@article{Tarazona2021,

title = {Undisclosed, unmet and neglected challenges in multi-omics studies},

author = {Sonia Tarazona and Angeles Arzalluz-Luque and Ana Conesa},

url = {http://conesalab.org/wp-content/uploads/2021/07/Undisclosed-unmet-and-neglected-challenges-in-multi-omics-studies-1.pdf},

doi = {10.1038/s43588-021-00086-z},

issn = {2662-8457},

year  = {2021},

date = {2021-06-01},

journal = {Nature Computational Science},

volume = {1},

number = {6},

pages = {395-402},

abstract = {Multi-omics approaches have become a reality in both large genomics projects and small laboratories. However, the multi-omics research community still faces a number of issues that have either not been sufficiently discussed or for which current solutions are still limited. In this Perspective, we elaborate on these limitations and suggest points of attention for future research. We finally discuss new opportunities and challenges brought to the field by the rapid development of single-cell high-throughput molecular technologies.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{N2021,

title = {STATegra: Multi-Omics Data Integration - A Conceptual Scheme With a Bioinformatics Pipeline},

author = {Planell N, Lagani V, Sebastian-Leon P, van der Kloet F, Ewing E, Karathanasis N, Urdangarin A, Arozarena I, Jagodic M, Tsamardinos I, Tarazona S, Conesa A, Tegner J, Gomez-Cabrero D},

url = {https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7970106/pdf/fgene-12-620453.pdf},

doi = {0.3389/fgene.2021.620453},

year  = {2021},

date = {2021-03-04},

journal = {Frontiers in Genetics},

volume = {12},

pages = {620453},

abstract = {Technologies for profiling samples using different omics platforms have been at the forefront since the human genome project. Large-scale multi-omics data hold the promise of deciphering different regulatory layers. Yet, while there is a myriad of bioinformatics tools, each multi-omics analysis appears to start from scratch with an arbitrary decision over which tools to use and how to combine them. Therefore, it is an unmet need to conceptualize how to integrate such data and implement and validate pipelines in different cases. We have designed a conceptual framework (STATegra), aiming it to be as generic as possible for multi-omics analysis, combining available multi-omic anlaysis tools (machine learning component analysis, non-parametric data combination, and a multi-omics exploratory analysis) in a step-wise manner. While in several studies, we have previously combined those integrative tools, here, we provide a systematic description of the STATegra framework and its validation using two The Cancer Genome Atlas (TCGA) case studies. For both, the Glioblastoma and the Skin Cutaneous Melanoma (SKCM) cases, we demonstrate an enhanced capacity of the framework (and beyond the individual tools) to identify features and pathways compared to single-omics analysis. Such an integrative multi-omics analysis framework for identifying features and components facilitates the discovery of new biology. Finally, we provide several options for applying the STATegra framework when parametric assumptions are fulfilled and for the case when not all the samples are profiled for all omics. The STATegra framework is built using several tools, which are being integrated step-by-step as OpenSource in the STATegRa Bioconductor package.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{arzalluz2021acorde,

title = {Acorde: unraveling functionally-interpretable networks of isoform co-usage from single cell data},

author = {Angeles Arzalluz-Luque and Pedro Salguero and Sonia Tarazona and Ana Conesa},

year  = {2021},

date = {2021-01-01},

journal = {bioRxiv},

publisher = {Cold Spring Harbor Laboratory},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{nanni2021ozone,

title = {Ozone sensitivity of diverse maize genotypes is associated with differences in gene regulation, not gene content},

author = {Adalena V Nanni and Alison M Morse and Jeremy RB Newman and Nicole E Choquette and Jessica M Wedow and Zihao Liu and Andrew DB Leakey and Ana Conesa and Elizabeth A Ainsworth and Lauren McIntyre},

year  = {2021},

date = {2021-01-01},

journal = {bioRxiv},

publisher = {Cold Spring Harbor Laboratory},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{rodriguez2021treatment,

title = {Treatment with tocilizumab or corticosteroids for COVID-19 patients with hyperinflammatory state: a multicentre cohort study (SAM-COVID-19)},

author = {Jes{'u}s Rodr{'i}guez-Ba{~n}o and Jerónimo Pachón and Jordi Carratal{`a} and Pablo Ryan and Inmaculada Jarr{'i}n and Mar{'i}a Yllescas and José Ramón Arribas and Juan Berenguer and Esther Aznar Mu{~n}oz and Pedro Gil Divasson and others},

year  = {2021},

date = {2021-01-01},

journal = {Clinical Microbiology and Infection},

volume = {27},

number = {2},

pages = {244--252},

publisher = {Elsevier},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{puig2021circadian,

title = {Circadian Transcriptomic and Epigenomic Remodeling in Response to Lipid Overload and Human Obesity},

author = {Laura Sardón Puig and Ali Altintas and Salvador Casani and Brendan M Gabriel and Romain Barres and Ana Conesa and Alexander V Chibalin and Erik Naslund and Anna Krook and Nicolas J Pillon and others},

year  = {2021},

date = {2021-01-01},

journal = {bioRxiv},

publisher = {Cold Spring Harbor Laboratory},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{rubio2021multi,

title = {Multi-omic analysis unveils biological pathways in peripheral immune system associated to minimal hepatic encephalopathy appearance in cirrhotic patients},

author = {Teresa Rubio and Vicente Felipo and Sonia Tarazona and Roberta Pastorelli and Desamparados Escudero-Garc{'i}a and Joan Tosca and Amparo Urios and Ana Conesa and Carmina Montoliu},

year  = {2021},

date = {2021-01-01},

journal = {Scientific reports},

volume = {11},

number = {1},

pages = {1--14},

publisher = {Nature Publishing Group},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{balzano2021integrative,

title = {Integrative analyses of TEDDY Omics data reveal lipid metabolism abnormalities, increased intracellular ROS and heightened inflammation prior to autoimmunity for type 1 diabetes},

author = {Leandro Balzano-Nogueira and Ricardo Ramirez and Tatyana Zamkovaya and Jordan Dailey and Alexandria N Ardissone and Srikar Chamala and Joan Serrano-Qu{'i}lez and Teresa Rubio and Michael J Haller and Patrick Concannon and others},

year  = {2021},

date = {2021-01-01},

journal = {Genome biology},

volume = {22},

number = {1},

pages = {1--27},

publisher = {BioMed Central},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{tarazona2021multi,

title = {A multi-omic study for uncovering molecular mechanisms associated with hyperammonemia-induced cerebellar function impairment in rats},

author = {Sonia Tarazona and Héctor Carmona and Ana Conesa and Marta Llansola and Vicente Felipo},

year  = {2021},

date = {2021-01-01},

journal = {Cell Biology and Toxicology},

volume = {37},

number = {1},

pages = {129--149},

publisher = {Springer Netherlands},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{zamkovaya2021network,

title = {A network approach to elucidate and prioritize microbial dark matter in microbial communities},

author = {Tatyana Zamkovaya and Jamie S Foster and Valérie de Crécy-Lagard and Ana Conesa},

year  = {2021},

date = {2021-01-01},

journal = {The ISME Journal},

volume = {15},

number = {1},

pages = {228--244},

publisher = {Nature Publishing Group},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{S2020,

title = {Harmonization of quality metrics and power calculation in multi-omic studies},

author = {Tarazona S, Balzano-Nogueira L, Gómez-Cabrero D, Schmidt A, Imhof A, Hankemeier T, Tegnér J, Westerhuis JA, Conesa A.},

url = {https://pubmed.ncbi.nlm.nih.gov/32555183/},

doi = {10.1038/s41467-020-16937-8},

year  = {2020},

date = {2020-06-18},

journal = {Nature Communications},

volume = {11},

number = {1},

pages = {3092},

abstract = {Multi-omic studies combine measurements at different molecular levels to build comprehensive models of cellular systems. The success of a multi-omic data analysis strategy depends largely on the adoption of adequate experimental designs, and on the quality of the measurements provided by the different omic platforms. However, the field lacks a comparative description of performance parameters across omic technologies and a formulation for experimental design in multi-omic data scenarios. Here, we propose a set of harmonized Figures of Merit (FoM) as quality descriptors applicable to different omic data types. Employing this information, we formulate the MultiPower method to estimate and assess the optimal sample size in a multi-omics experiment. MultiPower supports different experimental settings, data types and sample sizes, and includes graphical for experimental design decision-making. MultiPower is complemented with MultiML, an algorithm to estimate sample size for machine learning classification problems based on multi-omic data.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{doi:10.1177/0962280220907365,

title = {MultiBaC: A strategy to remove batch effects between different omic data types},

author = { Manuel Ugidos and Sonia Tarazona and José M Prats-Montalbán and Alberto Ferrer and Ana Conesa},

url = {https://doi.org/10.1177/0962280220907365},

doi = {10.1177/0962280220907365},

year  = {2020},

date = {2020-03-05},

journal = {Statistical Methods in Medical Research},

volume = {0},

number = {0},

pages = {1-14},

abstract = {Diversity of omic technologies has expanded in the last years together with the number of omic data integration strategies. However, multiomic data generation is costly, and many research groups cannot afford research projects where many different omic techniques are generated, at least at the same time. As most researchers share their data in public repositories, different omic datasets of the same biological system obtained at different labs can be combined to construct a multiomic study. However, data obtained at different labs or moments in time are typically subjected to batch effects that need to be removed for successful data integration. While there are methods to correct batch effects

on the same data types obtained in different studies, they cannot be applied to correct lab or batch effects across omics. This impairs multiomic meta-analysis. Fortunately, in many cases, at least one omics platform—i.e. gene expression— is repeatedly measured across labs, together with the additional omic modalities that are specific to each study. This

creates an opportunity for batch analysis. We have developed MultiBaC (multiomic Multiomics Batch-effect Correction

correction), a strategy to correct batch effects from multiomic datasets distributed across different labs or data acquisition events. Our strategy is based on the existence of at least one shared data type which allows data prediction across omics. We validate this approach both on simulated data and on a case where the multiomic design is fully shared by two labs, hence batch effect correction within the same omic modality using traditional methods can be compared with the MultiBaC correction across data types. Finally, we apply MultiBaC to a true multiomic data integration problem to show that we are able to improve the detection of meaningful biological effects.},

note = {PMID: 32131696},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{Nuño-Cabanes2020,

title = {A multi-omics dataset of heat-shock response in the yeast RNA binding protein Mip6},

author = {Nuño, Carme 

and Ugidos, Manuel 

and Tarazona, Sonia 

and Martín-Expósito, Manuel 

and Ferrer, Alberto 

and Rodríguez-Navarro, Susana 

and Conesa, Ana},

url = {https://pubmed.ncbi.nlm.nih.gov/32109230},

doi = {10.1038/s41597-020-0412-z},

issn = {2052-4463},

year  = {2020},

date = {2020-02-27},

journal = {Scientific data},

volume = {7},

number = {1},

pages = {69-69},

address = {England},

abstract = {Gene expression is a biological process regulated at different molecular levels, including chromatin accessibility, transcription, and RNA maturation and transport. In addition, these regulatory mechanisms have strong links with cellular metabolism. Here we present a multi-omics dataset that captures different aspects of this multi-layered process in yeast. We obtained RNA-seq, metabolomics, and H4K12ac ChIP-seq data for wild-type and mip6D strains during a heat-shock time course. Mip6 is an RNA-binding protein that contributes to RNA export during environmental stress and is informative of the contribution of post-transcriptional regulation to control cellular adaptations to environmental changes. The experiment was performed in quadruplicate, and the different omics measurements were obtained from the same biological samples, which facilitates the integration and analysis of data using covariance-based methods. We validate our dataset by showing that ChIP-seq, RNA-seq and metabolomics signals recapitulate existing knowledge about the response of ribosomal genes and the contribution of trehalose metabolism to heat stress. Raw data, processed data and preprocessing scripts are made available.},

note = {32109230[pmid]},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{Nuño-Cabanes2020b,

title = {A multi-omics dataset of heat-shock response in the yeast RNA binding protein Mip6},

author = {Carme Nuño and Manuel Ugidos and Sonia Tarazona and Manuel Martín-Expósito and Alberto Ferrer and Susana Rodríguez-Navarro and Ana Conesa},

url = {https://pubmed.ncbi.nlm.nih.gov/32109230},

doi = {10.1038/s41597-020-0412-z},

issn = {2052-4463},

year  = {2020},

date = {2020-02-27},

journal = {Scientific data},

volume = {7},

number = {1},

pages = {69-69},

address = {England},

abstract = {Gene expression is a biological process regulated at different molecular levels, including chromatin accessibility, transcription, and RNA maturation and transport. In addition, these regulatory mechanisms have strong links with cellular metabolism. Here we present a multi-omics dataset that captures different aspects of this multi-layered process in yeast. We obtained RNA-seq, metabolomics, and H4K12ac ChIP-seq data for wild-type and mip6D strains during a heat-shock time course. Mip6 is an RNA-binding protein that contributes to RNA export during environmental stress and is informative of the contribution of post-transcriptional regulation to control cellular adaptations to environmental changes. The experiment was performed in quadruplicate, and the different omics measurements were obtained from the same biological samples, which facilitates the integration and analysis of data using covariance-based methods. We validate our dataset by showing that ChIP-seq, RNA-seq and metabolomics signals recapitulate existing knowledge about the response of ribosomal genes and the contribution of trehalose metabolism to heat stress. Raw data, processed data and preprocessing scripts are made available.},

note = {32109230[pmid]},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{mcintyre2020gait,

