Course description

What genes cause cancer ? Have we inherited genes from Neanderthals ? How does a single genome code for the different cells ?

We can now begin to answer these fascinating questions in biology because the cost of genome sequencing has fallen faster than Moore's law. The bottleneck in answering these questions has shifted from data generation to powerful statistical models and inference algorithms that can make sense of this data. Statistical machine learning provides an important toolkit in this endeavor. Further, biological datasets offer new challenges to the field of machine learning.

We will learn about probabilistic models, inference and learning in these models, model assessment, and interpreting the inferences to address the biological questions of interest. The course aims to introduce CS/Statistics students to an important set of problems and Bioinformatics/Human Genetics students to a rich set of tools.


Familiarity with probability, statistics, linear algebra and algorithms is expected. No familiarity with biology is needed.

Contact Info

Instructor: Sriram Sankararaman
Office Hours: Boelter 4531D, Tuesday 10:00a - 11:00a (or by appointment)
Email: sriram at cs dot ucla dot edu


There is no formal textbook. Readings will be posted as needed. The following texts will serve as useful references:

Course format

Grading A tentative syllabus


The course website is based on material developed by Ameet Talwalkar and Fei Sha. Some of the administrative content on the course website is adapted from material from Jenn Wortman Vaughan, Rich Korf, and Alexander Sherstov.

Tentative Schedule

Date Topics Reading HW
3/29 Introduction to genomics Big Data: Astronomical or Genomical?

Introductory statistics.

Storey, False Discovery Rates
4/5 Multiple testing. Association studies: linear and logistic regression Storey, False Discovery Rates

Guest lecture

4/12 GWAS. Bayesian statistics. Ridge regression Eskin, CACM 2015
Okser et al. Regularized Machine Learning in the Genetic Prediction of Complex Traits
Homework 1
Data for Homework 1

Guest lecture

4/19 Bayesian and sparse regression. Linear Mixed Models. Heritability Zuk et al. PNAS 2011
Additional: Yang et al. Nature Genetics 2010

Latent Variable Models: Clustering, mixture models and the EM algorithm

4/26 Latent Variable Models: PCA and admixture models

Application: Population structure and stratification

5/3 Directed Graphical Models

Hidden Markov Models

Li and Stephens Genetics 2003
Homework 2
Data for Homework 2
5/10 Undirected graphical models and trees.Sum-product algorithm and MCMC (Gibbs sampling). Application to admixture models

Approximate inference: MCMC (Metropolis-Hastings) and variational inference

5/17 Kernel machines and Gaussian process. Application: Rare-variant association test

Bayesian nonparametrics: Dirichlet process

Homework 3
Data for Homework 3

Class cancelled


Genomic privacy: Learning with privacy constraints


Project presentations


Project presentations