SlideShare a Scribd company logo
1 of 23
Download to read offline
Problem deļ¬nition Methods Results Conclusions
Data Mining Activities for Shockomics
Vicent J. Ribas
Custom Software and Electronics
Barcelona, Catalonia
April 19, 2016
Vicent J. Ribas Custom Software and Electronics Barcelona, Catalonia
Data Mining Activities for Shockomics
Problem deļ¬nition Methods Results Conclusions
Contents
1 Problem deļ¬nition
2 Methods
3 Results
4 Conclusions
Vicent J. Ribas Custom Software and Electronics Barcelona, Catalonia
Data Mining Activities for Shockomics
Problem deļ¬nition Methods Results Conclusions
Problem deļ¬nition
Objective: detect the clinical variables, proteins and
metabolites that present the highest impact on the three
diļ¬€erent types of shock that we are studying at three diļ¬€erent
times (T1, T2 and discharge). Of course, attending to the
nature of this study, we will have many more variables/data
observed than patients.
Deļ¬nition: ā€˜a small n, large pā€™ is a data mining problem that
tries to predict response to treatment based on data having a
very small sample size (n) but very large dimensionality (p).
This problem needs to be tackled through data visualisation,
dimensionality reduction techniques (shrinkage methods) or a
combination of both.
Vicent J. Ribas Custom Software and Electronics Barcelona, Catalonia
Data Mining Activities for Shockomics
Problem deļ¬nition Methods Results Conclusions
small n large p
Vicent J. Ribas Custom Software and Electronics Barcelona, Catalonia
Data Mining Activities for Shockomics
Problem deļ¬nition Methods Results Conclusions
Contents
1 Problem deļ¬nition
2 Methods
3 Results
4 Conclusions
Vicent J. Ribas Custom Software and Electronics Barcelona, Catalonia
Data Mining Activities for Shockomics
Problem deļ¬nition Methods Results Conclusions
Methods
In line with the description of WP8, the following methods are
considered for studying our n >> p problem:
Graphical models:
Factorisation of the probability densty function (Hammersley
Cliļ¬€ord theorem).
Conditional independence maps (CIM - mutual information
between sets of variables).
Graphical LASSO.
Ensembles of classiļ¬cation and regression trees (bagged trees).
Dendrograms, Kohonen Maps and Heat Maps.
Vicent J. Ribas Custom Software and Electronics Barcelona, Catalonia
Data Mining Activities for Shockomics
Problem deļ¬nition Methods Results Conclusions
Methods
Regularised models:
Regularised linear regression.
LASSO.
Relevance vector machines (regularised support vector
machines with a-priori distributions).
Support Vector Machines with generative kernels (the
Quotient Basis Kernel).
Neural Networks (Restricted Boltzmann Machines/Factor
Analysis Models).
Vicent J. Ribas Custom Software and Electronics Barcelona, Catalonia
Data Mining Activities for Shockomics
Problem deļ¬nition Methods Results Conclusions
Conditional Independence for Gaussian Distribution
Let X = (X1, . . . , Xp) be a random vector with joint normal
distribution Np(Āµ, Ī£) with mean vector Āµ āˆˆ Rp and positive
deļ¬nite covariance matrix Ī£. For three pairwise disjoint index sets
A, B, C āŠ† {1, . . . , p}, the sub-vectors XA and XB are conditionally
independent given XC , iļ¬€
det Ī£A CƗB C = 0
Here A C Ɨ B C is the minor related to the variables over
which we are calculating the marginal dependence/independence
(i.e. the resulting minor after removing the rows and columns
corresponding to the conditional independence statement).
Vicent J. Ribas Custom Software and Electronics Barcelona, Catalonia
Data Mining Activities for Shockomics
Problem deļ¬nition Methods Results Conclusions
Markov Random Fields
Given and undirected graph G, a Markov Random Field (MRF) is
deļ¬ned as a set of probability distributions
MRFG := {p(x) : p(x) > 0, āˆ€p, x} such that āˆ€p āˆˆ MRFG and for
any three disjoint subsets A, B, C of G, if C separates A from B
then p satisļ¬es XA āŠ„āŠ„ XB|XC . If p āˆˆ MRFG, we often say p
respects G.
Vicent J. Ribas Custom Software and Electronics Barcelona, Catalonia
Data Mining Activities for Shockomics
Problem deļ¬nition Methods Results Conclusions
Hammersley Cliļ¬€ord theorem
If a pdf p āˆˆ MRFG, then p(x) must also factorize according to G,
i.e. there exist functions Ļˆc(x) on c āˆˆ C, such that
p(x) =
1
Z
exp
cāˆˆC
Ļˆc(xc) .
Vicent J. Ribas Custom Software and Electronics Barcelona, Catalonia
Data Mining Activities for Shockomics
Problem deļ¬nition Methods Results Conclusions
Statistical methods
The method above is exact but it requires the calculation of
the inverse of covariance matrices, which for the
dimenstionality that we are considering is not viable.
However, some numerical methods based on the same
framework will help.
CIM is an eļ¬ƒcient method for ļ¬nding the structure of a
graphical model. In particular, it is based on the measure of
mutual information between sets of variables. A mutual
information of zero corresponds to mutual statistical
independence.
