Jiajia Liu

This paper introduces SPAE, a model for analyzing cell cycle dynamics and states in scRNA-seq data, showing improved accuracy and robustness in cell cycle characterization and cancer cell cycle transition prediction.

Spatium is a foundation model for spatial proteomics that learns stable cell representations from constrained protein measurements, enabling accurate cell identity recovery and spatial microenvironment analysis.

scBiopsy-seq enables temporal single-cell RNA-seq analysis with high detection diversity and reliability, revealing key roles of fatty acid beta oxidation in transcriptional suppression.

The paper introduces CCAN, a model that removes cell cycle effects from integrated single-cell multi-omics data while preserving cell type-specific variations, showing strong performance in downstream tasks.

CCPE estimates cell cycle pseudotime and identifies cell cycle phases from scRNA-seq data, showing effectiveness and robustness in simulated and real datasets.

This study introduces FusionAI, a deep learning model that predicts gene fusion breakpoints from DNA sequences, aiding in the identification of genomic breakage mechanisms.

scIGANs uses GANs to impute dropouts in scRNA-seq data, improving downstream analysis and performance across datasets.