Advanced Topics in Genomic Data Analysis
3.0
creditsAverage Course Rating
Genomic data is becoming available in large quantities, but understanding how genetics contributes to human disease and other traits remains a major challenge. Machine learning approaches allow us to automatically analyze and combine genomic data, build predictive models, and identify genetic elements important to disease and cellular processes. This course will cover uses of machine learning in diverse genomic applications. Students will present and discuss current literature. Topics include predicting disease risk from genomic data, integrating diverse genomic data types, gene network reconstruction, and other topics guided by student interest. The course will include a project component with the opportunity to explore publicly available genomic data. Recommended course background: coursework in data mining, machine learning. [Applications] Students may receive credit for 600.441 or 600.641, but not both.
Spring 2015
Professor: Alexis Battle
The best aspects of the course included the engaging and effective professor who was invested in ensuring the students’ success. Some students noted that the professor’s feedback on assignments was both timely and insightful. Several students pointed out that some of the topics focused on in the course were outdated, and suggested including more up-to-date work in the syl abus. Prospective students should have a strong programming background as this course can be chal enging, and expect to develop firm foundations in automatic speech recognition.