The graphical lasso is an algorithm to estimate the precision
matrix (inverse of covariance matrix) from the available data.
The algorithm is based on a Lasso regularisation over the
estimated covariance matrix.
Vicent J. Ribas Custom Software and Electronics Barcelona, Catalonia
Data Mining Activities for Shockomics
Problem deļ¬nition Methods Results Conclusions
CIM
I(A, B) =
a,b
P(a, b) log
P(a, b)
P(a)P(b)
and the conditional mutual information, with respect to the
condition set C,
I(A, B|C) =
a,b,c
P(a, b, c) log
P(a, b|c)
P(a|c)P(b|c)
.
The conditional mutual information is consistent with Hammersley
Cliļ¬€ord and Factorisation because mutual information will be 0 iļ¬€
A āŠ„āŠ„ B|C.
Vicent J. Ribas Custom Software and Electronics Barcelona, Catalonia
Data Mining Activities for Shockomics
Problem deļ¬nition Methods Results Conclusions
Shrinkage methods
Linear Regression: minw LĪ»(w, y, x) = M
i=1 (yi āˆ’ g(xi))2
,
Regularised linear regression:
minw LĪ»(w, y, x) = minw Ī» w 2 + M
i=1 (yi āˆ’ g(xi))2
,
Lasso (L1 loss function):
minw LĪ»(w, y, x) = minw Ī»|w|1 + M
i=1 (yi āˆ’ g(xi))2
,
Regularised support vector machines with a-priori
distributions:
ln p(t | s, Ļƒāˆ’2) = 1
2
M
i=1 ln si āˆ’ N
2 ln Ļƒāˆ’2 + ln(2Ļ€)
āˆ’1
2 Ļƒāˆ’2tT t āˆ’ ĀµT Ī£āˆ’1Āµ + ln|Ī£| ,
which has to be maximized w.r.t. Ļƒāˆ’2 and s.
Vicent J. Ribas Custom Software and Electronics Barcelona, Catalonia
Data Mining Activities for Shockomics
Problem deļ¬nition Methods Results Conclusions
Contents
1 Problem deļ¬nition
2 Methods
3 Results
4 Conclusions
Vicent J. Ribas Custom Software and Electronics Barcelona, Catalonia
Data Mining Activities for Shockomics
Problem deļ¬nition Methods Results Conclusions
ProteoSepsis
Objective: assess the metabolites of the ProteoSepsis biobank
showing the strongest interaction with organ dysfunction
assessed through the SOFA score and Lactate levels.
Methodology: graphical models with Conditional
Independence Maps.
Vicent J. Ribas Custom Software and Electronics Barcelona, Catalonia
Data Mining Activities for Shockomics
Problem deļ¬nition Methods Results Conclusions
ProteoSepsis
At ICU admission, there was a signiļ¬cant interaction between
C3-DC / C4-OH (Hydroxybutyrylcarnitine) and C5
(Valerylcarnitine).
We also found a signiļ¬cant interaction between C3-DC /
C4-OH (Hydroxybutyrylcarnitine) and C5 (Valerylcarnitine)
and Isoleucine (Ile) at 48h and ICU discharge.
A separate conditional analysis for each metabolite family
yielded the interactions in the following table.
Vicent J. Ribas Custom Software and Electronics Barcelona, Catalonia
Data Mining Activities for Shockomics
Problem deļ¬nition Methods Results Conclusions
Phosphatidylcholines LysoPC a C18:1
PC aa C28:1
PC aa C38:1
MUPC / SPC
Amines and Amino-acids Creatinine
Kynurenine
Putrescine
t4-OH-Pro
Taurine
Total DMA
Glu
Ile
Ala
Leu
Arg
Sphingolipids SM C24:1
SM C18:0
SM C20:2
SM C24:0
SM C24:1
SM C26:1
Acylcarnitines C14:1
C14:2
C2
C5
Vicent J. Ribas Custom Software and Electronics Barcelona, Catalonia
Data Mining Activities for Shockomics
Problem deļ¬nition Methods Results Conclusions
Albios
Objective: assess the proteins of the Albios biobank showing
the strongest interaction with organ dysfunction assessed
through Lactate levels.
Methodology: Graphical Lasso and Elastic Network (Lasso)
over a set of 660 proteins (graph with 662 nodes and 28370
edges).
Vicent J. Ribas Custom Software and Electronics Barcelona, Catalonia
Data Mining Activities for Shockomics
Problem deļ¬nition Methods Results Conclusions
Albios
Vicent J. Ribas Custom Software and Electronics Barcelona, Catalonia
Data Mining Activities for Shockomics
Problem deļ¬nition Methods Results Conclusions
Albios
At ICU admission, there was a signiļ¬cant interaction with:
Angiotensinogen P01019 (p = 0.01).
Neural cell adhesion molecule L1-like protein O00533
(p = 0.02).
Complement C3 P01024 (p = 0.01)
Vicent J. Ribas Custom Software and Electronics Barcelona, Catalonia
Data Mining Activities for Shockomics
Problem deļ¬nition Methods Results Conclusions
Albios
At day 7, there was a signiļ¬cant interaction with:
Phosphatidylnositol-glycan biosynthesis class X protein
Q8TBF5 (p = 0.024).
Myosin 9 P35579 (p = 0.078).
Beta-2-Glycoprotein P02749 (p = 0.0614)
Vicent J. Ribas Custom Software and Electronics Barcelona, Catalonia
Data Mining Activities for Shockomics
Problem deļ¬nition Methods Results Conclusions
Contents
1 Problem deļ¬nition
2 Methods
3 Results
4 Conclusions
Vicent J. Ribas Custom Software and Electronics Barcelona, Catalonia
Data Mining Activities for Shockomics
Problem deļ¬nition Methods Results Conclusions
Conclusions
Methodology
We propose to analyse the interactions between the diļ¬€erent
ā€™omicsā€™ and clinical data for each shock.
If possible, we will provide a stratiļ¬cation framework to study
the evolution of patients over time.
Vicent J. Ribas Custom Software and Electronics Barcelona, Catalonia
Data Mining Activities for Shockomics