title = {GAIT-GM: Galaxy tools for modeling metabolite changes as a function of gene expression},

author = {Lauren M McIntyre and Francisco Huertas and Olexander Moskalenko and Marta Llansola and Vicente Felipo and Alison M Morse and Ana Conesa},

year  = {2020},

date = {2020-01-01},

journal = {bioRxiv},

publisher = {Cold Spring Harbor Laboratory},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{casani2020padhoc,

title = {Padhoc: a computational pipeline for pathway reconstruction on the fly},

author = {Salvador Casan{'i}-Galdón and Cecile Pereira and Ana Conesa},

year  = {2020},

date = {2020-01-01},

journal = {Bioinformatics},

volume = {36},

number = {Supplement_2},

pages = {i795--i803},

publisher = {Oxford University Press},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{ylla2020mircure,

title = {MirCure: a tool for quality control, filter and curation of microRNAs of animals and plants},

author = {Guillem Ylla and Tianyuan Liu and Ana Conesa},

year  = {2020},

date = {2020-01-01},

journal = {Bioinformatics},

volume = {36},

number = {Supplement_2},

pages = {i618--i624},

publisher = {Oxford University Press},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{bhattarai2020sequencing,

title = {Sequencing and analysis of gerbera daisy leaf transcriptomes reveal disease resistance and susceptibility genes differentially expressed and associated with powdery mildew resistance},

author = {Krishna Bhattarai and Ana Conesa and Shunyuan Xiao and Natalia A Peres and David G Clark and Saroj Parajuli and Zhanao Deng},

year  = {2020},

date = {2020-01-01},

journal = {BMC plant biology},

volume = {20},

number = {1},

pages = {1--17},

publisher = {BioMed Central},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{liu2020transcriptional,

title = {Transcriptional differences for COVID-19 Disease Map genes between males and females indicate a different basal immunophenotype relevant to the disease},

author = {Tianyuan Liu and Leandro Balzano-Nogueira and Ana Lleo and Ana Conesa},

year  = {2020},

date = {2020-01-01},

journal = {Genes},

volume = {11},

number = {12},

pages = {1447},

publisher = {Multidisciplinary Digital Publishing Institute},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{gardner2020assessment,

title = {Assessment of unconventional antimicrobial compounds for the control of ‘Candidatus liberibacter asiaticus’, the causative agent of citrus greening disease},

author = {Christopher L Gardner and Danilo R da Silva and Fernando A Pagliai and Lei Pan and Kaylie A Padgett-Pagliai and Ryan A Blaustein and Marcelo L Merli and Dan Zhang and Cécile Pereira and Max Teplitski and others},

year  = {2020},

date = {2020-01-01},

journal = {Scientific reports},

volume = {10},

number = {1},

pages = {1--15},

publisher = {Nature Publishing Group},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{de2020tappas,

title = {tappAS: a comprehensive computational framework for the analysis of the functional impact of differential splicing},

author = {Lorena de la Fuente and Ángeles Arzalluz-Luque and Manuel Tardáguila and Héctor Del Risco and Cristina Mart{'i} and Sonia Tarazona and Pedro Salguero and Raymond Scott and Alberto Lerma and Ana Alastrue-Agudo and others},

url = {https://genomebiology.biomedcentral.com/articles/10.1186/s13059-020-02028-w},

doi = {https://doi.org/10.1186/s13059-020-02028-w},

year  = {2020},

date = {2020-01-01},

journal = {Genome biology},

volume = {21},

pages = {1--32},

publisher = {BioMed Central},

abstract = {Recent advances in long-read sequencing solve inaccuracies in alternative transcript identification of full-length transcripts in short-read RNA-Seq data, which encourages the development of methods for isoform-centered functional analysis. Here, we present tappAS, the first framework to enable a comprehensive Functional Iso-Transcriptomics (FIT) analysis, which is effective at revealing the functional impact of context-specific post-transcriptional regulation. tappAS uses isoform-resolved annotation of coding and non-coding functional domains, motifs, and sites, in combination with novel analysis methods to interrogate different aspects of the functional readout of transcript variants and isoform regulation. tappAS software and documentation are available at https://app.tappas.org.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{Jansen2019,

title = {Building gene regulatory networks from scATAC-seq and scRNA-seq using Linked Self Organizing Maps},

author = { Camden Jansen and Ricardo N. Ramirez and Nicole C. El-Ali and David Gomez-Cabrero and Jesper Tegner and Matthias Merkenschlager and Ana Conesa and Ali Mortazavi},

editor = {Leslie, Christina S.},

url = {https://dx.plos.org/10.1371/journal.pcbi.1006555},

doi = {10.1371/journal.pcbi.1006555},

issn = {1553-7358},

year  = {2019},

date = {2019-11-01},

journal = {PLOS Computational Biology},

volume = {15},

number = {11},

pages = {e1006555},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{Sana2019,

title = {Differential Modulation of Quorum Sensing Signaling through QslA in Pseudomonas aeruginosa Strains PAO1 and PA14},

author = { T. G. Sana and R. Lomas and M. R. Gimenez and A. Laubier and C. Soscia and C. Chauvet and A. Conesa and R. Voulhoux and B. Ize and S. Bleves},

url = {https://jb.asm.org/content/201/21/e00362-19.abstract},

doi = {10.1128/JB.00362-19},

issn = {10985530},

year  = {2019},

date = {2019-11-01},

journal = {Journal of bacteriology},

volume = {201},

number = {21},

publisher = {NLM (Medline)},

abstract = {Two clinical isolates of the opportunist pathogen Pseudomonas aeruginosa named PAO1 and PA14 are commonly studied in research laboratories. Despite the isolates being closely related, PA14 exhibits increased virulence compared to that of PAO1 in various models. To determine which players are responsible for the hypervirulence phenotype of the PA14 strain, we elected a transcriptomic approach through RNA sequencing. We found 2,029 genes that are differentially expressed between the two strains, including several genes that are involved with or regulated by quorum sensing (QS), known to control most of the virulence factors in P. aeruginosa Among them, we chose to focus our study on QslA, an antiactivator of QS whose expression was barely detectable in the PA14 strain according our data. We hypothesized that lack of expression of qslA in PA14 could be responsible for higher QS expression in the PA14 strain, possibly explaining its hypervirulence phenotype. After confirming that QslA protein was highly produced in PAO1 but not in the PA14 strain, we obtained evidence showing that a PAO1 deletion strain of qslA has faster QS gene expression kinetics than PA14. Moreover, known virulence factors activated by QS, such as (i) pyocyanin production, (ii) H2-T6SS (type VI secretion system) gene expression, and (iii) Xcp-T2SS (type II secretion system) machinery production and secretion, were all lower in PAO1 than in PA14, due to higher qslA expression. However, biofilm formation and cytotoxicity toward macrophages, although increased in PA14 compared to PAO1, were independent of QslA control. Together, our findings implicated differential qslA expression as a major determinant of virulence factor expression in P. aeruginosa strains PAO1 and PA14.IMPORTANCEPseudomonas aeruginosa is an opportunistic pathogen responsible for acute nosocomial infections and chronic pulmonary infections. P. aeruginosa strain PA14 is known to be hypervirulent in different hosts. Despite several studies in the field, the underlining molecular mechanisms sustaining this phenotype remain enigmatic. Here we provide evidence that the PA14 strain has faster quorum sensing (QS) kinetics than the PAO1 strain, due to the lack of QslA expression, an antiactivator of QS. QS is a major regulator of virulence factors in P. aeruginosa; therefore, we propose that the hypervirulent phenotype of the PA14 strain is, at least partially, due to the lack of QslA expression. This mechanism could be of great importance, as it could be conserved among other P. aeruginosa isolates.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{Jansen2019b,

title = {Building gene regulatory networks from scATAC-seq and scRNA-seq using Linked Self Organizing Maps},

author = {Camden Jansen and Ricardo N Ramirez and Nicole C El-Ali and David Gomez-Cabrero and Jesper Tegner and Matthias Merkenschlager and Ana Conesa and Ali Mortazavi},

editor = {Christina S Leslie},

url = {https://dx.plos.org/10.1371/journal.pcbi.1006555},

doi = {10.1371/journal.pcbi.1006555},

issn = {1553-7358},

year  = {2019},

date = {2019-11-01},

journal = {PLOS Computational Biology},

volume = {15},

number = {11},

pages = {e1006555},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{MartinExposito2019,

title = {Mip6 binds directly to the Mex67 UBA domain to maintain low levels of Msn2/4 stress‐dependent mRNAs},

author = { Manuel Martín‐Expósito and Maria‐Eugenia Gas and Nada Mohamad and Carme Nuño‐Cabanes and Ana Tejada‐Colón and Pau Pascual‐García and Lorena Fuente and Belén Chaves‐Arquero and Jonathan Merran and Jeffry Corden and Ana Conesa and José Manuel Pérez‐Cañadillas and Jerónimo Bravo and Susana Rodríguez‐Navarro},

url = {https://onlinelibrary.wiley.com/doi/abs/10.15252/embr.201947964},

doi = {10.15252/embr.201947964},

issn = {1469-221X},

year  = {2019},

date = {2019-10-29},

journal = {EMBO reports},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{Tarazona2019,

title = {A Multiomics Study to Unravel the Effects of Developmental Exposure to Endosulfan in Rats: Molecular Explanation for Sex-Dependent Effects},

author = { Sonia Tarazona and Elena Bernabeu and Héctor Carmona and Belén Gómez-Giménez and Javier García-Planells and Pim E.G. Leonards and Stephan Jung and Ana Conesa and Vicente Felipo and Marta Llansola},

url = {https://www.ncbi.nlm.nih.gov/pubmed/31464424},

doi = {10.1021/acschemneuro.9b00304},

issn = {19487193},

year  = {2019},

date = {2019-10-01},

journal = {ACS Chemical Neuroscience},

volume = {10},

number = {10},

pages = {4264--4279},

publisher = {American Chemical Society},

abstract = {Exposure to low levels of environmental contaminants, including pesticides, induces neurodevelopmental toxicity. Environmental and food contaminants can reach the brain of the fetus, affecting brain development and leading to neurological dysfunction. The pesticide endosulfan is a persistent pollutant, and significant levels still remain detectable in the environment although its use is banned in some countries. In rats, endosulfan exposure during brain development alters motor activity, coordination, learning, and memory, even several months after uptake, and does so in a sex-dependent way. However, the molecular mechanisms driving these effects have not been studied in detail. In this work, we performed a multiomics study in cerebellum from rats exposed to endosulfan during embryonic development. Pregnant rats were orally exposed to a low dose (0.5 mg/kg) of endosulfan, daily, from gestational day 7 to postnatal day 21. The progeny was evaluated for cognitive and motor functions at adulthood. Expression of messenger RNA and microRNA genes, as well as protein and metabolite levels, were measured on cerebellar samples from males and females. An integrative analysis was conducted to identify altered processes under endosulfan effect. Effects between males and females were compared. Pathways significantly altered by endosulfan exposure included the phosphatidylinositol signaling system, calcium signaling, the cGMP-PKG pathway, the inflammatory and immune system, protein processing in the endoplasmic reticulum, and GABA and taurine metabolism. Sex-dependent effects of endosulfan in the omics results that matched sex differences in cognitive and motor tests were found. These results shed light on the molecular basis of impaired neurodevelopment and contribute to the identification of new biomarkers of neurotoxicity.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{Gomez-Cabrero2019,

title = {STATegra, a comprehensive multi-omics dataset of B-cell differentiation in mouse},

author = { David Gomez-Cabrero and Sonia Tarazona and Isabel Ferreirós-Vidal and Ricardo N. Ramirez and Carlos Company and Andreas Schmidt and Theo Reijmers and Veronica von Saint Paul and Francesco Marabita and Javier Rodríguez-Ubreva and Antonio Garcia-Gomez and Thomas Carroll and Lee Cooper and Ziwei Liang and Gopuraja Dharmalingam and Frans van der Kloet and Amy C. Harms and Leandro Balzano-Nogueira and Vincenzo Lagani and Ioannis Tsamardinos and Michael Lappe and Dieter Maier and Johan A. Westerhuis and Thomas Hankemeier and Axel Imhof and Esteban Ballestar and Ali Mortazavi and Matthias Merkenschlager and Jesper Tegner and Ana Conesa},

url = {https://www.nature.com/articles/s41597-019-0202-7},

doi = {10.1038/s41597-019-0202-7},

issn = {20524463},

year  = {2019},

date = {2019-10-01},

journal = {Scientific data},

volume = {6},

number = {1},

pages = {256},

publisher = {NLM (Medline)},

abstract = {Multi-omics approaches use a diversity of high-throughput technologies to profile the different molecular layers of living cells. Ideally, the integration of this information should result in comprehensive systems models of cellular physiology and regulation. However, most multi-omics projects still include a limited number of molecular assays and there have been very few multi-omic studies that evaluate dynamic processes such as cellular growth, development and adaptation. Hence, we lack formal analysis methods and comprehensive multi-omics datasets that can be leveraged to develop true multi-layered models for dynamic cellular systems. Here we present the STATegra multi-omics dataset that combines measurements from up to 10 different omics technologies applied to the same biological system, namely the well-studied mouse pre-B-cell differentiation. STATegra includes high-throughput measurements of chromatin structure, gene expression, proteomics and metabolomics, and it is complemented with single-cell data. To our knowledge, the STATegra collection is the most diverse multi-omics dataset describing a dynamic biological system.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{Garcia-Solano2019,

