@article {21479216, title = {Analysis of normal-tumour tissue interaction in tumours: prediction of prostate cancer features from the molecular profile of adjacent normal cells.}, journal = {PloS one}, volume = {6}, year = {2011}, month = {2011}, pages = {e16492}, abstract = {

Statistical modelling, in combination with genome-wide expression profiling techniques, has demonstrated that the molecular state of the tumour is sufficient to infer its pathological state. These studies have been extremely important in diagnostics and have contributed to improving our understanding of tumour biology. However, their importance in in-depth understanding of cancer patho-physiology may be limited since they do not explicitly take into consideration the fundamental role of the tissue microenvironment in specifying tumour physiology. Because of the importance of normal cells in shaping the tissue microenvironment we formulate the hypothesis that molecular components of the profile of normal epithelial cells adjacent the tumour are predictive of tumour physiology. We addressed this hypothesis by developing statistical models that link gene expression profiles representing the molecular state of adjacent normal epithelial cells to tumour features in prostate cancer. Furthermore, network analysis showed that predictive genes are linked to the activity of important secreted factors, which have the potential to influence tumor biology, such as IL1, IGF1, PDGF BB, AGT, and TGF\β.

}, author = {Trevino, Victor and Tadesse, Mahlet G and Vannucci, Marina and Fatima Al-Shahrour and Antczak, Philipp and Durant, Sarah and Bikfalvi, Andreas and Dopazo, Joaquin and Campbell, Moray J and Falciani, Francesco} } @article {850, title = {A large scale survey reveals that chromosomal copy-number alterations significantly affect gene modules involved in cancer initiation and progression}, journal = {BMC Medical Genomics}, volume = {4}, year = {2011}, month = {06/05/2011}, pages = {37}, type = {Research article}, abstract = {

Background

Recent observations point towards the existence of a large number of neighborhoods composed of functionally-related gene modules that lie together in the genome. This local component in the distribution of the functionality across chromosomes is probably affecting the own chromosomal architecture by limiting the possibilities in which genes can be arranged and distributed across the genome. As a direct consequence of this fact it is therefore presumable that diseases such as cancer, harboring DNA copy number alterations (CNAs), will have a symptomatology strongly dependent on modules of functionally-related genes rather than on a unique \"important\" gene.

Methods

We carried out a systematic analysis of more than 140,000 observations of CNAs in cancers and searched by enrichments in gene functional modules associated to high frequencies of loss or gains.

Results

The analysis of CNAs in cancers clearly demonstrates the existence of a significant pattern of loss of gene modules functionally related to cancer initiation and progression along with the amplification of modules of genes related to unspecific defense against xenobiotics (probably chemotherapeutical agents). With the extension of this analysis to an Array-CGH dataset (glioblastomas) from The Cancer Genome Atlas we demonstrate the validity of this approach to investigate the functional impact of CNAs.

Conclusions

The presented results indicate promising clinical and therapeutic implications. Our findings also directly point out to the necessity of adopting a function-centric, rather a gene-centric, view in the understanding of phenotypes or diseases harboring CNAs.

}, issn = {1755-8794}, doi = {10.1186/1755-8794-4-37}, url = {http://www.biomedcentral.com/1755-8794/4/37}, author = {Alloza, E. and Fatima Al-Shahrour and Cigudosa, J. C. and Dopazo, J.} } @article {20028698, title = {Changes in the pattern of DNA methylation associate with twin discordance in systemic lupus erythematosus.}, journal = {Genome research}, volume = {20}, year = {2010}, month = {2010 Feb}, pages = {170-9}, abstract = {

Monozygotic (MZ) twins are partially concordant for most complex diseases, including autoimmune disorders. Whereas phenotypic concordance can be used to study heritability, discordance suggests the role of non-genetic factors. In autoimmune diseases, environmentally driven epigenetic changes are thought to contribute to their etiology. Here we report the first high-throughput and candidate sequence analyses of DNA methylation to investigate discordance for autoimmune disease in twins. We used a cohort of MZ twins discordant for three diseases whose clinical signs often overlap: systemic lupus erythematosus (SLE), rheumatoid arthritis, and dermatomyositis. Only MZ twins discordant for SLE featured widespread changes in the DNA methylation status of a significant number of genes. Gene ontology analysis revealed enrichment in categories associated with immune function. Individual analysis confirmed the existence of DNA methylation and expression changes in genes relevant to SLE pathogenesis. These changes occurred in parallel with a global decrease in the 5-methylcytosine content that was concomitantly accompanied with changes in DNA methylation and expression levels of ribosomal RNA genes, although no changes in repetitive sequences were found. Our findings not only identify potentially relevant DNA methylation markers for the clinical characterization of SLE patients but also support the notion that epigenetic changes may be critical in the clinical manifestations of autoimmune disease.

}, author = {Javierre, Biola M and Fernandez, Agustin F and Richter, Julia and Fatima Al-Shahrour and Martin-Subero, J Ignacio and Rodriguez-Ubreva, Javier and Berdasco, Maria and Fraga, Mario F and O{\textquoteright}Hanlon, Terrance P and Rider, Lisa G and Jacinto, Filipe V and Lopez-Longo, F Javier and Dopazo, Joaquin and Forn, Marta and Peinado, Miguel A and Carre{\~n}o, Luis and Sawalha, Amr H and Harley, John B and Siebert, Reiner and Esteller, Manel and Miller, Frederick W and Ballestar, Esteban} } @article {19246752, title = {Exploring the antimicrobial action of a carbon monoxide-releasing compound through whole-genome transcription profiling of Escherichia coli}, journal = {Microbiology}, volume = {155}, number = {Pt 3}, year = {2009}, note = {

Nobre, Ligia S Al-Shahrour, Fatima Dopazo, Joaquin Saraiva, Ligia M Research Support, Non-U.S. Gov{\textquoteright}t England Microbiology (Reading, England) Microbiology. 2009 Mar;155(Pt 3):813-24.

}, pages = {813-24}, abstract = {

We recently reported that carbon monoxide (CO) has bactericidal activity. To understand its mode of action we analysed the gene expression changes occurring when Escherichia coli, grown aerobically and anaerobically, is treated with the CO-releasing molecule CORM-2 (tricarbonyldichlororuthenium(II) dimer). Microarray analysis shows that the E. coli CORM-2 response is multifaceted, with a high number of differentially regulated genes spread through several functional categories, namely genes involved in inorganic ion transport and metabolism, regulators, and genes implicated in post-translational modification, such as chaperones. CORM-2 has a higher impact in E. coli cells grown anaerobically, as judged by the repression of genes belonging to eight functional classes which are not seen in the response of aerobically CORM-2-treated cells. The biological relevance of the variations caused by CORM-2 was substantiated by studying the CORM-2 sensitivity of selected E. coli mutants. The results show that the deletion of redox-sensing regulators SoxS and OxyR increased the sensitivity to CORM-2 and suggest that while SoxS plays an important role in protection against CORM-2 under both growth conditions, OxyR seems to participate only in the aerobic CORM-2 response. Under anaerobic conditions, we found that the heat-shock proteins IbpA and IbpB contribute to CORM-2 defence since the deletion of these genes increases the sensitivity of the strain. The induction of several met genes and the hypersensitivity to CORM-2 of the DeltametR, DeltametI and DeltametN mutant strains suggest that CO has effects on the methionine metabolism of E. coli. CORM-2 also affects the transcription of several E. coli biofilm-related genes and increases biofilm formation in E. coli. In particular, the absence of tqsA or bhsA increases the resistance of E. coli to CORM-2, and deletion of tsqA leads to a strain that has lost its capacity to form biofilm upon treatment with CORM-2. In spite of the relatively stable nature of the CO molecule, our results show that CO is able to trigger a significant alteration in the transcriptome of E. coli which necessarily has effects in several key metabolic pathways.

