Peijie Zhou

Virtual dynamics of spatiotemporal single-cell interactions

CytoBridge reconstructs continuous virtual cell dynamics from sparse spatial transcriptomic data across development, regeneration, and neurodegeneration.

Building virtual cell dynamics that evolve with biological measurements

CellCompass, an agentic AI system, models cell dynamics from single-cell measurements and improves predictions by integrating new biological constraints and experimental data.

MOFI reveals dynamic multi-omics coordination during cell fate progression

MOFI reconstructs continuous cell fate transitions from paired multi-omics snapshots across time, revealing coordinated changes in transcriptomic, chromatin, and protein layers.

MEGA-ODE: Learning Biologically Structured and Navigable Continuous Perturbation Dynamics from Sparse Omics

MEGA-ODE reconstructs dynamic omics landscapes from sparse data, predicts unmeasured states, and prioritizes perturbations toward biological endpoints.

Reconstructing lineage-constrained gene-program dynamics with PhyloFM

PhyloFM reconstructs continuous cell-fate dynamics using lineage constraints from single-cell data, improving accuracy in multiple biological systems.

Unbalanced Perturbation Dynamics For Cell Fate Design

This paper introduces U-Pert, a framework for modeling unbalanced perturbation dynamics in single-cell data, enabling forward prediction and inverse design of cellular interventions.

Deciphering interaction syntax via decoupling intrinsic lineages and niche pressure

TRINUS decouples cell lineage identity from niche pressure to uncover interaction syntax in spatial transcriptomics data, showing improved clustering and domain detection across biological systems.

Generating and navigating single cell dynamics via a geodesic bridge between nonlinear transcriptional and linear latent manifolds

GeoBridge transforms sparse scRNA-seq data into a continuous landscape for reconstructing and navigating cellular state transitions.

Benchmarking zero-shot single-cell foundation model embeddings for cellular dynamics reconstruction

This study benchmarks zero-shot single-cell foundation model embeddings for cellular dynamics reconstruction and finds they underperform a traditional HVG baseline in capturing complex temporal patterns.

stVCR: Spatiotemporal dynamics of single cells

stVCR reconstructs spatiotemporal dynamics from time-series spatial transcriptome data by integrating generative deep learning with optimal transport and spatial priors.

Genetic deconvolution of embryonic and maternal cell-free DNA in spent culture medium of human preimplantation embryos through deep learning

This paper introduces DECENT, a deep learning method to reconstruct embryonic copy number variations and reduce maternal DNA contamination in cfDNA from SECM, improving the accuracy of noninvasive preimplantation genetic testing.

A perturbation proteomics-based foundation model for virtual cell construction

The paper develops a foundation model using perturbation proteomics data to predict drug responses and improve breast cancer prognosis.

On the Mathematics of RNA Velocity II: Algorithmic Aspects

This paper develops algorithmic methods to improve RNA velocity analysis by addressing time-scale fixation, uncertainty quantification, bandwidth selection, and temporal distance estimation.

Decoding cell identity with multi-scale explainable deep learning

The paper introduces Cell Decoder, a deep learning model that provides multi-scale interpretability for cell type decoding and data integration, showing its effectiveness in human and mouse datasets.

exFINDER: identify external communication signals using single-cell transcriptomics data

exFINDER identifies external signals received by cells from their environment using single-cell transcriptomics data, revealing signaling networks and biological activities.

Dissecting Transition Cells from Single-Cell Transcriptome Data through Multiscale Stochastic Dynamics

MuTrans identifies transition cells and quantifies cell-state transitions using multiscale stochastic dynamics, applied to diverse single-cell datasets.

Enhancing single-cell cellular state inference by incorporating molecular network features

The paper introduces SCORE, a network-based method that improves single-cell cellular state inference by incorporating molecular network features, identifying novel cell clusters and biological insights in human ileal scRNA-seq data.

On the Mathematics of RNA Velocity I: Theoretical Analysis

This paper provides a mathematical analysis of the RNA velocity model, deriving analytical solutions and parameter inference frameworks to improve understanding and future development of RNA velocity methods.