title = {Differences in gene expression profiling and biomarkers between histological colorectal carcinoma subsets from the serrated pathway},

author = { José García-Solano and María del Carmen Turpin-Sevilla and Francisco García-García and Rosa Carbonell-Muñoz and Daniel Torres-Moreno and Ana Conesa and Pablo Conesa-Zamora},

url = {https://www.ncbi.nlm.nih.gov/pubmed/31025430},

doi = {10.1111/his.13889},

issn = {13652559},

year  = {2019},

date = {2019-10-01},

journal = {Histopathology},

volume = {75},

number = {4},

pages = {496--507},

publisher = {Blackwell Publishing Ltd},

abstract = {Aims: To discern the differences in expression profiling of two histological subtypes of colorectal carcinoma (CRC) arising from the serrated route (serrated adenocarcinoma (SAC) and CRC showing histological and molecular features of a high level of microsatellite instability (hmMSI-H) both sharing common features (female gender, right-sided location, mucinous histology, and altered CpG methylation), but dramatically differing in terms of prognosis, development of an immune response, and treatment options. Methods and results: Molecular signatures of SAC and hmMSI-H were obtained by the use of transcriptomic arrays; quantitative polymerase chain reaction (qPCR) and immunohistochemistry (IHC) were used to validate differentially expressed genes. An over-representation of innate immunity functions (granulomonocytic recruitment, chemokine production, Toll-like receptor signalling, and antigen processing and presentation) was obtained from this comparison, and intercellular cell adhesion molecule-1 (ICAM1) was more highly expressed in hmMSI-H, whereas two genes [those encoding calcitonin gene-related peptide-receptor component protein and C-X-C motif chemokine ligand 14 (CXCL14)] were more highly expressed in SAC. These array results were subsequently validated by qPCR, and by IHC for CXCL14 and ICAM1. Information retrieved from public databanks confirmed our findings. Conclusions: Our findings highlight specific functions and genes that provide a better understanding of the role of the immune response in the serrated pathological route and may be of help in identifying actionable molecules.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{Conesa2019,

title = {Making multi-omics data accessible to researchers},

author = { Ana Conesa and Stephan Beck},

url = {https://www.nature.com/articles/s41597-019-0258-4},

doi = {10.1038/s41597-019-0258-4},

issn = {20524463},

year  = {2019},

date = {2019-10-01},

journal = {Scientific data},

volume = {6},

number = {1},

pages = {251},

publisher = {NLM (Medline)},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{Ferreiros-Vidal2019,

title = {Feedforward regulation of Myc coordinates lineage-specific with housekeeping gene expression during B cell progenitor cell differentiation},

author = { Isabel Ferreirós-Vidal and Thomas Carroll and Tianyi Zhang and Vincenzo Lagani and Ricardo N. Ramirez and Elizabeth Ing-Simmons and Alicia G. Gómez-Valadés and Lee Cooper and Ziwei Liang and Georgios Papoutsoglou and Gopuraja Dharmalingam and Ya Guo and Sonia Tarazona and Sunjay J. Fernandes and Peri Noori and Gilad Silberberg and Amanda G. Fisher and Ioannis Tsamardinos and Ali Mortazavi and Boris Lenhard and Ana Conesa and Jesper Tegner and Matthias Merkenschlager and David Gomez-Cabrero},

url = {https://journals.plos.org/plosbiology/article?id=10.1371/journal.pbio.2006506},

doi = {10.1371/journal.pbio.2006506},

issn = {15457885},

year  = {2019},

date = {2019-01-01},

journal = {PLoS Biology},

volume = {17},

number = {4},

publisher = {Public Library of Science},

abstract = {The differentiation of self-renewing progenitor cells requires not only the regulation of lineage- and developmental stage–specific genes but also the coordinated adaptation of housekeeping functions from a metabolically active, proliferative state toward quiescence. How metabolic and cell-cycle states are coordinated with the regulation of cell type–specific genes is an important question, because dissociation between differentiation, cell cycle, and metabolic states is a hallmark of cancer. Here, we use a model system to systematically identify key transcriptional regulators of Ikaros-dependent B cell–progenitor differentiation. We find that the coordinated regulation of housekeeping functions and tissue-specific gene expression requires a feedforward circuit whereby Ikaros down-regulates the expression of Myc. Our findings show how coordination between differentiation and housekeeping states can be achieved by interconnected regulators. Similar principles likely coordinate differentiation and housekeeping functions during progenitor cell differentiation in other cell lineages.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{10.1093/database/baz085,

title = {Large expert-curated database for benchmarking document similarity detection in biomedical literature search},

author = { Peter Brown and RELISH Consortium (Ana Conesa) and Yaoqi Zhou},

url = {https://doi.org/10.1093/database/baz085},

doi = {10.1093/database/baz085},

issn = {1758-0463},

year  = {2019},

date = {2019-01-01},

journal = {Database},

volume = {2019},

abstract = {Document recommendation systems for locating relevant literature have mostly relied on methods developed a decade ago. This is largely due to the lack of a large offline gold-standard benchmark of relevant documents that cover a variety of research fields such that newly developed literature search techniques can be compared, improved and translated into practice. To overcome this bottleneck, we have established the RElevant LIterature SearcH consortium consisting of more than 1500 scientists from 84 countries, who have collectively annotated the relevance of over 180 000 PubMed-listed articles with regard to their respective seed (input) article/s. The majority of annotations were contributed by highly experienced, original authors of the seed articles. The collected data cover 76% of all unique PubMed Medical Subject Headings descriptors. No systematic biases were observed across different experience levels, research fields or time spent on annotations. More importantly, annotations of the same document pairs contributed by different scientists were highly concordant. We further show that the three representative baseline methods used to generate recommended articles for evaluation (Okapi Best Matching 25, Term Frequency–Inverse Document Frequency and PubMed Related Articles) had similar overall performances. Additionally, we found that these methods each tend to produce distinct collections of recommended articles, suggesting that a hybrid method may be required to completely capture all relevant articles. The established database server located at https://relishdb.ict.griffith.edu.au is freely available for the downloading of annotation data and the blind testing of new methods. We expect that this benchmark will be useful for stimulating the development of new powerful techniques for title and title/abstract-based search engines for relevant articles in biomedical research.},

note = {baz085},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{duscher2018transcriptional,

title = {Transcriptional profiling of the mutualistic bacterium Vibrio fischeri and an hfq mutant under modeled microgravity},

author = { Alexandrea A Duscher and Ana Conesa and Mary Bishop and Madeline M Vroom and Sergio D Zubizarreta and Jamie S Foster},

url = {https://doi.org/10.1038/s41526-018-0060-1},

doi = {10.1038/s41526-018-0060-1},

year  = {2018},

date = {2018-12-18},

journal = {npj Microgravity},

volume = {4},

number = {1},

pages = {25},

publisher = {Nature Publishing Group},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{10.3389/fgene.2018.00578,

title = {Elucidating the Role of Chromatin State and Transcription Factors on the Regulation of the Yeast Metabolic Cycle: A Multi-Omic Integrative Approach},

author = {Víctor Sánchez-Gaya and Salvador Casaní-Galdón and Manuel Ugidos and Zheng Kuang and Jane Mellor and Ana Conesa and Sonia Tarazona},

url = {https://www.frontiersin.org/article/10.3389/fgene.2018.00578},

doi = {10.3389/fgene.2018.00578},

issn = {1664-8021},

year  = {2018},

date = {2018-11-30},

journal = {Frontiers in Genetics},

volume = {9},

pages = {578},

abstract = {The Yeast Metabolic Cycle (YMC) is a model system in which levels of around 60% of the yeast transcripts cycle over time. The spatial and temporal resolution provided by the YMC has revealed that changes in the yeast metabolic landscape and chromatin status can be related to cycling gene expression. However, the interplay between histone modifications and transcription factor activity during the YMC is still poorly understood. Here we apply an innovative statistical approach to integrate chromatin state (ChIP-seq) and gene expression (RNA-seq) data to investigate the transcriptional control during the YMC. By using the multivariate regression models N-PLS (Partial Least Squares) and MORE (Multi-Omics REgulation) methodologies, we assess the contribution of histone marks and transcription factors to the regulation of gene expression in the YMC. We found that H3K18ac and H3K9ac were the most important histone modifications, whereas Sfp1, Hfi1, Pip2, Mig2 and Yhp1 emerged as the most relevant transcription factors. A significant association in the co-regulation of gene expression was found between H3K18ac and the transcription factors Pip2 (involved in fatty acids metabolism), Xbp1 (cyclin implicated in the regulation of carbohydrate and amino acid metabolism), and Hfi1 (involved in the formation of the SAGA complex). These results evidence the crucial role of histone lysine acetylation levels in the regulation of gene expression in the YMC through the coordinated action of transcription factors and lysine acetyl transferases.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{García-Solano2018,

title = {Two histologically colorectal carcinomas subsets from the serrated pathway show different methylome signatures and diagnostic biomarkers},

author = {José García Solano and María C. Turpin and Daniel Torres-Moreno and Francisco Huertas-López and Anne Tuomisto and Markus J. Mäkinen and Ana Conesa and Pablo Conesa-Zamora},

url = {https://doi.org/10.1186/s13148-018-0571-3},

doi = {10.1186/s13148-018-0571-3},

issn = {1868-7083},

year  = {2018},

date = {2018-11-09},

journal = {Clinical Epigenetics},

volume = {10},

number = {1},

pages = {141},

abstract = {Altered methylation patterns are driving forces in colorectal carcinogenesis. The serrated adenocarcinoma (SAC) and sporadic colorectal carcinoma showing histological and molecular features of microsatellite instability (hmMSI-H) are two endpoints of the so-called serrated pathological route sharing some characteristics but displaying a totally different immune response and clinical outcome. However, there are no studies comparing the methylome of these two subtypes of colorectal carcinomas. The methylation status of 450,000 CpG sites using the Infinium Human Methylation 450 BeadChip array was investigated in 48 colorectal specimens, including 39 SACs and 9 matched hmMSI-H.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{fabregas2018overexpression,

title = {Overexpression of the vascular brassinosteroid receptor BRL3 confers drought resistance without penalizing plant growth},

author = {Norma Fábregas and Fidel Lozano-Elena and David Blasco-Escámez and Takayuki Tohge and Cristina Martínez-Andújar and Alfonso Albacete and Sonia Osorio and Mariana Bustamante and José Luis Riechmann and Takahito Nomura and Takao Yokota Ana Conesa and Francisco Pérez Alfocea and Alisdair R. Fernie,2 and Ana I. Caño-Delgado},

url = {https://doi.org/10.1038/s41467-018-06861-3},

doi = {10.1038/s41467-018-06861-3},

year  = {2018},

date = {2018-11-08},

journal = {Nature communications},

volume = {9},

number = {1},

pages = {4680},

publisher = {Nature Publishing Group},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{doi:10.1002/mrd.23082,

title = {Changes in the uterine metabolome of the cow during the first seven days after estrus},

author = { Paula Tríbulo and Leandro Balzano-Nogueira and Ana Conesa and Luiz G. Siqueira and Peter J. Hansen},

url = {https://onlinelibrary.wiley.com/doi/abs/10.1002/mrd.23082},

doi = {10.1002/mrd.23082},

year  = {2018},

date = {2018-11-01},

journal = {Molecular Reproduction and Development},

volume = {0},

number = {ja},

abstract = {Abstract The uterine microenvironment during the first 7 days after ovulation accommodates and facilitates sperm transit to the oviduct and constitutes the sole source of nutrients required for development of preimplantation embryos. Knowledge of the composition of uterine fluid is largely incomplete. Using untargeted mass spectrometry, we characterized the uterine metabolome during the first 7 days of the estrous cycle. Bovine uteri were collected on day 0 (N=4), 3 (N=4), 5 (N=3) and 7 (N=4) relative to ovulation and flushed with Dulbecco’s phosphate-buffered saline. A total of 1,993 molecular features were detected of which 184 peaks with putative identification represent 147 unique metabolites, including amino acids, benzoic acids, lipid molecules, carbohydrates, purines, pyrimidines, vitamins, and other intermediate and secondary metabolites. Results revealed changes in the uterine metabolome as the cow transitions from ovulation to day 7 of the estrous cycle. The majority of metabolites reached maximum intensity on either day 5 or day 7 relative to ovulation. Moreover, several metabolites found in uterine fluid have signaling capabilities and some have been shown to affect preimplantation embryonic development. In conclusion, the metabolome of the bovine uterus changes during early stages of the estrous cycle and is likely to participate in the regulation of preimplantation embryonic development. Data reported here will serve as basis for future studies aiming to evaluate maternal regulation of preimplantation embryonic development and optimal conditions for culture of embryos. This article is protected by copyright. All rights reserved.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{Sanchez-Gaya2018,

title = {Elucidating the Role of Chromatin State and Transcription Factors on the Regulation of the Yeast Metabolic Cycle: A Multi-Omic Integrative Approach},

author = {Víctor Sánchez-Gaya and Salvador Casaní-Galdón and Manuel Ugidos and Zheng Kuang and Jane Mellor and Ana Conesa and Sonia Tarazona},

