Spring 2021, Monday / Wednesday 10-11:20am (Pacific), Virtual
Instructor: Sara Mostafavi
Time and place: Monday and Wednesdays 10-11:20am PT. See Canvas for Zoom link.
Description: The field of computational biology has seen a dramatic transformation in the last few years, whereby application-inspired machine learning (ML) advances promise to enable key discoveries in biology and medicine. New measurement technologies are leading to large-scale datasets, enabling researchers to ask new questions about principles underlying complex biological systems and precise molecular mechanisms that lead to disease. However, fully realizing the scientific and clinical potential of complex and multi-modal biological datasets also requires developing novel supervised and unsupervised learning methods that are scalable, can accommodate heterogeneity, are robust to systematic noise and confounding factors, while able to provide mechanistic insights.
In this course, we will survey cutting edge research directions at the intersection of machine learning, computational biology, and applied statistics. We will focus on application areas where advances in ML are leading to new biological discoveries. These will include classical problems that can now be investigated with new data and approaches, such as predicting protein 3D structure, to models that explore complex mechanistic hypotheses bridging the gap between genetics and disease, population genetics and transcriptional regulation. We will discuss research challenges and open problems that are important to biological discovery, including incorporating biological knowledge into models, addressing confounding factors, and learning in the context of limited “labeled data”.
Computational Biology is a challenging multi-disciplinary area, so it is often not possible to fully understand all aspects (e.g., ML, stats and biology) of discussed papers, however, one goal of the course is to learn to navigate this complex intersection to be able to *critically* evaluate research results and formulate interesting and meaningful research questions.
See Schedule page for weekly topics and list of invited speakers
See Reading page for preparatory and weekly reading list
See Syllabus page for the following information:
Topics
Learning objectives
Course format
Pre-requisites
Student evaluation
Suggested background reading