@TECHREPORT{MclustSoftwareManual2006,
author = {{C}. {F}raley and {A}. {E}. {R}aftery},
title = {{MCLUST} {V}ersion 3 for {R}: {N}ormal {M}ixture {M}odeling and {M}odel-{B}ased
{C}lustering},
institution = {University of Washington},
year = {2006},
type = {Technical Report},
number = {504},
address = {Department of Statistics},
note = {revised 2009}
}
@ARTICLE{Schmidt2008,
author = {Marcus Schmidt and Daniel Böhm and Christian von Törne and Eric Steiner
and Alexander Puhl and Henryk Pilch and Hans-Anton Lehr and Jan G
Hengstler and Heinz Kölbl and Mathias Gehrmann},
title = {The humoral immune system has a key prognostic impact in node-negative
breast cancer.},
journal = {Cancer Res},
year = {2008},
volume = {68},
pages = {5405--5413},
number = {13},
month = {Jul},
__markedentry = {[anne:6]},
abstract = {Estrogen receptor (ER) expression and proliferative activity are established
prognostic factors in breast cancer. In a search for additional prognostic
motifs, we analyzed the gene expression patterns of 200 tumors of
patients who were not treated by systemic therapy after surgery using
a discovery approach. After performing hierarchical cluster analysis,
we identified coregulated genes related to the biological process
of proliferation, steroid hormone receptor expression, as well as
B-cell and T-cell infiltration. We calculated metagenes as a surrogate
for all genes contained within a particular cluster and visualized
the relative expression in relation to time to metastasis with principal
component analysis. Distinct patterns led to the hypothesis of a
prognostic role of the immune system in tumors with high expression
of proliferation-associated genes. In multivariate Cox regression
analysis, the proliferation metagene showed a significant association
with metastasis-free survival of the whole discovery cohort [hazard
ratio (HR), 2.20; 95\% confidence interval (95\% CI), 1.40-3.46].
The B-cell metagene showed additional independent prognostic information
in carcinomas with high proliferative activity (HR, 0.66; 95\% CI,
0.46-0.97). A prognostic influence of the B-cell metagene was independently
confirmed by multivariate analysis in a first validation cohort enriched
for high-grade tumors (n = 286; HR, 0.78; 95\% CI, 0.62-0.98) and
a second validation cohort enriched for younger patients (n = 302;
HR, 0.83; 95\% CI, 0.7-0.97). Thus, we could show in three cohorts
of untreated, node-negative breast cancer patients that the humoral
immune system plays a pivotal role in metastasis-free survival of
carcinomas of the breast.},
doi = {10.1158/0008-5472.CAN-07-5206},
institution = {Department of Obstetrics and Gynecology, Medical School, Johannes
Gutenberg University, Mainz, Germany.},
keywords = {Adult; Aged; Aged, 80 and over; Antibody Formation, physiology; Breast
Neoplasms, diagnosis/genetics/immunology/pathology; Carcinoma, diagnosis/genetics/immunology/pathology;
Cell Proliferation; Cluster Analysis; Cohort Studies; Female; Gene
Expression Profiling; Gene Expression Regulation, Neoplastic; Genes,
Neoplasm; Humans; Lymph Nodes, immunology/pathology; Lymphatic Metastasis;
Middle Aged; Neutrophil Infiltration, genetics; Oligonucleotide Array
Sequence Analysis; Prognosis},
language = {eng},
medline-pst = {ppublish},
owner = {anne},
pii = {68/13/5405},
pmid = {18593943},
timestamp = {2012.12.13},
url = {http://dx.doi.org/10.1158/0008-5472.CAN-07-5206}
}
@ARTICLE{FraleyRaftery2002,
author = {{C}. {F}raley and {A}. {E}. {R}aftery},
title = {{M}odel-{B}ased {C}lustering, {D}iscriminant {A}nalysis and {D}ensity
{E}stimation},
journal = {{J}ournal of the {A}merican {S}tatistical {A}ssociation},
year = {2002},
volume = {97},
pages = {611-631}
}
@ARTICLE{Falcon2007Using,
author = {Falcon, S. and Gentleman, R.},
title = {{{U}sing {G}{O}stats to test gene lists for {G}{O} term association}},
journal = {Bioinformatics},
year = {2007},
volume = {23},
pages = {257--258},
month = {Jan},
abstract = {MOTIVATION: Functional analyses based on the association of Gene Ontology
(GO) terms to genes in a selected gene list are useful bioinformatic
tools and the GOstats package has been widely used to perform such
computations. In this paper we report significant improvements and
extensions such as support for conditional testing. RESULTS: We discuss
the capabilities of GOstats, a Bioconductor package written in R,
that allows users to test GO terms for over or under-representation
using either a classical hypergeometric test or a conditional hypergeometric
that uses the relationships among GO terms to decorrelate the results.
