Welcome to the Kundaje Lab!

At the Kundaje Lab, we focus on developing statistical and machine learning methods to infer integrative models of transcriptional regulation and interpret non-coding genetic variation through the lens of gene regulation. At the core of our research is the idea that obtaining a genome-wide and system-level understanding of gene regulation is essential to decipher diseases' causal genetic and molecular basis. What makes our research unique is the ability to condense massive compendia of genomic data into interpretable and predictive computational models capable of capturing functional heterogeneity and context-specificity thereby allowing the discovery of exceptions rather than focusing only on the norms. We collaborate extensively with experimental biologists within and outside Stanford to validate hypotheses generated by our models and discover novel biology. We have led the Encyclopedia of DNA Elements (ENCODE) analysis efforts and The Roadmap Epigenomics Projects. We are currently working on the following key research areas.

1. Interpretable deep learning models of protein-DNA binding, chromatin accessibility, and chromatin state
2. Learning distal regulatory interactions between regulatory elements such as enhancers and gene promoters 
3. Leaning transcriptional regulatory networks that integrate cis-regulatory DNA sequence and activity of trans-regulators
4. Learning dynamic regulatory models by integrating functional genomic data from temporal (e.g. differentiation/reprogramming) and perturbation (e.g. CRISPR genome engineering) experiments
5. Prioritizing and interpreting functional genetic variation and its impact on chromatin, expression, and cellular phenotypes (growth, differentiation, drug response) in healthy and disease states
6. Early cancer detection and tissue-of-origin deconvolution from liquid biopsy (e.g. cell-free DNA) assays