Multidimensional analysis of data from high-throughput behavioral assays reveals many independent axes of behavioral variation among inbred animals reared in the same environment.

A novel automated behavior analysis method for Hydra identifies pre-defined and new behavior types, and reveals a stable behavior repertoire.

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 new analysis algorithm (DISC) enables accurate analysis of data from high-throughput single-molecule paradigms and reveals a non-cooperative binding mechanism of cyclic nucleotide-binding domains from HCN ion channels.

A computational framework allows the unsupervised analysis of samples from single cell data across conditions, inference of multicellular programs associated with disease, and meta-analysis of independent patient cohorts.

Unsupervised cluster analysis identified similar groups of children in different cohorts, with distinct developmental patterns of immunorespiratory health, asthma and allergy.

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

Single-cell analysis of skeletal mouse reveals highly diverse macrophage subgroups associated with diverse functions and age-related changes.

Rare, virus-specific immune cells in human blood are automatically identified by machine learning algorithm T-REX and characterized for signature features needed for tracking and isolation.

Perceptual haptic representation of materials emerges from unsupervised learning as a consequence of efficient encoding of the physical signals at the input of tactile sensory system.