Instructor GENE 520: Computational Human Genomics and Epigenomics

Taught units starting from the basics of Python programming building up to dimension reduction and representation learning techniques for biological data with a focus on single-cell genomics and epigenomics.

• Python basics and data analysis with Pandas and Numpy
• Data visualization with Matplotlib and Seaborn
• Working with sequencing data in Python
  • Assignment to build a simple transcription factor motif binding site predictor using a simple sliding window cross correlation approach
• Linear dimensionality reduction techniques such as PCA and MDS
• Nonlinear dimensionality reduction techniques such as t-SNE and UMAP
• Neural network-based representation learning techniques such as autoencoders and variational autoencoders
• Variational autoencoders for single-cell genomics and epigenomics data
  • Assignment to train a scVI model on a single-cell RNA-seq dataset and use the latent representation for downstream analysis such as clustering, visualization, and celltype classifications with the goal of comparing to PCA and other linear methods