1 A Presentation of ‘Bayesian Models for Gene Expression With DNA Microarray Data’ by Ibrahim, Chen, and Gray Presentation By Lara DePadilla.

Slides:



Advertisements
Similar presentations
Bayes rule, priors and maximum a posteriori
Advertisements

CSE 473/573 Computer Vision and Image Processing (CVIP) Ifeoma Nwogu Lecture 27 – Overview of probability concepts 1.
Probabilistic models Jouni Tuomisto THL. Outline Deterministic models with probabilistic parameters Hierarchical Bayesian models Bayesian belief nets.
Original Figures for "Molecular Classification of Cancer: Class Discovery and Class Prediction by Gene Expression Monitoring"
Week 11 Review: Statistical Model A statistical model for some data is a set of distributions, one of which corresponds to the true unknown distribution.
Statistics in Bioinformatics May 2, 2002 Quiz-15 min Learning objectives-Understand equally likely outcomes, Counting techniques (Example, genetic code,
CHAPTER 21 Inferential Statistical Analysis. Understanding probability The idea of probability is central to inferential statistics. It means the chance.
Parameter Estimation using likelihood functions Tutorial #1
Author: Jim C. Huang etc. Lecturer: Dong Yue Director: Dr. Yufei Huang.
Maximum Likelihood. Likelihood The likelihood is the probability of the data given the model.
Visual Recognition Tutorial
Simple Linear Regression
10 Hypothesis Testing. 10 Hypothesis Testing Statistical hypothesis testing The expression level of a gene in a given condition is measured several.
Predictive Automatic Relevance Determination by Expectation Propagation Yuan (Alan) Qi Thomas P. Minka Rosalind W. Picard Zoubin Ghahramani.
Microarrays and Cancer Segal et al. CS 466 Saurabh Sinha.
Basics of Statistical Estimation. Learning Probabilities: Classical Approach Simplest case: Flipping a thumbtack tails heads True probability  is unknown.
Chapter 3 Analysis of Variance
Evaluating Hypotheses
. PGM: Tirgul 10 Parameter Learning and Priors. 2 Why learning? Knowledge acquisition bottleneck u Knowledge acquisition is an expensive process u Often.
Using ranking and DCE data to value health states on the QALY scale using conventional and Bayesian methods Theresa Cain.
Computer vision: models, learning and inference Chapter 10 Graphical Models.
Computer vision: models, learning and inference
Thanks to Nir Friedman, HU
EE513 Audio Signals and Systems Statistical Pattern Classification Kevin D. Donohue Electrical and Computer Engineering University of Kentucky.
Statistics for Managers Using Microsoft Excel, 4e © 2004 Prentice-Hall, Inc. Chap 12-1 Chapter 12 Simple Linear Regression Statistics for Managers Using.
Bayes Factor Based on Han and Carlin (2001, JASA).
Probability Distributions and Test of Hypothesis Ka-Lok Ng Dept. of Bioinformatics Asia University.
Chapter 14: Nonparametric Statistics
1 Bayesian methods for parameter estimation and data assimilation with crop models Part 2: Likelihood function and prior distribution David Makowski and.
Bayesian approaches to cognitive sciences. Word learning Bayesian property induction Theory-based causal inference.
Principles of Pattern Recognition
Using Bayesian Networks to Analyze Expression Data N. Friedman, M. Linial, I. Nachman, D. Hebrew University.
Fundamentals of Data Analysis Lecture 4 Testing of statistical hypotheses.
Estimating parameters in a statistical model Likelihood and Maximum likelihood estimation Bayesian point estimates Maximum a posteriori point.
