| Schedule |
| Date |
Topic |
Presenters/Participants |
Papers |
 |
| 03/30 |
Organizational Meeting |
|
|
| 04/06 |
Exploring cancer and cancer therapies through agent-based
modeling. |
Guest Speaker: Carlo Maley, FHCRC |
Abstract |
| 04/13 |
Feature Selection: FS 101 |
Don, Ken |
|
| 04/20 |
Feature Selection: 2 nonparametric methods |
Gidon, Saurabh |
1 ,2 |
| 04/27 |
Feature Selection: a survey |
Jochen |
3 |
| 05/04 |
Feature Selection: SVMs |
Brian, Mathieu |
4, 5 |
| 05/11 |
Array Analysis: More SVMs |
Ka Yee |
10 |
| 05/18 |
Array Analysis: A Promoter Model |
Dan |
7 |
| 05/25 |
Computational issues in protein folding, structure prediction,
and design |
Guest Speaker: David Baker, Biochem |
|
| 06/01 |
Array Analysis: Bayes Nets |
Emily, Tammy |
8, 9 |
|
| Papers, etc. |
4/6:
Exploring cancer and cancer therapies through agent-based
modeling.
Dr. Carlo Maley,
Human Biology Division,
Fred Hutchinson Cancer Research Center
Abstract:
Curing cancer has proven to be an extremely hard problem.
The US government has invested billions of dollars in cancer
research over the last half century and still Americans have
about a 40% chance of developing cancer in their lifetime.
Why is it such a hard problem? Because the cells in a tumor
evolve. Like HIV, tumor cells mutate rapidly and quickly
develop resistance to any therapies that we apply. Until
recently, it has been difficult to study the evolutionary
dynamics of cancer, let alone counter them. This is
beginning to change. Today we have the technology to
examine mutant cells in detail. We are also developing the
theoretical tools necessary to understand these complex
dynamics. I will introduce a set of agent-based (a.k.a.,
"configuration" or "individual-based") models that simulate
both the evolutionary dynamics of cancer, as well as the
effects of some hypothetical therapies. I will introduce
these models as well as some of the insights we have gained
through their use.
Topic I: Classification and Feature Selection with Microarray Data
There is a rapidly growing literature on use of microarray data
to discriminate between, say, tumor and normal samples, and to
identify those genes that seem most strongly linked to such
discriminations. We're going to tackle some or all of the
following papers.
It would be great if any of you wanted to experiment with any of
these or other methods on some real data. Some of the data sets
that have been commonly used in these studies are the following.
Please let us know if you (a) find other data, and/or (b) learn
anything interesting from looking at it.
Data Sets:
References:
- Ben-dor et al. "Tissue classification with gene
expression profiles", JCB 2000.
Paper
[The following is a related TR: "Scoring genes for
relevance".
Paper]
- Park, Pagano, Bonetti, "A nonparametric scoring algorithm
for identifying informative genes from microarray data", PSB
2001.
Paper
- Claverie, "Computational methods for identification of
differential and coordinated gene expression", Human
Molecular Genetics 1999.
(pdf)
- Guyon, Weston, Barnhill, Vapnik, "Gene selection for cancer
classification using support vector machines", Machine
Learning 2000.
(pdf)
- Pavlidis, Weston, Cai, Grundy "Gene functional classification from
heterogenous data", Recomb 2001.
Paper
- Link to feature selection literature (for background/review).
There's a ton of stuff
here. To be used as a resource.
Topic 2: (Non-Clustering) Analysis of Microarray Data
We're going to tackle some or all of the
following papers.
References:
-
Bussemaker, Li, and Siggia, "Regulatory element detection
using correlation with expression." Nature Genetics, 27 (Feb
2001) 167-171.
(pdf,
Siggia's talk, from MSRI)
- Friedman, Linial, Nachman, and Pe'er,
"Using Bayesian networks to analyze expression data." J.
Computational Biology 7:601-620, 2000.
Paper.
- A.J. Hartemink, D.K. Gifford, T.S. Jaakkola, and R.A. Young,
"Using Graphical Models and Genomic Expression Data to
Statistically Validate Models of Genetic Regulatory Networks."
Pacific Symposium on Biocomputing 6:422-433 (2001).
Paper.
- Brown, MPS, WN Grundy, D Lin, N Cristianini, C Sugnet, TS
Furey, M Ares, Jr., and D Haussler. "Knowledge-based
analysis of microarray gene expression data by using support
vector machines." Proceedings of the National Academy of
Science. 97(1):262-267, 2000.
Paper.
- Pe'er, Regev, Elidan, and Friedman. "Inferring Subnetworks from
Perturbed Expression Profiles." Bioinformatics, 2001.
Paper.
- And three good web tutorials/resources on Bayes nets that Tammy found:
|