@article {726, title = {A comprehensive database for integrated analysis of omics data in autoimmune diseases.}, journal = {BMC Bioinformatics}, volume = {22}, year = {2021}, month = {2021 Jun 24}, pages = {343}, abstract = {

BACKGROUND: Autoimmune diseases are heterogeneous pathologies with difficult diagnosis and few therapeutic options. In the last decade, several omics studies have provided significant insights into the molecular mechanisms of these diseases. Nevertheless, data from different cohorts and pathologies are stored independently in public repositories and a unified resource is imperative to assist researchers in this field.

RESULTS: Here, we present Autoimmune Diseases Explorer ( https://adex.genyo.es ), a database that integrates 82 curated transcriptomics and methylation studies covering 5609 samples for some of the most common autoimmune diseases. The database provides, in an easy-to-use environment, advanced data analysis and statistical methods for exploring omics datasets, including meta-analysis, differential expression or pathway analysis.

CONCLUSIONS: This is the first omics database focused on autoimmune diseases. This resource incorporates homogeneously processed data to facilitate integrative analyses among studies.

}, keywords = {Autoimmune Diseases, Computational Biology, Databases, Factual, Humans}, issn = {1471-2105}, doi = {10.1186/s12859-021-04268-4}, author = {Martorell-Marug{\'a}n, Jordi and L{\'o}pez-Dom{\'\i}nguez, Ra{\'u}l and Garc{\'\i}a-Moreno, Adri{\'a}n and Toro-Dom{\'\i}nguez, Daniel and Villatoro-Garc{\'\i}a, Juan Antonio and Barturen, Guillermo and Mart{\'\i}n-G{\'o}mez, Adoraci{\'o}n and Troule, Kevin and G{\'o}mez-L{\'o}pez, Gonzalo and Al-Shahrour, F{\'a}tima and Gonz{\'a}lez-Rumayor, V{\'\i}ctor and Pe{\~n}a-Chilet, Maria and Dopazo, Joaquin and Saez-Rodriguez, Julio and Alarc{\'o}n-Riquelme, Marta E and Carmona-S{\'a}ez, Pedro} } @article {389, title = {Precision medicine needs pioneering clinical bioinformaticians.}, journal = {Brief Bioinform}, volume = {20}, year = {2019}, month = {2019 05 21}, pages = {752-766}, abstract = {

Success in precision medicine depends on accessing high-quality genetic and molecular data from large, well-annotated patient cohorts that couple biological samples to comprehensive clinical data, which in conjunction can lead to effective therapies. From such a scenario emerges the need for a new professional profile, an expert bioinformatician with training in clinical areas who can make sense of multi-omics data to improve therapeutic interventions in patients, and the design of optimized basket trials. In this review, we first describe the main policies and international initiatives that focus on precision medicine. Secondly, we review the currently ongoing clinical trials in precision medicine, introducing the concept of {\textquoteright}precision bioinformatics{\textquoteright}, and we describe current pioneering bioinformatics efforts aimed at implementing tools and computational infrastructures for precision medicine in health institutions around the world. Thirdly, we discuss the challenges related to the clinical training of bioinformaticians, and the urgent need for computational specialists capable of assimilating medical terminologies and protocols to address real clinical questions. We also propose some skills required to carry out common tasks in clinical bioinformatics and some tips for emergent groups. Finally, we explore the future perspectives and the challenges faced by precision medicine bioinformatics.

