Title: Data Mining of Gene Expression Profiles for the Diagnosis and Understanding of Diseases
1Data Mining of Gene Expression Profiles for the
Diagnosis and Understanding of Diseases
- Limsoon Wong
- Institute for Infocomm Research
2Plan
- Some accomplishments and challenges in knowledge
discovery from biological and clinical data - Data mining in microarray analysis
- diagnosis of disease state and subtype
- derivation of treatment plan
- understanding of gene interaction network
3Knowledge Discovery from Biological and Clinical
Data MOTIVATION
4Driving Forces Genes, Proteins, Interactions,
Diagnosis, Cures
5If we figure out how these work, we get these
Benefits
To the patient Better drug, better treatment To
the pharma Save time, save cost, make more To
the scientist Better science
6To figure these out,we bet on...
solution Data Mgmt Knowledge
Discovery Data Mgmt Integration
Transformation Cleansing Knowledge Discovery
Statistics Algorithms Databases
7Knowledge Discovery from Biological and Clinical
Data ACCOMPLISHMENT
88 years of bioinformatics RD in Singapore
9Predict Epitopes,Find Vaccine Targets
- Vaccines are often the only solution for viral
diseases - Finding developing effective vaccine targets is
slow and expensive process
10Recognize Functional Sites,Help Scientists
- Effective recognition of initiation, control, and
termination of biological processes is crucial to
speeding up and focusing scientific experiments
- Data mining of bio seqs to find rules for
recognizing understanding functional sites
Dragons 10x reduction of TSS recognition false
positives
11Diagnose Leukaemia, Benefit Children
- Childhood leukaemia is a heterogeneous disease
- Treatment is based on subtype
- 3 different tests and 4 different experts are
needed for accurate diagnosis - Curable in USA,
- fatal in Indonesia
- A single platform diagnosis
- based on gene expression
- Data mining to discover
- rules that are easy for
- doctors to understand
12Understand Proteins,Fight Diseases
- Understanding function and role of protein needs
organised info on interaction pathways - Such info are often reported in scientific paper
but are seldom found in structured databases
- Knowledge extraction
- system to process free text
- extract protein names
- extract interactions
Jak1
13Data Mining in Microarray AnalysisMICROARRAY
BACKGROUND
14Whats a Microarray?
- Contain large number of DNA molecules spotted on
glass slides, nylon membranes, or silicon wafers - Measure expression of thousands of genes
simultaneously
15Affymetrix GeneChip Array
16Making Affymetrix GeneChip
17Gene Expression Measurement by GeneChip
18A Sample Affymetrix GeneChip File (U95A)
19Data Mining in Microarray Analysis DISEASE
SUBSTYPE DIAGNOSIS
20Pediatric Acute Lymphoblastic Leukemia
- A heterogeneous disease with more than 12
subtypes, e.g., T-ALL, E2A-PBX1, TEL-AML1,
BCR-ABL, MLL, and Hyperdipgt50. - Treatment response is subtype dependent
- 80 continuous remission if subtype is correctly
diagnosed and the corresponding treatment plan is
applied
21Subtype Diagnosis
- Require different tests
- immunophenotyping
- cytogenetics
- molecular diagnostics
- Require different experts
- hematologist
- oncologist
- pathologist
- cytogeneticist
22Difficulties and Implications
- The different tests and experts are not commonly
available within a single hospital, especially in
less advanced countries - An 80-curable disease in USA can be a fatal
disease in Indonesia! - Is there a single diagnostic platform that does
not need multiple human specialists?
