Analysis of the Human Protein Atlas Weakly Supervised Single-Cell Classification competition.

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.

Cytoplasmic protein misfolding titrates Hsp70 to activate nuclear Hsf1.

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.