More Related Content

Similar to Shockomics milano april_2016_v2

MVPA with SpaceNet: sparse structured priors
MVPA with SpaceNet: sparse structured priorsMVPA with SpaceNet: sparse structured priors
MVPA with SpaceNet: sparse structured priorsElvis DOHMATOB
Ā 
Count-Distinct Problem
Count-Distinct ProblemCount-Distinct Problem
Count-Distinct ProblemKai Zhang
Ā 
Clustered compressive sensingbased
Clustered compressive sensingbasedClustered compressive sensingbased
Clustered compressive sensingbasedcsandit
Ā 
Clustered Compressive Sensingbased Image Denoising Using Bayesian Framework
Clustered Compressive Sensingbased Image Denoising Using Bayesian FrameworkClustered Compressive Sensingbased Image Denoising Using Bayesian Framework
Clustered Compressive Sensingbased Image Denoising Using Bayesian Frameworkcsandit
Ā 
Sensing Method for Two-Target Detection in Time-Constrained Vector Poisson Ch...
Sensing Method for Two-Target Detection in Time-Constrained Vector Poisson Ch...Sensing Method for Two-Target Detection in Time-Constrained Vector Poisson Ch...
Sensing Method for Two-Target Detection in Time-Constrained Vector Poisson Ch...sipij
Ā 
Sensing Method for Two-Target Detection in Time-Constrained Vector Poisson Ch...
Sensing Method for Two-Target Detection in Time-Constrained Vector Poisson Ch...Sensing Method for Two-Target Detection in Time-Constrained Vector Poisson Ch...
Sensing Method for Two-Target Detection in Time-Constrained Vector Poisson Ch...sipij
Ā 
bayesImageS: Bayesian computation for medical Image Segmentation using a hidd...
bayesImageS: Bayesian computation for medical Image Segmentation using a hidd...bayesImageS: Bayesian computation for medical Image Segmentation using a hidd...
bayesImageS: Bayesian computation for medical Image Segmentation using a hidd...Matt Moores
Ā 
Derivation and Application of Multistep Methods to a Class of First-order Ord...
Derivation and Application of Multistep Methods to a Class of First-order Ord...Derivation and Application of Multistep Methods to a Class of First-order Ord...
Derivation and Application of Multistep Methods to a Class of First-order Ord...AI Publications
Ā 
Introduction to Evidential Neural Networks
Introduction to Evidential Neural NetworksIntroduction to Evidential Neural Networks
Introduction to Evidential Neural NetworksFederico Cerutti
Ā 
Blind Source Separation using Dictionary Learning
Blind Source Separation using Dictionary LearningBlind Source Separation using Dictionary Learning
Blind Source Separation using Dictionary LearningDavide Nardone
Ā 
Image compression based on
Image compression based onImage compression based on
Image compression based onijma
Ā 
An Improved Iterative Method for Solving General System of Equations via Gene...
An Improved Iterative Method for Solving General System of Equations via Gene...An Improved Iterative Method for Solving General System of Equations via Gene...
An Improved Iterative Method for Solving General System of Equations via Gene...Zac Darcy
Ā 
An Improved Iterative Method for Solving General System of Equations via Gene...
An Improved Iterative Method for Solving General System of Equations via Gene...An Improved Iterative Method for Solving General System of Equations via Gene...
An Improved Iterative Method for Solving General System of Equations via Gene...Zac Darcy
Ā 
Regularized Compression of A Noisy Blurred Image
Regularized Compression of A Noisy Blurred Image Regularized Compression of A Noisy Blurred Image
Regularized Compression of A Noisy Blurred Image ijcsa
Ā 
On image intensities, eigenfaces and LDA
On image intensities, eigenfaces and LDAOn image intensities, eigenfaces and LDA
On image intensities, eigenfaces and LDARaghu Palakodety
Ā 
Linear regression [Theory and Application (In physics point of view) using py...
Linear regression [Theory and Application (In physics point of view) using py...Linear regression [Theory and Application (In physics point of view) using py...
Linear regression [Theory and Application (In physics point of view) using py...ANIRBANMAJUMDAR18
Ā 
StatPhysPerspectives_AMALEA_Cetraro_AnnaCarbone.pdf
StatPhysPerspectives_AMALEA_Cetraro_AnnaCarbone.pdfStatPhysPerspectives_AMALEA_Cetraro_AnnaCarbone.pdf
StatPhysPerspectives_AMALEA_Cetraro_AnnaCarbone.pdfAnna Carbone
Ā 
A Wearable Accelerometer System for Unobtrusive Monitoring of Parkinsonā€™s Dis...
A Wearable Accelerometer System for Unobtrusive Monitoring of Parkinsonā€™s Dis...A Wearable Accelerometer System for Unobtrusive Monitoring of Parkinsonā€™s Dis...
A Wearable Accelerometer System for Unobtrusive Monitoring of Parkinsonā€™s Dis...Michael J. Montgomery
Ā 

Similar to Shockomics milano april_2016_v2 (20)

KAUST_talk_short.pdf
KAUST_talk_short.pdfKAUST_talk_short.pdf
KAUST_talk_short.pdf
Ā 
MVPA with SpaceNet: sparse structured priors
MVPA with SpaceNet: sparse structured priorsMVPA with SpaceNet: sparse structured priors
MVPA with SpaceNet: sparse structured priors
Ā 
Count-Distinct Problem
Count-Distinct ProblemCount-Distinct Problem
Count-Distinct Problem
Ā 
Clustered compressive sensingbased
Clustered compressive sensingbasedClustered compressive sensingbased
Clustered compressive sensingbased
Ā 
Clustered Compressive Sensingbased Image Denoising Using Bayesian Framework
Clustered Compressive Sensingbased Image Denoising Using Bayesian FrameworkClustered Compressive Sensingbased Image Denoising Using Bayesian Framework
Clustered Compressive Sensingbased Image Denoising Using Bayesian Framework
Ā 
Sensing Method for Two-Target Detection in Time-Constrained Vector Poisson Ch...
Sensing Method for Two-Target Detection in Time-Constrained Vector Poisson Ch...Sensing Method for Two-Target Detection in Time-Constrained Vector Poisson Ch...
Sensing Method for Two-Target Detection in Time-Constrained Vector Poisson Ch...
Ā 
Sensing Method for Two-Target Detection in Time-Constrained Vector Poisson Ch...
Sensing Method for Two-Target Detection in Time-Constrained Vector Poisson Ch...Sensing Method for Two-Target Detection in Time-Constrained Vector Poisson Ch...
Sensing Method for Two-Target Detection in Time-Constrained Vector Poisson Ch...
Ā 
bayesImageS: Bayesian computation for medical Image Segmentation using a hidd...
bayesImageS: Bayesian computation for medical Image Segmentation using a hidd...bayesImageS: Bayesian computation for medical Image Segmentation using a hidd...
bayesImageS: Bayesian computation for medical Image Segmentation using a hidd...
Ā 
Derivation and Application of Multistep Methods to a Class of First-order Ord...
Derivation and Application of Multistep Methods to a Class of First-order Ord...Derivation and Application of Multistep Methods to a Class of First-order Ord...
Derivation and Application of Multistep Methods to a Class of First-order Ord...
Ā 
Introduction to Evidential Neural Networks
Introduction to Evidential Neural NetworksIntroduction to Evidential Neural Networks
Introduction to Evidential Neural Networks
Ā 
23
2323
23
Ā 
Blind Source Separation using Dictionary Learning
Blind Source Separation using Dictionary LearningBlind Source Separation using Dictionary Learning
Blind Source Separation using Dictionary Learning
Ā 
Image compression based on
Image compression based onImage compression based on
Image compression based on
Ā 
An Improved Iterative Method for Solving General System of Equations via Gene...
An Improved Iterative Method for Solving General System of Equations via Gene...An Improved Iterative Method for Solving General System of Equations via Gene...
An Improved Iterative Method for Solving General System of Equations via Gene...
Ā 
An Improved Iterative Method for Solving General System of Equations via Gene...
An Improved Iterative Method for Solving General System of Equations via Gene...An Improved Iterative Method for Solving General System of Equations via Gene...
An Improved Iterative Method for Solving General System of Equations via Gene...
Ā 
Regularized Compression of A Noisy Blurred Image
Regularized Compression of A Noisy Blurred Image Regularized Compression of A Noisy Blurred Image
Regularized Compression of A Noisy Blurred Image
Ā 
On image intensities, eigenfaces and LDA
On image intensities, eigenfaces and LDAOn image intensities, eigenfaces and LDA
On image intensities, eigenfaces and LDA
Ā 
Linear regression [Theory and Application (In physics point of view) using py...
Linear regression [Theory and Application (In physics point of view) using py...Linear regression [Theory and Application (In physics point of view) using py...
Linear regression [Theory and Application (In physics point of view) using py...
Ā 
StatPhysPerspectives_AMALEA_Cetraro_AnnaCarbone.pdf
StatPhysPerspectives_AMALEA_Cetraro_AnnaCarbone.pdfStatPhysPerspectives_AMALEA_Cetraro_AnnaCarbone.pdf
StatPhysPerspectives_AMALEA_Cetraro_AnnaCarbone.pdf
Ā 
A Wearable Accelerometer System for Unobtrusive Monitoring of Parkinsonā€™s Dis...
A Wearable Accelerometer System for Unobtrusive Monitoring of Parkinsonā€™s Dis...A Wearable Accelerometer System for Unobtrusive Monitoring of Parkinsonā€™s Dis...
A Wearable Accelerometer System for Unobtrusive Monitoring of Parkinsonā€™s Dis...
Ā 

