Tianyi Xia

DCAF improves single-cell perturbation simulation by addressing data, evaluation, and model validity, outperforming baselines in generalization and recapitulating regulatory heterogeneity in mouse brain.

The paper evaluates multi-view gene representations under a matched contract, showing condition-dependent fusion operator rankings across different view combinations and tasks.

This study compares how natural infection versus vaccination primes human CD4+ T cells, showing differences in TCR diversity, effector function, and integrin expression years later.

RegFormer improves single-cell RNA sequencing analysis by integrating gene regulatory networks with Mamba-based modeling, outperforming existing models in clustering, integration, and annotation.

BiOmics introduces an AI agent that improves multi-omics interpretation by combining reasoning and embedding spaces, outperforming existing methods in variant discovery, cell annotation, and drug repurposing.

DynPerturb models spatiotemporal perturbation dynamics in single-cell and spatial transcriptomics, outperforming existing methods in regulatory link prediction and uncovering dynamic regulatory rewiring in biological systems.

The paper tests optimization strategies for isolating mitochondria from rat liver tissue but finds that modifications do not significantly improve mitochondrial quality.

BioLLM integrates and benchmarks single-cell foundation models, revealing scGPTs' robust performance and highlighting limitations of scBERT in gene-level tasks.

UniCell improves cell type annotation and cross-dataset harmonization by combining Cell Ontology with transcriptomic data, outperforming existing tools in accuracy and rare cell detection.

Stereopy provides a framework for analyzing multi-sample spatial transcriptomics data to model comparative and spatiotemporal cellular heterogeneity through three key algorithms.

ST-GEARS improves spatial information recovery in 3D spatial transcriptomics by aligning sections and correcting distortions, enhancing accuracy for downstream analysis.

The paper fills a gap in 3D spatial transcriptomics by providing data from E9.5 and E11.5 mouse embryos, enabling detailed analysis of organogenesis with a new open-access database.

Spateo provides a framework for spatiotemporal modeling of single-cell spatial transcriptomics data to study cell-cell interactions and organ development in 3D space.