Download ppt - r-evolution research server

Clustering the samples by the
inner-pattern tendency.
http://ibb.uab.es/revresearch
Cedano, J. Huerta, M. and Querol, E. (2007) NCR-PCOPGene: A Tool for flexible analysis of the sample-conditions
effect over continuous gene-expression relationships . Advances in Bioinformatics, Vol 2008.
Objectives


Provide powerful tools for studying the noncontinuous dependence among gene
expressions focussed in researcher genes of
interest.
Taking advantage of the high-throughput
capability of microarray technology.
The PCOP calculus


The analysed variables with the PCOP
method can be independent because the
method uses a hidden variable for ordering
the data.
PCOP is defined using the generalisation, at
the local level, of the Principal-Components
variance properties. The set of POPs
obtained (PC at local level) makes up the
PCOP or inner pattern of the data cloud.
The PCOP is a very suitable analysis
for recognising non-lineal patterns
among independent variables.
POPj
POPi
The ‘hidden-variable-dependent’
clustering tool.


When a POP is selected, the samples belonging to
the POP local area are selected. In this way, the user
can separate the sample data for their belonging to
the different local behaviours among variables.
This new clustering approach permits to differentiate
the samples of a continuous data-set on the basis of
the not explicit reason (or hidden-variable role) of
these local tendencies.
Cedano, J. Huerta, M. and Querol, E. (2007) NCR-PCOPGene: A Tool for flexible analysis of the sample-conditions effect over continuous geneexpression relationships. Advances in Bioinformatics, Vol 2008.
Selecting a POP there are selected the
samples belonging to the POP hyper-cluster
POPj
Hyper-clusteri
POPi
Hyper-clusterj
Bibliografy





Delicado, P. (2001) Another look at principal curves and surfaces. J.
Multivariate Anal., 77, 84-116.
Delicado, P. and Huerta, M. (2003) Principal curves of oriented points:
Theoretical and computational improvements. Computation. Stat., 18,
293-315.
Cedano J, Huerta M, Estrada I, Ballllosera F, Conchillo O, Delicado P,
Querol E. (2007) A web server for automatic analysis and extraction of
relevant biological knowledge. Comput Biol Med, 37:1672-1675.
Huerta, M., Cedano, J. and Querol, E. (2008) Analysis of non-linear
relation between expression profiles by the Principal Curves of
Oriented-Points approach. J Bioinform Comput Biol, 6:367-386.
Cedano, J. Huerta, M. and Querol, E. (2008) NCR-PCOPGene: A Tool
for flexible analysis of the sample-conditions effect over continuous
gene-expression relationships. Advances in Bioinformatics, Vol 2008.