Aidong Zhang

Atacformer is a transformer-based model for scATAC-seq data analysis that improves clustering, cell-type annotation, and cross-modal alignment with RNA-seq data.

BEDMS standardizes genomic interval metadata by predicting standardized attributes using trained models and supports custom schemas for improved data interoperability.

The paper introduces methods to construct and evaluate consensus genomic interval sets, showing how to minimize loss of resolution while enabling interoperability of interval data.

The paper introduces scEmbed, a framework for fast clustering and cell-type annotation of scATAC-seq data using pre-trained embeddings, showing improved performance and transferability.

The paper introduces four metrics to evaluate unsupervised embeddings of genomic regions and provides guidelines for reliable embedding learning.

DeepGSEA provides an explainable deep learning approach for gene set enrichment analysis in single-cell RNA sequencing data, improving sensitivity and specificity over traditional methods.

This study develops a variational autoencoder to generate synthetic scRNA-seq data from bulk RNA-seq, enabling single-cell insights from large-scale bulk datasets.

The paper develops a system for fast and flexible genomic interval retrieval using joint representation learning of region sets and metadata.

DARDN uses deep learning to classify cancer-specific CTCF binding sites and identify oncogenic transcription factors in multiple cancer types.

The paper introduces a method to represent genomic region sets as embeddings using a modified word2vec approach, showing it effectively captures biological associations in lower dimensions.