AVAILABILITY: GOstats is available as an R package from the Bioconductor
project: http://bioconductor.org},
pmid = {17098774},
url = {http://bioinformatics.oxfordjournals.org/cgi/content/full/23/2/257?view=long&pmid=17098774}
}
@ARTICLE{Lee2003Application,
author = {Su-In Lee and Serafim Batzoglou},
title = {Application of independent component analysis to microarrays.},
journal = {Genome Biol},
year = {2003},
volume = {4},
pages = {R76},
number = {11},
abstract = {We apply linear and nonlinear independent component analysis (ICA)
to project microarray data into statistically independent components
that correspond to putative biological processes, and to cluster
genes according to over- or under-expression in each component. We
test the statistical significance of enrichment of gene annotations
within clusters. ICA outperforms other leading methods, such as principal
component analysis, k-means clustering and the Plaid model, in constructing
functionally coherent clusters on microarray datasets from Saccharomyces
cerevisiae, Caenorhabditis elegans and human.},
doi = {10.1186/gb-2003-4-11-r76},
institution = {Department of Computer Science, Stanford University, Stanford, CA94305-9010,
USA.},
keywords = {Algorithms; Animals; Caenorhabditis elegans; Cluster Analysis; Gene
Expression Profiling; Humans; Models, Genetic; Oligonucleotide Array
Sequence Analysis; Saccharomyces cerevisiae; Statistics as Topic,
Independent Component Analysis},
owner = {abiton},
pii = {gb-2003-4-11-r76},
pmid = {14611662},
timestamp = {2010.11.09},
url = {http://dx.doi.org/10.1186/gb-2003-4-11-r76}
}
@ARTICLE{Sanchez-Carbayo2006Defining,
author = {{S}anchez-{C}arbayo, {M}. and {S}occi, {N}. {D}. and {L}ozano, {J}.
and {S}aint, {F}. and {C}ordon-{C}ardo, {C}.},
title = {{Defining molecular profiles of poor outcome in patients with invasive
bladder cancer using oligonucleotide microarrays}},
journal = {{J}. {C}lin. {O}ncol.},
year = {2006},
volume = {24},
pages = {778--789},
month = {Feb},
abstract = {PURPOSE: Bladder cancer is a common malignancy characterized by a
poor clinical outcome when tumors progress into invasive disease.
We sought to define genetic signatures characteristic of aggressive
clinical behavior in advanced bladder tumors. METHODS: Oligonucleotide
arrays were utilized to analyze the transcript profiles of 105 bladder
tumors: 33 superficial, 72 invasive lesions, and 52 normal urothelium.
Hierarchical clustering and supervised algorithms were used to classify
and stratify bladder tumors on the basis of stage, node metastases,
and overall survival. Immunohistochemical analyses on bladder cancer
tissue arrays (n = 294 cases) served to validate associations between
marker expression, staging and outcome. RESULTS: Hierarchical clustering
classified normal urothelium, superficial, and invasive tumors with
82.2% accuracy, and stratified bladder tumors on the basis of clinical
outcome. Predictive algorithms rendered an 89%-correct rate for tumor
staging using genes differentially expressed between superficial
and invasive tumors. Accuracies of 82% and 90% were obtained for
predicting overall survival when considering all patients with bladder
cancer or only patients with invasive disease, respectively. A genetic
profile consisting of 174 probes was identified in those patients
with positive lymph nodes and poor survival. Two independent Global
Test runs confirmed the robust association of this profile with lymph
node metastases (P = 7.3(-13)) and overall survival (P = 1.9(-14))
simultaneously. Immunohistochemical analyses on tissue arrays sustained
the significant association of synuclein with tumor staging and clinical
outcome (P = .002). CONCLUSION: Gene profiling provides a genomic-based
classification scheme of diagnostic and prognostic utility for stratifying
advanced bladder cancer. Identification of this poor outcome profile
could assist in selecting patients who may benefit from more aggressive
therapeutic intervention.},
url = {http://jco.ascopubs.org/content/24/5/778.long}
}
@ARTICLE{Teschendorff2007Elucidating,
author = {{T}eschendorff, {A}. {E}. and {J}ournee, {M}. and {A}bsil, {P}. {A}.
and {S}epulchre, {R}. and {C}aldas, {C}.},
title = {{Elucidating the altered transcriptional programs in breast cancer
using independent component analysis}},
journal = {{PL}o{S} {C}omput. {B}iol.},
year = {2007},
volume = {3},
pages = {e161},
month = {Aug},
abstract = {The quantity of mRNA transcripts in a cell is determined by a complex
interplay of cooperative and counteracting biological processes.
