The application of deep learning fills a major gap in host–pathogen research providing for unbiased, multi-module high-throughput image analysis.

100,000s of images from different growth conditions and genetic backgrounds can be integrated into proteome-scale analysis.

A conceptually simple algorithm can analyze previously uncharacterized 2D coiled postures of the nematode C. elegans and has uncovered new reorientation behaviors in large amplitude turns.

Building on previous work (Bai et al., 2013), we describe an algorithm that allows cryo-EM structure determination to near-atomic resolution for protein complexes as small as 170 kDa.

Capacitance measurements and pH imaging reveal distinct modes of uptake for endocytotic presynaptic membrane and proteins.

MotionTracking is freely available software that can generate multi-scale geometrical models of mammalian tissue and perform quantitative analysis of tissue architecture.

Polarized assembly of cell-cell junctions drives Drosophila axis elongation.

MorphoGraphX summarizes full 3D datasets as curved surface images (2.5D), enabling the efficient quantification of growth and gene expression data from large time-lapse volumetric datasets.

Genetic interaction analysis by combinatorial genetic perturbation and high-throughput imaging maps time- and context-dependent crosstalk between signaling pathways.

A masked cryo-EM image classification approach and the structure of an inhibitor-bound complex provide insights into the molecular flexibility of the catalytic subunit of gamma-secretase.