J. Nathan Kutz

Learning the bistable cortical dynamics of the sleep-onset period

The paper introduces a stochastic dynamical model to capture bistable dynamics during sleep onset and shows its parameters correlate with subjective sleepiness reports.

Pervasive context-dependent effects in the genetic architecture of complex and quantitative traits revealed by a powerful multiparent mapping population in yeast

The paper uses a multiparent yeast population to identify QTL for growth rates across environments, revealing context-dependent genetic architectures and allelic heterogeneity.

Arousal as a universal embedding for spatiotemporal brain dynamics

The paper demonstrates that a single arousal measurement can reconstruct spatiotemporal brain dynamics across multiple modalities in awake mice.

Shallow Recurrent Decoders for Neural and Behavioral Dynamics

The paper introduces SHRED, a shallow recurrent decoder that maps neural population dynamics to individual neurons and behavior using limited sensor data across multiple organisms.

Human motion data expansion from arbitrary sparsesensors with shallow recurrent decoders

This paper develops a deep learning method to reconstruct dense human motion data from sparse sensors, enabling accurate tracking of unmonitored body segments and improving digital biomarker estimates.

Predicting the functional effect of compound heterozygous genotypes from large scale variant effect maps

The paper predicts the functional effect of compound heterozygous genotypes using a yeast-based assay and a linear model applied to variant effect maps.

The functional impact of 1,570 SNP-accessible missense variants in human OTC

The paper develops a high-throughput functional assay to assess the impact of 1,570 OTC missense variants, improving variant interpretation using ACMG/AMP guidelines.

A machine learning approach to quantify individual gait responses to ankle exoskeletons

This study uses neural networks to quantify individual gait responses to ankle exoskeletons by modeling discrepancies between nominal and exoskeleton gait data.

Non-Stationary Dynamic Mode Decomposition

This paper introduces Non-Stationary Dynamic Mode Decomposition (NS-DMD) to analyze time-varying spatiotemporal data, demonstrating its application to neural recordings from a non-human primate.

Extracting Reproducible Time-Resolved Resting State Networks using Dynamic Mode Decomposition

This paper introduces a dynamic mode decomposition method to extract time-resolved resting state networks from fMRI data, showing improved reproducibility and individualized structure.