Our group develops computational methods to study and model transcriptional, co-transcriptional, and post-transcriptional gene regulatory mechanisms and to dissect the dysregulation of gene expression in cancer. The techniques we use generally come from machine learning, a field at the intersection of computer science and statistics. In particular, we develop supervised learning methods -- algorithmic approaches for learning predictive models from data -- that we train on high-throughput experimental data, increasingly from next generation sequencing. As we try to advance the state-of-the-art in statistical and machine learning models of gene regulation, we also seek to drive biological discovery through close collaborations with experimentalists to study specific regulatory mechanisms.

Research Highlights

  • Affinity regression predicts the recognition code of nucleic acid-binding proteins
  • Early enhancer establishment and regulatory locus complexity shape transcriptional programs in hematopoietic differentiation
  • Breast Cancer Signaling Pathways Linked to Transcriptional Programs
  • Alternative Poly-Adenylation
  • Gliobastoma Regulator Inference
  • MicroRNA 155