}, keywords = {Bacterial Genes, Bacterial/genetics, Biofilms Carbon Monoxide/*metabolism Escherichia coli/*genetics/metabolism Escherichia coli Proteins/genetics/metabolism *Gene Expression Profiling Gene Expression Regulation, Regulator Genetic Complementation Test Methionine/metabolism Microbial Viability Mutation Oligonucleotide Array Sequence Analysis Organometallic Compounds/*pharmacology Phenotype RNA}, url = {http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?cmd=Retrieve\&db=PubMed\&dopt=Citation\&list_uids=19246752}, author = {Nobre, L. S. and Fatima Al-Shahrour and Dopazo, J. and Saraiva, L. M.} } @article {IgnacioMedina07012009, title = {Gene set-based analysis of polymorphisms: finding pathways or biological processes associated to traits in genome-wide association studies}, journal = {Nucl. Acids Res.}, volume = {37}, number = {suppl_2}, year = {2009}, pages = {W340-344}, abstract = {

Genome-wide association studies have become a popular strategy to find associations of genes to traits of interest. Despite the high-resolution available today to carry out genotyping studies, the success of its application in real studies has been limited by the testing strategy used. As an alternative to brute force solutions involving the use of very large cohorts, we propose the use of the Gene Set Analysis (GSA), a different analysis strategy based on testing the association of modules of functionally related genes. We show here how the Gene Set-based Analysis of Polymorphisms (GeSBAP), which is a simple implementation of the GSA strategy for the analysis of genome-wide association studies, provides a significant increase in the power testing for this type of studies. GeSBAP is freely available at http://bioinfo.cipf.es/gesbap/

}, keywords = {babelomics, gene set, GESBAP, pathway-based analysis, SNP}, doi = {10.1093/nar/gkp481}, url = {http://nar.oxfordjournals.org/cgi/content/abstract/37/suppl_2/W340}, author = {Medina, Ignacio and Montaner, David and Bonifaci, N{\'u}ria and Pujana, Miguel Angel and Carbonell, Jos{\'e} and T{\'a}rraga, Joaqu{\'\i}n and Fatima Al-Shahrour and Dopazo, Joaquin} } @article {PabloMinguez05192009, title = {SNOW, a web-based tool for the statistical analysis of protein-protein interaction networks}, journal = {Nucl. Acids Res.}, volume = {37}, year = {2009}, pages = {W109-114}, abstract = {

Understanding the structure and the dynamics of the complex intercellular network of interactions that contributes to the structure and function of a living cell is one of the main challenges of today{\textquoteright}s biology. SNOW inputs a collection of protein (or gene) identifiers and, by using the interactome as scaffold, draws the connections among them, calculates several relevant network parameters and, as a novelty among the rest of tools of its class, it estimates their statistical significance. The parameters calculated for each node are: connectivity, betweenness and clustering coefficient. It also calculates the number of components, number of bicomponents and articulation points. An interactive network viewer is also available to explore the resulting network. SNOW is available at http://snow.bioinfo.cipf.es.

}, keywords = {interactome, network, snow}, doi = {10.1093/nar/gkp402}, url = {http://nar.oxfordjournals.org/content/early/2009/05/19/nar.gkp402.full}, author = {Minguez, Pablo and Gotz, S. and Montaner, David and Fatima Al-Shahrour and Dopazo, Joaquin} } @article {18515841, title = {Babelomics: advanced functional profiling of transcriptomics, proteomics and genomics experiments}, journal = {Nucleic Acids Res}, volume = {36}, year = {2008}, note = {

Al-Shahrour, Fatima Carbonell, Jose Minguez, Pablo Goetz, Stefan Conesa, Ana Tarraga, Joaquin Medina, Ignacio Alloza, Eva Montaner, David Dopazo, Joaquin Research Support, Non-U.S. Gov{\textquoteright}t England Nucleic acids research Nucleic Acids Res. 2008 Jul 1;36(Web Server issue):W341-6. Epub 2008 May 31.

}, pages = {W341-6}, abstract = {

We present a new version of Babelomics, a complete suite of web tools for the functional profiling of genome scale experiments, with new and improved methods as well as more types of functional definitions. Babelomics includes different flavours of conventional functional enrichment methods as well as more advanced gene set analysis methods that makes it a unique tool among the similar resources available. In addition to the well-known functional definitions (GO, KEGG), Babelomics includes new ones such as Biocarta pathways or text mining-derived functional terms. Regulatory modules implemented include transcriptional control (Transfac, CisRed) and other levels of regulation such as miRNA-mediated interference. Moreover, Babelomics allows for sub-selection of terms in order to test more focused hypothesis. Also gene annotation correspondence tables can be imported, which allows testing with user-defined functional modules. Finally, a tool for the {\textquoteright}de novo{\textquoteright} functional annotation of sequences has been included in the system. This allows using yet unannotated organisms in the program. Babelomics has been extensively re-engineered and now it includes the use of web services and Web 2.0 technology features, a new user interface with persistent sessions and a new extended database of gene identifiers. Babelomics is available at http://www.babelomics.org.

}, keywords = {babelomics, funtional profiling}, url = {http://nar.oxfordjournals.org/content/36/suppl_2/W341.long}, author = {Fatima Al-Shahrour and Carbonell, J. and Minguez, P. and Goetz, S. and A. Conesa and Tarraga, J. and Medina, Ignacio and Alloza, E. and Montaner, D. and Dopazo, J.} } @article {18508806, title = {GEPAS, a web-based tool for microarray data analysis and interpretation}, journal = {Nucleic Acids Res}, volume = {36}, year = {2008}, note = {

Tarraga, Joaquin Medina, Ignacio Carbonell, Jose Huerta-Cepas, Jaime Minguez, Pablo Alloza, Eva Al-Shahrour, Fatima Vegas-Azcarate, Susana Goetz, Stefan Escobar, Pablo Garcia-Garcia, Francisco Conesa, Ana Montaner, David Dopazo, Joaquin Research Support, Non-U.S. Gov{\textquoteright}t England Nucleic acids research Nucleic Acids Res. 2008 Jul 1;36(Web Server issue):W308-14. Epub 2008 May 28.