More from Vicente RIBAS-RIPOLL

Modelling the variability of evolutionary processes
Modelling the variability of evolutionary processesModelling the variability of evolutionary processes
Modelling the variability of evolutionary processesVicente RIBAS-RIPOLL
Ā 
Poster Experimental Biology 2014
Poster Experimental Biology 2014Poster Experimental Biology 2014
Poster Experimental Biology 2014Vicente RIBAS-RIPOLL
Ā 
Rvm sepsis mortality_index_beamer
Rvm sepsis mortality_index_beamerRvm sepsis mortality_index_beamer
Rvm sepsis mortality_index_beamerVicente RIBAS-RIPOLL
Ā 
Disrupting healthcare with technology
Disrupting healthcare with technologyDisrupting healthcare with technology
Disrupting healthcare with technologyVicente RIBAS-RIPOLL
Ā 
Thursday 15h45 vicent_ribas ESANN
Thursday 15h45 vicent_ribas ESANNThursday 15h45 vicent_ribas ESANN
Thursday 15h45 vicent_ribas ESANNVicente RIBAS-RIPOLL
Ā 
PhD thesis "On the intelligent Management of Sepsis"
PhD thesis "On the intelligent Management of Sepsis"PhD thesis "On the intelligent Management of Sepsis"
PhD thesis "On the intelligent Management of Sepsis"Vicente RIBAS-RIPOLL
Ā 

More from Vicente RIBAS-RIPOLL (9)

Presentation iwbbio
Presentation iwbbioPresentation iwbbio
Presentation iwbbio
Ā 
Presentacion big data
Presentacion big dataPresentacion big data
Presentacion big data
Ā 
Modelling the variability of evolutionary processes
Modelling the variability of evolutionary processesModelling the variability of evolutionary processes
Modelling the variability of evolutionary processes
Ā 
Poster Experimental Biology 2014
Poster Experimental Biology 2014Poster Experimental Biology 2014
Poster Experimental Biology 2014
Ā 
Rvm sepsis mortality_index_beamer
Rvm sepsis mortality_index_beamerRvm sepsis mortality_index_beamer
Rvm sepsis mortality_index_beamer
Ā 
Disrupting healthcare with technology
Disrupting healthcare with technologyDisrupting healthcare with technology
Disrupting healthcare with technology
Ā 
Thursday 15h45 vicent_ribas ESANN
Thursday 15h45 vicent_ribas ESANNThursday 15h45 vicent_ribas ESANN
Thursday 15h45 vicent_ribas ESANN
Ā 
PhD Defense
PhD DefensePhD Defense
PhD Defense
Ā 
PhD thesis "On the intelligent Management of Sepsis"
PhD thesis "On the intelligent Management of Sepsis"PhD thesis "On the intelligent Management of Sepsis"
PhD thesis "On the intelligent Management of Sepsis"
Ā 

