Classification of Microarray Data

1. Classification of Microarray Data

2. The DNA Array Analysis Pipeline Question Experimental Design Array design Probe design Sample Preparation Hybridization Buy Chip/Array Image analysis Normalization Expression Index Calculation Comparable Gene Expression Data Statistical Analysis Fit to Model (time series) Advanced Data Analysis Clustering PCA Classification Promoter Analysis Meta analysis Survival analysis Regulatory Network

3. Outline • Example: Childhood leukemia • Classification • Feature selection • Classification methods • Cross-validation • Training and testing • Example continued: Results from a leukemia study

4. Childhood Leukemia • Cancer in the cells of the immune system • Approx. 35 new cases in Denmark every year • 50 years ago – all patients died • Today – approx. 78% are cured • Riskgroups • Standard • Intermediate • High • Very high • Extra high • Treatment • Chemotherapy • Bone marrow transplantation • Radiation

5. Prognostic Factors

6. Risk Classification Today Patient: Clinical data Immunopheno-typing Morphology Genetic measurements Prognostic factors: Immunophenotype Age Leukocyte count Number of chromosomes Translocations Treatment response Risk group: Standard Intermediate High Very high Ekstra high Microarray technology

7. Study of Childhood Leukemia • Diagnostic bone marrow samples from leukemia patients • Platform: Affymetrix Focus Array • 8793 human genes • Immunophenotype • 18 patients with precursor B immunophenotype • 17 patients with T immunophenotype • Outcome 5 years from diagnosis • 11 patients with relapse • 18 patients in complete remission

8. Reduction of data • Dimension reduction • PCA • Feature selection (gene selection) • Significant genes: t-test • Selection of a limited number of genes

9. Microarray Data

10. Outcome: PCA on all Genes

11. Outcome Prediction: CC against the Number of Genes

12. Nearest Centroid • Calculation of a centroid for each class • Calculation of the distance between a test sample and each class cetroid • Class prediction by the nearest centroid method

13. K-Nearest Neighbor • Based on distance measure • For example Euclidian distance • Parameter k = number of nearest neighbors • k=1 • k=3 • k=... • Always an odd number • Prediction by majority vote

14. Support Vector Machines • Machine learning • Relatively new and highely theoretic • Works on non-linearly seperable data • Finding a hyperplane between the two classes by minimizing of the distance between the hyperplane and closest points

15. Neural Networks Gene1 Gene2 Gene3 ... Input Hidden neurons Output B T

16. Comparison of Methods KNN

17. Cross-validation Data: 10 samples Cross-5-validation: Training: 4/5 of data (8 samples) Testing: 1/5 of data (2 samples) -> 5 different models Leave-one-out cross-validation (LOOCV) Training: 9/10 of data (9 samples) Testing: 1/10 of data (1 sample) -> 10 different models

18. Validation • Definition of • true and false positives • true and false negatives Actual class B B T T Predicted class B T T B TP FN TN FP

19. Accuracy • Definition: TP + TN TP + TN + FP + FN • Range: 0 – 100%

20. Matthews correlation coefficient • Definition: TP·TN - FN·FP √(TN+FN)(TN+FP)(TP+FN)(TP+FP) • Range: (-1) – 1

21. Sensitivity and Specificty Sensitivity: the ability to detect "true positives" TP TP + FN Specificity: the ability to avoid "false positives" TP TP + FP

22. Testing of classifier Independant test set Overview of Classification Expression data Subdivision of data for cross-validation into training sets and test sets Feature selection (t-test) Dimension reduction (PCA) • Training of classifier: • using cross-validation • choice of method • - choice of optimal parameters

23. Important Points • Avoid overfitting • Validate performance • Test on an independant test set • by using cross-validation • Include feature selection in cross-validation Why? • To avoid overestimation of performance! • To make a general classifier

24. Multiclass classification • Same prediction methods • multiclass prediction often implemented • Often bad performance • Solution • Division in small binary (2-class) problems

25. Study of Childhood Leukemia: Results • Classification of immunophenotype (precursorB og T) • 100% accuracy • During the training • When testing on an independant test set • Simple classification methods applied • K-nearest neighbor • Nearest centroid • Classification of outcome (relapse or remission) • 78% accuracy (CC = 0.59) • Simple and advanced classification methods applied

26. Risk classification in the future ? Patient: Clincal data Immunopheno-typing Morphology Genetic measurements Prognostic factors: Immunophenotype Age Leukocyte count Number of chromosomes Translocations Treatment response Risk group: Standard Intermediate High Very high Ekstra high Custom designed treatment Microarray technology

27. Summary • When do we use classification? • Reduction of dimension often nessesary • t-test, PCA • Methods • K nearest neighbor • Nearest centroid • Support vector machines • Neural networks • Validation • Cross-validation • Accuracy and correlation coefficient

28. Coffee break Next: Exercises in classification