doi = {10.3389/fgene.2018.00578},

issn = {1664-8021},

year  = {2018},

date = {2018-11-01},

journal = {Frontiers in Genetics},

volume = {9},

publisher = {Frontiers Media SA},

abstract = {The Yeast Metabolic Cycle (YMC) is a model system in which levels of around 60% of the yeast transcripts cycle over time. The spatial and temporal resolution provided by the YMC has revealed that changes in the yeast metabolic landscape and chromatin status can be related to cycling gene expression. However, the interplay between histone modifications and transcription factor activity during the YMC is still poorly understood. Here we apply an innovative statistical approach to integrate chromatin state (ChIP-seq) and gene expression (RNA-seq) data to investigate the transcriptional control during the YMC. By using the multivariate regression models N-PLS (Partial Least Squares) and MORE (Multi-Omics REgulation) methodologies, we assessed the contribution of histone marks and transcription factors to the regulation of gene expression in the YMC. We found that H3K18ac and H3K9ac were the most important histone modifications, whereas Sfp1, Hfi1, Pip2, Mig2, and Yhp1 emerged as the most relevant transcription factors. A significant association in the co-regulation of gene expression was found between H3K18ac and the transcription factors Pip2 (involved in fatty acids metabolism), Xbp1 (cyclin implicated in the regulation of carbohydrate and amino acid metabolism), and Hfi1 (involved in the formation of the SAGA complex). These results evidence the crucial role of histone lysine acetylation levels in the regulation of gene expression in the YMC through the coordinated action of transcription factors and lysine acetyltransferases.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{ARROYOCRESPO20188,

title = {Tumor microenvironment-targeted poly-L-glutamic acid-based combination conjugate for enhanced triple negative breast cancer treatment},

author = {Juan J. Arroyo-Crespo and Ana Armiñán and David Charbonnier and Leandro Balzano-Nogueira and Francisco Huertas-López and Cristina Martí and Sonia Tarazona and Jerónimo Forteza and Ana Conesa and María J. Vicent},

url = {http://www.sciencedirect.com/science/article/pii/S0142961218306604},

doi = {https://doi.org/10.1016/j.biomaterials.2018.09.023},

issn = {0142-9612},

year  = {2018},

date = {2018-09-18},

journal = {Biomaterials},

volume = {186},

pages = {8 - 21},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{COLLIDULA20181500,

title = {Gene expression profile and molecular pathway datasets resulting from benzo(a)pyrene exposure in the liver and testis of adult tilapia},

author = {Reyna Cristina Colli-Dula and Xiefan Fang and David Moraga-Amador and Nacira Albornoz-Abud and Roberto Zamora-Bustillos and Ana Conesa and Omar Zapata-Perez and Diego Moreno and Emanuel Hernandez-Nuñez},

url = {http://www.sciencedirect.com/science/article/pii/S2352340918310667},

doi = {https://doi.org/10.1016/j.dib.2018.08.206},

issn = {2352-3409},

year  = {2018},

date = {2018-09-05},

journal = {Data in Brief},

volume = {20},

pages = {1500 - 1509},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{Newman2923,

title = {Event Analysis: Using Transcript Events To Improve Estimates of Abundance in RNA-seq Data},

author = { Jeremy R. B. Newman and Patrick Concannon and Manuel Tardaguila and Ana Conesa and Lauren M. McIntyre},

url = {http://www.g3journal.org/content/8/9/2923},

doi = {10.1534/g3.118.200373},

year  = {2018},

date = {2018-08-30},

journal = {G3: Genes, Genomes, Genetics},

volume = {8},

number = {9},

pages = {2923--2940},

publisher = {G3: Genes, Genomes, Genetics},

abstract = {Alternative splicing leverages genomic content by allowing the synthesis of multiple transcripts and, by implication, protein isoforms, from a single gene. However, estimating the abundance of transcripts produced in a given tissue from short sequencing reads is difficult and can result in both the construction of transcripts that do not exist, and the failure to identify true transcripts. An alternative approach is to catalog the events that make up isoforms (splice junctions and exons). We present here the Event Analysis (EA) approach, where we project transcripts onto the genome and identify overlapping/unique regions and junctions. In addition, all possible logical junctions are assembled into a catalog. Transcripts are filtered before quantitation based on simple measures: the proportion of the events detected, and the coverage. We find that mapping to a junction catalog is more efficient at detecting novel junctions than mapping in a splice aware manner. We identify 99.8% of true transcripts while iReckon identifies 82% of the true transcripts and creates more transcripts not included in the simulation than were initially used in the simulation. Using PacBio Iso-seq data from a mouse neural progenitor cell model, EA detects 60% of the novel junctions that are combinations of existing exons while only 43% are detected by STAR. EA further detects ~5,000 annotated junctions missed by STAR. Filtering transcripts based on the proportion of the transcript detected and the number of reads on average supporting that transcript captures 95% of the PacBio transcriptome. Filtering the reference transcriptome before quantitation, results in is a more stable estimate of isoform abundance, with improved correlation between replicates. This was particularly evident when EA is applied to an RNA-seq study of type 1 diabetes (T1D), where the coefficient of variation among subjects (n = 81) in the transcript abundance estimates was substantially reduced compared to the estimation using the full reference. EA focuses on individual transcriptional events. These events can be quantitate and analyzed directly or used to identify the probable set of expressed transcripts. Simple rules based on detected events and coverage used in filtering result in a dramatic improvement in isoform estimation without the use of ancillary data (e.g., ChIP, long reads) that may not be available for many studies.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{Arzalluz-Luque2018,

title = {Single-cell RNAseq for the study of isoforms---how is that possible?},

author = {Ángeles Arzalluz-Luque and Conesa Ana },

url = {http://doi.org/10.1186/s13059-018-1496-z},

doi = {10.1186/s13059-018-1496-z},

issn = {1474-760X},

year  = {2018},

date = {2018-08-10},

journal = {Genome Biology},

volume = {19},

number = {1},

pages = {110},

abstract = {Single-cell RNAseq and alternative splicing studies have recently become two of the most prominent applications of RNAseq. However, the combination of both is still challenging, and few research efforts have been dedicated to the intersection between them. Cell-level insight on isoform expression is required to fully understand the biology of alternative splicing, but it is still an open question to what extent isoform expression analysis at the single-cell level is actually feasible. Here, we establish a set of four conditions that are required for a successful single-cell-level isoform study and evaluate how these conditions are met by these technologies in published research.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{Colli-Dula2018,

title = {Transcriptome analysis reveals novel insights into the response of low-dose benzo(a)pyrene exposure in male tilapia},

author = {Reyna Cristina Colli-Dula and Xiefan Fang and David Moraga-Amador and Nacira Albornoz-Abud and Roberto Zamora-Bustillos and Ana Conesa and Omar Zapata-Perez and Diego Moreno and Emanuel Hernandez-Nuñez},

url = {http://www.sciencedirect.com/science/article/pii/S0166445X18303503},

doi = {10.1016/j.aquatox.2018.06.005},

issn = {0166-445X},

year  = {2018},

date = {2018-08-01},

journal = {Aquatic Toxicology},

volume = {201},

pages = {162 - 173},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{tarazona2018multiomics,

title = {Multiomics Data Integration in Time Series Experiments},

author = { Sonia Tarazona and Leandro Balzano-Nogueira and Ana Conesa},

url = {https://doi.org/10.1016/bs.coac.2018.06.005},

doi = {10.1016/bs.coac.2018.06.005},

year  = {2018},

date = {2018-07-31},

journal = {Comprehensive Analytical Chemistry},

volume = {8},

pages = {505-532},

publisher = {Elsevier},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{Hernández-de-Diego2018,

title = {PaintOmics 3: a web resource for the pathway analysis and visualization of multi-omics data},

author = {Hernández-de-Diego, Rafael and Tarazona, Sonia and Martínez-Mira, Carlos and Balzano-Nogueira, Leandro and Furió-Tarí, Pedro and Pappas, Jr ,Georgios J and Conesa, Ana},

url = {http://dx.doi.org/10.1093/nar/gky466},

doi = {http://dx.doi.org/10.1093/nar/gky466},

year  = {2018},

date = {2018-07-02},

journal = {Nucleic Acids Research},

pages = {gky466},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{10.3389/fmicb.2018.01359,

title = {Comparative Metagenomics Provides Insight Into the Ecosystem Functioning of the Shark Bay Stromatolites, Western Australia},

author = {Joany Babilonia and Ana Conesa and Giorgio Casaburi and Cecile Pereira and Artemis S. Louyakis and R. Pamela Reid and Jamie S. Foster},

url = {http://www.frontiersin.org/article/10.3389/fmicb.2018.01359},

doi = {10.3389/fmicb.2018.01359},

issn = {1664-302X},

year  = {2018},

date = {2018-06-25},

journal = {Frontiers in Microbiology},

volume = {9},

pages = {1359},

abstract = {Stromatolites are organosedimentary build-ups that have formed as a result of the sediment trapping, binding and precipitating activities of microbes. Today, extant systems provide an ideal platform for understanding the structure, composition, and interactions between stromatolite-forming microbial communities and their respective environments. In this study, we compared the metagenomes of three prevalent stromatolite-forming microbial mat types in the Spaven Province of Hamelin Pool, Shark Bay located in Western Australia. These stromatolite-forming mat types included an intertidal pustular mat as well as a smooth and colloform mat types located in the subtidal zone. Additionally, the metagenomes of an adjacent, non-lithifying mat located in the upper intertidal zone were also sequenced for comparative purposes. Taxonomic and functional gene analyses revealed distinctive differences between the lithifying and non-lithifying mat types, which strongly correlated with water depth. Three distinct populations emerged including the upper intertidal non-lithifying mats, the intertidal pustular mats associated with unlaminated carbonate build-ups, and the subtidal colloform and smooth mat types associated with laminated structures. Functional analysis of metagenomes revealed that amongst stromatolite-forming mats there was an enrichment of photosynthesis pathways in the pustular stromatolite-forming mats. In the colloform and smooth stromatolite-forming mats, however, there was an increase in the abundance of genes associated with those heterotrophic metabolisms typically associated with carbonate mineralization, such as sulfate reduction. The comparative metagenomic analyses suggest that stromatolites of Hamelin Pool may form by two distinctive processes that are highly dependent on water depth. These results provide key insight into the potential adaptive strategies and synergistic interactions between microbes and their environments that may lead to stromatolite formation and accretion.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{doi:10.1093/gbe/evy116,

title = {Evidence of the Red-Queen Hypothesis from Accelerated Rates of Evolution of Genes Involved in Biotic Interactions in Pneumocystis},

author = { Luis Delaye and Susana Ruiz-Ruiz and Enrique Calderon and Sonia Tarazona and Ana Conesa and Andrés Moya},

url = {http://dx.doi.org/10.1093/gbe/evy116},

doi = {10.1093/gbe/evy116},

year  = {2018},

date = {2018-06-01},

journal = {Genome Biology and Evolution},

volume = {10},

number = {6},

pages = {1596-1606},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{Zhu2018,

title = {GRAM-CNN: a deep learning approach with local context for named entity recognition in biomedical text},

author = {Zhu, Qile and Li, Xiaolin and Conesa, Ana and Pereira, Cécile},

url = {http://dx.doi.org/10.1093/bioinformatics/btx815},

doi = {10.1093/bioinformatics/btx815},

year  = {2018},

date = {2018-05-01},

journal = {Bioinformatics},

volume = {34},

number = {9},

pages = {1547-1554},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{García-Molinero2018,

title = {The SAGA/TREX-2 subunit Sus1 binds widely to transcribed genes and affects mRNA turnover globally},

author = {García-Molinero, Varinia and Garcíaa-Martínez, José and Reja, Rohit and Furió-Tarí, Pedro and Antúnez, Oreto and Vinayachandran, Vinesh and Conesa, Ana and Pugh, B. Franklin and Pérez-Ortín, José E. and Rodríguez-Navarro, Susana},

url = {http://doi.org/10.1186/s13072-018-0184-2},

doi = {10.1186/s13072-018-0184-2},

year  = {2018},

date = {2018-03-29},

journal = {Epigenetics & Chromatin},

volume = {11},

number = {1},

pages = {13},

abstract = {Eukaryotic transcription is regulated through two complexes, the general transcription factor IID (TFIID) and the coactivator Spt--Ada--Gcn5 acetyltransferase (SAGA). Recent findings confirm that both TFIID and SAGA contribute to the synthesis of nearly all transcripts and are recruited genome-wide in yeast. However, how this broad recruitment confers selectivity under specific conditions remains an open question.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{Tardaguila2018,

title = {SQANTI: extensive characterization of long-read transcript sequences for quality control in full-length transcriptome identification and quantification},

author = {Tardaguila, Manuel and de la Fuente, Lorena and Marti, Cristina and Pereira, Cécile and Pardo-Palacios, Francisco Jose and del Risco, Hector and Ferrell, Marc and Mellado, Maravillas and Macchietto, Marissa and Verheggen, Kenneth and Edelmann, Mariola and Ezkurdia, Iakes and Vazquez, Jesus and Tress, Michael and Mortazavi, Ali and Martens, Lennart and Rodriguez-Navarro, Susana and Moreno-Manzano, Victoria and Conesa, Ana},