}, pages = {W308-14}, abstract = {

Gene Expression Profile Analysis Suite (GEPAS) is one of the most complete and extensively used web-based packages for microarray data analysis. During its more than 5 years of activity it has continuously been updated to keep pace with the state-of-the-art in the changing microarray data analysis arena. GEPAS offers diverse analysis options that include well established as well as novel algorithms for normalization, gene selection, class prediction, clustering and functional profiling of the experiment. New options for time-course (or dose-response) experiments, microarray-based class prediction, new clustering methods and new tests for differential expression have been included. The new pipeliner module allows automating the execution of sequential analysis steps by means of a simple but powerful graphic interface. An extensive re-engineering of GEPAS has been carried out which includes the use of web services and Web 2.0 technology features, a new user interface with persistent sessions and a new extended database of gene identifiers. GEPAS is nowadays the most quoted web tool in its field and it is extensively used by researchers of many countries and its records indicate an average usage rate of 500 experiments per day. GEPAS, is available at http://www.gepas.org.

}, keywords = {gepas, microarray data analysis}, url = {http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?cmd=Retrieve\&db=PubMed\&dopt=Citation\&list_uids=18508806}, author = {Tarraga, J. and Medina, Ignacio and Carbonell, J. and Huerta-Cepas, J. and Minguez, P. and Alloza, E. and Fatima Al-Shahrour and Vegas-Azcarate, S. and Goetz, S. and Escobar, P. and Garcia-Garcia, F. and A. Conesa and Montaner, D. and Dopazo, J.} } @article {17570147, title = {The AnnoLite and AnnoLyze programs for comparative annotation of protein structures}, journal = {BMC Bioinformatics}, volume = {8 Suppl 4}, year = {2007}, note = {Marti-Renom, Marc A Rossi, Andrea Al-Shahrour, Fatima Davis, Fred P Pieper, Ursula Dopazo, Joaquin Sali, Andrej Research Support, Non-U.S. Gov{\textquoteright}t England BMC bioinformatics BMC Bioinformatics. 2007 May 22;8 Suppl 4:S4.}, pages = {S4}, abstract = {BACKGROUND: Advances in structural biology, including structural genomics, have resulted in a rapid increase in the number of experimentally determined protein structures. However, about half of the structures deposited by the structural genomics consortia have little or no information about their biological function. Therefore, there is a need for tools for automatically and comprehensively annotating the function of protein structures. We aim to provide such tools by applying comparative protein structure annotation that relies on detectable relationships between protein structures to transfer functional annotations. Here we introduce two programs, AnnoLite and AnnoLyze, which use the structural alignments deposited in the DBAli database. DESCRIPTION: AnnoLite predicts the SCOP, CATH, EC, InterPro, PfamA, and GO terms with an average sensitivity of 90\% and average precision of 80\%. AnnoLyze predicts ligand binding site and domain interaction patches with an average sensitivity of 70\% and average precision of 30\%, correctly localizing binding sites for small molecules in 95\% of its predictions. CONCLUSION: The AnnoLite and AnnoLyze programs for comparative annotation of protein structures can reliably and automatically annotate new protein structures. The programs are fully accessible via the Internet as part of the DBAli suite of tools at http://salilab.org/DBAli/.}, keywords = {*Algorithms Amino Acid Sequence Confidence Intervals Data Interpretation, Amino Acid *Software Structure-Activity Relationship, Protein Information Storage and Retrieval/methods Molecular Sequence Data Proteins/*chemistry/classification/*metabolism Sensitivity and Specificity Sequence Alignment/*methods Sequence Analysis, Protein/*methods Sequence Homology, Statistical *Databases}, url = {http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?cmd=Retrieve\&db=PubMed\&dopt=Citation\&list_uids=17570147}, author = {M. A. Marti-Renom and Rossi, A. and Fatima Al-Shahrour and Davis, F. P. and Pieper, U. and Dopazo, J. and Sali, A.} } @article {17478513, title = {DBAli tools: mining the protein structure space}, journal = {Nucleic Acids Res}, volume = {35}, number = {Web Server issue}, year = {2007}, note = {Marti-Renom, Marc A Pieper, Ursula Madhusudhan, M S Rossi, Andrea Eswar, Narayanan Davis, Fred P Al-Shahrour, Fatima Dopazo, Joaquin Sali, Andrej GM 62529/GM/NIGMS NIH HHS/United States GM074929/GM/NIGMS NIH HHS/United States GM54762/GM/NIGMS NIH HHS/United States GM71790/GM/NIGMS NIH HHS/United States Research Support, N.I.H., Extramural Research Support, Non-U.S. Gov{\textquoteright}t England Nucleic acids research Nucleic Acids Res. 2007 Jul;35(Web Server issue):W393-7. Epub 2007 May 3.}, pages = {W393-7}, abstract = {The DBAli tools use a comprehensive set of structural alignments in the DBAli database to leverage the structural information deposited in the Protein Data Bank (PDB). These tools include (i) the DBAlit program that allows users to input the 3D coordinates of a protein structure for comparison by MAMMOTH against all chains in the PDB; (ii) the AnnoLite and AnnoLyze programs that annotate a target structure based on its stored relationships to other structures; (iii) the ModClus program that clusters structures by sequence and structure similarities; (iv) the ModDom program that identifies domains as recurrent structural fragments and (v) an implementation of the COMPARER method in the SALIGN command in MODELLER that creates a multiple structure alignment for a set of related protein structures. Thus, the DBAli tools, which are freely accessible via the World Wide Web at http://salilab.org/DBAli/, allow users to mine the protein structure space by establishing relationships between protein structures and their functions.}, keywords = {*Algorithms Amino Acid Sequence Computational Biology/*methods Data Interpretation, Amino Acid *Software Structure-Activity Relationship, Protein Internet Molecular Sequence Data Protein Conformation Proteins/*chemistry/classification/*metabolism Pseudomonas aeruginosa/*metabolism Sequence Alignment/*methods Sequence Analysis, Protein/*methods Sequence Homology, Statistical *Databases}, url = {http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?cmd=Retrieve\&db=PubMed\&dopt=Citation\&list_uids=17478513}, author = {M. A. Marti-Renom and Pieper, U. and Madhusudhan, M. S. and Rossi, A. and Eswar, N. and Davis, F. P. and Fatima Al-Shahrour and Dopazo, J. and Sali, A.} } @article {17584915, title = {Evidence for systems-level molecular mechanisms of tumorigenesis}, journal = {BMC Genomics}, volume = {8}, year = {2007}, note = {Hernandez, Pilar Huerta-Cepas, Jaime Montaner, David Al-Shahrour, Fatima Valls, Joan Gomez, Laia Capella, Gabriel Dopazo, Joaquin Pujana, Miguel Angel Research Support, Non-U.S. Gov{\textquoteright}t England BMC genomics BMC Genomics. 2007 Jun 20;8:185.}, pages = {185}, abstract = {BACKGROUND: Cancer arises from the consecutive acquisition of genetic alterations. Increasing evidence suggests that as a consequence of these alterations, molecular interactions are reprogrammed in the context of highly connected and regulated cellular networks. Coordinated reprogramming would allow the cell to acquire the capabilities for malignant growth. RESULTS: Here, we determine the coordinated function of cancer gene products (i.e., proteins encoded by differentially expressed genes in tumors relative to healthy tissue counterparts, hereafter referred to as "CGPs") defined as their topological properties and organization in the interactome network. We show that CGPs are central to information exchange and propagation and that they are specifically organized to promote tumorigenesis. Centrality is identified by both local (degree) and global (betweenness and closeness) measures, and systematically appears in down-regulated CGPs. Up-regulated CGPs do not consistently exhibit centrality, but both types of cancer products determine the overall integrity of the network structure. In addition to centrality, down-regulated CGPs show topological association that correlates with common biological processes and pathways involved in tumorigenesis. CONCLUSION: Given the current limited coverage of the human interactome, this study proposes that tumorigenesis takes place in a specific and organized way at the molecular systems-level and suggests a model that comprises the precise down-regulation of groups of topologically-associated proteins involved in particular functions, orchestrated with the up-regulation of specific proteins.}, keywords = {*Cell Transformation, Biological Models, Genetic Models, Messenger/metabolism Signal Transduction Systems Biology, Neoplastic *Gene Expression Profiling *Gene Expression Regulation, Neoplastic Humans Male Models, Statistical Neoplasm Proteins/*physiology Neoplasms/etiology/*genetics Prostatic Neoplasms/genetics Protein Interaction Mapping RNA}, url = {http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?cmd=Retrieve\&db=PubMed\&dopt=Citation\&list_uids=17584915}, author = {Hernandez, P. and Huerta-Cepas, J. and Montaner, D. and Fatima Al-Shahrour and Valls, J. and Gomez, L. and Capella, G. and Dopazo, J. and Pujana, M. A.} } @article {17478504, title = {FatiGO +: a functional profiling tool for genomic data. Integration of functional annotation, regulatory motifs and interaction data with microarray experiments}, journal = {Nucleic Acids Res}, volume = {35}, number = {Web Server issue}, year = {2007}, note = {