1 1 Slide © 2008 Thomson South-Western. All Rights Reserved Chapter 15 Multiple Regression n Multiple Regression Model n Least Squares Method n Multiple.
User Study Evaluation Human-Computer Interaction.
Chapter 1 Introduction to Statistics. Statistical Methods Were developed to serve a purpose Were developed to serve a purpose The purpose for each statistical.
Ch 8. Graphical Models Pattern Recognition and Machine Learning, C. M. Bishop, Revised by M.-O. Heo Summarized by J.W. Nam Biointelligence Laboratory,
Randomized Algorithms for Bayesian Hierarchical Clustering
MRNA Expression Experiment Measurement Unit Array Probe Gene Sequence n n n Clinical Sample Anatomy Ontology n 1 Patient 1 n Disease n n ProjectPlatform.
Probability Course web page: vision.cis.udel.edu/cv March 19, 2003  Lecture 15.
Application of Class Discovery and Class Prediction Methods to Microarray Data Kellie J. Archer, Ph.D. Assistant Professor Department of Biostatistics.
Gene expression & Clustering. Determining gene function Sequence comparison tells us if a gene is similar to another gene, e.g., in a new species –Dynamic.
Conditional Probability Mass Function. Introduction P[A|B] is the probability of an event A, giving that we know that some other event B has occurred.
Sequential Monte-Carlo Method -Introduction, implementation and application Fan, Xin
Guest lecture: Feature Selection Alan Qi Dec 2, 2004.
The generalization of Bayes for continuous densities is that we have some density f(y|  ) where y and  are vectors of data and parameters with  being.
Probabilistic models Jouni Tuomisto THL. Outline Deterministic models with probabilistic parameters Hierarchical Bayesian models Bayesian belief nets.
Sampling and estimation Petter Mostad
Molecular Classification of Cancer Class Discovery and Class Prediction by Gene Expression Monitoring.
Université d’Ottawa / University of Ottawa 2001 Bio 8100s Applied Multivariate Biostatistics L1a.1 Lecture 1a: Some basic statistical concepts l The use.
A shared random effects transition model for longitudinal count data with informative missingness Jinhui Li Joint work with Yingnian Wu, Xiaowei Yang.
1 Chapter 8: Model Inference and Averaging Presented by Hui Fang.
Bayesian Models for Gene expression With DNA Microarray Data Joseph G. Ibrahim, Ming-Hui Chen, and Robert J. Gray Presented by Yong Zhang.
Review of statistical modeling and probability theory Alan Moses ML4bio.
Probabilistic Robotics Introduction Probabilities Bayes rule Bayes filters.
THE CHI-SQUARE TEST BACKGROUND AND NEED OF THE TEST Data collected in the field of medicine is often qualitative. --- For example, the presence or absence.
Jump to first page Inferring Sample Findings to the Population and Testing for Differences.
Statistical NLP: Lecture 4 Mathematical Foundations I: Probability Theory (Ch2)
BIOL 582 Lecture Set 2 Inferential Statistics, Hypotheses, and Resampling.
Chapter 7: Hypothesis Testing. Learning Objectives Describe the process of hypothesis testing Correctly state hypotheses Distinguish between one-tailed.
Fundamentals of Data Analysis Lecture 4 Testing of statistical hypotheses pt.1.
Model Comparison. Assessing alternative models We don’t ask “Is the model right or wrong?” We ask “Do the data support a model more than a competing model?”
Lecture 1.31 Criteria for optimal reception of radio signals.
Bayesian Semi-Parametric Multiple Shrinkage
Bayes Net Learning: Bayesian Approaches
Discrete Event Simulation - 4
Statistical NLP: Lecture 4
Parametric Methods Berlin Chen, 2005 References:
Mathematical Foundations of BME Reza Shadmehr
Presentation transcript:

1 A Presentation of ‘Bayesian Models for Gene Expression With DNA Microarray Data’ by Ibrahim, Chen, and Gray Presentation By Lara DePadilla

2 Goal To “develop a novel class of parametric statistical models for analyzing DNA microarray data’. Parametric statistical models require making assumptions about the data, such as believing it follows some probabilistic law, and therefore we know something about it.

3 The Goal Applied The researchers are trying to discover which genes play a major role for the disease of endometrial cancer. This knowledge can help to determine whether it is inherited and target applicable therapies.

4 Motivation Determine which genes best discriminate between different types of tissue Why? Because of the sheer number of genes in the human genome we must identify which one are relevant to our purpose. Characterize gene expression patterns in tumor tissues Why? We must develop models to explain the patterns in order to recognize them.

5 About Bayesion Models (Liu pp. 306) The full process has three main steps: 1.Setting up a probability model to describe the data. This is a joint distribution that makes use of our prior knowledge of the subject: Joint = Prior * Likelihood f(y,Ө) = f(Ө) * f(y|Ө) It must capture the elements of the scientific problem.

6 About Bayesion Models (Cont.) The next step invokes Bayes rule 2. f(Ө,y) = f(Ө) * f(y|Ө) f(y) Now we know what we are looking for. 3. This step is evaluate and improve upon what we have done.

7 Back to Our Goal Applied Data Structure of Observations The array contains more than 7,000 probe sets, which are thought to represent 5,600 genes. Each probe set consists of 16 – 20 perfect match and mismatch pairs. A match is a strand of DNA that compliments a specific DNA sequences. A mismatch has a single base mismatch position (one piece out of approx. 25 doesn’t match). Using pairs from the same gene from different probes will be more specific than is possible with a single probe.

8 Back to Our Goal Applied More Data Preparation The probes are compared and normalized, resulting in a dataset of expression levels that have atypical results filtered out. After the filtering process, the data set was 14 x 3214, with 14 samples (10 cancerous, 4 normal) and 3214 genes.

9 The Model Setup: Data j = 1, 2 (for each tissue type) i = 1… n (for each individual) n j individuals available (n for each tissue type) G genes are measure for each individual x is the represents each gene in the dataset ⇒ c 0 is the threshold value for a gene is considered not expressed (and therefore not what we are seeking), so if x = c 0, it is not expressed so, x = c 0 with probability p x = c 0 + y with probability 1 – p where y is the level of expression x jig denotes the random variable y jig denotes the expression level

10 The Model Setup: Likelihood Let  = 1 if x = c 0 (not expressed) and 0 otherwise (expressed) Remember the expressed/not expressed probability from before, so there is one probability for each gene within each tissue type: p jg = P( x jig = c 0 ) = P(δ = 1) 1 – p jg = P( x jig = c 0 + y jig ) = P(δ = 0) Based on whether the gene had the qualified expression level, we have δ = (δ 111, …, δ 2,n 2,G ), meaning one for each gene, for each individual, for each tissue type).

11 The Model Setup: Likelihood The mean expression level of each gene for both tissue types: μ = (μ 11,…, μ 2,G ) The variance of each expression for each gene for both tissue types: σ 2 = (σ 2 11,…, σ 2 2,G ) The probability the gene not being expressed for each gene for both tissue types: p = (p 11,…, p 2,G )

12 The Model Setup: Likelihood Ө = (μ, σ 2, p) is the likelihood function based on the data: D = ( x 111,…, x 2,n 2,G ) L( Ө|D) = П j = 1 to 2 П I = 1 to n j П g = 1 to G (p jg δ jig )(1- p) 1 - δ jig * p(y jig | μ jg,σ 2 jg ) 1 - δ jig Interpreted: This is the product of the probability distribution function (the probability that a gene qualifies for being of interest to the study) of each data point to give the overall likelihood.

13 The Posterior: Which Genes Discriminate? The posterior is a ratio between the average expression level for a particular gene across subjects in cancerous tissue and the same gene across subject in non- cancerous tissue. The value of each element comprising the mean is based on whether or not the gene for that individual and that tissue type meets the necessary expression level to count.

14 The Posterior: The Function Ψ jg is the value for the expected value of the joint distribution of (δ,y) with individual subjects in the data comprising the elements that create the expected value. The distribution describes whether the expression level enough to count, and what is the level if it does?

