Computational Statistics,Genetics & Microbiology.

Susan Holmes,

Schedule & Location

MW 11:00-12:15, McCullough 122. Labs F 11-12, GAtes B12.

Instructor & TAs

Instructor

Susan Holmes

• Office: Sequoia Hall #102
• Phone: 725-1925,
• Email: susan AT stat DOT stanford etc
• Office hours: M, F 2:15-3:15

Teaching Assistant

Austen Head

• Office: Sequoia Hall 208
• Office hours: Thursday 2.30-3.30
• Email

This course will show a series of statistical concepts in action. We will cover a series of case studies showing you how to use R and relevant tools to analyse your complex biological data sets.

Computer examples

We will be using R for most examples, and more precisely the Bioconductor suite. Both of these sites have large numbers of documents and tutorials.

Prerequisites

Some familiarity with linear algebra and statistical methods.

Evaluation

• Class participation and scribing; 20%
• Labs/homework (5 total, best 4 count); 40%
• midterm (project proposal); 15%
• final project (according to Stanford calendar: due on June, 13th); 25%

Preliminary Schedule

Results of survey

Week	Subject	Lect Link	Lect Link	Lab Friday
April 2-6	Genomes and Sequences	Lect 1	Lect2	Lab 1
April 9-13	CpG Islands Multinomials/Markov Chains/HMMs	Lect3	Lect4	Lab 2
April 16-20	Multivariate Examples	Lect 5	Lect 6	Lab 3
April 23-27	PCA-MDS-CA and graphs	Lect 7	Lect 8	Lab 4
April 30-May 4	ML and Bayesian estimation(MCMC)	Lect 9	Lect 10	None
May 7-11	Phylogenetic Trees/ Bootstrap	Lect 11	Lect 12	Lab 5
May 14-18	Microarray Normalization/lowess	Lect 13	Lect 14	None
May 21-25	Multivariate Analyses plots/interpretation/permutation tests	Lect 15	Lect16	None
May 28-June 1	Kernel Methods	Lect 17	Lect18	None
June 4-8	High Throughput sequence analyses	Lect 19	Lect20	None

Materials

• Crash Course in Genomics
• Seeing the structure and the surprises
• Sequence Data are Strings
• Markov Chains
• Hidden Markov Models - the Unfair Casino
• Hidden Markov Model for CpG islands
• Underlying Algorithms
• PCA : Interpretation Examples
• PCA, SVD and MDS
• Binary Table/Contingency Table representation
• Binary Data and Graphs
• Modelling Mixtures: the Dirichlet distribution
• Gibbs Sampler Examples
• Microarrays

Assignments

• HW1 Stats 366 - Stats 166
• Lab1 Reading and Manipulating genomes in R
• Lab2/Hw 2 Hidden Markov Models
• Lab3/Hw 3 Visualization and PCA
• Lab4 Networks
• Lab 5: Phylogenetic Trees and the Bootstrap

Lecture Materials

For relevant slides click on time table above which will lead you to the coursework repository.

Acknowledgements

I was inspired to rewrite my previous notes for this course up as a sphinx document by the wonderful work of Avril Coghlan and her little book on Bioinformatics.

Jonathan Taylor helped me through the process of getting started using sphinx, especially interfacing it with R.

All the cartoons from the website are shamelessly poached from Randall Munroe s xkcd webcomics.

License

The content of this website are licensed under a Creative Commons Attribution Share Alike 3.0 License.