url = {http://genome.cshlp.org/content/early/2018/02/09/gr.222976.117.abstract},

doi = {10.1101/gr.222976.117},

year  = {2018},

date = {2018-02-09},

journal = {Genome Research},

abstract = {High-throughput sequencing of full-length transcripts using long reads has paved the way for the discovery of thousands of novel transcripts, even in well-annotated mammalian species. The advances in sequencing technology have created a need for studies and tools that can characterize these novel variants. Here, we present SQANTI, an automated pipeline for the classification of long-read transcripts that can assess the quality of data and the preprocessing pipeline using 47 unique descriptors. We apply SQANTI to a neuronal mouse transcriptome using Pacific Biosciences (PacBio) long reads and illustrate how the tool is effective in characterizing and describing the composition of the full-length transcriptome. We perform extensive evaluation of ToFU PacBio transcripts by PCR to reveal that an important number of the novel transcripts are technical artifacts of the sequencing approach and that SQANTI quality descriptors can be used to engineer a filtering strategy to remove them. Most novel transcripts in this curated transcriptome are novel combinations of existing splice sites, resulting more frequently in novel ORFs than novel UTRs, and are enriched in both general metabolic and neural-specific functions. We show that these new transcripts have a major impact in the correct quantification of transcript levels by state-of-the-art short-read-based quantification algorithms. By comparing our iso-transcriptome with public proteomics databases, we find that alternative isoforms are elusive to proteogenomics detection. SQANTI allows the user to maximize the analytical outcome of long-read technologies by providing the tools to deliver quality-evaluated and curated full-length transcriptomes.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{doi:10.1093/bioinformatics/btx578,

title = {Identification and visualization of differential isoform expression in RNA-seq time series},

author = { María José Nueda and Jordi Martorell-Marugan and Cristina Martí and Sonia Tarazona and Ana Conesa},

url = {http://dx.doi.org/10.1093/bioinformatics/btx578},

doi = {10.1093/bioinformatics/btx578},

year  = {2018},

date = {2018-02-01},

journal = {Bioinformatics},

volume = {34},

number = {3},

pages = {524-526},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{martinez2018mosim,

title = {MOSim: Multi-Omics Simulation in R},

author = { Carlos Martínez-Mira and Ana Conesa and Sonia Tarazona},

url = {https://doi.org/10.1101/421834},

doi = {10.1101/421834},

year  = {2018},

date = {2018-01-01},

journal = {bioRxiv},

pages = {421834},

publisher = {Cold Spring Harbor Laboratory},

keywords = {},

pubstate = {forthcoming},

tppubtype = {article}

}

@article{ISI:000417056500003,

title = {Growth of Chlamydia pneumoniae Is Enhanced in Cell swith Impaired 

Mitochondrial Function},

author = { N. Kaeding and I. Kaufhold and C. Mueller and M. Szaszak and K. Shima and T. Weinmaier and R. Lomas and A. Conesa and P. Schmitt-Kopplin and T. Rattei and J. Rupp},

url = {http://dx.doi.org/10.3389/fcimb.2017.00499},

doi = {10.3389/fcimb.2017.00499},

issn = {2235-2988},

year  = {2017},

date = {2017-12-01},

journal = {FRONTIERS IN CELLULAR AND INFECTION MICROBIOLOGY},

volume = {7},

abstract = {Effective growth and replication of obligate intracellular pathogens 

depend on host cell metabolism. How this is connected to host cell 

mitochondrial function has not been studied so far. Recent studies 

suggest that growth of intracellular bacteria such as Chlamydia 

pneumoniae is enhanced in a low oxygen environment, arguing for a 

particular mechanistic role of the mitochondrial respiration in 

controlling intracellular progeny. Metabolic changes in C. pneumoniae 

infected epithelial cells were analyzed under normoxic (O-2 approximate 

to 20%) and hypoxic conditions (O-2 < 3%). We observed that infection 

of epithelial cells with C. pneumoniae under normoxia impaired 

mitochondrial function characterized by an enhanced mitochondrial 

membrane potential and ROS generation. Knockdown and mutation of the 

host cell ATP synthase resulted in an increased chlamydial replication 

already under normoxic conditions. As expected, mitochondrial 

hyperpolarization was observed in non-infected control cells cultured 

under hypoxic conditions, which was beneficial for C. pneumoniae growth. 

Taken together, functional and genetically encoded mitochondrial 

dysfunction strongly promotes intracellular growth of C. pneumoniae.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{ISI:000414165900003,

title = {Disease-specific biases in alternative splicing and tissue-specific 

dysregulation revealed by multitissue profiling of lymphocyte gene 

expression in type 1 diabetes},

author = { J. R. B. Newman and A. Conesa and M. Mika and F. N. New and S. Onengut-Gumuscu and M. A. Atkinson and S. S. Rich and L. M. McIntyre and P. Concannon},

url = {http://dx.doi.org/10.1101/gr.217984.116},

doi = {10.1101/gr.217984.116},

issn = {1088-9051},

year  = {2017},

date = {2017-11-01},

journal = {GENOME RESEARCH},

volume = {27},

number = {11},

pages = {1807-1815},

abstract = {Genome-wide association studies (GWAS) have identified multiple, shared 

allelic associations with many autoimmune diseases. However, the 

pathogenic contributions of variants residing in risk loci remain 

unresolved. The location of the majority of shared disease-associated 

variants in noncoding regions suggests they contribute to risk of 

autoimmunity through effects on gene expression in the immune system. In 

the current study, we test this hypothesis by applying RNA sequencing to 

CD4(+), CD8(+), and CD19(+) lymphocyte populations isolated from 81 

subjects with type 1 diabetes (T1D). We characterize and compare the 

expression patterns across these cell types for three gene sets: all 

genes, the set of genes implicated in autoimmune disease risk by GWAS, and the subset of these genes specifically implicated in T1D. We 

performed RNA sequencing and aligned the reads to both the human 

reference genome and a catalog of all possible splicing events developed 

from the genome, thereby providing a comprehensive evaluation of the 

roles of gene expression and alternative splicing (AS) in autoimmunity. 

Autoimmune candidate genes displayed greater expression specificity in 

the three lymphocyte populations relative to other genes, with 

significantly increased levels of splicing events, particularly those 

predicted to have substantial effects on protein isoform structure and 

function (e.g., intron retention, exon skipping). The majority of 

single-nucleotide polymorphisms within T1D-associated loci were also 

associated with one or more cis-expression quantitative trait loci 

(ciseQTLs) and/or splicing eQTLs. Our findings highlight a substantial, and previously underrecognized, role for AS in the pathogenesis of 

autoimmune disorders and particularly for T1D.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{doi:10.1093/bib/bbx122,

title = {A benchmarking of workflows for detecting differential splicing and differential expression at isoform level in human RNA-seq studies},

author = { Gabriela A. Merino and Ana Conesa and Elmer A. Fernández},

url = {http://dx.doi.org/10.1093/bib/bbx122},

doi = {10.1093/bib/bbx122},

year  = {2017},

date = {2017-10-13},

journal = {Briefings in Bioinformatics},

pages = {bbx122},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{ISI:000411824103042,

title = {Certolizumab Pegol Effectiveness and Retention Rate in Psoriatic 

Arthritis. Real Life Data},

author = { A. Conesa and M. Fernandez and R. Exposito and J. Campos and J. Ramon Lamua and M. del Pilar Navarro and P. Rubio-Munoz and P. Ahijado-Guzman and C. M. Gonzalez},

issn = {2326-5191},

year  = {2017},

date = {2017-10-01},

journal = {ARTHRITIS & RHEUMATOLOGY},

volume = {69},

number = {10},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{ISI:000411874500006,

title = {Guidelines for Developing Successful Short Advanced Courses in Systems 

Medicine and Systems Biology},

author = { D. Gomez-Cabrero and F. Marabita and S. Tarazona and I. Cano and J. Roca and A. Conesa and P. Sabatier and J. Tegner},

url = {http://dx.doi.org/10.1016/j.cels.2017.05.013},

doi = {10.1016/j.cels.2017.05.013},

issn = {2405-4712},

year  = {2017},

date = {2017-09-01},

journal = {CELL SYSTEMS},

volume = {5},

number = {3},

pages = {168-175},

abstract = {Systems medicine and systems biology have inherent educational 

challenges. These have largely been addressed either by providing new 

masters programs or by redesigning undergraduate programs. In contrast, short courses can respond to a different need: they can provide 

condensed updates for professionals across academia, the clinic, and 

industry. These courses have received less attention. Here, we share our 

experiences in developing and providing such courses to current and 

future leaders in systems biology and systems medicine. We present 

guidelines for how to reproduce our courses, and we offer suggestions 

for how to select students who will nurture an interdisciplinary 

learning environment and thrive there.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{ISI:000411981000002,

title = {The eBioKit, a stand-alone educational platform for bioinformatics},

author = { R. Hernandez-de-Diego and E. P. de Villiers and T. Klingstrom and H. Gourle and A. Conesa and E. Bongcam-Rudloff},

url = {http://dx.doi.org/10.1371/journal.pcbi.1005616},

doi = {10.1371/journal.pcbi.1005616},

issn = {1553-734X},

year  = {2017},

date = {2017-09-01},

journal = {PLOS COMPUTATIONAL BIOLOGY},

volume = {13},

number = {9},

abstract = {Bioinformatics skills have become essential for many research areas; 

however, the availability of qualified researchers is usually lower than 

the demand and training to increase the number of able bioinformaticians 

is an important task for the bioinformatics community. When conducting 

training or hands-on tutorials, the lack of control over the analysis 

tools and repositories often results in undesirable situations during 

training, as unavailable online tools or version conflicts may delay, complicate, or even prevent the successful completion of a training 

event. The eBioKit is a stand-alone educational platform that hosts 

numerous tools and databases for bioinformatics research and allows 

training to take place in a controlled environment. A key advantage of 

the eBioKit over other existing teaching solutions is that all the 

required software and databases are locally installed on the system, significantly reducing the dependence on the internet. Furthermore, the 

architecture of the eBioKit has demonstrated itself to be an excellent 

balance between portability and performance, not only making the eBioKit 

an exceptional educational tool but also providing small research groups 

with a platform to incorporate bioinformatics analysis in their 

research. As a result, the eBioKit has formed an integral part of 

training and research performed by a wide variety of universities and 

organizations such as the Pan African Bioinformatics Network (H3ABioNet) 

as part of the initiative Human Heredity and Health in Africa 

(H3Africa), the Southern Africa Network for Biosciences (SAnBio) 

initiative, the Biosciences eastern and central Africa (BecA) hub, and 

the International Glossina Genome Initiative.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{ISI:000402747300007,

title = {Dynamic Gene Regulatory Networks of Human Myeloid Differentiation},

author = { R. N. Ramirez and N. C. El-Ali and M. A. Mager and D. Wyman and A. Conesa and A. Mortazavi},

url = {http://dx.doi.org/10.1016/j.cels.2017.03.005},

doi = {10.1016/j.cels.2017.03.005},

issn = {2405-4712},

year  = {2017},

date = {2017-04-01},

journal = {CELL SYSTEMS},

volume = {4},

number = {4},

pages = {416+},

abstract = {The reconstruction of gene regulatory networks underlying cell 

differentiation from high-throughput gene expression and chromatin data 

remains a challenge. Here, we derive dynamic gene regulatory networks 

for human myeloid differentiation using a 5-day time series of RNA-seq 

and ATAC-seq data. We profile HL-60 promyelocytes differentiating into 

macrophages, neutrophils, monocytes, and monocyte-derived macrophages. 

We find a rapid response in the expression of key transcription factors 

and lineage markers that only regulate a subset of their targets at a 

given time, which is followed by chromatin accessibility changes that 

occur later along with further gene expression changes. We observe 

differences between promyelocyte-and monocytederived macrophages at both 

the transcriptional and chromatin landscape level, despite using the 

same differentiation stimulus, which suggest that the path taken by 

cells in the differentiation landscape defines their end cell state. 

More generally, our approach of combining neighboring time points and 

replicates to achieve greater sequencing depth can efficiently infer 

footprint-based regulatory networks from long series data.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{ISI:000399043900345,

title = {Network Biology of Menstrual Cycle to Understand the Key Drivers of 

Endometrial Receptivity.},

author = { P. Sebastian-Leon and A. Conesa and V. Arnau and J. Remohi and A. Pellicer and C. Simon and P. Diaz-Gimeno},

issn = {1933-7191},

year  = {2017},

date = {2017-03-01},

journal = {REPRODUCTIVE SCIENCES},

volume = {24},

number = {1},

pages = {162A},

organization = {Soc Reprod Invest},

note = {64th Annual Scientific Meeting of the 

Society-for-Reproductive-Investigation (SRI), Orlando, FL, MAR 15-18, 2017},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{ISI:000392353200004,

title = {Identification of miRNA from Bouteloua gracilis, a drought tolerant 

grass, by deep sequencing and their in silico analysis},

author = { P. Lucia Ordonez-Baquera and E. Gonzalez-Rodriguez and G. Armando Aguado-Santacruz and Q. Rascon-Cruz and A. Conesa and V. Moreno-Brito and R. Echavarria and J. Dominguez-Viveros},

url = {http://dx.doi.org/10.1016/j.compbiolchem.2016.11.001},

doi = {10.1016/j.compbiolchem.2016.11.001},

issn = {1476-9271},

year  = {2017},

date = {2017-02-01},

journal = {COMPUTATIONAL BIOLOGY AND CHEMISTRY},

volume = {66},

pages = {26-35},

abstract = {Background: MicroRNAs (miRNAs) are small non-coding RNA molecules that 

regulate signal transduction, development, metabolism, and stress 

responses in plants through post-transcriptional degradation and/or 

translational repression of target mRNAs. Several studies have addressed 

the role of miRNAs in model plant species, but miRNA expression and 

function in economically important forage crops, such as Bouteloua 

gracilis (Poaceae), a high-quality and drought-resistant grass 

distributed in semiarid regions of the United States and northern Mexico 

remain unknown. 