Al-Shahrour, Fatima Minguez, Pablo Tarraga, Joaquin Medina, Ignacio Alloza, Eva Montaner, David Dopazo, Joaquin Research Support, Non-U.S. Gov{\textquoteright}t England Nucleic acids research Nucleic Acids Res. 2007 Jul;35(Web Server issue):W91-6. Epub 2007 May 3.

}, pages = {W91-6}, abstract = {

The ultimate goal of any genome-scale experiment is to provide a functional interpretation of the data, relating the available information with the hypotheses that originated the experiment. Thus, functional profiling methods have become essential in diverse scenarios such as microarray experiments, proteomics, etc. We present the FatiGO+, a web-based tool for the functional profiling of genome-scale experiments, specially oriented to the interpretation of microarray experiments. In addition to different functional annotations (gene ontology, KEGG pathways, Interpro motifs, Swissprot keywords and text-mining based bioentities related to diseases and chemical compounds) FatiGO+ includes, as a novelty, regulatory and structural information. The regulatory information used includes predictions of targets for distinct regulatory elements (obtained from the Transfac and CisRed databases). Additionally FatiGO+ uses predictions of target motifs of miRNA to infer which of these can be activated or deactivated in the sample of genes studied. Finally, properties of gene products related to their relative location and connections in the interactome have also been used. Also, enrichment of any of these functional terms can be directly analysed on chromosomal coordinates. FatiGO+ can be found at: http://www.fatigoplus.org and within the Babelomics environment http://www.babelomics.org.

}, keywords = {babelomics, functional enrichment analysys}, url = {http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?cmd=Retrieve\&db=PubMed\&dopt=Citation\&list_uids=17478504}, author = {Fatima Al-Shahrour and Minguez, P. and Tarraga, J. and Medina, Ignacio and Alloza, E. and Montaner, D. and Dopazo, J.} } @article {17407596, title = {From genes to functional classes in the study of biological systems}, journal = {BMC Bioinformatics}, volume = {8}, year = {2007}, note = {

Al-Shahrour, Fatima Arbiza, Leonardo Dopazo, Hernan Huerta-Cepas, Jaime Minguez, Pablo Montaner, David Dopazo, Joaquin Research Support, Non-U.S. Gov{\textquoteright}t England BMC bioinformatics BMC Bioinformatics. 2007 Apr 3;8:114.

}, pages = {114}, abstract = {

BACKGROUND: With the popularization of high-throughput techniques, the need for procedures that help in the biological interpretation of results has increased enormously. Recently, new procedures inspired in systems biology criteria have started to be developed. RESULTS: Here we present FatiScan, a web-based program which implements a threshold-independent test for the functional interpretation of large-scale experiments that does not depend on the pre-selection of genes based on the multiple application of independent tests to each gene. The test implemented aims to directly test the behaviour of blocks of functionally related genes, instead of focusing on single genes. In addition, the test does not depend on the type of the data used for obtaining significance values, and consequently different types of biologically informative terms (gene ontology, pathways, functional motifs, transcription factor binding sites or regulatory sites from CisRed) can be applied to different classes of genome-scale studies. We exemplify its application in microarray gene expression, evolution and interactomics. CONCLUSION: Methods for gene set enrichment which, in addition, are independent from the original data and experimental design constitute a promising alternative for the functional profiling of genome-scale experiments. A web server that performs the test described and other similar ones can be found at: http://www.babelomics.org.

}, keywords = {Algorithms Chromosome Mapping/*methods Computer Simulation Gene Expression Profiling/methods *Models, babelomics, Biological Multigene Family/*physiology Signal Transduction/*physiology *Software Systems Biology/*methods *User-Computer Interface}, url = {http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?cmd=Retrieve\&db=PubMed\&dopt=Citation\&list_uids=17407596}, author = {Fatima Al-Shahrour and Arbiza, L. and H. Dopazo and Huerta-Cepas, J. and Minguez, P. and Montaner, D. and Dopazo, J.} } @inbook {478, title = {Functional annotation of microarray experiments}, booktitle = {Microarray Technology Through Applications}, year = {2007}, publisher = {Taylor \& Francis, F. Falciani}, organization = {Taylor \& Francis, F. Falciani}, address = {New York, USA}, author = {Dopazo, J. and Fatima Al-Shahrour} } @article {17597935, title = {Functional profiling and gene expression analysis of chromosomal copy number alterations}, journal = {Bioinformation}, volume = {1}, number = {10}, year = {2007}, note = {

Conde, Lucia Montaner, David Burguet-Castell, Jordi Tarraga, Joaquin Al-Shahrour, Fatima Dopazo, Joaquin Singapore Bioinformation Bioinformation. 2007 Apr 10;1(10):432-5.

}, pages = {432-5}, abstract = {

Contrarily to the traditional view in which only one or a few key genes were supposed to be the causative factors of diseases, we discuss the importance of considering groups of functionally related genes in the study of pathologies characterised by chromosomal copy number alterations. Recent observations have reported the existence of regions in higher eukaryotic chromosomes (including humans) containing genes of related function that show a high degree of coregulation. Copy number alterations will consequently affect to clusters of functionally related genes, which will be the final causative agents of the diseased phenotype, in many cases. Therefore, we propose that the functional profiling of the regions affected by copy number alterations must be an important aspect to take into account in the understanding of this type of pathologies. To illustrate this, we present an integrated study of DNA copy number variations, gene expression along with the functional profiling of chromosomal regions in a case of multiple myeloma.