}, keywords = {Cohort Studies, Computational Biology, Humans, Precision Medicine}, issn = {1477-4054}, doi = {10.1093/bib/bbx144}, author = {G{\'o}mez-L{\'o}pez, Gonzalo and Dopazo, Joaquin and Cigudosa, Juan C and Valencia, Alfonso and Al-Shahrour, F{\'a}tima} } @article {808, title = {Selection upon Genome Architecture: Conservation of Functional Neighborhoods with Changing Genes}, journal = {PLoS Comput. Biol.}, volume = {6}, number = {10}, year = {2010}, pages = {e1000953}, doi = {doi:10.1371/journal.pcbi.1000953}, url = {http://www.ploscompbiol.org/article/info:doi/10.1371/journal.pcbi.1000953}, author = {Al-Shahrour, F{\'a}tima and Minguez, Pablo and Marqu{\'e}s-Bonet, Tom{\'a}s and Gazave, Elodie and Navarro, Arcadi and Dopazo, Joaquin} } @article {578, title = {Exploring the antimicrobial action of a carbon monoxide-releasing compound through whole-genome transcription profiling of Escherichia coli.}, journal = {Microbiology (Reading)}, volume = {155}, year = {2009}, month = {2009 Mar}, pages = {813-824}, 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 = {Biofilms, Carbon Monoxide, Escherichia coli, Escherichia coli Proteins, Gene Expression Profiling, Gene Expression Regulation, Bacterial, Genes, Bacterial, Genes, Regulator, Genetic Complementation Test, Methionine, Microbial Viability, mutation, Oligonucleotide Array Sequence Analysis, Organometallic Compounds, Phenotype, RNA, Bacterial}, issn = {1350-0872}, doi = {10.1099/mic.0.023911-0}, author = {Nobre, L{\'\i}gia S and Al-Shahrour, F{\'a}tima and Dopazo, Joaquin and Saraiva, L{\'\i}gia M} } @article {581, title = {Functional signatures identified in B-cell non-Hodgkin lymphoma profiles.}, journal = {Leuk Lymphoma}, volume = {50}, year = {2009}, month = {2009 Oct}, pages = {1699-708}, abstract = {

Gene-expression profiling in B-cell lymphomas has provided crucial data on specific lymphoma types, which can contribute to the identification of essential lymphoma survival genes and pathways. In this study, the gene-expression profiling data of all major B-cell lymphoma types were analyzed by unsupervised clustering. The transcriptome classification so obtained, was explored using gene set enrichment analysis generating a heatmap for B-cell lymphoma that identifies common lymphoma survival mechanisms and potential therapeutic targets, recognizing sets of coregulated genes and functional pathways expressed in different lymphoma types. Some of the most relevant signatures (stroma, cell cycle, B-cell receptor (BCR)) are shared by multiple lymphoma types or subclasses. A specific attention was paid to the analysis of BCR and coregulated pathways, defining molecular heterogeneity within multiple B-cell lymphoma types.

}, keywords = {Adult, Cluster Analysis, Gene Expression Profiling, Gene Expression Regulation, Leukemic, Genetic Heterogeneity, Humans, Lymphoma, B-Cell, Neoplasm Proteins, Oligonucleotide Array Sequence Analysis, RNA, Messenger, RNA, Neoplasm, Transcription, Genetic}, issn = {1029-2403}, doi = {10.1080/10428190903189035}, author = {Aggarwal, Mohit and S{\'a}nchez-Beato, Margarita and G{\'o}mez-L{\'o}pez, Gonzalo and Al-Shahrour, F{\'a}tima and Mart{\'\i}nez, Nerea and Rodr{\'\i}guez, Antonia and Ruiz-Ballesteros, Elena and Camacho, Francisca I and P{\'e}rez-Rosado, Alberto and de la Cueva, Paloma and Artiga, Mar{\'\i}a J and Pisano, David G and Kimby, Eva and Dopazo, Joaquin and Villuendas, Raquel and Piris, Miguel A} } @article {582, title = {Gene set internal coherence in the context of functional profiling.}, journal = {BMC Genomics}, volume = {10}, year = {2009}, month = {2009 Apr 27}, pages = {197}, abstract = {

BACKGROUND: Functional profiling methods have been extensively used in the context of high-throughput experiments and, in particular, in microarray data analysis. Such methods use available biological information to define different types of functional gene modules (e.g. gene ontology -GO-, KEGG pathways, etc.) whose representation in a pre-defined list of genes is further studied. In the most popular type of microarray experimental designs (e.g. up- or down-regulated genes, clusters of co-expressing genes, etc.) or in other genomic experiments (e.g. Chip-on-chip, epigenomics, etc.) these lists are composed by genes with a high degree of co-expression. Therefore, an implicit assumption in the application of functional profiling methods within this context is that the genes corresponding to the modules tested are effectively defining sets of co-expressing genes. Nevertheless not all the functional modules are biologically coherent entities in terms of co-expression, which will eventually hinder its detection with conventional methods of functional enrichment.

RESULTS: Using a large collection of microarray data we have carried out a detailed survey of internal correlation in GO terms and KEGG pathways, providing a coherence index to be used for measuring functional module co-regulation. An unexpected low level of internal correlation was found among the modules studied. Only around 30\% of the modules defined by GO terms and 57\% of the modules defined by KEGG pathways display an internal correlation higher than the expected by chance.This information on the internal correlation of the genes within the functional modules can be used in the context of a logistic regression model in a simple way to improve their detection in gene expression experiments.

