Adam Youlin He

The paper develops deep learning models to predict transcription initiation patterns from DNA sequences across human tissues and cancers.

pydreg is a Python port of dREG that improves runtime and memory efficiency while maintaining similar performance in identifying active cis-regulatory elements.

The paper identifies candidate causal SNPs and target genes in CD4+ T cells for juvenile idiopathic arthritis using GWAS data, chromatin accessibility, and functional assays.

This study shows that training deep learning models on functional genomic data with matched personal genomes improves variant effect prediction.

The paper identifies disease-driving SNPs in JIA risk haplotypes using functional genomic data and genotyping, and links them to target genes through chromatin interactions.

The paper introduces CLIPNET, a deep learning model that predicts transcription initiation with single nucleotide resolution from DNA sequences, revealing core promoter motifs and non-additive interactions between activators and promoters.