}, keywords = {babelomics}, url = {http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?cmd=Retrieve\&db=PubMed\&dopt=Citation\&list_uids=17597935}, author = {L. Conde and Montaner, D. and Burguet-Castell, J. and Tarraga, J. and Fatima Al-Shahrour and Dopazo, J.} } @article {17855415, title = {Functional profiling of microarray experiments using text-mining derived bioentities}, journal = {Bioinformatics}, volume = {23}, number = {22}, year = {2007}, note = {

Minguez, Pablo Al-Shahrour, Fatima Montaner, David Dopazo, Joaquin Research Support, Non-U.S. Gov{\textquoteright}t England Bioinformatics (Oxford, England) Bioinformatics. 2007 Nov 15;23(22):3098-9. Epub 2007 Sep 13.

}, pages = {3098-9}, abstract = {

MOTIVATION: The increasing use of microarray technologies brought about a parallel demand in methods for the functional interpretation of the results. Beyond the conventional functional annotations for genes, such as gene ontology, pathways, etc. other sources of information are still to be exploited. Text-mining methods allow extracting informative terms (bioentities) with different functional, chemical, clinical, etc. meanings, that can be associated to genes. We show how to use these associations within an appropriate statistical framework and how to apply them through easy-to-use, web-based environments to the functional interpretation of microarray experiments. Functional enrichment and gene set enrichment tests using bioentities are presented.

}, keywords = {Artificial Intelligence *Databases, babelomics, Protein Gene Expression Profiling/*methods Information Storage and Retrieval/*methods *Natural Language Processing Proteins/*classification/*metabolism Research/*methods Systems Integration}, url = {http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?cmd=Retrieve\&db=PubMed\&dopt=Citation\&list_uids=17855415}, author = {Minguez, P. and Fatima Al-Shahrour and Montaner, D. and Dopazo, J.} } @article {17468499, title = {ISACGH: a web-based environment for the analysis of Array CGH and gene expression which includes functional profiling}, journal = {Nucleic Acids Res}, volume = {35}, number = {Web Server issue}, year = {2007}, note = {Conde, Lucia Montaner, David Burguet-Castell, Jordi Tarraga, Joaquin Medina, Ignacio Al-Shahrour, Fatima Dopazo, Joaquin Research Support, Non-U.S. Gov{\textquoteright}t England Nucleic acids research Nucleic Acids Res. 2007 Jul;35(Web Server issue):W81-5. Epub 2007 Apr 27.}, pages = {W81-5}, abstract = {We present the ISACGH, a web-based system that allows for the combination of genomic data with gene expression values and provides different options for functional profiling of the regions found. Several visualization options offer a convenient representation of the results. Different efficient methods for accurate estimation of genomic copy number from array-CGH hybridization data have been included in the program. Moreover, the connection to the gene expression analysis package GEPAS allows the use of different facilities for data pre-processing and analysis. A DAS server allows exporting the results to the Ensembl viewer where contextual genomic information can be obtained. The program is freely available at: http://isacgh.bioinfo.cipf.es or within http://www.gepas.org.}, keywords = {Animals Cluster Analysis Computational Biology/*methods Computer Graphics Gene Expression Profiling/*methods Humans Internet Models, Genetic *Nucleic Acid Hybridization Oligonucleotide Array Sequence Analysis/*methods Programming Languages *Software Systems Integration User-Computer Interface}, url = {http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?cmd=Retrieve\&db=PubMed\&dopt=Citation\&list_uids=17468499}, author = {L. Conde and Montaner, D. and Burguet-Castell, J. and Tarraga, J. and Medina, Ignacio and Fatima Al-Shahrour and Dopazo, J.} } @inbook {680, title = {New Trends in the Analysis of Functional Genomic Data}, booktitle = {Progress in Industrial Mathematics at ECMI 2006}, volume = {12}, year = {2007}, pages = {576-580}, publisher = {Springer}, organization = {Springer}, address = {Berlin}, issn = {978-3-540-71991-5}, doi = {10.1007/978-3-540-71992-2_94}, url = {http://www.springerlink.com/content/m62p07r8111004vr/}, author = {Montaner, D. and Fatima Al-Shahrour and Dopazo, J.} } @article {16845052, title = {BABELOMICS: a systems biology perspective in the functional annotation of genome-scale experiments}, journal = {Nucleic Acids Res}, volume = {34}, year = {2006}, note = {

Al-Shahrour, Fatima Minguez, Pablo Tarraga, Joaquin Montaner, David Alloza, Eva Vaquerizas, Juan M Conde, Lucia Blaschke, Christian Vera, Javier Dopazo, Joaquin Research Support, Non-U.S. Gov{\textquoteright}t England Nucleic acids research Nucleic Acids Res. 2006 Jul 1;34(Web Server issue):W472-6.

}, pages = {W472-6}, abstract = {

We present a new version of Babelomics, a complete suite of web tools for functional analysis of genome-scale experiments, with new and improved tools. New functionally relevant terms have been included such as CisRed motifs or bioentities obtained by text-mining procedures. An improved indexing has considerably speeded up several of the modules. An improved version of the FatiScan method for studying the coordinate behaviour of groups of functionally related genes is presented, along with a similar tool, the Gene Set Enrichment Analysis. Babelomics is now more oriented to test systems biology inspired hypotheses. Babelomics can be found at http://www.babelomics.org.

}, keywords = {babelomics, functional profiling}, url = {http://nar.oxfordjournals.org/content/34/suppl_2/W472.long}, author = {Fatima Al-Shahrour and Minguez, P. and Tarraga, J. and Montaner, D. and Alloza, E. and Vaquerizas, J. M. and L. Conde and Blaschke, C. and Vera, J. and Dopazo, J.} } @article {17503379, title = {A function-centric approach to the biological interpretation of microarray time-series}, journal = {Genome Inform}, volume = {17}, number = {2}, year = {2006}, note = {

Minguez, Pablo Al-Shahrour, Fatima Dopazo, Joaquin Research Support, Non-U.S. Gov{\textquoteright}t Japan Genome informatics. International Conference on Genome Informatics Genome Inform. 2006;17(2):57-66.