Recently uploaded

Best Rate (Guwahati ) Call Girls Guwahati āŸŸ 8617370543 āŸŸ High Class Call Girl...
Best Rate (Guwahati ) Call Girls Guwahati āŸŸ 8617370543 āŸŸ High Class Call Girl...Best Rate (Guwahati ) Call Girls Guwahati āŸŸ 8617370543 āŸŸ High Class Call Girl...
Best Rate (Guwahati ) Call Girls Guwahati āŸŸ 8617370543 āŸŸ High Class Call Girl...Dipal Arora
Ā 
All Time Service Available Call Girls Marine Drive šŸ“³ 9820252231 For 18+ VIP C...
All Time Service Available Call Girls Marine Drive šŸ“³ 9820252231 For 18+ VIP C...All Time Service Available Call Girls Marine Drive šŸ“³ 9820252231 For 18+ VIP C...
All Time Service Available Call Girls Marine Drive šŸ“³ 9820252231 For 18+ VIP C...Arohi Goyal
Ā 
VIP Mumbai Call Girls Hiranandani Gardens Just Call 9920874524 with A/C Room ...
VIP Mumbai Call Girls Hiranandani Gardens Just Call 9920874524 with A/C Room ...VIP Mumbai Call Girls Hiranandani Gardens Just Call 9920874524 with A/C Room ...
VIP Mumbai Call Girls Hiranandani Gardens Just Call 9920874524 with A/C Room ...Garima Khatri
Ā 
Russian Call Girls in Jaipur Riya WhatsApp ā¤8445551418 VIP Call Girls Jaipur
Russian Call Girls in Jaipur Riya WhatsApp ā¤8445551418 VIP Call Girls JaipurRussian Call Girls in Jaipur Riya WhatsApp ā¤8445551418 VIP Call Girls Jaipur
Russian Call Girls in Jaipur Riya WhatsApp ā¤8445551418 VIP Call Girls Jaipurparulsinha
Ā 
Call Girls Bangalore Just Call 9907093804 Top Class Call Girl Service Available
Call Girls Bangalore Just Call 9907093804 Top Class Call Girl Service AvailableCall Girls Bangalore Just Call 9907093804 Top Class Call Girl Service Available
Call Girls Bangalore Just Call 9907093804 Top Class Call Girl Service AvailableDipal Arora
Ā 
VIP Service Call Girls Sindhi Colony šŸ“³ 7877925207 For 18+ VIP Call Girl At Th...
VIP Service Call Girls Sindhi Colony šŸ“³ 7877925207 For 18+ VIP Call Girl At Th...VIP Service Call Girls Sindhi Colony šŸ“³ 7877925207 For 18+ VIP Call Girl At Th...
VIP Service Call Girls Sindhi Colony šŸ“³ 7877925207 For 18+ VIP Call Girl At Th...jageshsingh5554
Ā 
Vip Call Girls Anna Salai Chennai šŸ‘‰ 8250192130 ā£ļøšŸ’Æ Top Class Girls Available
Vip Call Girls Anna Salai Chennai šŸ‘‰ 8250192130 ā£ļøšŸ’Æ Top Class Girls AvailableVip Call Girls Anna Salai Chennai šŸ‘‰ 8250192130 ā£ļøšŸ’Æ Top Class Girls Available
Vip Call Girls Anna Salai Chennai šŸ‘‰ 8250192130 ā£ļøšŸ’Æ Top Class Girls AvailableNehru place Escorts
Ā 
Low Rate Call Girls Kochi Anika 8250192130 Independent Escort Service Kochi
Low Rate Call Girls Kochi Anika 8250192130 Independent Escort Service KochiLow Rate Call Girls Kochi Anika 8250192130 Independent Escort Service Kochi
Low Rate Call Girls Kochi Anika 8250192130 Independent Escort Service KochiSuhani Kapoor
Ā 
Call Girls Ooty Just Call 9907093804 Top Class Call Girl Service Available
Call Girls Ooty Just Call 9907093804 Top Class Call Girl Service AvailableCall Girls Ooty Just Call 9907093804 Top Class Call Girl Service Available
Call Girls Ooty Just Call 9907093804 Top Class Call Girl Service AvailableDipal Arora
Ā 
Call Girls Dehradun Just Call 9907093804 Top Class Call Girl Service Available
Call Girls Dehradun Just Call 9907093804 Top Class Call Girl Service AvailableCall Girls Dehradun Just Call 9907093804 Top Class Call Girl Service Available
Call Girls Dehradun Just Call 9907093804 Top Class Call Girl Service AvailableDipal Arora
Ā 
Call Girls Horamavu WhatsApp Number 7001035870 Meeting With Bangalore Escorts
Call Girls Horamavu WhatsApp Number 7001035870 Meeting With Bangalore EscortsCall Girls Horamavu WhatsApp Number 7001035870 Meeting With Bangalore Escorts
Call Girls Horamavu WhatsApp Number 7001035870 Meeting With Bangalore Escortsvidya singh
Ā 
Night 7k to 12k Chennai City Center Call Girls šŸ‘‰šŸ‘‰ 7427069034ā­ā­ 100% Genuine E...
Night 7k to 12k Chennai City Center Call Girls šŸ‘‰šŸ‘‰ 7427069034ā­ā­ 100% Genuine E...Night 7k to 12k Chennai City Center Call Girls šŸ‘‰šŸ‘‰ 7427069034ā­ā­ 100% Genuine E...
Night 7k to 12k Chennai City Center Call Girls šŸ‘‰šŸ‘‰ 7427069034ā­ā­ 100% Genuine E...hotbabesbook
Ā 
šŸ’ŽVVIP Kolkata Call Girls ParganasšŸ©±7001035870šŸ©±Independent Girl ( Ac Rooms Avai...
šŸ’ŽVVIP Kolkata Call Girls ParganasšŸ©±7001035870šŸ©±Independent Girl ( Ac Rooms Avai...šŸ’ŽVVIP Kolkata Call Girls ParganasšŸ©±7001035870šŸ©±Independent Girl ( Ac Rooms Avai...
šŸ’ŽVVIP Kolkata Call Girls ParganasšŸ©±7001035870šŸ©±Independent Girl ( Ac Rooms Avai...Taniya Sharma
Ā 
Call Girls Nagpur Just Call 9907093804 Top Class Call Girl Service Available
Call Girls Nagpur Just Call 9907093804 Top Class Call Girl Service AvailableCall Girls Nagpur Just Call 9907093804 Top Class Call Girl Service Available
Call Girls Nagpur Just Call 9907093804 Top Class Call Girl Service AvailableDipal Arora
Ā 
Top Rated Bangalore Call Girls Richmond Circle āŸŸ 8250192130 āŸŸ Call Me For Gen...
Top Rated Bangalore Call Girls Richmond Circle āŸŸ 8250192130 āŸŸ Call Me For Gen...Top Rated Bangalore Call Girls Richmond Circle āŸŸ 8250192130 āŸŸ Call Me For Gen...
Top Rated Bangalore Call Girls Richmond Circle āŸŸ 8250192130 āŸŸ Call Me For Gen...narwatsonia7
Ā 
Lucknow Call girls - 8800925952 - 24x7 service with hotel room
Lucknow Call girls - 8800925952 - 24x7 service with hotel roomLucknow Call girls - 8800925952 - 24x7 service with hotel room
Lucknow Call girls - 8800925952 - 24x7 service with hotel roomdiscovermytutordmt
Ā 
Chandrapur Call girls 8617370543 Provides all area service COD available
Chandrapur Call girls 8617370543 Provides all area service COD availableChandrapur Call girls 8617370543 Provides all area service COD available
Chandrapur Call girls 8617370543 Provides all area service COD availableDipal Arora
Ā 
Call Girls Ludhiana Just Call 9907093804 Top Class Call Girl Service Available
Call Girls Ludhiana Just Call 9907093804 Top Class Call Girl Service AvailableCall Girls Ludhiana Just Call 9907093804 Top Class Call Girl Service Available
Call Girls Ludhiana Just Call 9907093804 Top Class Call Girl Service AvailableDipal Arora
Ā 
Book Paid Powai Call Girls Mumbai š– ‹ 9930245274 š– ‹Low Budget Full Independent H...
Book Paid Powai Call Girls Mumbai š– ‹ 9930245274 š– ‹Low Budget Full Independent H...Book Paid Powai Call Girls Mumbai š– ‹ 9930245274 š– ‹Low Budget Full Independent H...
Book Paid Powai Call Girls Mumbai š– ‹ 9930245274 š– ‹Low Budget Full Independent H...Call Girls in Nagpur High Profile
Ā 

Recently uploaded (20)

