Cell & Systems Biology (CSB)
@uoftcellsysbiol.bsky.social
Advancing research and teaching in the most dynamic and vital areas of biological research
Sangster’s paper in PLoS Comp Biol shows how “Zero-shot segmentation using embeddings from a protein language model identifies functional regions in the human proteome”!
They apply zero-shot segmentation without training/fine-tuning, so can generalize to rare and poorly annotated protein segments!
They apply zero-shot segmentation without training/fine-tuning, so can generalize to rare and poorly annotated protein segments!
Zero-shot segmentation using embeddings from a protein language model identifies functional regions in the human proteome
Author summary Understanding protein function has been a major focus of computational biology for decades. Classical approaches have used amino acid sequences and compositional biases that are conserv...
journals.plos.org
November 25, 2025 at 6:17 PM
Sangster’s paper in PLoS Comp Biol shows how “Zero-shot segmentation using embeddings from a protein language model identifies functional regions in the human proteome”!
They apply zero-shot segmentation without training/fine-tuning, so can generalize to rare and poorly annotated protein segments!
They apply zero-shot segmentation without training/fine-tuning, so can generalize to rare and poorly annotated protein segments!