journal Article
SR Electronic
T1 Self-Supervised Deep Learning Encodes High-Resolution Features of Protein Subcellular Localization
JF bioRxiv
FD Cold Spring Harbor Laboratory
SP 2021.03.29.437595
DO 10.1101/2021.03.29.437595
A1 Hirofumi Kobayashi
A1 Keith C. Cheveralls
A1 Manuel D. Leonetti
A1 Loic A. Royer
YR 2021
UL http://biorxiv.org/content/early/2021/07/03/2021.03.29.437595.abstract
AB Elucidating the diversity and complexity of protein localization is essential to fully understand cellular architecture. Here, we present cytoself, a deep learning-based approach for fully self-supervised protein localization profiling and clustering. cytoself leverages a self-supervised training scheme that does not require pre-existing knowledge, categories, or annotations. Applying cytoself to images of 1311 endogenously labeled proteins from the recently released OpenCell database creates a highly resolved protein localization atlas. We show that the representations derived from cytoself encapsulate highly specific features that can be used to derive functional insights for proteins on the sole basis of their localization. Finally, to better understand the inner workings of our model, we dissect the emergent features from which our clustering is derived, interpret these features in the context of the fluorescence images, and analyze the performance contributions of the different components of our approach.Competing Interest StatementThe authors have declared no competing interest.