Cancer Classification with Datadependent Kernels

1
Cancer Classification with Data-dependent Kernels

• Anne Ya Zhang
• (with Xue-wen Chen Huilin Xiong)
• EECS ITTC
• University of Kansas

2
Outline

• Introduction
• Data-dependent Kernel
• Results
• Conclusion

3
Cancer facts

• Cancer is a group of many related diseases
• Cells continue to grow and divide and do not die
  when they should.
• Changes in the genes that control normal cell
  growth and death.
• Cancer is the second leading cause of death in
  the United States
• Cancer causes 1 of every 4 deaths
• NIH estimate overall costs for cancer in 2004 at
  189.8 billion (64.9 billion for direct medical
  cost)
• Cancer types
• Breast cancer, Lung cancer, Colon cancer,
• Death rates vary greatly by cancer type and stage
  at diagnosis

4
Motivation

• Why do we need to classify cancers?
• The general way of treating cancer is to
• Categorize the cancers in different classes
• Use specific treatment for each of the classes
• Traditional way to classify cancers
• Morphological appearance
• Not accurate!
• Enzyme-based histochemical analyses.
• Immunophenotyping.
• Cytogenetic analysis.
• Complicated needs highly specialized
  laboratories

5
Motivation

• Why traditional ways are not enough ?
• There exists some tumors in the same class with
  completely different clinical courses
• May be more accurate classification is needed
• Assigning new tumors to known cancer classes is
  not easy
• e.g. assigning an acute leukemia tumor to one of
  the
• AML (acute myeloid leukemia)
• ALL (acute lymphoblastic leukemia)

6
DNA Microarray-based Cancer Diagnosis

• Cancer is caused by changes in the genes that
  control normal cell growth and death.
• Molecular diagnostics offer the promise of
  precise, objective, and systematic cancer
  classification
• These tests are not widely applied because
  characteristic molecular markers for most solid
  tumors have to be identified.
• Recently, microarray tumor gene expression
  profiles have been used for cancer diagnosis.

7
Microarray

• A microarray experiment monitors the expression
  levels for thousands of genes simultaneously.
• Microarray techniques will lead to a more
  complete understanding of the molecular
  variations among tumors, hence to a more reliable
  classification.

8
Microarray

• Microarray analysis allows the monitoring of the
  activities of thousands of genes over many
  different conditions.
• From a machine learning point of view

The large volume of the data requires the
computational aid in analyzing the expression
data.
9
Machine learning tasks in cancer classification

• There are three main types of machine learning
  problems associated with cancer classification
• The identification of new cancer classes using
  gene expression profiles
• The classification of cancer into known classes
• The identifications of marker genes that
  characterize the different cancer classes
• In this presentation, we focus on the second type
  of problems.

10
Project Goals

• To develop a more systematic machine learning
  approach to cancer classification using
  microarray gene expression profiles.
• Use an initial collection of samples belonging to
  the known classes of cancer to create a class
  predictor for new, unknown, samples.

11
Challenges in cancer classification

• Gene expression data are typically characterized
  by
• high dimensionality (i.e. a large number of
  genes)
• small sample size
• Curse of dimensionality!

• Methods
• Kernel techniques
• Data resampling
• Gene selection

12
Outline

• Introduction
• Data-dependent Kernel
• Results
• Conclusion

13
Data-dependent kernel model
Data dependent
Optimizing the data-dependent kernel is to choose
the coefficient vector
14
Optimizing the kernel

• Criterion for kernel optimization
• Maximum class separability of the training data
  in the kernel-induced feature space

15
The Kernel Optimization
In reality, the matrix N0 is usually singular
a eigenvector corresponding to the largest
eigenvalue
16
Kernel optimization
Training data
Test data
Before Kernel Optimization
After Kernel Optimization
17
Distributed resampling

• Original training data
• Training data with resampling

18
Gene selection

• A filter method class separability

19
Outline

• Introduction
• Data-dependent Kernel
• Results
• Conclusion

20
Comparison with other methods

• k-Nearest Neighbor (kNN)
• Diagonal linear discriminant analysis (DLDA)
• Uncorrelated Linear Discriminant analysis (ULDA)
• Support vector machines (SVM)

21
Data sets
AML
Subtypes ALL vs. AML
Status of Estrogen receptor
Status of lymph nodal
Outcome of treatment
Tumor vs. healthy tissue
Subtypes MPM vs. ADCA
Different lymphomas cells
Cancer vs. non-cancer
Tumor vs. healthy tissue
22
Experimental setup

• Data normalization
• Zero mean and unity variance at the gene
  direction
• Random partition data into two disjoint subsets
  of equal size training data test data
• Repeat each experiment 100 times

23
Parameters

• DLDA no parameter
• KNN Euclidean distance, K3
• ULDA K3
• SVM Gaussian kernel, use leave-one-out on the
  training data to tune parameters
• KerNN Gaussian kernel for basic kernel k0, ?0
  andsare empirically set. Use leave-one-out on the
  training data to tune the rest parameters. KNN
  for classification

24
Effect of data resampling
Prostate 102 samples
Lung 181 samples
25
Effect of gene selection
ALL-AML
26
Effect of gene selection
Colon
27
Effect of gene selection
Prostate
28
Comparison results
BreastER
ALL-AML
BreastLN
Colon
29
Comparison results
CNS
lung
Prostate
Ovarian
30
Outline

• Introduction
• Data-dependent Kernel
• Results
• Conclusion

31
Conclusion

• By maximizing the class separability of training
  data, the data-dependent kernel is also able to
  increase the separability of test data.
• The kernel method is robust to high dimensional
  microarray data
• The distributed resampling strategy helps to
  alleviate the problem of overfitting

32
Conclusion

• The classifier assign samples more accurately
  than other approaches so we can have better
  treatments respectively.
• The method can be used for clarifying unusual
  cases
• e.g. a patient which was diagnosed as AML but
  with atypical morphology.
• The method can be applied to distinctions
  relating to future clinical outcomes.

33
Future work

• How to estimate the parameters
• Study the genes selected

34
Reference

• H. Xiong, M.N.S. Swamy, and M.O. Ahmad.
  Optimizing the data-dependent kernel in the
  empirical feature space. IEEE Trans. on Neural
  Networks 2005, 16460-474.
• H. Xiong, Y. Zhang, and X. Chen. Data-dependent
  Kernels for Cancer Classification. Under review.
• A. Ben-Dor, L. Bruhn, N. Friedman, I. Nachman, M.
  Schummer, and Z. Yakhini. Tissue classification
  with gene expression profiles. J. Computational
  Biology 2000, 7559-584.
• S. Dudoit, J. Fridlyand, and T.P. Speed.
  Comparison of discrimination method for the
  classification of tumor using gene expression
  data. J. Am. Statistical Assoc. 2002, 9777-87
• T.S. Furey, N. Cristianini, N. Duffy, D.W.
  Bednarski, M. Schummer, and D. Haussler. Support
  vector machine classification and validation of
  cancer tissue samples using microarray expression
  data. Bioinformatics 2000, 16906-914.
• J. Ye, T. Li, T. Xiong, and R. Janardan. Using
  uncorrelated discriminant analysis for tissue
  classification with gene expression data.
  IEEE/ACM Trans. on Computational Biology and
  Bioinformatics 2004, 1181-190.

35
Thanks!Questions?