}, pages = {57-66}, abstract = {

The interpretation of microarray experiments is commonly addressed by means a two-step approach in which the relevant genes are firstly selected uniquely on the basis of their experimental values (ignoring their coordinate behaviors) and in a second step their functional properties are studied to hypothesize about the biological roles they are fulfilling in the cell. Recently, different methods (e.g. GSEA or FatiScan) have been proposed to study the coordinate behavior of blocks of functionally-related genes. These methods study the distribution of functional information across lists of genes ranked according their different experimental values in a static situation, such as the comparison between two classes (e.g. healthy controls versus diseased cases). Nevertheless there is no an equivalent way of studying a dynamic situation from a functional point of view. We present a method for the functional analysis of microarrays series in which the experiments display autocorrelation between successive points (e.g. time series, dose-response experiments, etc.) The method allows to recover the dynamics of the molecular roles fulfilled by the genes along the series which provides a novel approach to functional interpretation of such experiments. The method finds blocks of functionally-related genes which are significantly and coordinately over-expressed at different points of the series. This method draws inspiration from systems biology given that the analysis does not focus on individual properties of genes but on collective behaving blocks of functionally-related genes. The FatiScan algorithm used in the method proposed is available at: http://fatiscan.bioinfo.cipf.es, or within the Babelomics suite: http://www.babelomics.org. Additional material is available at: http://bioinfo.cipf.es/data/plasmodium.

}, keywords = {babelomics}, author = {Minguez, P. and Fatima Al-Shahrour and Dopazo, J.} } @article {16845056, title = {Next station in microarray data analysis: GEPAS}, journal = {Nucleic Acids Res}, volume = {34}, year = {2006}, note = {

Montaner, David Tarraga, Joaquin Huerta-Cepas, Jaime Burguet, Jordi Vaquerizas, Juan M Conde, Lucia Minguez, Pablo Vera, Javier Mukherjee, Sach Valls, Joan Pujana, Miguel A G Alloza, Eva Herrero, Javier Al-Shahrour, Fatima Dopazo, Joaquin Research Support, Non-U.S. Gov{\textquoteright}t England Nucleic acids research Nucleic Acids Res. 2006 Jul 1;34(Web Server issue):W486-91.

}, pages = {W486-91}, abstract = {

The Gene Expression Profile Analysis Suite (GEPAS) has been running for more than four years. During this time it has evolved to keep pace with the new interests and trends in the still changing world of microarray data analysis. GEPAS has been designed to provide an intuitive although powerful web-based interface that offers diverse analysis options from the early step of preprocessing (normalization of Affymetrix and two-colour microarray experiments and other preprocessing options), to the final step of the functional annotation of the experiment (using Gene Ontology, pathways, PubMed abstracts etc.), and include different possibilities for clustering, gene selection, class prediction and array-comparative genomic hybridization management. GEPAS is extensively used by researchers of many countries and its records indicate an average usage rate of 400 experiments per day. The web-based pipeline for microarray gene expression data, GEPAS, is available at http://www.gepas.org.

}, keywords = {gepas, microarray data analysis}, url = {http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?cmd=Retrieve\&db=PubMed\&dopt=Citation\&list_uids=16845056}, author = {Montaner, D. and Tarraga, J. and Huerta-Cepas, J. and Burguet, J. and Vaquerizas, J. M. and L. Conde and Minguez, P. and Vera, J. and Mukherjee, S. and Valls, J. and Pujana, M. A. and Alloza, E. and Herrero, J. and Fatima Al-Shahrour and Dopazo, J.} } @article {16671401, title = {Ontology-driven approaches to analyzing data in functional genomics}, journal = {Methods Mol Biol}, volume = {316}, year = {2006}, note = {

Azuaje, Francisco Al-Shahrour, Fatima Dopazo, Joaquin Research Support, N.I.H., Extramural Research Support, Non-U.S. Gov{\textquoteright}t Review United States Methods in molecular biology (Clifton, N.J.) Methods Mol Biol. 2006;316:67-86.

}, pages = {67-86}, abstract = {

Ontologies are fundamental knowledge representations that provide not only standards for annotating and indexing biological information, but also the basis for implementing functional classification and interpretation models. This chapter discusses the application of gene ontology (GO) for predictive tasks in functional genomics. It focuses on the problem of analyzing functional patterns associated with gene products. This chapter is divided into two main parts. The first part overviews GO and its applications for the development of functional classification models. The second part presents two methods for the characterization of genomic information using GO. It discusses methods for measuring functional similarity of gene products, and a tool for supporting gene expression clustering analysis and validation.

}, keywords = {babelomics, Cluster Analysis, Cluster Analysis Computational Biology/*methods *Data Interpretation, Computational Biology, Statistical Gene Expression Profiling, Statistical Gene Expression Profiling *Genomics Humans}, url = {http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?cmd=Retrieve\&db=PubMed\&dopt=Citation\&list_uids=16671401}, author = {F. Azuaje and Fatima Al-Shahrour and Dopazo, J.} } @article {15980512, title = {BABELOMICS: a suite of web tools for functional annotation and analysis of groups of genes in high-throughput experiments}, journal = {Nucleic Acids Res}, volume = {33}, year = {2005}, note = {

Al-Shahrour, Fatima Minguez, Pablo Vaquerizas, Juan M Conde, Lucia Dopazo, Joaquin Research Support, Non-U.S. Gov{\textquoteright}t England Nucleic acids research Nucleic Acids Res. 2005 Jul 1;33(Web Server issue):W460-4.

}, pages = {W460-4}, abstract = {

We present Babelomics, a complete suite of web tools for the functional analysis of groups of genes in high-throughput experiments, which includes the use of information on Gene Ontology terms, interpro motifs, KEGG pathways, Swiss-Prot keywords, analysis of predicted transcription factor binding sites, chromosomal positions and presence in tissues with determined histological characteristics, through five integrated modules: FatiGO (fast assignment and transference of information), FatiWise, transcription factor association test, GenomeGO and tissues mining tool, respectively. Additionally, another module, FatiScan, provides a new procedure that integrates biological information in combination with experimental results in order to find groups of genes with modest but coordinate significant differential behaviour. FatiScan is highly sensitive and is capable of finding significant asymmetries in the distribution of genes of common function across a list of ordered genes even if these asymmetries were not extreme. The strong multiple-testing nature of the contrasts made by the tools is taken into account. All the tools are integrated in the gene expression analysis package GEPAS. Babelomics is the natural evolution of our tool FatiGO (which analysed almost 22,000 experiments during the last year) to include more sources on information and new modes of using it. Babelomics can be found at http://www.babelomics.org.

}, keywords = {babelomics, functional profiling}, url = {http://nar.oxfordjournals.org/content/33/suppl_2/W460.long}, author = {Fatima Al-Shahrour and Minguez, P. and Vaquerizas, J. M. and L. Conde and Dopazo, J.} } @article {15840702, title = {Discovering molecular functions significantly related to phenotypes by combining gene expression data and biological information}, journal = {Bioinformatics}, volume = {21}, number = {13}, year = {2005}, note = {

Al-Shahrour, Fatima Diaz-Uriarte, Ramon Dopazo, Joaquin Evaluation Studies Research Support, Non-U.S. Gov{\textquoteright}t England Bioinformatics (Oxford, England) Bioinformatics. 2005 Jul 1;21(13):2988-93. Epub 2005 Apr 19.

