Keyi Li

EpiZoo is a cross-species single-cell epigenomic foundation model that uses DNA sequence-aware architecture to improve cell type annotation and mutation prioritization across species.

HoloCell is a generative foundation model that integrates epigenomics, transcriptomics, and proteomics data across single-cell multi-omics modalities, demonstrating superior performance in representation learning and cross-modal generation.

HitAnno annotates cell types in atlas-level scATAC-seq data using a hierarchical language model, accurately handling major and rare cell types across multiple settings.

The paper introduces Human-scATAC-Corpus, a database of human scATAC-seq data, and presents a foundation model for epigenomic analysis.

EpiAgent is a foundation model for single-cell epigenomic data that excels in feature extraction, cell annotation, and data imputation.

This paper introduces Descartes, a model for identifying spatially variable chromatin accessibility peaks using inter-cellular correlations, showing improved performance and efficiency over existing methods.

Cofea selects biologically relevant features from single-cell chromatin accessibility data by focusing on correlations between accessible regions, improving downstream analysis.

scEpiTools is a database that organizes and recommends tools for analyzing single-cell epigenomic data, including an ensemble method for chromatin accessibility analysis.

The paper develops UGES, a genetic and epigenetic classifier for breast cancer subtypes using hierarchical structure learning, achieving higher AUC and improved clinical stratification.