15 The Posterior: The Function ε g = Ψ 2g / Ψ 1g This is a ratio of the expression means between normal and cancer tissues for all of the genes, so there will be one distribution for each of the G genes. A key summary to compute is P(ε g) > 1|D), which is the probability given the data (the individuals in the study) that the ratio will exceed 1.

16 Priors The purpose of the prior in this situation is to create a correlation between the genes for a given individual The priors are hierarchal: there are different priors for different parameters, and some parameters of interest are incorporated into other priors. In some cases, the values are based on information from the data.

17 Gene Selection: Applying the Posterior Compute the Posterior for g = 1…G Compare these probability that the ratios will exceed 1 to a threshold γ. This threshold might be.9,.8,.7 etc. One the threshold has established each gene as being different enough between tissues, develop a sub-model of the genes that describes which are different and which are not. Different levels of γ will create different sub- models.

18 Back to Bayes: Step 3 Step 3 was to evaluate our process. In this case, we use the L measure to evaluate the sub-models. The model with the smallest L measure is the best-fitting model It assesses goodness of fit based on: ⇒ how well the model predictions compare to the observed data ⇒ the variability of the predictions

19 Sampling From the Posterior: Gibbs Sampler Generating the mean expression levels for each type of tissue for each gene requires the parameters μ and σ 2 Gibbs Sampler makes use of conditional distributions; in our case these stem from the priors. The algorithm will ultimately yield μ, σ 2, b 0, μ 0, e, and u 0 for each tissue type. All but μ and σ 2 are integrated out, and the resulting μ and σ 2 can be passed into the posterior equation.

20 The Results: Table 2 Number of genes to be declared different based on Several Choices of Hyperparameters and Various Choices of γ 0 η 0, d 0, k 0, h 0 γ0γ

21 The Results: Table 3 Number of genes to be declared different based on Several Choices of Hyperparameters Mean η 0, d 0, k 0, h 0 Normal TissueCancer Tissue L measure , , , ,624

22 The Results: Tables 4 & 5 This determines nonparametrical (based on no prior knowledge of the parameters in the distribution ie μ and σ 2 that we got from our priors) results with the results of our algorithm Table 4 Compares Genes identified using Informative Priors and Table 5 Compares Genes identified using Moderate Priors (less informative) The percentages are the posterior probabilities—this would correspond to the thresholds. The sum is the number of genes that overlapped—we can see that the lower the threshold, the more genes overlap. Comparing Table 4 to Table 5, we can see that a less informative prior will result in more genes overlapping (which supports the result of analyzing the L statistic in Table 3).

23 The Results: Table 6 That is not to say more genes passing the test (of able to help distinguish cancerous tissue from non-cancerous tissue) is better; the threshold uses more discretion in declaring a gene different, and the L statistic tells us the goodness of the fit. We need both. CriterionL measure# of diff genes Full Model98,3053,214 γ = 70%97,9322,055 γ = 80%98,9051,505 γ = 90%102,0171,004 PERMAX110,80947

24

25 The Results: Table 7 Using the Full Model (ie, no threshold) change the informative level of the prior and compare to the L measure (η 0, d 0, k 0, h 0 )L meas (1,1,1,1)116,246 (10,10,10,10)101,326 (20,20,20,20) 99,699 (100,100,20,20) 99,690 (50,50,50,50) 98,307 (20,20,50,50) 98,307 (100,100,50,50) 98,307 (10,10,50,50) 98,305

26 Conclusion Apply a Gibbs Sampler to sample from a hierarchical class of prior distribution Use the results to sample from the posterior distribution and produce a summary of the results that describes how likely the gene is to be different based on tissue type. Use thresholds to decide which genes are different enough to make a model of genes that can be applied to this problem. Assess the model with the L measure to check the goodness of fit.

27 Bibliography ‘Bayesion Models for Gene Expression With DNA Microarray Data’, Ibrahim, Chen, and Gray, Journal of the American Statistical Association, Mar 02; 97,457 Monte Carlo Strategies in Scientific Computing, Liu, Springer-Verlag New York, Inc. 2001