Yan Cui

Pop-Corn: Predicting Perturbation Phenotype Effects Across Single-Cell and Spatial Contexts

Pop-Corn predicts how genetic perturbations reshape cell-type composition in single-cell and spatial contexts without reconstructing gene expression.

Spatially resolved contrastive analysis of perturbation-driven microenvironmental heterogeneity across tissues and conditions

Haruka identifies condition-specific and shared spatial domains across tissues and conditions using contrastive learning, demonstrating improved detection of spatially heterogeneous perturbation responses.

Identifying Differential Spatial Expression Patterns across Different Slices, Conditions and Developmental Stages with Interpretable Deep Learning

The paper introduces River, an interpretable deep learning method to identify differential spatial expression patterns across slices, conditions, and developmental stages, validated on diverse biological datasets.

Computational exploration of dynamic mechanisms of steady state visual evoked potentials at the whole brain level

This study uses a large-scale brain model to simulate and analyze the dynamic mechanisms of steady-state visual evoked potentials (SSVEPs) at the whole-brain level, revealing frequency-specific responses and network properties.

Dynamic Configuration of Coactive Micropatterns in the Default Mode Network during Wakefulness and Sleep

This paper introduces a novel method to analyze dynamic configurations of the default mode network (DMN) in rats during wakefulness and sleep, revealing three distinct micropatterns and their association with different alertness levels.