Results: We applied high-throughput sequencing technology and 

bioinformatics analysis and identified 31 conserved miRNA families and 

53 novel putative miRNAs with different abundance of reads in 

chlorophyllic cell cultures derived from B. gracilis. Some conserved 

miRNA families were highly abundant and possessed predicted targets 

involved in metabolism, plant growth and development, and stress 

responses. We also predicted additional identified novel miRNAs with 

specific targets, including B. gracilis ESTs, which were detected under 

drought stress conditions. 

Conclusions: Here we report 31 conserved miRNA families and 53 putative 

novel miRNAs in B. gracilis. Our results suggested the presence of 

regulatory miRNAs involved in modulating physiological and stress 

responses in this grass species. (C) 2016 Elsevier Ltd. All rights 

reserved.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{ISI:000390471900128,

title = {Impacts of abundance of Candidatus Liberibacter on the citrus 

phyto-microbiome},

author = { R. Blaustein and J. Meyer and A. Conesa and G. Lorca and M. Teplitski},

issn = {0031-949X},

year  = {2016},

date = {2016-12-01},

journal = {PHYTOPATHOLOGY},

volume = {106},

number = {12, S},

pages = {25-26},

organization = {Amer Phytopathol Soc},

note = {Annual Meeting of the American-Phytopathological-Society (APS), Tampa, FL, JUL 30-AUG 03, 2016},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{ISI:000387621900001,

title = {Making sense of big data in health research: towards an EU action plan 

(vol 8, pg 71, 2016)},

author = { C. Auffray and R. Balling and I. Barroso and L. Bencze and M. Benson and J. Bergeron and E. Bernal-Delgado and N. Blomberg and C. Bock and A. Conesa and S. Del Signore and C. Delogne and P. Devilee and A. Di Meglio and M. Eijkemans and P. Flicek and N. Graf and V. Grimm and H. Guchelaar and Y. Guo and I. G. Gut and A. Hanbury and S. Hanif and R. Hilgers and A. Honrado and D. R. Hose and J. Houwing-Duistermaat and T. Hubbard and S. H. Janacek and H. Karanikas and T. Kievits and M. Kohler and A. Kremer and J. Lanfear and T. Lengauer and E. Maes and T. Meert and W. Muller and D. Nickel and P. Oledzki and B. Pedersen and M. Petkovic and K. Pliakos and M. Rattray and J. Redon i Mas and R. Schneider and T. Sengstag and X. Serra-Picamal and W. Spek and L. A. I. Vaas and O. van Batenburg and M. Vandelaer and P. Varnai and P. Villoslada and J. A. Vizcaino and J. P. M. Wubbe and G. Zanetti},

url = {http://dx.doi.org/10.1186/s13073-016-0376-y},

doi = {10.1186/s13073-016-0376-y},

issn = {1756-994X},

year  = {2016},

date = {2016-11-01},

journal = {GENOME MEDICINE},

volume = {8},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{ISI:000392470500001,

title = {RGmatch: matching genomic regions to proximal genes in omics data 

integration},

author = { P. Furio-Tari and A. Conesa and S. Tarazona},

url = {http://dx.doi.org/10.1186/s12859-016-1293-1},

doi = {10.1186/s12859-016-1293-1},

issn = {1471-2105},

year  = {2016},

date = {2016-11-01},

journal = {BMC BIOINFORMATICS},

volume = {17},

number = {15},

abstract = {Background: The integrative analysis of multiple genomics data often 

requires that genome coordinates-based signals have to be associated 

with proximal genes. The relative location of a genomic region with 

respect to the gene (gene area) is important for functional data 

interpretation; hence algorithms that match regions to genes should be 

able to deliver insight into this information. 

Results: In this work we review the tools that are publicly available 

for making region-to-gene associations. We also present a novel method, RGmatch, a flexible and easy-to-use Python tool that computes 

associations either at the gene, transcript, or exon level, applying a 

set of rules to annotate each region-gene association with the region 

location within the gene. RGmatch can be applied to any organism as long 

as genome annotation is available. Furthermore, we qualitatively and 

quantitatively compare RGmatch to other tools. 

Conclusions: RGmatch simplifies the association of a genomic region with 

its closest gene. At the same time, it is a powerful tool because the 

rules used to annotate these associations are very easy to modify 

according to the researcher's specific interests. Some important 

differences between RGmatch and other similar tools already in existence 

are RGmatch's flexibility, its wide range of user options, compatibility 

with any annotatable organism, and its comprehensive and user-friendly 

output.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{ISI:000383344400010,

title = {Transcriptome modulation during host shift is driven by secondary 

metabolites in desert Drosophila},

author = { D. N. De Panis and J. Padro and P. Furio-Tari and S. Tarazona and P. S. Milla Carmona and I. M. Soto and H. Dopazo and A. Conesa and E. Hasson},

url = {http://dx.doi.org/10.1111/mec.13785},

doi = {10.1111/mec.13785},

issn = {0962-1083},

year  = {2016},

date = {2016-09-01},

journal = {MOLECULAR ECOLOGY},

volume = {25},

number = {18},

pages = {4534-4550},

abstract = {High-throughput transcriptome studies are breaking new ground to 

investigate the responses that organisms deploy in alternative 

environments. Nevertheless, much remains to be understood about the 

genetic basis of host plant adaptation. Here, we investigate genome-wide 

expression in the fly Drosophila buzzatii raised in different 

conditions. This species uses decaying tissues of cactus of the genus 

Opuntia as primary rearing substrate and secondarily, the necrotic 

tissues of the columnar cactus Trichocereus terscheckii. The latter 

constitutes a harmful host, rich in mescaline and other related 

phenylethylamine alkaloids. We assessed the transcriptomic responses of 

larvae reared in Opuntia sulphurea and T. terscheckii, with and without 

the addition of alkaloids extracted from the latter. Whole-genome 

expression profiles were massively modulated by the rearing environment, mainly by the presence of T. terscheckii alkaloids. Differentially 

expressed genes were mainly related to detoxification, oxidation-reduction and stress response; however, we also found genes 

involved in development and neurobiological processes. In conclusion, our study contributes new data onto the role of transcriptional 

plasticity in response to alternative rearing environments.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{ISI:000383427700002,

title = {A survey of best practices for RNA-seq data analysis (vol 17, 13, 2016)},

author = { A. Conesa and P. Madrigal and S. Tarazona and D. Gomez-Cabrero and A. Cervera and A. McPherson and M. W. Szczesniak and D. J. Gaffney and L. L. Elo and X. Zhang and A. Mortazavi},

url = {http://dx.doi.org/10.1186/s13059-016-1047-4},

doi = {10.1186/s13059-016-1047-4},

issn = {1474-760X},

year  = {2016},

date = {2016-08-01},

journal = {GENOME BIOLOGY},

volume = {17},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{ISI:000379786800029,

title = {spongeScan: A web for detecting microRNA binding elements in lncRNA 

sequences},

author = { P. Furio-Tari and S. Tarazona and T. Gabaldon and A. J. Enright and A. Conesa},

url = {http://dx.doi.org/10.1093/nar/gkw443},

doi = {10.1093/nar/gkw443},

issn = {0305-1048},

year  = {2016},

date = {2016-07-01},

journal = {NUCLEIC ACIDS RESEARCH},

volume = {44},

number = {W1},

pages = {W176-W180},

abstract = {Non-coding RNA transcripts such as microRNAs (miRNAs) and long 

non-coding RNAs (lncRNAs) are important genetic regulators. However, the 

functions of many of these transcripts are still not clearly understood. 

Recently, it has become apparent that there is significant crosstalk 

between miRNAs and lncRNAs and that this creates competition for binding 

between the miRNA, a lncRNA and other regulatory targets. Indeed, various competitive endogenous RNAs (ceRNAs) have already been 

identified where a lncRNA acts by sequestering miRNAs. This implies the 

down-regulation in the interaction of the miRNAs with their mRNA 

targets, what has been called a sponge effect. Multiple approaches exist 

for the prediction of miRNA targets in mRNAs. However, few methods exist 

for the prediction of miRNA response elements (MREs) in lncRNAs acting 

as ceRNAs (sponges). Here, we present spongeScan 

(http://spongescan.rc.ufl.edu), a graphical web tool to compute and 

visualize putative MREs in lncRNAs, along with different measures to 

assess their likely behavior as ceRNAs.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{ISI:000378592900001,

title = {Making sense of big data in health research: Towards an EU action plan},

author = { C. Auffray and R. Balling and I. Barroso and L. Bencze and M. Benson and J. Bergeron and E. Bernal-Delgado and N. Blomberg and C. Bock and A. Conesa and S. Del Signore and C. Delogne and P. Devilee and A. Di Meglio and M. Eijkemans and P. Flicek and N. Graf and V. Grimm and H. Guchelaar and Y. Guo and I. G. Gut and A. Hanbury and S. Hanif and R. Hilgers and A. Honrado and D. R. Hose and J. Houwing-Duistermaat and T. Hubbard and S. H. Janacek and H. Karanikas and T. Kievits and M. Kohler and A. Kremer and J. Lanfear and T. Lengauer and E. Maes and T. Meert and W. Mueller and D. Nickel and P. Oledzki and B. Pedersen and M. Petkovic and K. Pliakos and M. Rattray and J. Redon i Mas and R. Schneider and T. Sengstag and X. Serra-Picamal and W. Spek and L. A. I. Vaas and O. van Batenburg and M. Vandelaer and P. Varnai and P. Villoslada and J. A. Vizcaino and J. P. M. Wubbe and G. Zanetti},

url = {http://dx.doi.org/10.1186/s13073-016-0323-y},

doi = {10.1186/s13073-016-0323-y},

issn = {1756-994X},

year  = {2016},

date = {2016-06-01},

journal = {GENOME MEDICINE},

volume = {8},

abstract = {Medicine and healthcare are undergoing profound changes. Whole-genome 

sequencing and high-resolution imaging technologies are key drivers of 

this rapid and crucial transformation. Technological innovation combined 

with automation and miniaturization has triggered an explosion in data 

production that will soon reach exabyte proportions. How are we going to 

deal with this exponential increase in data production? The potential of 

``big data'' for improving health is enormous but, at the same time, we face a wide range of challenges to overcome urgently. Europe is very 

proud of its cultural diversity; however, exploitation of the data made 

available through advances in genomic medicine, imaging, and a wide 

range of mobile health applications or connected devices is hampered by 

numerous historical, technical, legal, and political barriers. European 

health systems and databases are diverse and fragmented. There is a lack 

of harmonization of data formats, processing, analysis, and data 

transfer, which leads to incompatibilities and lost opportunities. Legal 

frameworks for data sharing are evolving. Clinicians, researchers, and 

citizens need improved methods, tools, and training to generate, analyze, and query data effectively. Addressing these barriers will 

contribute to creating the European Single Market for health, which will 

improve health arid healthcare for all Europearis.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{ISI:000381318400009,

title = {Separating common from distinctive variation},

author = { F. M. van der Kloet and P. Sebastian-Leon and A. Conesa and A. K. Smilde and J. A. Westerhuis},

url = {http://dx.doi.org/10.1186/s12859-016-1037-2},

doi = {10.1186/s12859-016-1037-2},

issn = {1471-2105},

year  = {2016},

date = {2016-06-01},

journal = {BMC BIOINFORMATICS},

volume = {17},

number = {5},

abstract = {Background: Joint and individual variation explained (JIVE), distinct 

and common simultaneous component analysis (DISCO) and O2-PLS, a 

two-block (X-Y) latent variable regression method with an integral OSC 

filter can all be used for the integrated analysis of multiple data sets 

and decompose them in three terms: a low(er)-rank approximation 

capturing common variation across data sets, low(er)-rank approximations 

for structured variation distinctive for each data set, and residual 

noise. In this paper these three methods are compared with respect to 

their mathematical properties and their respective ways of defining 

common and distinctive variation. 

Results: The methods are all applied on simulated data and mRNA and 

miRNA data-sets from GlioBlastoma Multiform (GBM) brain tumors to 

examine their overlap and differences. When the common variation is 

abundant, all methods are able to find the correct solution. With real 

data however, complexities in the data are treated differently by the 

three methods. 

Conclusions: All three methods have their own approach to estimate 

common and distinctive variation with their specific strength and 

weaknesses. Due to their orthogonality properties and their used 

algorithms their view on the data is slightly different. By assuming 

orthogonality between common and distinctive, true natural or biological 

phenomena that may not be orthogonal at all might be misinterpreted.},

note = {Conference on Statistical Methods for Omics Data Integration and 

Analysis, Heraklion, GREECE, NOV 10-12, 2014},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{ISI:000368360100020,

title = {Qualimap 2: advanced multi-sample quality control for high-throughput 

sequencing data},

author = { K. Okonechnikov and A. Conesa and F. Garcia-Alcalde},

url = {http://dx.doi.org/10.1093/bioinformatics/btv566},

doi = {10.1093/bioinformatics/btv566},

issn = {1367-4803},

year  = {2016},

date = {2016-01-01},

journal = {BIOINFORMATICS},

volume = {32},

number = {2},

pages = {292-294},

abstract = {Motivation: Detection of random errors and systematic biases is a 

crucial step of a robust pipeline for processing high-throughput 

sequencing (HTS) data. Bioinformatics software tools capable of 

performing this task are available, either for general analysis of HTS 

data or targeted to a specific sequencing technology. However, most of 

the existing QC instruments only allow processing of one sample at a 

time. 