}, pages = {2988-93}, abstract = {

MOTIVATION: The analysis of genome-scale data from different high throughput techniques can be used to obtain lists of genes ordered according to their different behaviours under distinct experimental conditions corresponding to different phenotypes (e.g. differential gene expression between diseased samples and controls, different response to a drug, etc.). The order in which the genes appear in the list is a consequence of the biological roles that the genes play within the cell, which account, at molecular scale, for the macroscopic differences observed between the phenotypes studied. Typically, two steps are followed for understanding the biological processes that differentiate phenotypes at molecular level: first, genes with significant differential expression are selected on the basis of their experimental values and subsequently, the functional properties of these genes are analysed. Instead, we present a simple procedure which combines experimental measurements with available biological information in a way that genes are simultaneously tested in groups related by common functional properties. The method proposed constitutes a very sensitive tool for selecting genes with significant differential behaviour in the experimental conditions tested. RESULTS: We propose the use of a method to scan ordered lists of genes. The method allows the understanding of the biological processes operating at molecular level behind the macroscopic experiment from which the list was generated. This procedure can be useful in situations where it is not possible to obtain statistically significant differences based on the experimental measurements (e.g. low prevalence diseases, etc.). Two examples demonstrate its application in two microarray experiments and the type of information that can be extracted.

}, keywords = {babelomics, Biological Neoplasm Proteins/genetics/*metabolism Phenotype Software Structure-Activity Relationship Systems Integration Tumor Markers, Biological/genetics/*metabolism, Breast Neoplasms/genetics/*metabolism Computer Simulation *Database Management Systems *Databases, Protein Documentation/methods Gene Expression Profiling/*methods Humans *Models}, url = {http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?cmd=Retrieve\&db=PubMed\&dopt=Citation\&list_uids=15840702}, author = {Fatima Al-Shahrour and Diaz-Uriarte, R. and Dopazo, J.} } @article {15980548, title = {GEPAS, an experiment-oriented pipeline for the analysis of microarray gene expression data}, journal = {Nucleic Acids Res}, volume = {33}, year = {2005}, note = {

Vaquerizas, Juan M Conde, Lucia Yankilevich, Patricio Cabezon, Amaya Minguez, Pablo Diaz-Uriarte, Ramon Al-Shahrour, Fatima Herrero, Javier Dopazo, Joaquin Research Support, Non-U.S. Gov{\textquoteright}t England Nucleic acids research Nucleic Acids Res. 2005 Jul 1;33(Web Server issue):W616-20.

}, pages = {W616-20}, abstract = {

The Gene Expression Profile Analysis Suite, GEPAS, has been running for more than three years. With \>76,000 experiments analysed during the last year and a daily average of almost 300 analyses, GEPAS can be considered a well-established and widely used platform for gene expression microarray data analysis. GEPAS is oriented to the analysis of whole series of experiments. Its design and development have been driven by the demands of the biomedical community, probably the most active collective in the field of microarray users. Although clustering methods have obviously been implemented in GEPAS, our interest has focused more on methods for finding genes differentially expressed among distinct classes of experiments or correlated to diverse clinical outcomes, as well as on building predictors. There is also a great interest in CGH-arrays which fostered the development of the corresponding tool in GEPAS: InSilicoCGH. Much effort has been invested in GEPAS for developing and implementing efficient methods for functional annotation of experiments in the proper statistical framework. Thus, the popular FatiGO has expanded to a suite of programs for functional annotation of experiments, including information on transcription factor binding sites, chromosomal location and tissues. The web-based pipeline for microarray gene expression data, GEPAS, is available at http://www.gepas.org.

}, keywords = {gepas, microarray data analysis}, url = {http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?cmd=Retrieve\&db=PubMed\&dopt=Citation\&list_uids=15980548}, author = {Vaquerizas, J. M. and L. Conde and Yankilevich, P. and Cabezon, A. and Minguez, P. and Diaz-Uriarte, R. and Fatima Al-Shahrour and Herrero, J. and Dopazo, J.} } @inbook {485, title = {Ontologies and functional genomics}, booktitle = {Data analysis and visualisation in genomics and proteomics}, year = {2005}, pages = {99-102}, publisher = {Wiley, F. Azuaje and J. Dopazo}, organization = {Wiley, F. Azuaje and J. Dopazo}, author = {Fatima Al-Shahrour and Dopazo, J.} } @article {15297397, title = {Expression profiling of T-cell lymphomas differentiates peripheral and lymphoblastic lymphomas and defines survival related genes.}, journal = {Clinical cancer research : an official journal of the American Association for Cancer Research}, volume = {10}, year = {2004}, month = {2004 Aug 1}, pages = {4971-82}, abstract = {

PURPOSE: T-Cell lymphomas constitute heterogeneous and aggressive tumors in which pathogenic alterations remain largely unknown. Expression profiling has demonstrated to be a useful tool for molecular classification of tumors. EXPERIMENTAL DESIGN: Using DNA microarrays (CNIO-OncoChip) containing 6386 cancer-related genes, we established the expression profiling of T-cell lymphomas and compared them to normal lymphocytes and lymph nodes. RESULTS: We found significant differences between the peripheral and lymphoblastic T-cell lymphomas, which include a deregulation of nuclear factor-kappaB signaling pathway. We also identify differentially expressed genes between peripheral T-cell lymphoma tumors and normal T lymphocytes or reactive lymph nodes, which could represent candidate tumor markers of these lymphomas. Additionally, a close relationship between genes associated to survival and those that differentiate among the stages of disease and responses to therapy was found. CONCLUSIONS: Our results reflect the value of gene expression profiling to gain insight about the molecular alterations involved in the pathogenesis of T-cell lymphomas.

}, url = {http://clincancerres.aacrjournals.org/content/10/15/4971.long}, author = {Martinez-Delgado, Beatriz and Mel{\'e}ndez, Barbara and Cuadros, Marta and Alvarez, Javier and Castrillo, Jose Maria and Ruiz De La Parte, Ana and Mollejo, Manuela and Bellas, Carmen and Diaz, Ramon and Lombard{\'\i}a, Luis and Fatima Al-Shahrour and Dom{\'\i}nguez, Orlando and Cascon, Alberto and Robledo, Mercedes and Rivas, Carmen and Benitez, Javier} } @article {14990455, title = {FatiGO: a web tool for finding significant associations of Gene Ontology terms with groups of genes}, journal = {Bioinformatics}, volume = {20}, number = {4}, year = {2004}, note = {

Al-Shahrour, Fatima Diaz-Uriarte, Ramon Dopazo, Joaquin England Bioinformatics (Oxford, England) Bioinformatics. 2004 Mar 1;20(4):578-80. Epub 2004 Jan 22.

}, pages = {578-80}, abstract = {

We present a simple but powerful procedure to extract Gene Ontology (GO) terms that are significantly over- or under-represented in sets of genes within the context of a genome-scale experiment (DNA microarray, proteomics, etc.). Said procedure has been implemented as a web application, FatiGO, allowing for easy and interactive querying. FatiGO, which takes the multiple-testing nature of statistical contrast into account, currently includes GO associations for diverse organisms (human, mouse, fly, worm and yeast) and the TrEMBL/Swissprot GOAnnotations@EBI correspondences from the European Bioinformatics Institute.

