A new automated and unsupervised algorithm, Risk Assessment Population IDentification, identifies risk-stratifying cells in single cell datasets with robust statistical and biological validation.

A biologically plausible learning rule enables recurrent neural networks to model the way in which neural circuits use supervised learning to perform time-dependent computations.

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

Combining high-resolution imaging with automated image segmentation and supervised machine learning achieves accurate cellular feature extraction and automated cell type recognition in a large-scale developmental process.

An analysis of 67,885 preprints on bioRxiv finds evidence for disparities in international participation that are similar to the disparities found in conventional journals.

Advances in techniques for analysing single cells and tissues have inspired an international effort to create comprehensive reference maps of all human cells - the fundamental units of life - as a basis for both understanding human health and diagnosing, monitoring and treating disease.

The single-cell eQTLGen consortium aims to pinpoint the cellular contexts in which disease-causing genetic variants affect gene expression and its regulation.

A high-throughput functional genomics approach combining inducible CRISPR-interference and quantitative imaging yields an atlas of 'phenoprints' to guide gene function assignments, identify metabolic pathway-specific morphotypes, and inform antibiotic mechanism-of-action studies.

A new tool to visualize blood-feeding mosquitoes in high resolution and quantitatively characterize their behavior sheds light on contact-dependent sensing and blood-feeding dynamics of several medically relevant mosquito species.

The transcriptomic profiles of the constituent monotherapies of synergistic drug pairs tend to be correlated and result in novel gene expression in the combinations.