Yong‐Ju Lee

X-Cell: Scaling Causal Perturbation Prediction Across Diverse Cellular Contexts via Diffusion Language Models

X-Cell predicts causal perturbation responses across diverse cellular contexts using a diffusion language model trained on a large CRISPRi Perturb-seq dataset.

Gene-embedding-based prediction and functional evaluation of perturbation expression responses with PRESAGE

PRESAGE predicts perturbation expression responses using gene embeddings and outperforms existing methods in functional evaluations.

PerTurboAgent: A Self-Planning Agent for Boosting Sequential Perturb-seq Experiments

PerTurboAgent predicts gene panels for sequential Perturb-Seq experiments using an LLM-based agent, outperforming existing strategies in identifying phenotypically impactful genes.

SpatialAgent: An Autonomous AI Agent for Spatial Biology

SpatialAgent integrates large language models with dynamic tool retrieval, multimodal interpretation, and claim verification to automate end-to-end spatial biology workflows from gene-panel design to tissue annotation and hypothesis generation.

PathOmCLIP: Connecting tumor histology with spatial gene expression via locally enhanced contrastive learning of Pathology and Single-cell foundation model

PathOmCLIP infers spatial gene expression from histology images by combining pathology and single-cell RNA-seq foundation models, achieving better gene expression prediction than existing methods.

Identification of B cell subsets based on antigen receptor sequences using deep learning

This paper introduces BCR-SORT, a deep learning model that predicts B cell subsets from BCR sequences, revealing inter-individual heterogeneity in memory B cell evolution post-COVID-19 vaccination.

GRIP: Graph representation of immune repertoire using graph neural network and transformer

GRIP improves cancer patient survival prediction by modeling immune repertoires as hierarchical graphs, outperforming set-based methods and providing interpretable results.

Constructing and visualizing cancer genomic maps in 3D spatial context by phenotype-based high-throughput laser-aided isolation and sequencing (PHLI-seq)

This paper introduces PHLI-seq, a method to isolate and sequence cancer cells in 3D space, revealing genomic heterogeneity and linking genotypes to phenotypes in breast cancer.