Best Rate (Guwahati ) Call Girls Guwahati āŸŸ 8617370543 āŸŸ High Class Call Girl...
Best Rate (Guwahati ) Call Girls Guwahati āŸŸ 8617370543 āŸŸ High Class Call Girl...Best Rate (Guwahati ) Call Girls Guwahati āŸŸ 8617370543 āŸŸ High Class Call Girl...
Best Rate (Guwahati ) Call Girls Guwahati āŸŸ 8617370543 āŸŸ High Class Call Girl...
Ā 
All Time Service Available Call Girls Marine Drive šŸ“³ 9820252231 For 18+ VIP C...
All Time Service Available Call Girls Marine Drive šŸ“³ 9820252231 For 18+ VIP C...All Time Service Available Call Girls Marine Drive šŸ“³ 9820252231 For 18+ VIP C...
All Time Service Available Call Girls Marine Drive šŸ“³ 9820252231 For 18+ VIP C...
Ā 
VIP Mumbai Call Girls Hiranandani Gardens Just Call 9920874524 with A/C Room ...
VIP Mumbai Call Girls Hiranandani Gardens Just Call 9920874524 with A/C Room ...VIP Mumbai Call Girls Hiranandani Gardens Just Call 9920874524 with A/C Room ...
VIP Mumbai Call Girls Hiranandani Gardens Just Call 9920874524 with A/C Room ...
Ā 
Russian Call Girls in Jaipur Riya WhatsApp ā¤8445551418 VIP Call Girls Jaipur
Russian Call Girls in Jaipur Riya WhatsApp ā¤8445551418 VIP Call Girls JaipurRussian Call Girls in Jaipur Riya WhatsApp ā¤8445551418 VIP Call Girls Jaipur
Russian Call Girls in Jaipur Riya WhatsApp ā¤8445551418 VIP Call Girls Jaipur
Ā 
Call Girls Bangalore Just Call 9907093804 Top Class Call Girl Service Available
Call Girls Bangalore Just Call 9907093804 Top Class Call Girl Service AvailableCall Girls Bangalore Just Call 9907093804 Top Class Call Girl Service Available
Call Girls Bangalore Just Call 9907093804 Top Class Call Girl Service Available
Ā 
VIP Service Call Girls Sindhi Colony šŸ“³ 7877925207 For 18+ VIP Call Girl At Th...
VIP Service Call Girls Sindhi Colony šŸ“³ 7877925207 For 18+ VIP Call Girl At Th...VIP Service Call Girls Sindhi Colony šŸ“³ 7877925207 For 18+ VIP Call Girl At Th...
VIP Service Call Girls Sindhi Colony šŸ“³ 7877925207 For 18+ VIP Call Girl At Th...
Ā 
Vip Call Girls Anna Salai Chennai šŸ‘‰ 8250192130 ā£ļøšŸ’Æ Top Class Girls Available
Vip Call Girls Anna Salai Chennai šŸ‘‰ 8250192130 ā£ļøšŸ’Æ Top Class Girls AvailableVip Call Girls Anna Salai Chennai šŸ‘‰ 8250192130 ā£ļøšŸ’Æ Top Class Girls Available
Vip Call Girls Anna Salai Chennai šŸ‘‰ 8250192130 ā£ļøšŸ’Æ Top Class Girls Available
Ā 
Low Rate Call Girls Kochi Anika 8250192130 Independent Escort Service Kochi
Low Rate Call Girls Kochi Anika 8250192130 Independent Escort Service KochiLow Rate Call Girls Kochi Anika 8250192130 Independent Escort Service Kochi
Low Rate Call Girls Kochi Anika 8250192130 Independent Escort Service Kochi
Ā 
Call Girls Ooty Just Call 9907093804 Top Class Call Girl Service Available
Call Girls Ooty Just Call 9907093804 Top Class Call Girl Service AvailableCall Girls Ooty Just Call 9907093804 Top Class Call Girl Service Available
Call Girls Ooty Just Call 9907093804 Top Class Call Girl Service Available
Ā 
Call Girls Dehradun Just Call 9907093804 Top Class Call Girl Service Available
Call Girls Dehradun Just Call 9907093804 Top Class Call Girl Service AvailableCall Girls Dehradun Just Call 9907093804 Top Class Call Girl Service Available
Call Girls Dehradun Just Call 9907093804 Top Class Call Girl Service Available
Ā 
Call Girls Horamavu WhatsApp Number 7001035870 Meeting With Bangalore Escorts
Call Girls Horamavu WhatsApp Number 7001035870 Meeting With Bangalore EscortsCall Girls Horamavu WhatsApp Number 7001035870 Meeting With Bangalore Escorts
Call Girls Horamavu WhatsApp Number 7001035870 Meeting With Bangalore Escorts
Ā 
Night 7k to 12k Chennai City Center Call Girls šŸ‘‰šŸ‘‰ 7427069034ā­ā­ 100% Genuine E...
Night 7k to 12k Chennai City Center Call Girls šŸ‘‰šŸ‘‰ 7427069034ā­ā­ 100% Genuine E...Night 7k to 12k Chennai City Center Call Girls šŸ‘‰šŸ‘‰ 7427069034ā­ā­ 100% Genuine E...
Night 7k to 12k Chennai City Center Call Girls šŸ‘‰šŸ‘‰ 7427069034ā­ā­ 100% Genuine E...
Ā 
šŸ’ŽVVIP Kolkata Call Girls ParganasšŸ©±7001035870šŸ©±Independent Girl ( Ac Rooms Avai...
šŸ’ŽVVIP Kolkata Call Girls ParganasšŸ©±7001035870šŸ©±Independent Girl ( Ac Rooms Avai...šŸ’ŽVVIP Kolkata Call Girls ParganasšŸ©±7001035870šŸ©±Independent Girl ( Ac Rooms Avai...
šŸ’ŽVVIP Kolkata Call Girls ParganasšŸ©±7001035870šŸ©±Independent Girl ( Ac Rooms Avai...
Ā 
Call Girls Nagpur Just Call 9907093804 Top Class Call Girl Service Available
Call Girls Nagpur Just Call 9907093804 Top Class Call Girl Service AvailableCall Girls Nagpur Just Call 9907093804 Top Class Call Girl Service Available
Call Girls Nagpur Just Call 9907093804 Top Class Call Girl Service Available
Ā 
Top Rated Bangalore Call Girls Richmond Circle āŸŸ 8250192130 āŸŸ Call Me For Gen...
Top Rated Bangalore Call Girls Richmond Circle āŸŸ 8250192130 āŸŸ Call Me For Gen...Top Rated Bangalore Call Girls Richmond Circle āŸŸ 8250192130 āŸŸ Call Me For Gen...
Top Rated Bangalore Call Girls Richmond Circle āŸŸ 8250192130 āŸŸ Call Me For Gen...
Ā 
Lucknow Call girls - 8800925952 - 24x7 service with hotel room
Lucknow Call girls - 8800925952 - 24x7 service with hotel roomLucknow Call girls - 8800925952 - 24x7 service with hotel room
Lucknow Call girls - 8800925952 - 24x7 service with hotel room
Ā 
Chandrapur Call girls 8617370543 Provides all area service COD available
Chandrapur Call girls 8617370543 Provides all area service COD availableChandrapur Call girls 8617370543 Provides all area service COD available
Chandrapur Call girls 8617370543 Provides all area service COD available
Ā 
Russian Call Girls in Delhi Tanvi āž”ļø 9711199012 šŸ’‹šŸ“ž Independent Escort Service...
Russian Call Girls in Delhi Tanvi āž”ļø 9711199012 šŸ’‹šŸ“ž Independent Escort Service...Russian Call Girls in Delhi Tanvi āž”ļø 9711199012 šŸ’‹šŸ“ž Independent Escort Service...
Russian Call Girls in Delhi Tanvi āž”ļø 9711199012 šŸ’‹šŸ“ž Independent Escort Service...
Ā 
Call Girls Ludhiana Just Call 9907093804 Top Class Call Girl Service Available
Call Girls Ludhiana Just Call 9907093804 Top Class Call Girl Service AvailableCall Girls Ludhiana Just Call 9907093804 Top Class Call Girl Service Available
Call Girls Ludhiana Just Call 9907093804 Top Class Call Girl Service Available
Ā 
Book Paid Powai Call Girls Mumbai š– ‹ 9930245274 š– ‹Low Budget Full Independent H...
Book Paid Powai Call Girls Mumbai š– ‹ 9930245274 š– ‹Low Budget Full Independent H...Book Paid Powai Call Girls Mumbai š– ‹ 9930245274 š– ‹Low Budget Full Independent H...
Book Paid Powai Call Girls Mumbai š– ‹ 9930245274 š– ‹Low Budget Full Independent H...
Ā 

