Zehua Zeng

Navigo models mouse embryogenesis to predict cell fates and disease by learning developmental trajectories from scRNA-seq data.

OmicOS provides an agent-operable omics ecosystem that enables AI systems to execute and verify analyses using community methods, achieving high performance in benchmark tasks.

OmicClaw provides a natural-language framework for reproducible multi-omics analysis using the OmicVerse ecosystem, improving performance over baseline models in complex workflows.

PantheonOS introduces a multi-agent framework for automated genomics analysis, achieving super-human performance in batch correction and gene panel selection across diverse biological tasks.

CellOntologyMapper standardizes cell type annotations by mapping user-defined names to standardized ontological terms, improving data integration and analysis across diverse single-cell datasets.

MERFISH+ enables high-resolution spatial multi-omics mapping of gene expression and chromatin organization in developing human hearts with subcellular resolution.

FT-Kernel predicts cell fate factors and dynamics along pseudotime using cell-state density and regression weights, outperforming existing methods in capturing lineage transitions and interactions.

OmicVerse integrates bulk and single-cell RNA-seq analysis with a pipeline that restores continuity in interrupted single-cell data using Beta-Variational AutoEncoder and graph neural networks.

This paper introduces scLTNN, a method for automatically inferring origin and end cell states and developmental trajectories from scRNA-seq data with low computational cost.

The paper predicts the binding domain and identifies potential new drug targets for 2019-nCoV by analyzing its surface glycoprotein and comparing it to SARS-CoV.