1. Data Mining in Genomics: the dawn of personalized medicine
Gregory Piatetsky-Shapiro
KDnuggets
Connecticut College, October 15, 2003

2. Overview Data Mining and Knowledge Discovery Genomics and Microarrays
Microarray Data Mining

3. Trends leading to Data Flood
More data is generated:
Bank, telecom, other business transactions ...
Scientific Data: astronomy, biology, etc
Web, text, and e-commerce
More data is captured:
Storage technology faster and cheaper
DBMS capable of handling bigger DB

4. Knowledge Discovery Process
Integration
Interpretation
& Evaluation
Knowledge
Data Mining
Patterns
and
Rules
Knowledge
RawData __
____
Transformation
Selection
& Cleaning
Understanding
Transformed
Data
DATA
Ware
house
Target
Data

5. Major Data Mining Tasks
Classification: predicting an item class
Clustering: finding clusters in data
Associations: e.g. A & B & C occur frequently
Visualization: to facilitate human discovery
Summarization: describing a group
Estimation: predicting a continuous value
Deviation Detection: finding changes
Link Analysis: finding relationships

6. Major Application Areas for Data Mining Solutions
Advertising
Bioinformatics
Customer Relationship Management (CRM)
Database Marketing
Fraud Detection
eCommerce
Health Care
Investment/Securities
Manufacturing, Process Control
Sports and Entertainment
Telecommunications
Web

7. Genome, DNA & Gene Expression
An organism’s genome is the “program” for making the organism, encoded in DNA
Human DNA has about 30-35,000 genes
A gene is a segment of DNA that specifies how to make a protein
Cells are different because of differential gene expression
About 40% of human genes are expressed at one time
Microarray devices measure gene expression

8. Molecular Biology Overview
Nucleus
Cell
Chromosome
Gene
expression
Gene (DNA)
Protein
Gene (mRNA),
single strand
Graphics courtesy of the National Human Genome Research Institute

9. Affymetrix Microarrays
1.28cm
50um
~107 oligonucleotides,
half Perfectly Match mRNA (PM),
half have one Mismatch (MM)
Gene expression computed from PM and MM

10. Affymetrix Microarray Raw Image
Gene Value
D26528_at
D26561_cds1_at
D26561_cds2_at
D26561_cds3_at
D26579_at
D26598_at
D26599_at
D26600_at
D28114_at
Scanner
raw data
enlarged section of raw image

11. Microarray Potential Applications
New and better molecular diagnostics
New molecular targets for therapy
few new drugs, large pipeline, …
Outcome depends on genetic signature
best treatment?
Fundamental Biological Discovery
finding and refining biological pathways
Personalized medicine ?!

12. Microarray Data Mining Challenges
Avoiding false positives, due to
too few records (samples), usually < 100
too many columns (genes), usually > 1,000
Model needs to be robust in presence of noise
For reliability need large gene sets; for diagnostics or drug targets, need small gene sets
Estimate class probability
Model needs to be explainable to biologists

13. False Positives in Astronomy
cartoon used with permission

14. CATs: Clementine Application Templates
CATs - examples of complete data mining processes
Microarray CAT
Preparation
Multi-
Class
Clustering
2-Class

15. Key Ideas Capture the complete process
X-validation loop w. feature selection inside
Randomization to select significant genes
Internal iterative feature selection loop
For each class, separate selection of optimal gene sets
Neural nets – robust in presence of noise
Bagging of neural nets

16. Microarray Classification
Train data
Feature and Parameter Selection
Data
Model Building
Evaluation
Test data

17. Classification: External X-val
Gene Data
Train data
Feature and Parameter Selection
T r a i n
Data
Model Building
Evaluation
Test data
FinalTest
Final Model
Final Results

18. Measuring false positives with randomization
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

19. Gene Reduction improves Classification
most learning algorithms look for non-linear combinations of features -- can easily find many spurious combinations given small # of records and large # of genes
Classification accuracy improves if we first reduce # of genes by a linear method, e.g. T-values of mean difference
Heuristic: select equal # genes from each class
Then apply a favorite machine learning algorithm

20. Iterative Wrapper approach to selecting the best gene set
Test models using 1,2,3, …, 10, 20, 30, 40, ..., 100 top genes with x-validation.
Heuristic 1: evaluate errors from each class; select # number of genes from each class that minimizes error for that class
For randomized algorithms, average 10+ Cross-validation runs!
Select gene set with lowest average error

21. Clementine stream for subset selection by x-validation

22. Microarrays: ALL/AML Example
Leukemia: Acute Lymphoblastic (ALL) vs Acute Myeloid (AML), Golub et al, Science, v.286, 1999
72 examples (38 train, 34 test), about 7,000 genes
well-studied (CAMDA-2000), good test example
ALL
AML
Visually similar, but genetically very different

23. Gene subset selection: one X-validation
Single Cross-Validation run

24. Gene subset selection: multiple cross-validation runs
For ALL/AML data, 10 genes per class had the lowest error: (<1%)
Point in the center
is the average error
from 10 cross-validation runs
Bars indicate 1 st. dev
above and below

25. ALL/AML: Results on the test data
Genes selected and model trained on Train set ONLY!
Best Net with 10 top genes per class (20 overall) was applied to the test data (34 samples):
33 correct predictions (97% accuracy),
1 error on sample 66
Actual Class AML, Net prediction: ALL
other methods consistently misclassify sample misclassified by a pathologist?

26. Pediatric Brain Tumour Data
92 samples, 5 classes (MED, EPD, JPA, EPD, MGL, RHB) from U. of Chicago Children’s Hospital
Outer cross-validation with gene selection inside the loop
Ranking by absolute T-test value (selects top positive and negative genes)
Select best genes by adjusted error for each class
Bagging of 100 neural nets

27. Selecting Best Gene Set
Minimizing Combined Error for all classes is not optimal
Average, high and low error rate for all classes

28. Error rates for each class
Genes per Class

29. Evaluating One Network
Averaged over 100 Networks:
Class
Error rate
MED
2.1%
MGL
17%
RHB
24%
EPD 9%
JPA
19%
*ALL*
8.3%

30. Bagging 100 Networks Class Individual Error Rate Bag Error rate
Bag Avg Conf
MED
2.1%
2% (0)*
98%
MGL
17%
10%
83%
RHB
24%
11%
76%
EPD 9%
91%
JPA
19%
81%
*ALL*
8.3%
3% (2)*
92%
Note: suspected error on one sample (labeled as MED but consistently classified as RHB)

31. AF1q: New Marker for Medulloblastoma?
AF1Q ALL1-fused gene from chromosome 1q
transmembrane protein
Related to leukemia (3 PUBMED entries) but not to Medulloblastoma

32. Future directions for Microarray Analysis
Algorithms optimized for small samples
Integration with other data
biological networks
medical text
protein data
Cost-sensitive classification algorithms
error cost depends on outcome (don’t want to miss treatable cancer), treatment side effects, etc.

33. Acknowledgements
Eric Bremer, Children’s Hospital (Chicago) & Northwestern U.
Greg Cooper, U. Pittsburgh
Tom Khabaza, SPSS
Sridhar Ramaswamy, MIT/Whitehead Institute
Pablo Tamayo, MIT/Whitehead Institute

34. Thank you Further resources on Data Mining: www.KDnuggets.com
Microarrays:
Contact:
Gregory Piatetsky-Shapiro: