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.

Estimated Pulse Wave Velocity and All-Cause and Cardiovascular Mortality in the General Population.

Background: Carotid-femoral pulse wave velocity (cfPWV), acknowledged as a reliable proxy of arterial stiffness, is an independent predictor of cardiovascular (CV) events. Carotid-femoral PWV is considered the gold standard for the estimation of arterial stiffness. cfPWV is a demanding, time consuming and expensive method, and an estimated PWV (ePWV) has been suggested as an alternative method when cfPWV is not available. Our aim was to analyze the predictive role of ePWV for CV and all-cause mortality in the general population. Methods: In a stratified random sample of 1086 subjects from the general Croatian adult population (EH-UH study) (men 42.4%, average age 53 ± 16), subjects were followed for 17 years. ePWV was calculated using the following formula: ePWV = 9.587 - 0.402 × age + 4.560 × 10-3 × age2 - 2.621 × 10-5 × age2 × MBP + 3.176 × 10-3 × age × MBP - 1.832 × 10-2 × MBP. MBP= (DBP) + 0.4(SBP - DBP). Results: At the end of the follow-up period, there were 228 deaths (CV, stroke, cancer, dementia and degenerative diseases, COLD, and others 43.4%, 10.5%, 28.5%, 5.2%, 3.1%, 9.3%, respectively). In the third ePWV tercile, we observed more deaths due to CV disease than to cancer (20.5% vs. 51.04%). In a Cox regression analysis, for each increase in ePWV of 1 m/s, there was a 14% increase risk for CV death. In the subgroup of subjects with higher CV risk, we found ePWV to be a significant predictor of CV deaths (ePWV (m/s) CI 1.108; p < 0.029; HR 3.03, 95% CI 1.118-8.211). Conclusions: In subjects with high CV risk, ePWV was a significant and independent predictor of CV mortality.