CONCLUSION: For the first time, an exhaustive study on the internal co-expression of the most popular functional categories has been carried out. Interestingly, the real level of coexpression within many of them is lower than expected (or even inexistent), which will preclude its detection by means of most conventional functional profiling methods. If the gene-to-function correlation information is used in functional profiling methods, the results obtained improve the ones obtained by conventional enrichment methods.

}, keywords = {Algorithms, Breast Neoplasms, Carcinoma, Intraductal, Noninfiltrating, Computational Biology, Databases, Nucleic Acid, Female, Gene Expression Profiling, Genomics, Humans, Oligonucleotide Array Sequence Analysis, Papillomavirus Infections, Reproducibility of Results}, issn = {1471-2164}, doi = {10.1186/1471-2164-10-197}, author = {Montaner, David and Minguez, Pablo and Al-Shahrour, F{\'a}tima and Dopazo, Joaquin} } @article {583, title = {Gene set-based analysis of polymorphisms: finding pathways or biological processes associated to traits in genome-wide association studies.}, journal = {Nucleic Acids Res}, volume = {37}, year = {2009}, month = {2009 Jul}, pages = {W340-4}, 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 = {Biological Phenomena, Breast Neoplasms, Female, Genes, Genetic Variation, Genome-Wide Association Study, Humans, Polymorphism, Single Nucleotide, Software, User-Computer Interface}, issn = {1362-4962}, doi = {10.1093/nar/gkp481}, 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 Al-Shahrour, F{\'a}tima and Dopazo, Joaquin} } @article {586, title = {SNOW, a web-based tool for the statistical analysis of protein-protein interaction networks.}, journal = {Nucleic Acids Res}, volume = {37}, year = {2009}, month = {2009 Jul}, pages = {W109-14}, 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 = {Computer Graphics, Data Interpretation, Statistical, Databases, Protein, Humans, Internet, Protein Interaction Mapping, Software}, issn = {1362-4962}, doi = {10.1093/nar/gkp402}, author = {Minguez, Pablo and G{\"o}tz, Stefan and Montaner, David and Al-Shahrour, F{\'a}tima and Dopazo, Joaquin} } @article {591, title = {Expression and microarrays.}, journal = {Methods Mol Biol}, volume = {453}, year = {2008}, month = {2008}, pages = {245-55}, abstract = {

High throughput methodologies have increased by several orders of magnitude the amount of experimental microarray data available. Nevertheless, translating these data into useful biological knowledge remains a challenge. There is a risk of perceiving these methodologies as mere factories that produce never-ending quantities of data if a proper biological interpretation is not provided. Methods of interpreting these data are continuously evolving. Typically, a simple two-step approach has been used, in which genes of interest are first selected based on thresholds for the experimental values, and then enrichment in biologically relevant terms in the annotations of these genes is analyzed in a second step. For various reasons, such methods are quite poor in terms of performance and new procedures inspired by systems biology that directly address sets of functionally related genes are currently under development.

