Several offerings each quarter, on topics of current interest. Prerequisite: permission of instructor.
Machine learning (ML) techniques have become very useful tools for resolving important questions in biology by providing mathematical frameworks to analyze vast amount of biological information. Biology is a fascinating application area of ML because it presents new sets of computational challenges that can ultimately advance ML methodology. In this course, we will discuss recent papers describing successful examples of the development of ML algorithms applied to exciting problems in genetics and molecular biology. An example problem is to predict whether a person x has cancer based on xís expression (activity) levels of 20 thousand genes or based on xís genetic information defined by 1 million numbers. Some of the ML techniques we will discuss are based on hidden Markov models, Bayesian networks, Markov random fields, or support vector machines.
Student learning goals
Becoming familiar with research trends in applying ML to the context of biology; gaining new insights or ideas which can help the studentís own research.
General method of instruction
In each meeting, we will discuss one or two papers for about an hour. The format of the discussion will be described on the course website. The instructor will then lecture to provide biological background and motivation for the topic to be discussed in the next meeting. We will also have an optional discussion session to brainstorm on ML methods to solve a particular problem in biology.
If you are looking for a deeper level of commitment by working on a research project for developing a ML algorithm for bio-applications, email the instructor, Su-In Lee, in advance: firstname.lastname@example.org.
No background in biology is assumed.
Class assignments and grading
Reading weekly assigned papers; leading the discussion on one or two papers per quarter; participating in discussions.