LizIzhikevich/CS273a_EnhancersProject

Predicting the function of different regions of the genome is one of the grand challenges of genomics. In this project, you will use an existing database of tested enhancers to devise a strategy for predicting novel enhancers, using both sequence features and numerous epigenetic marks. The advent of ChIP-seq has empowered high resolution genome-wide identification of the regions with specific marks, and correlation with functional annotation has identified combinations of marks that are characteristic of active and repressed genes, enhancers, repressors, and other types of functional elements (Ernst et al 2011 “Mapping and analysis of chromatin state dynamics in nine human cell types.”). Here, you will be leveraging assays of many different marks in many different tissues to predict enhancers. In doing so, you should also identify which marks, or combinations of marks, are most discriminative in predicting enhancers.

Jupyter Notebook