Yujia Xiang

PerturbTrace evaluates how AI co-scientist agents use feedback in perturbation discovery, finding that high recall does not imply effective feedback use.

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

PertDiffBench benchmarks diffusion models for predicting transcriptional responses to perturbations in single-cell and bulk RNA-seq data, showing mixed performance across different tasks and settings.

SciCore-Omics is a tri-modal foundation model that integrates histology, spatial transcriptomics, and language to improve spatial biology analysis and interpretation.

ChiMER detects enhancer-exon fusion transcripts by integrating chromatin architecture into splicing graphs, improving sensitivity over conventional methods.

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.

The paper develops a database of viral post-translational modification sites and a classifier for predicting viral protein phosphorylation sites.