Jiarui Ding

ProtoCloud improves cell type annotation by providing interpretable, uncertainty-aware predictions and better performance on rare cell types across multiple datasets.

CellUntangler disentangles multiple biological signals in single-cell data using deep generative models, separating cell cycle from other signals like cell type and differentiation.

scPairing generates multiomics data from single cells using deep learning, capturing biological structures and enabling trimodal data creation.

EpitopeGen generates T-cell epitopes from TCR sequences using a transformer model, outperforming baselines and identifying antigen-specific T cells in cancer and COVID-19.

This paper introduces scPhere, a deep generative model that embeds scRNA-seq data into hyperspherical or hyperbolic spaces to better represent biological relationships and correct for technical biases.

The paper introduces SHARE-seq, a method to profile RNA and chromatin in single cells, and identifies DORCs that predict lineage commitment by chromatin accessibility changes.

Seven single-cell and single-nucleus protocols run side by side on the same cell lines, PBMCs and mouse cortex, analysed through one pipeline: 10x Chromium led the high-throughput methods.

The paper introduces scvis, a deep generative model for dimensionality reduction of single-cell RNA-seq data, preserving both local and global structures in low-dimensional representations.