Ten popular spike sorting codes are reproducibly benchmarked for accuracy on electrophysiology datasets from eleven laboratories with interactive web-based exploration of thousands of ground-truth units.

A spike sorting toolbox to quickly and reliably access the activity of thousands of neurons recorded with dense extracellular probes.

Unbiased and automatic annotation using structured prediction framework with efficiently built data-driven atlases is more accurate than registration-based methods for cell identifications in dense images and enables fast whole-brain analysis.

A comparison of different bioimage analysis pipelines reveals how deep learning can be used for automatized and reliable analysis of fluorescent features in biological datasets.

Convolutional neural networks and graph partitioning algorithms can be combined into an easy-to-use tool for segmentation of cells in dense plant tissue volumes imaged with light microscopy.

Transient transcriptome sequencing and kinetic modeling suggest how the kinetics and yield of RNA splicing are encoded in the human genome.

Genetic and biochemical analysis reveal a variant in HSF2BP causing POI and C19ORF57/BRME1 as an interactor and stabilizer of HSF2BP by forming a complex with BRCA2, RAD51, RPA and PALB2.

An open-source user-friendly toolbox implementing machine learning for single-molecule FRET analysis enabling experts and non-experts to reproducibly provide dynamic structural biology insights.

What can authors and reviewers do to keep common statistical mistakes out of the literature?

A dual-channel image registration pipeline combined with deep-learning inference achieves accurate-and-flexible registration/segmentation/mapping of mouse brain.