Deep learning approach for deciphering protein subcellular localization
2022
Chan Zuckerberg Biohub, San Francisco, USA
Explaining the diversity and complexity of protein localization is essential to fully understanding cellular architecture. Here, the researchers present cytoself, a deep-learning 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. The researchers quantitatively validate cytoself’s ability to cluster proteins into organelles and protein complexes, showing that cytoself outperforms previous self-supervised approaches.
Self-supervised deep learning encodes high-resolution features of protein subcellular localization
Manuel D. Leonetti, Hirofumi Kobayashi, Loic A. Royer
Added on: 10-24-2022
[1] https://www.nature.com/articles/s41592-022-01541-z[2] https://www.drugtargetreview.com/news/104568/new-machine-learning-technique-to-accelerate-the-process-of-drug-screening/?utm_source=Email+marketing&utm_medium=email&utm_campaign=DTR+-+Industry+Insight+-+Thermo+Fisher+-+Informatics+-+14.10.2022&utm_term=Using+computational+modelling+to+gain+insights+into+flu+viruses&utm_content=https%3a%2f%2femails.drugtargetreview.com%2frussellpublishinglz%2f&gator_td=IUcSF6GWjJ6XMiIK0E97KpsRmIMCn%2f3gtYslFGn%2bECZbVO5xEN0hnuoDQucMncTwUCbpxQ9igcloo1zWJDmJwawBH9xJljYT25yFbhwBnH7foAwfmsv9lPb4%2bnhFzfQASJmGkBTLX43Ou2MFZqck8xGJ9ka%2bQZsR12tZBWVCv4%2bCV1mUM8L3DGV6R%2bk%2bOdJ1SOFjTih3Wk1yCVCpcIcRlMSDXv8X%2b89U4ekc2SsmwDReETvzp%2bMHcRO7wJtasBxsL5hfJOFa7vCtCtR0N6TT5Q%3d%3d
