RESUMEN
While spatial proteomics by fluorescence imaging has quickly become an essential discovery tool for researchers, fast and scalable methods to classify and embed single-cell protein distributions in such images are lacking. Here, we present the design and analysis of the results from the competition Human Protein Atlas - Single-Cell Classification hosted on the Kaggle platform. This represents a crowd-sourced competition to develop machine learning models trained on limited annotations to label single-cell protein patterns in fluorescent images. The particular challenges of this competition include class imbalance, weak labels and multi-label classification, prompting competitors to apply a wide range of approaches in their solutions. The winning models serve as the first subcellular omics tools that can annotate single-cell locations, extract single-cell features and capture cellular dynamics.
Asunto(s)
Aprendizaje Automático , Proteínas , Humanos , Proteínas/análisis , ProteómicaRESUMEN
Hsf1 is an ancient transcription factor that responds to protein folding stress by inducing the heat-shock response (HSR) that restore perturbed proteostasis. Hsp70 chaperones negatively regulate the activity of Hsf1 via stress-responsive mechanisms that are poorly understood. Here, we have reconstituted budding yeast Hsf1-Hsp70 activation complexes and find that surplus Hsp70 inhibits Hsf1 DNA-binding activity. Hsp70 binds Hsf1 via its canonical substrate binding domain and Hsp70 regulates Hsf1 DNA-binding activity. During heat shock, Hsp70 is out-titrated by misfolded proteins derived from ongoing translation in the cytosol. Pushing the boundaries of the regulatory system unveils a genetic hyperstress program that is triggered by proteostasis collapse and involves an enlarged Hsf1 regulon. The findings demonstrate how an apparently simple chaperone-titration mechanism produces diversified transcriptional output in response to distinct stress loads.