Course Descriptions

4 units. Letter grading.

This course provides a background in the mathematical and engineering foundations that are the building blocks of data science.  Topics covered include linear algebra, probability, and statistics.  The course also provides an overview of science software engineering and reproducibility fundamentals including working on a compute cluster, pipeline development, virtual notebooks, version control.

4 units. Letter grading.

Requisites: Foundations of Data Science or equivalent background. 

Introduction to machine learning analysis of biomedical data, with a focus on formulating interdisciplinary problems as computational problems and then solving those problems using machine learning techniques. and computational interdisciplinary research in genetics.  Fundamentals of machine learning and applications to genetics and health records.

4 units. Letter grading.

Requisites: DSB 205, Machine learning applications in Biomedicine.

Statistical models for analysis of Biomedical data that captures the structure of the data and accounts for the constraints. Topics include Bayesian models, Probabilistic Graphical models, Deep Learning, Time series, Dynamical systems, Stochastic processes, Scalable inference (gradient descent, SGD, EM, MCMC, Variational inference), Privacy-preserving inference (differential privacy, inference over encrypted data), Interpretable ML, and Fairness and Bias.

4 units. Letter grading.

Requisites: Foundations of Data Science or equivalent background.

Overview of medical image modalities and 3D visualization, classical image processing (histogram analysis and filtering), modern deep learning techniques (convolutional networks), image alignment and statistical analysis of populations. 

4 units. Letter grading.

Requisites: Foundations of Data Science or equivalent background.

Introduction to computational approaches in bioinformatics, genomics, computational genetics, electronic health records, medical images and other analysis of biomedical data. Topics include emerging methods and their applications to genomics, epigenomics, population genetics, analysis of health records within medical systems, medical imaging, and genomic technologies. Computational techniques include those from statistics and computer science. This course satisfies the capstone requirement. Students will present their results.

4 units. Letter grading.

Requisites: Foundations of Data Science or equivalent background. 

Development and application of algorithmic approaches to problems in biomedicine, with focus on formulating interdisciplinary problems as computational problems and then solving these problems using algorithmic techniques.   Design, analysis, optimization, and implementation of algorithms.  Topics include string algorithms in genomics and scalable machine learning algorithms applied to medical data.  This course satisfies the capstone requirement. Students will present their results.

4 units. Letter grading.

Requisites: Foundations of Data Science of equivalent background.

Overview of recent research in machine learning applied to medicine.  The course will cover recent papers utilizing data science approaches to analyze large amounts of medical data.  Topics include analysis of medical imaging data, electronic health records and waveforms.  Students will receive instruction on how to read recent research papers and present these papers in the course. 

4 units.  Letter grading.

Requisites: Foundations of Data Science or equivalent background.

Overview of recent research in data science applied to genomic medicine.  The course will cover recent papers that use data science approaches to analyze large amounts of genomic data along with medical data with the goal of improving patient care.  Topics include analysis of genomic data to diagnose rare diseases, estimation and utilization of polygenic risk scores in electronic medical records and integrating novel types of genomic data into clinical care.  Students will receive instruction on how to read recent research papers and present these papers in the course. 

4 - 8 units.  Letter grading.

Limited to Master of Science in Data Science in Biomedicine students. Hands-on applied analytics project that helps prepare students for a career in data science in biomedicine by testing their ability to solve complex data science problems in real-world settings. Students hone their communication skills and delve deeply into areas of interest beyond the classroom.  This course satisfies the capstone requirement.