Greg J. Stephens

DISK uses deep learning to impute missing skeleton data in animal behavior studies, improving reliability and enabling more accurate motion analysis.

The paper identifies a novel fungal peptide from Ophiocordyceps that binds to scramblase channels in ants, disrupting motor coordination and olfactory systems.

The paper decomposes predictive information in social dynamics using mutual prediction analysis in zebrafish dominance contests, revealing disruptions in autism-linked mutants.

This study analyzes zebrafish fighting behavior using 3D tracking and computer vision to identify hierarchical dominance through posture and movement patterns.

This paper introduces a computational method to track entire honey bee colonies using video, achieving high accuracy in position and orientation tracking and revealing collective behaviors.

OrganoidTracker automates cell tracking in organoids using machine learning and manual error correction, achieving high accuracy with minimal manual intervention.

The paper introduces a density-based clustering method using percolation theory to identify functionally related gene modules from noisy, high-dimensional RNA sequencing data across different organisms.

This study shows that observing an acute traumatic event in mice leads to long-term behavioral and physiological changes, with social relationships playing a key role in the development of PTSD-like behaviors.

The paper develops a method for tracking densely packed honeybees in 2D hives using pixel personality for object recognition, achieving 46% trajectory reconstruction in 5 min recordings.