Machine learning in conjunction with super-resolution imaging allows for the first time to quantitatively analyse large and heterogenous virus samples structure at a high throughput and specificity.

A new cross-species machine learning-based strategy is applied to find enhancers that specifically label parvalbumin neurons in the mouse and macaque.

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.

A new combined approach using X-ray fluoroscopy and machine learning provides detailed new insights into bladder function in awake, unrestrained mice and unveils important limitations of current approaches to study bladder function.

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

In an investigation into the effects of drugs on proteins, an active machine learning algorithm chose which sets of experiments to perform and was able to learn an accurate model of the effects after doing only a fraction of the experiments.

A method of generating comprehensive maps of cochlear cells was created and enabled researchers to study characteristics of cellular damage in aged and noise-exposed inner ear.

A machine learning method for action detection is developed and applied toward mouse grooming behavior.

A physics-based, statistically rigorous mathematical model enables automated, objective interpretation of images from single-molecule fluorescence colocalization microscopy experiments.

Human blood derived macrophage polarisation can be classified by proxy of their metabolism, using advanced microscopy techniques generating single-cell parameters that are clustered and validated using machine learning classification models.