Modern biological techniques are generating a variety of large-scale data, and require sophisticated algorithms for their analysis. Tasks include assembling the genomic sequence, predicting the protein-coding regions, their function and the manner in which they are regulated. The course will provide a broad overview of computational techniques currently used in bioinformatics with a focus on deep learning models for protein and DNA sequence data. Students completing the course will be able to analyze biological data, a skill they will develop through the hands-on lab component, which will consist of algorithm implementation and biological case studies using those algorithms. In addition to modern deep learning models for genomics data we will cover dynamic programming for sequence alignment, probabilistic methods for motif finding, and efficient string algorithms for read mapping. No previous biology background is assumed. Programming assignments will be in Python using modern machine learning libraries (PyTorch and scikit-learn). The class project will provide a more open-ended opportunity to apply these tools to realistic problems in genomics.<\/p>\n\n\n\n
(CS 320 or BZ 360) and CS 345.<\/p>\n\n\n\n