BST 227: Machine Learning in Genomics
Taught by Professor Quon. Emerging problems in molecular biology and current machine learning-based solutions to those problems. How deep learning, kernel methods, graphical models, feature selection, non-parametric models and other techniques can be applied to application areas such as gene editing, gene network inference and analysis, chromatin state inference, cancer genomics and single cell genomics.
BME 254: Statistical Methods in Genomics
Taught by Professor Aviran. Statistical approaches to problems in computational molecular biology and genomics; formulation of questions via probabilistic modeling, statistical inference methods for parameter estimation, and interpretation of results to address biological questions; application to high-impact problems in functional genomics and molecular biology.
ECS 124: Theory and Application of Bioinformatics
Taught by Professor Tagkopoulos, this course covers Fundamental biological, mathematical and algorithmic models underlying bioinformatics and systems biology; sequence analysis, database search, genome annotation, clustering and classification, functional gene networks, regulatory network inference, phylogenetic trees; applications of common bioinformatics tools in molecular biology and genetics.
ECS 171: Machine learning
Taught by Professor Tagkopoulos. Introduction to machine learning. Supervised and unsupervised learning, including classification, dimensionality reduction, regression and clustering using modern machine learning methods. Applications of machine learning to other fields.
ECS 224: String Algorithms in Computational Biology
Taught by Professor Gusfield. Algorithms that operate on strings. Pattern matching, sets of patterns, regular expression pattern matching, suffix trees and applications, inexact similarity, parametric sequence alignment, applications to DNA sequencing and protein database searching. Offered in alternate years.
ECS 229: Computational Structural Bioinformatics
Taught by Professor Koehl. Algorithmic problems in structural biology; protein structure classification; protein structure prediction (including comparative modeling and ab initio protein structure prediction); molecular simulations (molecular dynamics and Monte Carlo simulations).