Results: Qualimap 2 represents a next step in the QC analysis of HTS 

data. Along with comprehensive single-sample analysis of alignment data, it includes new modes that allow simultaneous processing and comparison 

of multiple samples. As with the first version, the new features are 

available via both graphical and command line interface. Additionally, it includes a large number of improvements proposed by the user 

community.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{ISI:000368903900004,

title = {A survey of best practices for RNA-seq data analysis},

author = { A. Conesa and P. Madrigal and S. Tarazona and D. Gomez-Cabrero and A. Cervera and A. McPherson and M. W. Szczesniak and D. J. Gaffney and L. L. Elo and X. Zhang and A. Mortazavi},

url = {http://dx.doi.org/10.1186/s13059-016-0881-8},

doi = {10.1186/s13059-016-0881-8},

issn = {1474-760X},

year  = {2016},

date = {2016-01-01},

journal = {GENOME BIOLOGY},

volume = {17},

abstract = {RNA-sequencing (RNA-seq) has a wide variety of applications, but no 

single analysis pipeline can be used in all cases. We review all of the 

major steps in RNA-seq data analysis, including experimental design, quality control, read alignment, quantification of gene and transcript 

levels, visualization, differential gene expression, alternative 

splicing, functional analysis, gene fusion detection and eQTL mapping. 

We highlight the challenges associated with each step. We discuss the 

analysis of small RNAs and the integration of RNA-seq with other 

functional genomics techniques. Finally, we discuss the outlook for 

novel technologies that are changing the state of the art in 

transcriptomics.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{ISI:000366410900003,

title = {Data quality aware analysis of differential expression in RNA-seq with 

NOISeq R/Bioc package},

author = { S. Tarazona and P. Furio-Tari and D. Turra and A. Di Pietro and M. Jose Nueda and A. Ferrer and A. Conesa},

url = {http://dx.doi.org/10.1093/nar/gkv711},

doi = {10.1093/nar/gkv711},

issn = {0305-1048},

year  = {2015},

date = {2015-12-01},

journal = {NUCLEIC ACIDS RESEARCH},

volume = {43},

number = {21},

abstract = {As the use of RNA-seq has popularized, there is an increasing 

consciousness of the importance of experimental design, bias removal, accurate quantification and control of false positives for proper data 

analysis. We introduce the NOISeq R-package for quality control and 

analysis of count data. We show how the available diagnostic tools can 

be used to monitor quality issues, make pre-processing decisions and 

improve analysis. We demonstrate that the nonparametric NOISeqBIO 

efficiently controls false discoveries in experiments with biological 

replication and outperforms state-of-the-art methods. NOISeq is a 

comprehensive resource that meets current needs for robust data-aware 

analysis of RNA-seq differential expression.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{ISI:000361363000001,

title = {Methylome profiling reveals functions and genes which are differentially 

methylated in serrated compared to conventional colorectal carcinoma},

author = { P. Conesa-Zamora and J. Garcia-Solano and M. del Carmen Turpin and P. Sebastian-Leon and D. Torres-Moreno and E. Estrada and A. Tuomisto and J. Wilce and M. J. Maekinen and M. Perez-Guillermo and A. Conesa},

url = {http://dx.doi.org/10.1186/s13148-015-0128-7},

doi = {10.1186/s13148-015-0128-7},

issn = {1868-7083},

year  = {2015},

date = {2015-09-01},

journal = {CLINICAL EPIGENETICS},

volume = {7},

abstract = {Background: Serrated adenocarcinoma (SAC) is a recently recognized 

colorectal cancer (CRC) subtype accounting for 7.5-8.7 % of CRCs. It 

has been shown that SAC has a worse prognosis and different histological 

and molecular features compared to conventional carcinoma (CC) but, to 

date, there is no study analysing its methylome profile. 

Results: The methylation status of 450,000 CpG sites using the Infinium 

Human Methylation 450 BeadChip array was investigated in 103 colorectal 

specimens, including 39 SACs and 34 matched CCs, from Spanish and 

Finnish patients. Microarray data showed a higher representation of 

morphogenesis-, neurogenesis-, cytoskeleton-and vesicle 

transport-related functions and also significant differential 

methylation of 15 genes, including the iodothyronine deiodinase DIO3 and 

the forkhead family transcription factor FOXD2 genes which were 

validated at the CpG, mRNA and protein level using pyrosequencing, methylation-specific PCR, quantitative polymerase chain reaction (qPCR) 

and immunohistochemistry. A quantification study of the methylation 

status of CpG sequences in FOXD2 demonstrated a novel region controlling 

gene expression. Moreover, differences in these markers were also 

evident when comparing SAC with CRC showing molecular and histological 

features of high-level microsatellite instability. 

Conclusions: This methylome study demonstrates distinct epigenetic 

regulation patterns in SAC which are consistent to previous expression 

profile studies and that DIO3 and FOXD2 might be molecular targets for a 

specific histology-oriented treatment of CRC.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{ISI:000363355400007,

title = {Comparative RNA-seq analysis of the Tritrichomonas foetus PIG30/1 

isolate from pigs reveals close association with Tritrichomonas foetus 

BP-4 isolate `bovine genotype'},

author = { V. Morin-Adeline and K. Mueller and A. Conesa and J. Slapeta},

url = {http://dx.doi.org/10.1016/j.vetpar.2015.08.012},

doi = {10.1016/j.vetpar.2015.08.012},

issn = {0304-4017},

year  = {2015},

date = {2015-09-01},

journal = {VETERINARY PARASITOLOGY},

volume = {212},

number = {3-4},

pages = {111-117},

abstract = {Tritrichomonas foetus was described as a commensal of the stomach, caecum and nasal cavity of pigs before it was recognised as the cause of 

reproductive tract disease of cattle. T. foetus also causes chronic 

large bowel diarrhoea in domestic cats. Multi-locus genotyping and 

comparative transcriptome analysis has previously revealed that T. 

foetus isolated from cat and cattle hosts are genetically distinct, referred to as the `feline genotype' and `bovine genotype', respectively. Conversely, multi-locus genotyping has grouped porcine T. 

foetus with the `bovine genotype'. To compare the extent of the 

similarity between porcine T. foetus and cattle `bovine genotype' 

isolates, RNA-sequencing (RNA-seq) was used to produce the first 

cell-wide transcriptome library of porcine T. foetus PIG30/1. 

Comparative transcriptome analysis of the PIG30/1 with the published 

bovine (BP-4) and feline (G10/1) transcriptomes revealed that the 

porcine T. foetus shares a 4.7 fold greater number of orthologous genes 

with the bovine T. foetus than with the feline T. foetus. Comparing 

transcription of the virulence factors, cysteine proteases (CP) between 

the three isolates, the porcine T. foetus was found to preferentially 

transcribe CP8 like the `bovine genotype' T. foetus, compared to thehigh 

transcription of CP7 seen for `feline genotype' T. foetus. At the 

cell-wide transcriptome level, the porcine T. foetus isolate (PIG30/1) 

groups closer with the `bovine genotype' T. foetus rather than the 

`feline genotype' T. foetus. (C) 2015 Elsevier B.V. All rights reserved.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{ISI:000360039300003,

title = {RNAseq analysis of Aspergillus fumigatus in blood reveals a just wait 

and see resting stage behavior},

author = { H. Irmer and S. Tarazona and C. Sasse and P. Olbermann and J. Loeffler and S. Krappmann and A. Conesa and G. H. Braus},

url = {http://dx.doi.org/10.1186/s12864-015-1853-1},

doi = {10.1186/s12864-015-1853-1},

issn = {1471-2164},

year  = {2015},

date = {2015-08-01},

journal = {BMC GENOMICS},

volume = {16},

abstract = {Background: Invasive aspergillosis is started after germination of 

Aspergillus fumigatus conidia that are inhaled by susceptible 

individuals. Fungal hyphae can grow in the lung through the epithelial 

tissue and disseminate hematogenously to invade into other organs. Low 

fungaemia indicates that fungal elements do not reside in the 

bloodstream for long. 

Results: We analyzed whether blood represents a hostile environment to 

which the physiology of A. fumigatus has to adapt. An in vitro model of 

A. fumigatus infection was established by incubating mycelium in blood. 

Our model allowed to discern the changes of the gene expression profile 

of A. fumigatus at various stages of the infection. The majority of 

described virulence factors that are connected to pulmonary infections 

appeared not to be activated during the blood phase. Three active 

processes were identified that presumably help the fungus to survive the 

blood environment in an advanced phase of the infection: iron 

homeostasis, secondary metabolism, and the formation of detoxifying 

enzymes. 

Conclusions: We propose that A. fumigatus is hardly able to propagate in 

blood. After an early stage of sensing the environment, virtually all 

uptake mechanisms and energy-consuming metabolic pathways are shut-down. 

The fungus appears to adapt by trans-differentiation into a resting 

mycelial stage. This might reflect the harsh conditions in blood where 

A. fumigatus cannot take up sufficient nutrients to establish 

self-defense mechanisms combined with significant growth.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{ISI:000355704700013,

title = {Genome-wide changes in histone H3 lysine 27 trimethylation associated 

with bud dormancy release in peach},

author = { L. de la Fuente and A. Conesa and A. Lloret and M. Luisa Badenes and G. Rios},

url = {http://dx.doi.org/10.1007/s11295-015-0869-7},

doi = {10.1007/s11295-015-0869-7},

issn = {1614-2942},

year  = {2015},

date = {2015-06-01},

journal = {TREE GENETICS & GENOMES},

volume = {11},

number = {3},

abstract = {Bud dormancy is an evolutionary adaptation of perennial plants to the 

seasonal fluctuation of temperatures in temperate climates, affected by 

intrinsic and environmental signals. Recent investigations point to a 

relevant role of epigenetic mechanisms in the regulation of bud 

dormancy. We have performed a chromatin immunoprecipitation sequencing 

(ChIP-seq) analysis of histone H3 lysine-27 trimethylation (H3K27me3), a 

chromatin mark associated with stable gene silencing, in dormant (D) and 

dormancy-released (ND) buds of peach (Prunus persica). H3K27me3 regions 

were more abundant in gene-rich euchromatic zones of chromosomes and 

associated with gene bodies. The dormancy regulators DORMANCY-ASSOCIATED 

MADS-box (DAM) 1, DAM4, DAM5 and DAM6 were found significantly enriched 

in H3K27me3 in ND samples, in close agreement with their 

dormancy-specific expression. The DAM locus was modified at specific 

short regions, allowing the uneven regulation of distinct DAM genes. 

Additional regulatory factors related to meristem activity and flowering 

genes from Arabidopsis thaliana were differentially H3K27 trimethylated, which suggests that meristem reactivation and flower development could 

be also epigenetically regulated in reproductive buds of peach. A (GA)n 

motif and CACTA-type transposon-related sequences were found 

over-represented in H3K27me3 regions.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{ISI:000350585600002,

title = {Two independent epigenetic biomarkers predict survival in neuroblastoma},

author = { Y. Yanez and E. Grau and V. C. Rodriguez-Cortez and D. Hervas and E. Vidal and R. Noguera and M. Hernandez and V. Segura and A. Canete and A. Conesa and J. Font de Mora and V. Castel},

url = {http://dx.doi.org/10.1186/s13148-015-0054-8},

doi = {10.1186/s13148-015-0054-8},

issn = {1868-7083},

year  = {2015},

date = {2015-02-01},

journal = {CLINICAL EPIGENETICS},

volume = {7},

abstract = {Background: Neuroblastoma (NB) is the most common extracranial pediatric 

solid tumor with a highly variable clinical course, ranging from 

spontaneous regression to life-threatening disease. Survival rates for 

high-risk NB patients remain disappointingly low despite multimodal 

treatment. Thus, there is an urgent clinical need for additional 

biomarkers to improve risk stratification, treatment management, and 

survival rates in children with aggressive NB. 

Results: Using gene promoter methylation analysis in 48 neuroblastoma 

tumors with microarray technology, we found a strong association between survival and gene promoter hypermethylation (P = 0.036). 

Hypermethylation of 70 genes significantly differentiated high-risk 

survivor patients from those who died during follow-up time. Sixteen 

genes with relevant roles in cancer biology were further validated in an 

additional cohort of 83 neuroblastoma tumors by bisulfite 

pyrosequencing. High promoter methylation rates of these genes were 

found in patients with metastatic tumors (either stage metastatic (M) or 

metastatic special (MS)), 18 months or older at first diagnosis, MYCN 

amplification, relapsed, and dead. Notably, the degree of methylation of 

retinoblastoma 1 (RB1) and teratocarcinoma-derived growth factor 1 

(TDGF1) predicts event-free and overall survival independently of the 

established risk factors. In addition, low RB1 mRNA expression levels 

associate with poor prognosis suggesting that promoter methylation could 

contribute to the transcriptional silencing of this gene in NB. 

Conclusions: We found a new epigenetic signature predictive for NB 

patients' outcome: the methylation status of RB1 and TDGF1 associate 

with poorer survival. This information is useful to assess prognosis and 

improve treatment selection.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{ISI:000345790500001,

title = {Comparative transcriptomics reveals striking similarities between the 

bovine and feline isolates of Tritrichomonas foetus: consequences for in 

silico drug-target identification},

author = { V. Morin-Adeline and R. Lomas and D. O'Meally and C. Stack and A. Conesa and J. Slapeta},

url = {http://dx.doi.org/10.1186/1471-2164-15-955},

doi = {10.1186/1471-2164-15-955},

issn = {1471-2164},

year  = {2014},

date = {2014-11-01},

journal = {BMC GENOMICS},

volume = {15},

abstract = {Background: Few, if any, protozoan parasites are reported to exhibit 

extreme organ tropism like the flagellate Tritrichomonas foetus. In 

cattle, T. foetus infects the reproductive system causing abortion, whereas the infection in cats results in chronic large bowel diarrhoea. 