23A Potential Solution by MicroarraysYeoh et al.,
Cancer Cell 1133--143, 2002
24Some Caveats
- Study was performed on Americans
- May not be applicable to Singaporeans,
Malaysians, Indonesians, etc. - Large-scale study on local populations currently
in the works
25Typical Procedure in Analysing Gene Expression
for Diagnosis
- Gene expression data collection
- Gene selection
- Classifier training
- Classifier tuning (optional for some machine
learning methods) - Apply classifier for diagnosis of future cases
26Feature Selection Methods
A refresher of feature selection methods
27Signal Selection (Basic Idea)
- Choose a signal w/ low intra-class distance
- Choose a signal w/ high inter-class distance
28Signal Selection (eg., t-statistics)
29Signal Selection (eg., ?2)
30Signal Selection (eg., CFS)
- Instead of scoring individual signals, how about
scoring a group of signals as a whole? - CFS
- Correlation-based Feature Selection
- A good group contains signals that are highly
correlated with the class, and yet uncorrelated
with each other
31Gene Expression Profile Classification
An introduction to gene expression profile
classification by the example on ALL subtype
diagnosis
32Subtype Classification of ALL
A tree-structured diagnostic workflow was
recommended by the doctors, as per Yeoh et al.,
Cancer Cell 1133--143, 2002
33Training and Testing Sets
34Our procedure for ALL subtype diagnosis
- Gene expression data collection
- Gene selection by entropy
- Classifier training by emerging pattern
- Classifier tuning (optional for some machine
learning methods) - Apply classifier for diagnosis of future cases by
PCL
35Signal Selection (eg., entropy)
36Emerging Patterns (EPs)
- An EP is a set of conditions
- usually involving several features
- that most members of a class satisfy
- but none or few of the other class satisfy
- A jumping EP is an EP that
- some members of a class satisfy
- but no members of the other class satisfy
- We use only most general jumping EPs
37PCL Prediction by Collective Likelihood
38Accuracy (using 20 genes of lowest entropy)
39Comprehensibility
40Gene Expression Profile ClassificationHow about
other feature selection and classification
methods?
41Some gene selection heuristics
- all-CFS all features from CFS
- top20-?2 20 features w/ highest ?2 stats
- top20-t 20 features w/ highest t-stats
- top20-mit 20 features w/ highest MIT stats
- entropy 20 features w/ lowest entropy
- all-?2 all features meeting 5 significance
level of ?2 stats
42Some other classification methods
- k-NN (k1)
- majority votes of the k nearest neighbours
determined by Euclidean distance - C4.5
- widely used decision tree method.
- Naïve Bayes (NB)
- probabilistic prediction using Bayes rule
- SVM
- (linear) discriminant function that maximizes
separation of boundary samples
43Accuracy
- Feature selection improves performance
- EntropyPCL has consistent high performance
44When 20 genes are selected randomly
Average over 100 experiments
Cf. 7-15 mistakes total with good feature
selection
45Data Mining in Microarray Analysis TREATMENT
PLAN DERIVATION
A pure speculation!
46Can we do more with EPs?
- Detect gene groups that are significantly related
to a disease - Derive coordinated gene expression patterns from
these groups - Derive treatment plan based on these patterns
47Colon Tumour DatasetAlon et al., PNAS
966745--6750, 1999
- We use the colon tumour dataset above to
illustrate our ideas - 22 normal samples
- 40 colon tumour samples
48Detect Gene Groups
- Feature Selection
- Use entropy method
- 35 genes have cut points
- Generate EPs
- 19501 EPs in normals
- 2165 EPs in tumours
- EPs with largest support are gene groups
significantly co-related to disease
49Top 20 EPs
50Observation 1
- Some EPs contain large number of genes and still
have high freq - E.g., 2, 3, 6, 7, 13, 17, 33 has freq 90.91 in
normal and 0 in cancer samples - Nearly all normal samples gene expr. values
satisfy all conds. implied by these 7 items
51Observation 2
- Freq of singleton EP is not necessarily larger
than EP having multiple genes - E.g., 5 is EP in cancer samples and has freq
32.5 - E.g., 16, 58, 62 is EP in cancer samples and
has freq 75.5 - Groups of genes and their correlation's could be
more impt than single genes
52Observation 3
- M33680 has lowest entropy of the 35 genes if
cutpoint is set at 352 - 18/40 of cancer samples shift expr level of
M33680 from its normal range to its abnormal range
53Treatment Plan Idea
- Increase/decrease expression level of particular
genes in a cancer cell so that - it has the common EPs of normal cells
- it has no common EPs of cancer cells
54Treatment Plan Example
- From the EP 2,3,6,7,13,17,33
- 91 of normal cells express the 7 genes (T51560,
T49941, M62994, R34701, L02426, U20428, R10707)
in the corr. Intervals - a cancer cell never express all 7 genes in the
same way - if expression level of improperly expressed genes
can be adjusted, the cancer cell can have one
common EP of normal cells - a cancer cell can then be iteratively converted
into a normal one
55Choosing Genes to Adjust
56Doing more adjustments...
