Mike Phuycharoen

This paper introduces UVAE to integrate unpaired clinical flow cytometry data, improving cell type signal and clustering by correcting batch effects.

This paper introduces a deep learning model, Enformer Celltyping, that predicts cell type-agnostic epigenomic profiles and outperforms existing methods, while highlighting limitations in genetic variant effect predictions.

The paper investigates how HOX paralogs interact with TALE TFs to generate tissue-specific enhancer activation patterns in mouse embryos.

The paper uses deep learning to identify tissue-specific TF binding sites by analyzing ChIP-seq data from MEIS and HOXA2 in mouse branchial arches.