Sean Whalen

This paper develops a deep learning model called Performer to predict gene expression from personal genomes, achieving accuracy close to cis-heritability of most genes.

The paper identifies cis-regulatory elements and transcription factors controlling FOXP3 expression in human Tregs and Tconvs, revealing mechanisms that restrict FOXP3 to Tregs in mice.

This study benchmarks genomic footprinting algorithms for predicting transcription factor binding sites in single-cell data, finding peak-level read coverage as the strongest predictor and proposing an ensemble model to improve concordance with ChIP-seq.

The paper identifies 46,802 enhancers and 164 psychiatric disorder variants with regulatory effects in the developing cortex and organoids using massively parallel reporter assays and deep learning.

The paper maps lamin-associated chromatin across twelve human cell types, identifying two subtypes with distinct features and developmental dynamics.

The paper uses single-cell epigenomics and machine learning to model cell-cell communication networks in cardiac development and identify dysregulation in TBX1 deletion.

The paper shows POGZ promotes chromatin accessibility and expression of synaptic genes in mouse and human brains, and its reduction disrupts cortical function through interactions with ADNP.

The paper creates a chromatin accessibility atlas of the developing human telencephalon to identify regulatory elements and their role in gene expression and neurodevelopmental disorders.

AlleleAnalyzer designs personalized and allele-specific sgRNAs to improve CRISPR/Cas editing performance by accounting for individual genetic variants.

The paper shows that regulatory interactions and linkage disequilibrium are not correlated, suggesting they are independent genomic features.

The paper introduces TargetFinder, a computational method that predicts distal regulatory interactions using chromatin features, achieving high accuracy with fewer datasets.