- Down regulating T49941 leads to 2 more top 10 EPs
of normal cells to show up in the adjusted T1 - Down regulating X62153 to below 396 and T72403 to
below 296 leads to T1 having 9 top 10 EPs of
normal cells - Ave. no. of EPs in normal cells is 9
- So the adjusted T1 now has impt features of
normal cells
57Next, eliminate common EPs of cancer cells in T1
- 6 more genes (K03001, T49732, U29171, R76254,
D31767, L40992) are adjusted - All top 10 EPs of cancer cells now disappear from
T1 - Ave. no. of top 10 EPs contained in cancer cells
is 6 - The adjusted T1 now holds enough common features
of normal cells and no features of cancer cells - T1 is converted to normal cells
58Treatment Plan Validation
- Adjustments were made to the 40 colon tumour
samples based on EPs as described - Classifiers trained on original samples were
applied to the adjusted samples
It works!
59A Big But...
- Effective means for identifying mechanisms and
pathways through which to modulate gene
expression of selected genes need to be developed
60Data Mining in Microarray AnalysisGENE
INTERACTION PREDICTION
61Beyond Classification of Gene Expression Profiles
- After identifying the candidate genes by feature
selection, do we know which ones are causal genes
and which ones are surrogates?
62Gene Regulatory Circuits
- Genes are connected in circuit or network
- Expression of a gene in a network depends on
expression of some other genes in the network - Can we reconstruct the gene network from gene
expression data?
63Key Questions
- For each gene in the network
- which genes affect it?
- How they affect it?
- Positively?
- Negatively?
- More complicated ways?
64Some Techniques
- Bayesian Networks
- Friedman et al., JCB 7601--620, 2000
- Boolean Networks
- Akutsu et al., PSB 2000, pages 293--304
- Differential equations
- Chen et al., PSB 1999, pages 29--40
- Classification-based method
- Soinov et al., Towards reconstruction of gene
network from expression data by supervised
learning, Genome Biology 4R6.1--9, 2003
65A Classification-based TechniqueSoinov et al.,
Genome Biology 4R6.1-9, Jan 2003
- Given a gene expression matrix X
- each row is a gene
- each column is a sample
- each element xij is expression of gene i in
sample j - Find the average value ai of each gene i
- Denote sij as state of gene i in sample j,
- sij up if xij gt ai
- sij down if xij ? ai
66A Classification-based TechniqueSoinov et al.,
Genome Biology 4R6.1-9, Jan 2003
- To see whether the state of gene g is determined
by the state of other genes - we see whether ?sij i ? g? can predict sgj
- if can predict with high accuracy, then yes
- Any classifier can be used, such as C4.5, PCL,
SVM, etc.
- To see how the state of gene g is determined by
the state of other genes - apply C4.5 (or PCL or other rule-based
classifiers) to predict sgj from ?sij i ? g? - and extract the decision tree or rules used
67Advantages of this method
- Can identify genes affecting a target gene
- Dont need discretization thresholds
- Each data sample is treated as an example
- Explicit rules can be extracted from the
classifier (assuming C4.5 or PCL) - Generalizable to time series
68Acknowledgements
69Data Mining in Microarray Analysis NOTES
70References
- J.Li, L. Wong, Geography of differences between
two classes of data, Proc. 6th European Conf. on
Principles of Data Mining and Knowledge
Discovery, pp. 325--337, 2002 - J.Li, L. Wong, Identifying good diagnostic genes
or gene groups from gene expression data by using
the concept of emerging patterns,
Bioinformatics, 18725--734, 2002 - J.Li et al., A comparative study on feature
selection and classification methods using a
large set of gene expression profiles, GIW,
1351--60, 2002
71References
- E.-J. Yeoh et al., Classification, subtype
discovery, and prediction of outcome in pediatric
acute lymphoblastic leukemia by gene expression
profiling, Cancer Cell, 1133--143, 2002 - U.Alon et al., Broad patterns of gene expression
revealed by clustering analysis of tumor colon
tissues probed by oligonucleotide arrays, PNAS
966745--6750, 1999 - L.A.Soinov et al., Towards reconstruction of
gene networks from expression data by supervised
learning, Genome Biology 4R6.1--9, 2003.
72gt Data Mining of Gene Expression
Profiles for gt the Diagnosis and
Understanding of Diseases gt gt This talk is
divided into two parts. In Part I, I will provide
a gt brief overview of some accomplishments and
challenges gt in Bioinformatics. In Part II, I
will discuss the data mining gt in the analysis
of microarray gene expression profiles for gt
(a) diagnosis of disease state or subtype, (b)
derivation of gt disease treatment plan, and (c)
understanding of gene gt interaction networks. gt