stefan arnborg, kth, sics ingrid agartz, håkan hall, erik jönsson,
DESCRIPTION
Data Mining in Schizophrenia Research. Stefan Arnborg, KTH, SICS Ingrid Agartz, Håkan Hall, Erik Jönsson, Anna Sillén, Göran Sedvall, Karolinska Institutet ’Principles of Data Mining and Knowledge Discovery’, Helsinki, Aug 2002. http://www.nada.kth.se/~stefan. - PowerPoint PPT PresentationTRANSCRIPT
Stefan Arnborg, KTH, SICS
Ingrid Agartz, Håkan Hall, Erik Jönsson, Anna Sillén, Göran Sedvall, Karolinska Institutet
’Principles of Data Mining and Knowledge Discovery’,Helsinki, Aug 2002
http://www.nada.kth.se/~stefan
Data Mining in Schizophrenia Research
HUBIN page: 1000 hits/day
Schizophrenia -Questions and Clues
• Cause(s) of schizophrenia not known.• Medication effective against some symptoms - discovered by
chance 100-2000 years ago.• Does not appear in animals-no experimental clues.• Explanation models vary over time.• Disturbed neuronal circuitry in schizophrenia?
(currently hottest hypothesis)• Influenced by genotype or/and environment?
(clustering in families)
Schizophrenia -Questions and Clues
• Which processes result in disease?• Traces of disturbed development visible in MRI
(anatomy) and blood tests?• Genetic risk factors?• Causal pathways?• MAIN PROBLEM:
Connect psychiatry to physiology
Preliminary analysis
Test case:144 subjects: 61 affected, 83 controlsVariables:•Diagnosis (DSM-IV)•Demography (age, gender, ..)•Blood tests (liver, heart,…)•Genetics (20 SNP:s, receptor, growth factors, …)•Anatomy (MRI)•Neuropsychology(working memory, reactions)•Clinicaltest batteries (type of delusions, history, medication)
Brain boxes
Picture fromBRAINS II manual,Magnotta et al,University of Iowa
Manually drawn vermis regions
ROIs drawn by GakuOkugawa
Single Nucleotide Polymorphism
A U G U U C C A U U A U U G U
A U G U U U C A U U A U U A U
RNA:
Protein A Phe
Phe
His
His
Tyr
Tyr
Cys
Phe
non-coding SNP
coding SNP
TyrProtein A’
Protein A can be slightly different from A´
Some genes studied
• DBH dopamine beta-hydroxylase• DRD2 dopamine receptor D2 +• DRD3 dopamine receptor D3• HTR5A serotonin receptor 5A• NPY neuropeptide Y• SLC6A4 serotonin transporter• BDNF brain derived neurotrophic factor• NRG1 neuregulin +
Intracranial volume (ml)
Cumulative distribution
+ = schizo = controls
Elementary Visualizations MRI Intracranial volume
Elementary VisualizationsMRI data
Total CSF volumes (ml)
Cumulative distribution
+ = schizo = controls
p < 0.0002
Men
Women25 30 35 40 45 50 55
0
0.1
0.2
0.3
0.4
0.5
0.6
0.7
0.8
0.9
1
Sub White-women
30 35 40 45 50 55 60 650
0.1
0.2
0.3
0.4
0.5
0.6
0.7
0.8
0.9
1
Sub White-men
Subcortical white
+ = schizo = controls
Subcortical white
+ = schizo = controls
Gender differences
MRI
Which methods to use?
• Visualizations, cdf and scatter plots, give intuitive grasp of variables - problems with many interrelated variables
• Statistical modelling required to decide significance of visible trend, and to rank effects
Statistical methods
• Bayesian methods intuitive and rational - but conventional testing required for publications
• Linear models - need to account for mixing and over-dispersion(Glenn Lawyer thesis project).