}, keywords = {Animals, Computational Biology, gene expression, Gene Expression Profiling, Humans, Oligonucleotide Array Sequence Analysis}, issn = {1064-3745}, doi = {10.1007/978-1-60327-429-6_12}, author = {Dopazo, Joaquin and Al-Shahrour, F{\'a}tima} } @article {593, title = {GEPAS, a web-based tool for microarray data analysis and interpretation.}, journal = {Nucleic Acids Res}, volume = {36}, year = {2008}, month = {2008 Jul 01}, 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 = {Computer Graphics, Dose-Response Relationship, Drug, Gene Expression Profiling, Internet, Kinetics, Oligonucleotide Array Sequence Analysis, Software}, issn = {1362-4962}, doi = {10.1093/nar/gkn303}, author = {T{\'a}rraga, Joaqu{\'\i}n and Medina, Ignacio and Carbonell, Jos{\'e} and Huerta-Cepas, Jaime and Minguez, Pablo and Alloza, Eva and Al-Shahrour, F{\'a}tima and Vegas-Azc{\'a}rate, Susana and Goetz, Stefan and Escobar, Pablo and Garcia-Garcia, Francisco and Conesa, Ana and Montaner, David and Dopazo, Joaquin} } @article {603, title = {DBAli tools: mining the protein structure space.}, journal = {Nucleic Acids Res}, volume = {35}, year = {2007}, month = {2007 Jul}, 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, Data Interpretation, Statistical, Databases, Protein, Internet, Molecular Sequence Data, Protein Conformation, Proteins, Pseudomonas aeruginosa, Sequence Alignment, Sequence Analysis, Protein, Sequence Homology, Amino Acid, Software, Structure-Activity Relationship}, issn = {1362-4962}, doi = {10.1093/nar/gkm236}, author = {Marti-Renom, Marc A and Pieper, Ursula and Madhusudhan, M S and Rossi, Andrea and Eswar, Narayanan and Davis, Fred P and Al-Shahrour, F{\'a}tima and Dopazo, Joaquin and Sali, Andrej} } @article {604, title = {Evidence for systems-level molecular mechanisms of tumorigenesis.}, journal = {BMC Genomics}, volume = {8}, year = {2007}, month = {2007 Jun 20}, 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, Neoplastic, Gene Expression Profiling, Gene Expression Regulation, Neoplastic, Humans, Male, Models, Biological, Models, Genetic, Models, Statistical, Neoplasm Proteins, Neoplasms, Prostatic Neoplasms, Protein Interaction Mapping, RNA, Messenger, Signal Transduction, Systems biology}, issn = {1471-2164}, doi = {10.1186/1471-2164-8-185}, author = {Hern{\'a}ndez, Pilar and Huerta-Cepas, Jaime and Montaner, David and Al-Shahrour, F{\'a}tima and Valls, Joan and G{\'o}mez, Laia and Capell{\`a}, Gabriel and Dopazo, Joaquin and Pujana, Miguel Angel} } @article {605, 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}, year = {2007}, month = {2007 Jul}, 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 = {Amino Acid Motifs, Animals, Binding Sites, Computational Biology, Gene Expression Profiling, Genes, Genomics, Humans, Internet, Oligonucleotide Array Sequence Analysis, Programming Languages, Software, Systems Integration, Transcription Factors}, issn = {1362-4962}, doi = {10.1093/nar/gkm260}, author = {Al-Shahrour, F{\'a}tima and Minguez, Pablo and T{\'a}rraga, Joaqu{\'\i}n and Medina, Ignacio and Alloza, Eva and Montaner, David and Dopazo, Joaquin} } @article {606, title = {From genes to functional classes in the study of biological systems.}, journal = {BMC Bioinformatics}, volume = {8}, year = {2007}, month = {2007 Apr 03}, 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, Computer Simulation, Gene Expression Profiling, Models, Biological, Multigene Family, Signal Transduction, Software, Systems biology, User-Computer Interface}, issn = {1471-2105}, doi = {10.1186/1471-2105-8-114}, author = {Al-Shahrour, F{\'a}tima and Arbiza, Leonardo and Dopazo, Hern{\'a}n and Huerta-Cepas, Jaime and Minguez, Pablo and Montaner, David and Dopazo, Joaquin} } @article {607, title = {Functional profiling and gene expression analysis of chromosomal copy number alterations.}, journal = {Bioinformation}, volume = {1}, year = {2007}, month = {2007 Apr 10}, 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.

}, issn = {0973-2063}, doi = {10.6026/97320630001432}, author = {Conde, Lucia and Montaner, David and Burguet-Castell, Jordi and T{\'a}rraga, Joaqu{\'\i}n and Al-Shahrour, F{\'a}tima and Dopazo, Joaquin} } @article {592, title = {Functional profiling of microarray experiments using text-mining derived bioentities.}, journal = {Bioinformatics}, volume = {23}, year = {2007}, month = {2007 Nov 15}, 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, Protein, Gene Expression Profiling, Information Storage and Retrieval, Natural Language Processing, Proteins, Research Design, Systems Integration}, issn = {1367-4811}, doi = {10.1093/bioinformatics/btm445}, author = {Minguez, Pablo and Al-Shahrour, F{\'a}tima and Montaner, David and Dopazo, Joaquin} } @article {608, 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}, year = {2007}, month = {2007 Jul}, 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, Computer Graphics, Gene Expression Profiling, Humans, Internet, Models, Genetic, Nucleic Acid Hybridization, Oligonucleotide Array Sequence Analysis, Programming Languages, Software, Systems Integration, User-Computer Interface}, issn = {1362-4962}, doi = {10.1093/nar/gkm257}, author = {Conde, Lucia and Montaner, David and Burguet-Castell, Jordi and T{\'a}rraga, Joaqu{\'\i}n and Medina, Ignacio and Al-Shahrour, F{\'a}tima and Dopazo, Joaquin} }