A Comparative Evaluation of Different machine Learning Methods on Microarray Gene Expression Data

1
A Comparative Evaluation of Different machine
Learning Methods on Microarray Gene Expression
Data
CS573 Class Project

• Song Li

2
What is Microarray

• We want to know how genes are expressed in an
  individual (is this gene turned on ? )
• Microarray technology allows researchers to
  monitor the expression levels of thousands of
  genes simultaneously

3
Microarray Data
Each row represent a specific gene. Each column
represent an experiment. Xij is the expression
intensity of gene i observed in sample j.
4
Classification of Microarray Data

• A typical usage of microarray data is tumor
  classification in cancer research.

Data of one microarray experiment
Is it cancer? if yes, what type ?
Learning
Training
Labeled microarray data
5
Challenge

• big p, small n problem
• Normally thousands of genes are tested in a
  single microarray experiment
• The number of samples are relatively small (still
  an expensive experiment)
• Many learning algorithm cannot handle it well
• Dimension reduction is needed

6
Methods

• Support Vector Machine
• Linear regression based methods
• Huang et al. 1 summarized several models as
  linear regression models
• They also proposed PLS (Partial Least Squares)
  and PPLS (Penalized Partial Least Squares) based
  linear regression model
• Clustering Bayesian classification
• Ji et al. 2 proposed a two-stage model using
  clustering and Bayesian classification
• 1 X. Huang and W. Pan. Linear regression and
  two-class classification with gene expression
  data. Bioinformatics, 19 2072 - 2078, 2003.
• 2 X. Ji, K. Tsui, and K. Kim. A novel means of
  using gene clusters in a two-step empirical bayes
  method for predicting classes of samples.
  Bioinformatics, 21 1055 - 1061, 2005.

7
Evaluation of Existing Models

• Very limited number of datasets has been tested
  on these newly proposed models
• Huangs paper has results on Leukemia data and
  colon data. However, according to the paper the
  colon data used is not publicly available
• Jis paper has results on an anonymous dataset,
  and Leukemia data.
• Helman et al. studied the performances of a large
  number of microarray data classifiers, but the
  data is from the original papers 3
• How about using WEKA as the evaluation platform?
• 3 P. Helman, R. Veroff, S. Atlas, and
  C. Willman. A bayesian network classification
  methodology for gene expression data. J. of
  Computational Biology, 11, 581-615, 2004.

8
This Project

• Collects microarray datasets and converts them
  into WEKAs .arff files
• Implements
• PLS and PPLS based linear regression model
  described in Huangs paper
• Two-stage clusteringBayesian method described in
  Jis paper
• Compare the results that these new methods and
  WEKAs SVM SMO implementation( 2-class
  classification)

9
Datasets

• Source caGEDA at University of Pittsburgh
  (http//bioinformatics.upmc.edu/GE2/GEDA.html)

10
Model 1 Linear regression

• PLS
• Define

11
Contd
12
Contd
13
Predictor
14
PPLS
15
Model 2 Clustering Bayesian
Original data (p genes)
k meta-genes
Clustering
Bayesian model

• K ltlt p
• My implementation use K-mean as clustering method

16
Bayesian Model
17
Contd
18
Result
19
Discussion

• These newly proposed methods offer comparable
  performance with WEKAs SVM-SMO
• Parameter selection sometimes matters a lot. e.g.
  K value in Bayesian method, q value in PPLS
  method.
• Clustering thousands of genes is computationally
  intensive
• Question does clustering algorithm has impact on
  the performance ?

20
Project Web Site

• http//www.cs.iastate.edu/lisong/cs573