Shockomics milano april_2016_v2

  • 1. Problem deļ¬nition Methods Results Conclusions Data Mining Activities for Shockomics Vicent J. Ribas Custom Software and Electronics Barcelona, Catalonia April 19, 2016 Vicent J. Ribas Custom Software and Electronics Barcelona, Catalonia Data Mining Activities for Shockomics
  • 2. Problem deļ¬nition Methods Results Conclusions Contents 1 Problem deļ¬nition 2 Methods 3 Results 4 Conclusions Vicent J. Ribas Custom Software and Electronics Barcelona, Catalonia Data Mining Activities for Shockomics
  • 3. Problem deļ¬nition Methods Results Conclusions Problem deļ¬nition Objective: detect the clinical variables, proteins and metabolites that present the highest impact on the three diļ¬€erent types of shock that we are studying at three diļ¬€erent times (T1, T2 and discharge). Of course, attending to the nature of this study, we will have many more variables/data observed than patients. Deļ¬nition: ā€˜a small n, large pā€™ is a data mining problem that tries to predict response to treatment based on data having a very small sample size (n) but very large dimensionality (p). This problem needs to be tackled through data visualisation, dimensionality reduction techniques (shrinkage methods) or a combination of both. Vicent J. Ribas Custom Software and Electronics Barcelona, Catalonia Data Mining Activities for Shockomics
  • 4. Problem deļ¬nition Methods Results Conclusions small n large p Vicent J. Ribas Custom Software and Electronics Barcelona, Catalonia Data Mining Activities for Shockomics
  • 5. Problem deļ¬nition Methods Results Conclusions Contents 1 Problem deļ¬nition 2 Methods 3 Results 4 Conclusions Vicent J. Ribas Custom Software and Electronics Barcelona, Catalonia Data Mining Activities for Shockomics
  • 6. Problem deļ¬nition Methods Results Conclusions Methods In line with the description of WP8, the following methods are considered for studying our n >> p problem: Graphical models: Factorisation of the probability densty function (Hammersley Cliļ¬€ord theorem). Conditional independence maps (CIM - mutual information between sets of variables). Graphical LASSO. Ensembles of classiļ¬cation and regression trees (bagged trees). Dendrograms, Kohonen Maps and Heat Maps. Vicent J. Ribas Custom Software and Electronics Barcelona, Catalonia Data Mining Activities for Shockomics
  • 7. Problem deļ¬nition Methods Results Conclusions Methods Regularised models: Regularised linear regression. LASSO. Relevance vector machines (regularised support vector machines with a-priori distributions). Support Vector Machines with generative kernels (the Quotient Basis Kernel). Neural Networks (Restricted Boltzmann Machines/Factor Analysis Models). Vicent J. Ribas Custom Software and Electronics Barcelona, Catalonia Data Mining Activities for Shockomics
  • 8. Problem deļ¬nition Methods Results Conclusions Conditional Independence for Gaussian Distribution Let X = (X1, . . . , Xp) be a random vector with joint normal distribution Np(Āµ, Ī£) with mean vector Āµ āˆˆ Rp and positive deļ¬nite covariance matrix Ī£. For three pairwise disjoint index sets A, B, C āŠ† {1, . . . , p}, the sub-vectors XA and XB are conditionally independent given XC , iļ¬€ det Ī£A CƗB C = 0 Here A C Ɨ B C is the minor related to the variables over which we are calculating the marginal dependence/independence (i.e. the resulting minor after removing the rows and columns corresponding to the conditional independence statement). Vicent J. Ribas Custom Software and Electronics Barcelona, Catalonia Data Mining Activities for Shockomics
  • 9. Problem deļ¬nition Methods Results Conclusions Markov Random Fields Given and undirected graph G, a Markov Random Field (MRF) is deļ¬ned as a set of probability distributions MRFG := {p(x) : p(x) > 0, āˆ€p, x} such that āˆ€p āˆˆ MRFG and for any three disjoint subsets A, B, C of G, if C separates A from B then p satisļ¬es XA āŠ„āŠ„ XB|XC . If p āˆˆ MRFG, we often say p respects G. Vicent J. Ribas Custom Software and Electronics Barcelona, Catalonia Data Mining Activities for Shockomics
  • 10. Problem deļ¬nition Methods Results Conclusions Hammersley Cliļ¬€ord theorem If a pdf p āˆˆ MRFG, then p(x) must also factorize according to G, i.e. there exist functions Ļˆc(x) on c āˆˆ C, such that p(x) = 1 Z exp cāˆˆC Ļˆc(xc) . Vicent J. Ribas Custom Software and Electronics Barcelona, Catalonia Data Mining Activities for Shockomics
  • 11. Problem deļ¬nition Methods Results Conclusions Statistical methods The method above is exact but it requires the calculation of the inverse of covariance matrices, which for the dimenstionality that we are considering is not viable. However, some numerical methods based on the same framework will help. CIM is an eļ¬ƒcient method for ļ¬nding the structure of a graphical model. In particular, it is based on the measure of mutual information between sets of variables. A mutual information of zero corresponds to mutual statistical independence. The graphical lasso is an algorithm to estimate the precision matrix (inverse of covariance matrix) from the available data. The algorithm is based on a Lasso regularisation over the estimated covariance matrix. Vicent J. Ribas Custom Software and Electronics Barcelona, Catalonia Data Mining Activities for Shockomics
