1. Whole Genome Expression Analysis

2. In this presentation……
Part 1 – Gene Expression Microarray Data
Part 2 – Global Expression & Sequence Data Analysis
Part 3 – Proteomic Data Analysis

3. Part 1
Microarray Data

4. Examples of Problems
Gene sequence problems: Given a DNA sequence state which sections
are coding or noncoding regions. Which sections are promoters etc...
Protein Structure problems: Given a DNA or amino acid sequence
state what structure the resulting protein takes.
Gene expression problems: Given DNA/gene microarray expression data
infer either clinical or biological class labels or genetic machinery that
gives rise to the expression data.
Protein expression problems: Study expression of proteins and their
function.

5. Microarray Technology
Basic idea:
The state of the cell is determined by proteins.
A gene codes for a protein which is assembled via mRNA.
Measuring amount particular mRNA gives measure of
amount of corresponding protein.
Copies of mRNA is expression of a gene.
Microarray technology allows us to measure the expression
of thousands of genes at once.
Measure the expression of thousands of genes
under different experimental conditions and ask what is
different and why.

6. Oligo vs cDNA arrays
Lockhart and Winzler 2000

7. Format What is whole genome expression analysis? Clustering algorithm
- Hierarchical clustering
- K-means clustering
- Principal component analysis
- Self organizing maps
Beyond clustering
- Support vector machines
- Automatic discovery of regulatory patterns in promoter region
- Bayesian networks analysis

8. What is whole genome expression analysis?
Messenger RNA is only an
intermediate of gene expression

9. What is whole genome expression analysis? (continued)
Why measure mRNA?

10. What is whole genome expression analysis? (continued)

11. Why Separate Feature selection ?
most learning algorithms looks for non-linear combinations of features -- can easily find many spurious combinations given small # of records and large # of genes
We first reduce number of genes by a linear method, e.g. T-values
Heuristic: select genes from each class
Then apply a favorite machine learning algorithm

12. Feature selection approach
Rank genes by measure; select top
T-test for Mean Difference =
Signal to Noise (S2N) =
Other: Information-based, biological?
Almost any method works well with a good feature selection

13. Heatmap Visualization of selected fields
ALL
AML
Heatmap visualization
is done by normalizing
each gene to mean 0,
std. 1 to get a picture
like this.
Good correlation overall
AML-related
Possible outliers
sample #12
ALL-related

14. Controlling False Positives
CD37 antigen
Class
178
105
4174
7133 1 2
Mean Difference between Classes:
T-value = -3.25
Significance: p=0.0007

15. Controlling False Positives with Randomization
Randomized
Class
CD37 antigen
Class
Randomization is
Less Conservative
Preserves inner
structure of data
178
105
4174
7133 1 2 2 1
Randomize
Class
178
105
4174
7133 2 1
T-value = -1.1

16. Controlling false positives with randomization, II
Class
Gene
Class
178
105
4174
7133 1 2 2 1
Randomize
500 times
Gene
Class
Bottom
1% T-value = -2.08
Select potentially interesting genes at 1%
178
105
4174
7133 2 1

17. Microarray Data Classification
Part 2
Microarray Data Classification

18. Classification desired features: simplest approaches are most robust
robust in presence of false positives
understandable
return confidence/probability
fast enough
simplest approaches are most robust

19. Popular Classification Methods
Decision Trees/Rules
find smallest gene sets, but also false positives
Neural Nets -
work well if # of genes is reduced
SVM
good accuracy, does its own gene selection, hard to understand
K-nearest neighbor - robust for small # genes
Bayesian nets - simple, robust

20. Model-building Methodology
Select gene set (and other parameters) on a train set.
When the final model is built, evaluate it on the independent test set which should not be used in the model building

21. Selecting the best gene set
We tested 9 sets, 10 fold x-validation (90 neural nets)
Select gene set with lowest average error Heuristically, at least 10 genes overall

22. Results on the test data
Evaluation of the 10 genes per class on the test data (34 samples) gives
33 correct predictions (97% accuracy),
1 error on sample 66
Actual Class AML, Net prediction: ALL
net confidence low

23. Classification - other applications
Combining clinical and genetic data
Outcome / Treatment prediction
Age, Sex, stage of disease, are useful
e.g. if Data from Male, not Ovarian cancer

24. Classification: Multi-Class
Similar Approach:
select top genes most correlated to each class
select best subset using cross-validation
build a single model separating all classes
Advanced:
build separate model for each class vs. rest
choose model making the strongest prediction

25. Multi-class Data Example
Brain data, Pomeroy et al 2002, Nature (415), Jan 2002
42 examples, about 7,000 genes, 5 classes
Selected top 100 genes most correlated to each class
Selected best subset by testing 1,2, …, 20 genes subsets, leave-one-out x-validation for each

26. Number of genes (same from each class)
Brain data results
Optimal set:
8 genes per class
(4 errors
from 42)
Number of genes (same from each class)

27. Classification of Cancer Microarray Data
Part 3
Classification of Cancer Microarray Data

28. Cancer Classification
38 examples of Myeloid and Lymphoblastic leukemias
Affymetrix human 6800, (7128 genes including control genes)
34 examples to test classifier
Results: 33/34 correct
d perpendicular distance
from hyperplane d
Test data

29. Gene expression and Coregulation

30. Nonlinear classifier

31. Nonlinear SVM
Nonlinear SVM does not help when using all genes but does help when
removing top genes, ranked by Signal to Noise (Golub et al).

32. Rejections
Golub et al classified 29 test points correctly, rejected 5 of which 2 were errors using 50 genes
Need to introduce concept of rejects to SVM g1 g2
Cancer
Reject
Normal

33. Rejections

34. Estimating a CDF

35. The Regularized Solution

36. Rejections for SVM 95% confidence or p = .05 d = .107 P(c=1 | d) 1/d
.95
P(c=1 | d)
1/d

37. Results with rejections
Results: 31 correct, 3 rejected of which 1 is an error d
Test data

38. Why Feature Selection SVMs as stated use all genes/features
Molecular biologists/oncologists seem to be conviced that only a small subset of genes are responsible for particular biological properties, so they want which genes are are most important in discriminating
Practical reasons, a clinical device with thousands of genes is not financially practical
Possible performance improvement

39. Results with Gene Selection
AML vs ALL: 40 genes 34/34 correct, 0 rejects.
5 genes 31/31 correct, 3 rejects of which 1 is an error. d
Test data
B vs T cells for AML: 10 genes 33/33 correct, 0 rejects.

40. Leave-one-out Procedure
Leave-one-out Procedure

41. The Basic Idea
Use leave-one-out (LOO) bounds for SVMs as a criterion to select features by searching over all possible subsets of n features for the ones that minimizes the bound.
When such a search is impossible because of combinatorial explosion, scale each feature by a real value variable and compute this scaling via gradient descent on the leave-one-out bound. One can then keep the features corresponding to the largest scaling variables.
The rescaling can be done in the input space or in a “Principal Components” space.