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.

A machine-learning approach is used to predict 1.35 million interactions for 85% of the human proteome.

The Mouse Action Recognition System is a computational pipeline for automated classification of social behaviors in freely interacting mice, accompanied by a graphical interface for analysis of multimodal neuroscience datasets.

The ability to accurately predict a protein's structure gives us an entirely new way to annotate the human genome.

A computational method identifies the functions of orphan enzymes by organizing them into metabolic pathways; the prediction of a new l-gulonate catabolic pathway is experimentally tested and confirmed.

A framework has been devised that enables global participation in the curation of publications on any topic involving two or more living organisms, ranging from microscopic to larger sizes, in their natural or artificial environments or ecosystems.

DAS is a universal tool for segmenting and identifying acoustic signals in single and multi channel recordings robustly, reliably, and at low latency.

A statistical model systematically associates functions of intrinsically disordered regions with sequence-distributed molecular features such as charge, residue composition, or repeat content.

A machine learning model predicts the properties of proteins from their amino acid sequences and can run in a user's web browser.

Widespread, rapidly evolving disordered regions contain molecular features that are preserved over evolution and are associated with specific biological functions.