}, keywords = {*Algorithms Artificial Intelligence Databases, babelomics, DNA/*methods *Software, Genetic Gene Expression Profiling/*methods *Hypermedia Information Storage and Retrieval/*methods *Internet *Phylogeny Sequence Alignment/methods Sequence Analysis}, url = {http://bioinformatics.oxfordjournals.org/content/20/4/578.abstract}, author = {Fatima Al-Shahrour and Diaz-Uriarte, R. and Dopazo, J.} } @article {15215434, title = {New challenges in gene expression data analysis and the extended GEPAS}, journal = {Nucleic Acids Res}, volume = {32}, year = {2004}, note = {

Herrero, Javier Vaquerizas, Juan M Al-Shahrour, Fatima Conde, Lucia Mateos, Alvaro Diaz-Uriarte, Javier Santoyo Ramon Dopazo, Joaquin England Nucleic acids research Nucleic Acids Res. 2004 Jul 1;32(Web Server issue):W485-91.

}, pages = {W485-91}, abstract = {

Since the first papers published in the late nineties, including, for the first time, a comprehensive analysis of microarray data, the number of questions that have been addressed through this technique have both increased and diversified. Initially, interest focussed on genes coexpressing across sets of experimental conditions, implying, essentially, the use of clustering techniques. Recently, however, interest has focussed more on finding genes differentially expressed among distinct classes of experiments, or correlated to diverse clinical outcomes, as well as in building predictors. In addition to this, the availability of accurate genomic data and the recent implementation of CGH arrays has made mapping expression and genomic data on the chromosomes possible. There is also a clear demand for methods that allow the automatic transfer of biological information to the results of microarray experiments. Different initiatives, such as the Gene Ontology (GO) consortium, pathways databases, protein functional motifs, etc., provide curated annotations for genes. Whereas many resources on the web focus mainly on clustering methods, GEPAS has evolved to cope with the aforementioned new challenges that have recently arisen in the field of microarray data analysis. The web-based pipeline for microarray gene expression data, GEPAS, is available at http://gepas.bioinfo.cnio.es.

}, keywords = {gepas, microarray data analysis}, url = {http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?cmd=Retrieve\&db=PubMed\&dopt=Citation\&list_uids=15215434}, author = {Herrero, J. and Vaquerizas, J. M. and Fatima Al-Shahrour and L. Conde and A. Mateos and Diaz-Uriarte, J. S. and Dopazo, J.} } @article {15215388, title = {PupaSNP Finder: a web tool for finding SNPs with putative effect at transcriptional level}, journal = {Nucleic Acids Res}, volume = {32}, number = {Web Server issue}, year = {2004}, note = {Conde, Lucia Vaquerizas, Juan M Santoyo, Javier Al-Shahrour, Fatima Ruiz-Llorente, Sergio Robledo, Mercedes Dopazo, Joaquin England Nucleic acids research Nucleic Acids Res. 2004 Jul 1;32(Web Server issue):W242-8.}, pages = {W242-8}, abstract = {We have developed a web tool, PupaSNP Finder (PupaSNP for short), for high-throughput searching for single nucleotide polymorphisms (SNPs) with potential phenotypic effect. PupaSNP takes as its input lists of genes (or generates them from chromosomal coordinates) and retrieves SNPs that could affect the conserved regions that the cellular machinery uses for the correct processing of genes (intron/exon boundaries or exonic splicing enhancers), predicted transcription factor binding sites (TFBS) and changes in amino acids in the proteins. The program uses the mapping of SNPs in the genome provided by Ensembl. Additionally, user-defined SNPs (not yet mapped in the genome) can be easily provided to the program. Also, additional functional information from Gene Ontology, OMIM and homologies in other model organisms is provided. In contrast to other programs already available, which focus only on SNPs with possible effect in the protein, PupaSNP includes SNPs with possible transcriptional effect. PupaSNP will be of significant help in studies of multifactorial disorders, where the use of functional SNPs will increase the sensitivity of identification of the genes responsible for the disease. The PupaSNP web interface is accessible through http://pupasnp.bioinfo.cnio.es.}, keywords = {Amino Acid Substitution Binding Sites Humans Internet Phenotype *Polymorphism, Genetic, Single Nucleotide RNA Splicing *Software Transcription Factors/metabolism *Transcription}, url = {http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?cmd=Retrieve\&db=PubMed\&dopt=Citation\&list_uids=15215388}, author = {L. Conde and Vaquerizas, J. M. and J. Santoyo and Fatima Al-Shahrour and Ruiz-Llorente, S. and M. Robledo and Dopazo, J.} } @article {12824345, title = {GEPAS: A web-based resource for microarray gene expression data analysis}, journal = {Nucleic Acids Res}, volume = {31}, number = {13}, year = {2003}, note = {

Herrero, Javier Al-Shahrour, Fatima Diaz-Uriarte, Ramon Mateos, Alvaro Vaquerizas, Juan M Santoyo, Javier Dopazo, Joaquin Research Support, Non-U.S. Gov{\textquoteright}t England Nucleic acids research Nucleic Acids Res. 2003 Jul 1;31(13):3461-7.

}, pages = {3461-7}, abstract = {

We present a web-based pipeline for microarray gene expression profile analysis, GEPAS, which stands for Gene Expression Profile Analysis Suite (http://gepas.bioinfo.cnio.es). GEPAS is composed of different interconnected modules which include tools for data pre-processing, two-conditions comparison, unsupervised and supervised clustering (which include some of the most popular methods as well as home made algorithms) and several tests for differential gene expression among different classes, continuous variables or survival analysis. A multiple purpose tool for data mining, based on Gene Ontology, is also linked to the tools, which constitutes a very convenient way of analysing clustering results. On-line tutorials are available from our main web server (http://bioinfo.cnio.es).

}, keywords = {gepas, microarray data analysis}, url = {http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?cmd=Retrieve\&db=PubMed\&dopt=Citation\&list_uids=12824345}, author = {Herrero, J. and Fatima Al-Shahrour and Diaz-Uriarte, R. and A. Mateos and Vaquerizas, J. M. and J. Santoyo and Dopazo, J.} } @inbook {491, title = {Use of GO Terms to Understand the Biological Significance of Microarray Differential Gene Expression Data}, booktitle = {Microarray data analysis III}, year = {2003}, pages = {233-247}, publisher = {Kluwer Academic, K. F. Johnson and S. M. Lin}, organization = {Kluwer Academic, K. F. Johnson and S. M. Lin}, author = {D{\'\i}az-Uriarte, R and Fatima Al-Shahrour and Dopazo, J.} } @inbook {492, title = {Using Gene Ontology on genome-scale studies to find significant associations of biologically relevant terms to group of genes}, booktitle = {Neural Networks for Signal Processing XIII}, year = {2003}, pages = {43-52}, publisher = {IEEE Press}, organization = {IEEE Press}, address = {New York, USA}, keywords = {babelomics}, author = {Fatima Al-Shahrour and Herrero, J. and A. Mateos and J. Santoyo and D{\'\i}az-Uriarte, R and Dopazo, J.} }