• Mixture models(Valery Savcenko thesis project).• Discretization and Bayesian analysis of discrete
distributions - intuitive, but information lost
Model adequate? -Gelman’s post-predictive check
• Best tested with classical p-values.• Determine posterior for parameter:
• Design test function • Compute p-value:
• Reject model if p small, e.g., <1%, <5%
f (λ |D)∝ f(D |λ) f (λ)
t : D→ Rp=P(t(Dr )<t(D))
Dr ~f (⋅|λ) f (λ |D)
Graphical models
Y
Z
X
Y
Z
X
Y
Z
Xf(x,y,z)=f(x)f(y)f(z)
f(x,y,z)=f(x,z)f(x,y)/f(x)
f(x,y,z)
MRI volumes, blood, demography
Dia
BrsCSF TemCSF
SubCSF TotCSF
Multivariate characterization by graphical models
Adding Vermis variables
Dia
BrsCSF TemCSF
PSV
10 20 30 40 50 60 70 80 90 100
5
10
15
10 20 30 40 50 60 70 80 90 100
5
10
15
10 20 30 40 50 60 70 80 90 100
5
10
15
left right CSF grey white CerebellumVermis CC Brainstem FrontalParietalVent2TemporalTotal ic
1:RAVTA16:RAVLTATOT11:TMT14:WAIS-R15:WCST64
Pos Corr
Neg Corr
Area Code
Learning, Intelligence, Executive vs Anatomy
10 20 30 40 50 60 70 80 90 100
0.5
0.6
0.7
0.8
0.9
1
1.1
1.2
1.3
1.4
1.5
Color code(0 to 1):
p-values
20 40 60 80 100
5
10
15
rho:s
20 40 60 80 100
5
10
15
cw
20 40 60 80 100
5
10
15
20 40 60 80 100
5
10
15
cm
20 40 60 80 100
5
10
15
20 40 60 80 100
5
10
15
aw
20 40 60 80 100
5
10
15
20 40 60 80 100
5
10
15
am
20 40 60 80 100
5
10
15
20 40 60 80 100
5
10
15
20 40 60 80 100
10
20
30
20 40 60 80 100
10
20
30
1:RAVTA16:RAVLTATOT11:TMT14:WAIS-R15:WCST64
leftrightCSFgreywhiteCerebellar-TonsilCerebellumVermisCorpusCallosumIntracranialBrainstemFrontalOccipitalParietalSubcorticalVentr2Temporal
2 4 6 8 10 12 14 16 18
2
4
6
8
10
12
14
16
18
1RAVLTA1 Verbal inlärning2RAVLTA2 Verbal inlärning3RAVLTA3 Verbal inlärning4RAVLTA4 Verbal inlärning5RAVLTA5 Verbal inlärning6RAVLTATOT Verbal inlärn., total7RAVLTB Verbal inlärn, distraktion8 RAVLTA6 Verbalt minne, om.9 RAVLTA7 Verbalt minne, fördröjt10 CPT d' Uppmärksamhet11 TMT A Visuo-motorik, snabbhet12 TMT B Visuo-motorik, flexibilitet13 LNS Arbetsminne 14 WAIS-R Verbal begåvning, IQ.15 WCST64 categories Exekutiv funktion16 WCST64 total errors Exekutiv funktion17 WCST64 pers errors Exekutiv funktion18 WCST64 pers. respons Exekutiv funktion
Covariances: Cognitive Performance Index
5 10 15 20 25 30 35 40 45 50
5
10
15
20
25
30
35
40
45
50
Correlationcoefficient-left vs right
CSF grey white w+g
MR brain volumes
0.5 1 1.5 250
52
54
56
58
60
62
64
66
68
VermisMiddle-*w+g*-left-
rho=0.33118 pv=0.1686
0.5 1 1.5 2 2.5 340
45
50
55
60
65
70
VermisMiddle-*w+g*-left-
rho=0.26018 pv=0.1407
0 0.5 1 1.535
40
45
50
55
60
65
70
75
VermisMiddle-*w+g*-left-
rho=0.66363 pv=0.0221
0 0.5 1 1.5 220
25
30
35
40
45
50
55
60
65
VermisMiddle-*w+g*-left-
rho=0.14339 pv=0.2405
wc mcwa ma
cpd
0.5 1 1.5 27
8
9
10
11
12
13
14
15
VermisLower-*w+g*-right-
rho=0.27032 pv=0.2196
0 0.5 1 1.5 27
8
9
10
11
12
13
14
15
16
VermisLower-*w+g*-right-
rho=0.15481 pv=0.2615
0 0.5 1 1.5 22
4
6
8
10
12
14
VermisLower-*w+g*-right-
rho=-0.68411 pv=0.9983
0 0.5 1 1.5 24
6
8
10
12
14
16
VermisLower-*w+g*-right-
rho=-0.12977 pv=0.7403
wc mcwa ma
Executiveability
Pairs associated to Diagnosis
Y
Z
D
Y
Z
D
Y
Z
D
Y
Z
D
Y and Z co-vary differentlyfor Affected and Controls
Age-dependency of Posterior Superior Vermis
Age at MRI
Post sup vermis
+ = schizo = controls
70 80 90 100 110 120 1300.08
0.1
0.12
0.14
0.16
0.18
0.2
0.22
0.24
ParWhite
0
No co-variation between Posterior inferior vermis and parietal white for affected
Parietal white
Post inf vermis
+ = schizo = controls
PSV has best explanatory power
affected - healthy
0.05 0.1 0.15 0.2 0.25 0.30
0.1
0.2
0.3
0.4
0.5
0.6
0.7
0.8
0.9
1
PS VermisPosterior superior vermis
+ = schizo = controls
Classification explains data!(Can Mert Thesis project)
XY
Z
XY
Z
H
W W
But where is the model?
