Vivek Kumar

This study uses automated behavioral quantification to show that opioid withdrawal behaviors vary with genetic background, but severity can still be assessed within strains.

This paper develops an automated machine vision-based index for Rett Syndrome that improves preclinical phenotyping by detecting disease-relevant behaviors and reducing animal use.

The paper introduces a tissue-clearing framework and mesoSPIM-ultra system for large-scale single-neuron tracing in cleared mouse tissue.

This paper benchmarks pose estimation models for animal tracking using MMPose, finding trade-offs between accuracy and speed and highlighting the need for diverse training data.

This paper benchmarks intermediate representations for mouse behavior classification, finding that performance is robust to keypoint variation and temporal features improve accuracy, with segmentation matching pose estimation.

The paper combines supervised and unsupervised machine learning to improve aging predictions in mice by identifying latent frailty signatures.

This study uses supervised machine learning to automatically quantify seizure severity from video data in mice, enabling high-throughput and standardized seizure scoring.

The paper extends a machine vision-based frailty assessment tool to genetically diverse mice, enabling accurate prediction of frailty, age, and lifespan proportions using video data.

The paper introduces a scalable rodent home cage monitoring system with AI for behavioral analysis and digital biomarker development.

This paper demonstrates a computer vision method to estimate mouse body mass from video data with 4.8% error, enabling noninvasive and continuous monitoring.

This study identifies Tmod2 as a regulator of cocaine-induced plasticity and addiction-related behaviors through effects on neuronal excitability and synaptic function.

This study identifies and validates 22 genes that drive drug intake and related behavioral traits in mice through knockout screening and behavioral assays.

The paper develops a neural network for automated mouse grooming behavior detection and uses it to study the genetic basis of grooming and its links to psychiatric traits.

The paper introduces MiniMUGA, a genotyping array for mouse genetic QC, showing it effectively discriminates strains, detects genetic constructs, and identifies sex chromosome abnormalities.

The paper introduces a method called soft windowing to improve analysis of high-throughput phenotyping data by reducing false positives and increasing significant results.

This study shows that Cyfip1 haploinsufficiency increases compulsive-like behavior and modulates palatable food intake in a parent-of-origin and genetic background-dependent manner in mice.

This study identifies insertion sites in 40 transgenic mouse lines, revealing frequent disruptions of endogenous genes and structural variations.

The paper identifies 122 novel sleep-related genes from a large-scale knockout mouse study using non-invasive sleep monitoring.

This paper introduces mean-variance QTL mapping to identify novel QTL for circadian activity and exploratory behavior in mice, showing its superiority over traditional interval mapping in detecting both mean- and variance-controlling QTL.

The paper identifies a mutation in Slc2a4 (GLUT4) in mice that causes chronic fatigue-like behaviors through a forward genetic screen.