  • 12. Problem deļ¬nition Methods Results Conclusions CIM I(A, B) = a,b P(a, b) log P(a, b) P(a)P(b) and the conditional mutual information, with respect to the condition set C, I(A, B|C) = a,b,c P(a, b, c) log P(a, b|c) P(a|c)P(b|c) . The conditional mutual information is consistent with Hammersley Cliļ¬€ord and Factorisation because mutual information will be 0 iļ¬€ A āŠ„āŠ„ B|C. Vicent J. Ribas Custom Software and Electronics Barcelona, Catalonia Data Mining Activities for Shockomics
  • 13. Problem deļ¬nition Methods Results Conclusions Shrinkage methods Linear Regression: minw LĪ»(w, y, x) = M i=1 (yi āˆ’ g(xi))2 , Regularised linear regression: minw LĪ»(w, y, x) = minw Ī» w 2 + M i=1 (yi āˆ’ g(xi))2 , Lasso (L1 loss function): minw LĪ»(w, y, x) = minw Ī»|w|1 + M i=1 (yi āˆ’ g(xi))2 , Regularised support vector machines with a-priori distributions: ln p(t | s, Ļƒāˆ’2) = 1 2 M i=1 ln si āˆ’ N 2 ln Ļƒāˆ’2 + ln(2Ļ€) āˆ’1 2 Ļƒāˆ’2tT t āˆ’ ĀµT Ī£āˆ’1Āµ + ln|Ī£| , which has to be maximized w.r.t. Ļƒāˆ’2 and s. Vicent J. Ribas Custom Software and Electronics Barcelona, Catalonia Data Mining Activities for Shockomics
  • 14. Problem deļ¬nition Methods Results Conclusions Contents 1 Problem deļ¬nition 2 Methods 3 Results 4 Conclusions Vicent J. Ribas Custom Software and Electronics Barcelona, Catalonia Data Mining Activities for Shockomics
  • 15. Problem deļ¬nition Methods Results Conclusions ProteoSepsis Objective: assess the metabolites of the ProteoSepsis biobank showing the strongest interaction with organ dysfunction assessed through the SOFA score and Lactate levels. Methodology: graphical models with Conditional Independence Maps. Vicent J. Ribas Custom Software and Electronics Barcelona, Catalonia Data Mining Activities for Shockomics
  • 16. Problem deļ¬nition Methods Results Conclusions ProteoSepsis At ICU admission, there was a signiļ¬cant interaction between C3-DC / C4-OH (Hydroxybutyrylcarnitine) and C5 (Valerylcarnitine). We also found a signiļ¬cant interaction between C3-DC / C4-OH (Hydroxybutyrylcarnitine) and C5 (Valerylcarnitine) and Isoleucine (Ile) at 48h and ICU discharge. A separate conditional analysis for each metabolite family yielded the interactions in the following table. Vicent J. Ribas Custom Software and Electronics Barcelona, Catalonia Data Mining Activities for Shockomics
  • 17. Problem deļ¬nition Methods Results Conclusions Phosphatidylcholines LysoPC a C18:1 PC aa C28:1 PC aa C38:1 MUPC / SPC Amines and Amino-acids Creatinine Kynurenine Putrescine t4-OH-Pro Taurine Total DMA Glu Ile Ala Leu Arg Sphingolipids SM C24:1 SM C18:0 SM C20:2 SM C24:0 SM C24:1 SM C26:1 Acylcarnitines C14:1 C14:2 C2 C5 Vicent J. Ribas Custom Software and Electronics Barcelona, Catalonia Data Mining Activities for Shockomics
  • 18. Problem deļ¬nition Methods Results Conclusions Albios Objective: assess the proteins of the Albios biobank showing the strongest interaction with organ dysfunction assessed through Lactate levels. Methodology: Graphical Lasso and Elastic Network (Lasso) over a set of 660 proteins (graph with 662 nodes and 28370 edges). Vicent J. Ribas Custom Software and Electronics Barcelona, Catalonia Data Mining Activities for Shockomics
  • 19. Problem deļ¬nition Methods Results Conclusions Albios Vicent J. Ribas Custom Software and Electronics Barcelona, Catalonia Data Mining Activities for Shockomics
  • 20. Problem deļ¬nition Methods Results Conclusions Albios At ICU admission, there was a signiļ¬cant interaction with: Angiotensinogen P01019 (p = 0.01). Neural cell adhesion molecule L1-like protein O00533 (p = 0.02). Complement C3 P01024 (p = 0.01) Vicent J. Ribas Custom Software and Electronics Barcelona, Catalonia Data Mining Activities for Shockomics
  • 21. Problem deļ¬nition Methods Results Conclusions Albios At day 7, there was a signiļ¬cant interaction with: Phosphatidylnositol-glycan biosynthesis class X protein Q8TBF5 (p = 0.024). Myosin 9 P35579 (p = 0.078). Beta-2-Glycoprotein P02749 (p = 0.0614) Vicent J. Ribas Custom Software and Electronics Barcelona, Catalonia Data Mining Activities for Shockomics
  • 22. Problem deļ¬nition Methods Results Conclusions Contents 1 Problem deļ¬nition 2 Methods 3 Results 4 Conclusions Vicent J. Ribas Custom Software and Electronics Barcelona, Catalonia Data Mining Activities for Shockomics
  • 23. Problem deļ¬nition Methods Results Conclusions Conclusions Methodology We propose to analyse the interactions between the diļ¬€erent ā€™omicsā€™ and clinical data for each shock. If possible, we will provide a stratiļ¬cation framework to study the evolution of patients over time. Vicent J. Ribas Custom Software and Electronics Barcelona, Catalonia Data Mining Activities for Shockomics