Yuan Luo

This paper introduces gANCHOR, a T-cell foundation model that predicts CAR T-cell immunotherapy response by integrating gene-level structure with clinical outcomes, achieving high F1 score and biological insights.

The paper develops an AI framework to analyze blood scans and predict patient outcomes by characterizing tumor-immune ecosystems in circulation.

This study uses exome sequencing to identify genetic associations with interstitial cystitis/bladder pain syndrome, finding new links and extending known associations.

This study identifies 21 novel genetic loci associated with keloids through a multi-ancestry GWAS, highlighting integrin signaling and fibrosis pathways.

This study compares DNA methylation profiles of breast tumors, adjacent normal tissues, and healthy controls to identify epigenetic differences and their association with estrogen receptor status.

The paper develops a pipeline for integrated breast cancer risk assessment using polygenic risk scores and other factors in the eMERGE study, showing high concordance between API and UI results.

The paper shows that lipid metabolism, specifically through OA, shifts metabolic pathways in breast cells, increasing SAM and 2-HG, which contribute to oncogenic properties and epigenetic changes.

The paper uses a polygenic risk score for colorectal cancer in a PheWAS to find genetic correlations with other phenotypes from electronic health records.

This paper presents a 3D-printed composite scaffold system for bone regeneration that accelerates ECM and mineralized osteoid deposition in vivo.

The paper shows the APOL1 p.N264K variant reduces the risk of FSGS and kidney disease in individuals with G2 APOL1 risk alleles.

This paper introduces PhenoPLIER, a method that maps gene-trait and drug associations into gene modules to reveal disease mechanisms and drug targets.

The paper selects and validates ten polygenic risk scores for clinical use in diverse populations, focusing on chronic diseases and addressing disparities in predictive performance.

This paper introduces STdGCN, a graph neural network for spatial transcriptomic cell-type deconvolution, outperforming existing methods and revealing spatial patterns in cancer and heart tissue.

This study evaluates how ancestry, GWAS sample size, and LD reference panels affect BMI PRS performance across different age groups and ancestries.

This study uses EHR data to identify gene-phenotype associations and develop phenotype risk scores for variant interpretation in hereditary cancer genes.

SOAR provides a curated spatial transcriptomics database and analysis tools to facilitate disease mechanism studies and drug discovery.

This paper introduces polygenic risk vectors (PRV) to improve genetic risk stratification for cardio-metabolic diseases by combining additive and dominant genetic effects, outperforming traditional polygenic risk scores.

The paper uses multi-ancestry biobank data and integrative methods to identify gene-disease associations across different ancestry groups, finding shared and ancestry-specific genetic links.

This study uses machine learning to predict Parkinson's disease onset and subtype from germline variants, achieving ROC scores of 0.77 and 0.61.

This study uses clustering algorithms to analyze SARS-CoV-2 genomic data and identifies six major subtypes with distinct geographical distributions.

The paper identifies genetic aberrations in benign breast lesions that distinguish breast cancer cases from controls and predict cancer risk.

This study introduces DeepCues, a deep learning model that improves cancer type classification using DNA sequencing data, achieving 77.6% accuracy on TCGA data and showing significant improvement over conventional methods.