Comparing the relative similarity of cellular molecules to alternate templates allows classification of related complexes in the cell using fewer particles than needed for 3D classification and is more practicable for low abundance complexes.

ScRNA-seq of diverse pheochromocytoma patients reveals distinct microenvironment characteristics and supports an informative molecular classification system.

Similarities in climatic niches of terrestrial vertebrates indicate the Earth's climate regions, which differ among groups and from previous plant-based climate classifications.

Both human and microbe cell-free RNA features in plasma could distinguish tumors of different primary locations.

A new user-intervention-free classification, using single-fluorescent markers, measures conventionally unmeasureable phenotypes in early stages during clathrin-mediated endocytosis.

An intelligent method is developed to morphologically classify platelet aggregates by agonist type, which potentially opens a window on novel clinical diagnostics and therapeutics of thrombotic disorders.

Machine learning in conjunction with super-resolution imaging allows for the first time to quantitatively analyse large and heterogenous virus samples structure at a high throughput and specificity.

Hippocampome.org is an online resource that provides free human- and machine-readable access to the comprehensive property-based classification of hippocampal neurons from 14,000 pieces of published experimental evidence.

Using GPUs for the costly computations in cryo-EM enables structure determination in mere days on a single workstation.

Integrated molecular analysis demonstrated that colorectal cancer can be classified into four molecular subtypes (proliferative, immunomodulatory, immunosuppressed, and immune-excluded subtypes), providing valuable insight into the intricate relationship between tumor microenvironment heterogeneity and various clinical phenotypes.