Independent Component Analysis (ICA) is one of a few number of unsupervised
algorithms that have been applied to microarray gene expression data
in an attempt to understand phenotype differences in terms of changes
in the activation/inhibition patterns of biological pathways. While
the ICA model has been shown to outperform other linear representations
of the data such as Principal Components Analysis (PCA), a validation
using explicit pathway and regulatory element information has not
yet been performed. We apply a range of popular ICA algorithms to
six of the largest microarray cancer datasets and use pathway-knowledge
and regulatory-element databases for validation. We show that ICA
outperforms PCA and clustering-based methods in that ICA components
map closer to known cancer-related pathways, regulatory modules,
and cancer phenotypes. Furthermore, we identify cancer signalling
and oncogenic pathways and regulatory modules that play a prominent
role in breast cancer and relate the differential activation patterns
of these to breast cancer phenotypes. Importantly, we find novel
associations linking immune response and epithelial-mesenchymal transition
pathways with estrogen receptor status and histological grade, respectively.
In addition, we find associations linking the activity levels of
biological pathways and transcription factors (NF1 and NFAT) with
clinical outcome in breast cancer. ICA provides a framework for a
more biologically relevant interpretation of genomewide transcriptomic
data. Adopting ICA as the analysis tool of choice will help understand
the phenotype-pathway relationship and thus help elucidate the molecular
taxonomy of heterogeneous cancers and of other complex genetic diseases.},
keywords = {Independent Component Analysis},
url = {http://www.ploscompbiol.org/article/info:doi/10.1371/journal.pcbi.0030161}
}
@ARTICLE{Saidi2004Independent,
author = {{S}aidi, {S}. {A}. and {H}olland, {C}. {M}. and {K}reil, {D}. {P}.
and {M}ac{K}ay, {D}. {J}. and {C}harnock-{J}ones, {D}. {S}. and {P}rint,
{C}. {G}. and {S}mith, {S}. {K}.},
title = {{Independent component analysis of microarray data in the study of
endometrial cancer}},
journal = {{O}ncogene},
year = {2004},
volume = {23},
pages = {6677--6683},
month = {Aug},
abstract = {Gene microarray technology is highly effective in screening for differential
gene expression and has hence become a popular tool in the molecular
investigation of cancer. When applied to tumours, molecular characteristics
may be correlated with clinical features such as response to chemotherapy.
Exploitation of the huge amount of data generated by microarrays
is difficult, however, and constitutes a major challenge in the advancement
of this methodology. Independent component analysis (ICA), a modern
statistical method, allows us to better understand data in such complex
and noisy measurement environments. The technique has the potential
to significantly increase the quality of the resulting data and improve
the biological validity of subsequent analysis. We performed microarray
experiments on 31 postmenopausal endometrial biopsies, comprising
11 benign and 20 malignant samples. We compared ICA to the established
methods of principal component analysis (PCA), Cyber-T, and SAM.
We show that ICA generated patterns that clearly characterized the
malignant samples studied, in contrast to PCA. Moreover, ICA improved
the biological validity of the genes identified as differentially
expressed in endometrial carcinoma, compared to those found by Cyber-T
and SAM. In particular, several genes involved in lipid metabolism
that are differentially expressed in endometrial carcinoma were only
found using this method. This report highlights the potential of
ICA in the analysis of microarray data.},
keywords = {Independent Component Analysis}
}
@ARTICLE{Frigyesi2006Independent,
author = {{F}rigyesi, {A}. and {V}eerla, {S}. and {L}indgren, {D}. and {H}oglund,
{M}.},
title = {{Independent component analysis reveals new and biologically significant
structures in micro array data}},
journal = {{BMC} {B}ioinformatics},
year = {2006},
volume = {7},
pages = {290},
abstract = {BACKGROUND: An alternative to standard approaches to uncover biologically
meaningful structures in micro array data is to treat the data as
a blind source separation (BSS) problem. BSS attempts to separate
a mixture of signals into their different sources and refers to the
problem of recovering signals from several observed linear mixtures.