Model is parametrized mixture
XY
Z
H
WParameter is mixing vectorand classification partition!
P(W,Y,Z| H,λ ) =P(λ ) λiP(W(i))P(Y(i))P(Z(i))i
∑
P(H,λ |W,Y,Z) =P(W,Y,Z |H,λ ) f(H |λ ) f (λ )
Autoclass1
Total gray
A= schizC= controls
Weak signals in genetics data
• Numerous investigations have indicated ‘almost significant’ signals of SNP:s to diagnosis
• Typically, these findings cannot be confirmed in other studies - populations genetically heterogeneous and measurements nonstandardized.
• We try to connect SNP:s both to diagnosis and to other phenotypical variables
• Multiple testing and weak signal problems.
Genetics data - weak statistics
Gene SNP type genotypes
DRD3 SerGly A/C 49 59 14DRD2 Ser311Cys C/G 118 4 0NPY Ley7Pro A/C 1 7 144DBH Ala55Ser G/T 98 24 0BDNF Val66Met A/G 5 37 80HTR5A Pro15Ser C/T 109 11 2PNOC Gln172Arg A/G 11 37 28SLC6A4 (del(44bp)in pr) S/L 20 60 42
Empirical distribution by genotypeGene BDNF (schiz + controls)
Frontal CSF
A/A A/G G/G
Cumulativedistribution
25 30 35 40 45 50 55 60 65 70 750
0.1
0.2
0.3
0.4
0.5
0.6
0.7
0.8
0.9
1Frontal-CSF-right-
G/G G/A A/A
0 20 40 60 80 100 120 1400
0.002
0.004
0.006
0.008
0.01
0.012
0.014
0.016
0.018
0.02
Benjamini & Yekutieli, Annals of Math Stat, (ta)
‘no effect’Observedp-values
FDRi 71
FDRd 62
Bonferroni-Hochberg-Benjamini methodsMRI and lab data
Number of p-values
p-values
Compensating multiple comparisons
• Bonferroni 1937: For level and n tests, use level /n
• Hochberg 1988: step-up procedure• Benjamini,Hochberg 1996: False Discovery
Rate• J. Storey, 2002: pFDRi, pFDRd• Bayesian interpretations being developed
(Wasserman & Genovese, 2002)
Diagnosis-genotype
bdnf drd2 nrg1
0.1136 0.0735 0.8709
0.0801 0.2213 0.7666
0.0316 0.0823 0.6426
0.5499 1.0000 0.0244
0.7314 0.7312 0.0103
bdnf drd2 nrg1
0.1137 0.0749 0.8744
0.7293 0.7276 0.0096
21 tests on three genes
multiple comparisons:
what is the significanceof min p-values 1,1,2,3%in 20 tests?What is the probability of obtainingmore extreme result when no effect?
| | | |
| | | |
| | | |
| | | |
| | | |
| | | | . . .
7% - not quite significant!but better than Bonferroni: 20%
p-values 3%, 2%, 1%, 1% in 20 tests
0 50 100 150 200 250 300 350 4000
0.1
0.2
0.3
0.4
0.5
0.6
0.7
0.8
0.9
1TPH:SNP000002367
q-value - FDR rate in prefix
0 50 100 150 200 250 300 350 4000
0.1
0.2
0.3
0.4
0.5
0.6
0.7
0.8
0.9
1BDNF:SNP000006430
0 50 100 150 200 250 300 350 4000
0.1
0.2
0.3
0.4
0.5
0.6
0.7
0.8
0.9
1sex
Beyond Robustness: SVM
Support Vector Methods are - distribution-independent- insensitive to dimension- error of classifier no more than
R
γbl
+cl
R2
γ2 log2l +log1/δ( )⎛
⎝ ⎜ ⎞
⎠
with probability training set size l,unclassified examples b,margin pdf support within R-sphere
+
+ ++
-
-
-
-
+
-
--
b=1
Beyond Robustness: SVM
Support Vector Methods are - distribution-independent- insensitive to dimension- error of classifier no more than
R
γbl
+cl
R2
γ2 log2l +log1/δ( )⎛
⎝ ⎜ ⎞
⎠
with probability training set size l,unclassified examples b,margin all examples within R-sphere
+
+ ++
-
-
-
-
+
-
--
b=0
That’s all, folks!
• High-quality databases for medical research of the HUBIN type open up for intelligent data analysis methods used in engineering and business
• Already with the limited data presently available, interesting clues emerge
• Multiple testing considerations are important• Long term effort - stable economy and
engagement is vital.