The Shen lab focuses on Genome AI and large-scale genomic data analysis to advance biological discovery. A major direction of our research is developing deep learning models that learn the functional grammar of the genome directly from DNA sequence, including sequence-to-function and genomic language models that capture long-range regulatory context to predict gene expression, regulatory activity, and the functional impact of genetic variation. By leveraging transformer architectures and large-scale biological datasets, we aim to build foundation models that decode the regulatory logic of the human genome and enable variant-to-function and variant-to-phenotype prediction. We also apply machine learning to diverse biomedical problems, including breast cancer detection and risk prediction from mammography, sequence-to-phenotype modeling, and automated genome annotation. Since 2009, our group has analyzed tens of thousands of NGS datasets totaling more than 300 terabytes in collaboration with researchers across the United States, with work published in journals such as Nature, Science, Nature Medicine, and Nature Genetics. We have also developed widely used tools for genomic data analysis, including ngs.plot and diffReps. Our long-term goal is to bridge artificial intelligence and genomics by building scalable models that transform genome interpretation, disease research, and precision medicine.