In the context of micro array data, "sources" may correspond to specific
cellular responses or to co-regulated genes. RESULTS: We applied
independent component analysis (ICA) to three different microarray
data sets; two tumor data sets and one time series experiment. To
obtain reliable components we used iterated ICA to estimate component
centrotypes. We found that many of the low ranking components indeed
may show a strong biological coherence and hence be of biological
significance. Generally ICA achieved a higher resolution when compared
with results based on correlated expression and a larger number of
gene clusters with significantly enriched for gene ontology (GO)
categories. In addition, components characteristic for molecular
subtypes and for tumors with specific chromosomal translocations
were identified. ICA also identified more than one gene clusters
significant for the same GO categories and hence disclosed a higher
level of biological heterogeneity, even within coherent groups of
genes. CONCLUSION: Although the ICA approach primarily detects hidden
variables, these surfaced as highly correlated genes in time series
data and in one instance in the tumor data. This further strengthens
the biological relevance of latent variables detected by ICA.},
keywords = {Independent Component Analysis},
url = {http://www.ncbi.nlm.nih.gov/pubmed/16762055}
}
@ARTICLE{Himberg2004Validating,
author = {{J}ohan {H}imberg and {A}apo {H}yvärinen and {F}abrizio {E}sposito},
title = {{V}alidating the independent components of neuroimaging time series
via clustering and visualization.},
journal = {{N}euroimage},
year = {2004},
volume = {22},
pages = {1214--1222},
number = {3},
month = {Jul},
abstract = {Recently, independent component analysis (ICA) has been widely used
in the analysis of brain imaging data. An important problem with
most ICA algorithms is, however, that they are stochastic; that is,
their results may be somewhat different in different runs of the
algorithm. Thus, the outputs of a single run of an ICA algorithm
should be interpreted with some reserve, and further analysis of
the algorithmic reliability of the components is needed. Moreover,
as with any statistical method, the results are affected by the random
sampling of the data, and some analysis of the statistical significance
or reliability should be done as well. Here we present a method for
assessing both the algorithmic and statistical reliability of estimated
independent components. The method is based on running the ICA algorithm
many times with slightly different conditions and visualizing the
clustering structure of the obtained components in the signal space.
In experiments with magnetoencephalographic (MEG) and functional
magnetic resonance imaging (fMRI) data, the method was able to show
that expected components are reliable; furthermore, it pointed out
components whose interpretation was not obvious but whose reliability
should incite the experimenter to investigate the underlying technical
or physical phenomena. The method is implemented in a software package
called Icasso.},
doi = {10.1016/j.neuroimage.2004.03.027},
institution = {Neural Networks Research Centre, Helsinki University of Technology,
Helsinki, Finland.},
keywords = {Algorithms; Brain; Cluster Analysis; Data Interpretation, Statistical;
Fingers; Humans; Image Processing, Computer-Assisted; Magnetic Resonance
Imaging; Magnetoencephalography; Models, Neurological; Motor Activity;
Software, Independent Component Analysis},
owner = {abiton},
pii = {S1053811904001661},
pmid = {15219593},
timestamp = {2010.11.10},
url = {http://dx.doi.org/10.1016/j.neuroimage.2004.03.027}
}
@ARTICLE{Cline2007Integration,
author = {{M}elissa {S} {C}line and {M}ichael {S}moot and {E}than {C}erami
and {A}llan {K}uchinsky and {N}erius {L}andys and {C}hris {W}orkman
and {R}owan {C}hristmas and {I}liana {A}vila-{C}ampilo and {M}ichael
{C}reech and {B}enjamin {G}ross and {K}ristina {H}anspers and {R}uth
{I}sserlin and {R}yan {K}elley and {S}arah {K}illcoyne and {S}amad
{L}otia and {S}teven {M}aere and {J}ohn {M}orris and {K}eiichiro
{O}no and {V}uk {P}avlovic and {A}lexander {R} {P}ico and {A}ditya
{V}ailaya and {P}eng-{L}iang {W}ang and {A}nnette {A}dler and {B}ruce
{R} {C}onklin and {L}eroy {H}ood and {M}artin {K}uiper and {C}hris
{S}ander and {I}lya {S}chmulevich and {B}enno {S}chwikowski and {G}uy
{J} {W}arner and {T}rey {I}deker and {G}ary {D} {B}ader},
title = {{I}ntegration of biological networks and gene expression data using
{C}ytoscape.},
journal = {{N}at {P}rotoc},
year = {2007},
volume = {2},
pages = {2366--2382},
number = {10},
abstract = {Cytoscape is a free software package for visualizing, modeling and
analyzing molecular and genetic interaction networks. This protocol
explains how to use Cytoscape to analyze the results of mRNA expression
profiling, and other functional genomics and proteomics experiments,
in the context of an interaction network obtained for genes of interest.
Five major steps are described: (i) obtaining a gene or protein network,
(ii) displaying the network using layout algorithms, (iii) integrating
with gene expression and other functional attributes, (iv) identifying
putative complexes and functional modules and (v) identifying enriched
Gene Ontology annotations in the network. These steps provide a broad
sample of the types of analyses performed by Cytoscape.},
doi = {10.1038/nprot.2007.324},
institution = {Institut Pasteur, 25-28 rue du Docteur Roux, 75724 Paris cedex 15,
France.},
keywords = {Computational Biology; Gene Expression Profiling; Gene Regulatory
Networks; Genomics; Proteomics; RNA, Messenger; Software},
owner = {abiton},
pii = {nprot.2007.324},
pmid = {17947979},
timestamp = {2011.01.04},
url = {http://dx.doi.org/10.1038/nprot.2007.324}
}