In the absence of a T. foetus genome, we utilized a de novo approach to 

assemble the transcriptome of the bovine and feline genotype to identify 

host-specific adaptations and virulence factors specific to each 

genotype. Furthermore, a subset of orthologs was used to characterize 

putative druggable targets and expose complications of in silico drug 

target mining in species with indefinite host-ranges. 

Results: Illumina RNA-seq reads were assembled into two representative 

bovine and feline transcriptomes containing 42,363 and 36,559 contigs, respectively. Coding and non-coding regions of the genome libraries 

revealed striking similarities, with 24,620 shared homolog pairs reduced 

down to 7,547 coding orthologs between the two genotypes. The 

transcriptomes were near identical in functional category distribution; 

with no indication of selective pressure acting on orthologs despite 

differences in parasite origins/host. Orthologs formed a large 

proportion of highly expressed transcripts in both genotypes (bovine 

genotype: 76%, feline genotype: 56%). Mining the libraries for 

protease virulence factors revealed the cysteine proteases (CP) to be 

the most common. In total, 483 and 445 bovine and feline T. foetus 

transcripts were identified as putative proteases based on MEROPS 

database, with 9 hits to putative protease inhibitors. In bovine T. 

foetus, CP8 is the preferentially transcribed CP while in the feline 

genotype, transcription of CP7 showed higher abundance. In silico 

druggability analysis of the two genotypes revealed that when host 

sequences are taken into account, drug targets are genotype-specific. 

Conclusion: Gene discovery analysis based on RNA-seq data analysis 

revealed prominent similarities between the bovine and feline T. foetus, suggesting recent adaptation to their respective host/niche. T. foetus 

represents a unique case of a mammalian protozoan expanding its 

parasitic grasp across distantly related host lineages. Consequences of 

the host-range for in silico drug targeting are exposed here, demonstrating that targets of the parasite in one host are not 

necessarily ideal for the same parasite in another host.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{ISI:000347559200001,

title = {Understanding disease mechanisms with models of signaling pathway 

activities},

author = { P. Sebastian-Leon and E. Vidal and P. Minguez and A. Conesa and S. Tarazona and A. Amadoz and C. Armero and F. Salavert and A. Vidal-Puig and D. Montaner and J. Dopazo},

url = {http://dx.doi.org/10.1186/s12918-014-0121-3},

doi = {10.1186/s12918-014-0121-3},

issn = {1752-0509},

year  = {2014},

date = {2014-10-01},

journal = {BMC SYSTEMS BIOLOGY},

volume = {8},

abstract = {Background: Understanding the aspects of the cell functionality that 

account for disease or drug action mechanisms is one of the main 

challenges in the analysis of genomic data and is on the basis of the 

future implementation of precision medicine. 

Results: Here we propose a simple probabilistic model in which signaling 

pathways are separated into elementary sub-pathways or signal 

transmission circuits (which ultimately trigger cell functions) and then 

transforms gene expression measurements into probabilities of activation 

of such signal transmission circuits. Using this model, differential 

activation of such circuits between biological conditions can be 

estimated. Thus, circuit activation statuses can be interpreted as 

biomarkers that discriminate among the compared conditions. This type of 

mechanism-based biomarkers accounts for cell functional activities and 

can easily be associated to disease or drug action mechanisms. The 

accuracy of the proposed model is demonstrated with simulations and real 

datasets. 

Conclusions: The proposed model provides detailed information that 

enables the interpretation disease mechanisms as a consequence of the 

complex combinations of altered gene expression values. Moreover, it 

offers a framework for suggesting possible ways of therapeutic 

intervention in a pathologically perturbed system.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{ISI:000342600300030,

title = {A comprehensive assessment of RNA-seq accuracy, reproducibility and 

information content by the Sequencing Quality Control Consortium},

author = { Z. Su and P. P. Labaj and S. Li and J. Thierry-Mieg and D. Thierry-Mieg and W. Shi and C. Wang and G. P. Schroth and R. A. Setterquist and J. F. Thompson and W. D. Jones and W. Xiao and W. Xu and R. V. Jensen and R. Kelly and J. Xu and A. Conesa and C. Furlanello and H. Gao and H. Hong and N. Jafari and S. Letovsky and Y. Liao and F. Lu and E. J. Oakeley and Z. Peng and C. A. Praul and J. Santoyo-Lopez and A. Scherer and T. Shi and G. K. Smyth and F. Staedtler and P. Sykacek and X. Tan and E. A. Thompson and J. Vandesompele and M. D. Wang and J. Wang and R. D. Wolfinger and J. Zavadil and S. S. Auerbach and W. Bao and H. Binder and T. Blomquist and M. H. Brilliant and P. R. Bushel and W. Cain and J. G. Catalano and C. Chang and T. Chen and G. Chen and R. Chen and M. Chierici and T. Chu and D. Clevert and Y. Deng and A. Derti and V. Devanarayan and Z. Dong and J. Dopazo and T. Du and H. Fang and Y. Fang and M. Fasold and A. Fernandez and M. Fischer and P. Furio-Tari and J. C. Fuscoe and F. Caiment and S. Gaj and J. Gandara and H. Gao and W. Ge and Y. Gondo and B. Gong and M. Gong and Z. Gong and B. Green and C. Guo and L. Guo and L. Guo and J. Hadfield and J. Hellemans and S. Hochreiter and M. Jia and M. Jian and C. D. Johnson and S. Kay and J. Kleinjans and S. Lababidi and S. Levy and Q. Li and L. Li and L. Li and P. Li and Y. Li and H. Li and J. Li and S. Li and S. M. Lin and F. J. Lopez and X. Lu and H. Luo and X. Ma and J. Meehan and D. B. Megherbi and N. Mei and B. Mu and B. Ning and A. Pandey and J. Perez-Florido and R. G. Perkins and R. Peters and J. H. Phan and M. Pirooznia and F. Qian and T. Qing and L. Rainbow and P. Rocca-Serra and L. Sambourg and S. Sansone and S. Schwartz and R. Shah and J. Shen and T. M. Smith and O. Stegle and N. Stralis-Pavese and E. Stupka and Y. Suzuki and L. T. Szkotnicki and M. Tinning and B. Tu and J. van Deft and A. Vela-Boza and E. Venturini and S. J. Walker and L. Wan and W. Wang and J. Wang and J. Wang and E. D. Wieben and J. C. Willey and P. Wu and J. Xuan and Y. Yang and Z. Ye and Y. Yin and Y. Yu and Y. Yuan and J. Zhang and K. K. Zhang and W. Zhang and W. Zhang and Y. Zhang and C. Zhao and Y. Zheng and Y. Zhou and P. Zumbo and W. Tong and D. P. Kreil and C. E. Mason and L. Shi},

url = {http://dx.doi.org/10.1038/nbt.2957},

doi = {10.1038/nbt.2957},

issn = {1087-0156},

year  = {2014},

date = {2014-09-01},

journal = {NATURE BIOTECHNOLOGY},

volume = {32},

number = {9},

pages = {903-914},

abstract = {We present primary results from the Sequencing Quality Control (SEQC) 

project, coordinated by the US Food and Drug Administration. Examining 

Illumina HiSeq, Life Technologies SOLiD and Roche 454 platforms at 

multiple laboratory sites using reference RNA samples with built-in 

controls, we assess RNA sequencing (RNA-seq) performance for junction 

discovery and differential expression profiling and compare it to 

microarray and quantitative PCR (qPCR) data using complementary metrics. 

At all sequencing depths, we discover unannotated exon-exon junctions, with >80% validated by qPCR. We find that measurements of relative 

expression are accurate and reproducible across sites and platforms if 

specific-filters are used. In contrast, RNA-seq and microarrays do not 

provide accurate absolute measurements, and gene-specific biases are 

observed for all examined platforms, including qPCR. Measurement 

performance depends on the platform and data analysis pipeline, and 

variation is large for transcript-level profiling. The complete SEQC 

data sets, comprising >100 billion reads (10Tb), provide unique 

resources for evaluating RNA-seq analyses for clinical and regulatory 

settings.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{ISI:000342913000008,

title = {Next maSigPro: updating maSigPro bioconductor package for RNA-seq time 

series},

author = { M. J. Nueda and S. Tarazona and A. Conesa},

url = {http://dx.doi.org/10.1093/bioinformatics/btu333},

doi = {10.1093/bioinformatics/btu333},

issn = {1367-4803},

year  = {2014},

date = {2014-09-01},

journal = {BIOINFORMATICS},

volume = {30},

number = {18},

pages = {2598-2602},

abstract = {Motivation: The widespread adoption of RNA-seq to quantitatively measure 

gene expression has increased the scope of sequencing experimental 

designs to include time-course experiments. maSigPro is an R package 

specifically suited for the analysis of time-course gene expression 

data, which was developed originally for microarrays and hence was 

limited in its application to count data. 

Results: We have updated maSigPro to support RNA-seq time series 

analysis by introducing generalized linear models in the algorithm to 

support the modeling of count data while maintaining the traditional 

functionalities of the package. We show a good performance of the 

maSigPro-GLM method in several simulated time-course scenarios and in a 

real experimental dataset.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{ISI:000343030500001,

title = {Assessing technical performance in differential gene expression 

experiments with external spike-in RNA control ratio mixtures},

author = { S. A. Munro and S. P. Lund and P. S. Pine and H. Binder and D. Clevert and A. Conesa and J. Dopazo and M. Fasold and S. Hochreiter and H. Hong and N. Jafari and D. P. Kreil and P. P. Labaj and S. Li and Y. Liao and S. M. Lin and J. Meehan and C. E. Mason and J. Santoyo-Lopez and R. A. Setterquist and L. Shi and W. Shi and G. K. Smyth and N. Stralis-Pavese and Z. Su and W. Tong and C. Wang and J. Wang and J. Xu and Z. Ye and Y. Yang and Y. Yu and M. Salit},

url = {http://dx.doi.org/10.1038/ncomms6125},

doi = {10.1038/ncomms6125},

issn = {2041-1723},

year  = {2014},

date = {2014-09-01},

journal = {NATURE COMMUNICATIONS},

volume = {5},

abstract = {There is a critical need for standard approaches to assess, report and 

compare the technical performance of genome-scale differential gene 

expression experiments. Here we assess technical performance with a 

proposed standard `dashboard' of metrics derived from analysis of 

external spike-in RNA control ratio mixtures. These control ratio 

mixtures with defined abundance ratios enable assessment of diagnostic 

performance of differentially expressed transcript lists, limit of 

detection of ratio (LODR) estimates and expression ratio variability and 

measurement bias. The performance metrics suite is applicable to 

analysis of a typical experiment, and here we also apply these metrics 

to evaluate technical performance among laboratories. An interlaboratory 

study using identical samples shared among 12 laboratories with three 

different measurement processes demonstrates generally consistent 

diagnostic power across 11 laboratories. Ratio measurement variability 

and bias are also comparable among laboratories for the same measurement 

process. We observe different biases for measurement processes using 

different mRNA-enrichment protocols.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{ISI:000351589702079,

title = {Differentially expressed functions and genes between serrated 

adenocarcinoma and sporadic colorectal carcinoma showing histological 

and molecular features of high level of microsatellite instability},

author = { M. Turpin Sevilla and R. Carbonell-Munoz and J. Garcia-Solano and D. Torres-Moreno and F. Garcia-Garcia and A. Conesa and M. Perez-Guillermo and P. Conesa-Zamora},

issn = {0959-8049},

year  = {2014},

date = {2014-07-01},

journal = {EUROPEAN JOURNAL OF CANCER},

volume = {50},

number = {5},

pages = {S219},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{ISI:000338246200001,

title = {Relationship between genome and epigenome - challenges and requirements 

for future research},

author = { G. Almouzni and L. Altucci and B. Amati and N. Ashley and D. Baulcombe and N. Beaujean and C. Bock and E. Bongcam-Rudloff and J. Bousquet and S. Braun and B. Bressac-de Paillerets and M. Bussemakers and L. Clarke and A. Conesa and X. Estivill and A. Fazeli and N. Grgurevic and I. Gut and B. T. Heijmans and S. Hermouet and J. Houwing-Duistermaat and I. Iacobucci and J. Ilas and R. Kandimalla and S. Krauss-Etschmann and P. Lasko and S. Lehmann and A. Lindroth and G. Majdic and E. Marcotte and G. Martinelli and N. Martinet and E. Meyer and C. Miceli and K. Mills and M. Moreno-Villanueva and G. Morvan and D. Nickel and B. Niesler and M. Nowacki and J. Nowak and S. Ossowski and M. Pelizzola and R. Pochet and U. Potocnik and M. Radwanska and J. Raes and M. Rattray and M. D. Robinson and B. Roelen and S. Sauer and D. Schinzer and E. Slagboom and T. Spector and H. G. Stunnenberg and E. Tiligada and M. Torres-Padilla and R. Tsonaka and A. Van Soom and M. Vidakovic and M. Widschwendter},

url = {http://dx.doi.org/10.1186/1471-2164-15-487},

doi = {10.1186/1471-2164-15-487},

issn = {1471-2164},

year  = {2014},

date = {2014-06-01},

journal = {BMC GENOMICS},

volume = {15},

abstract = {Understanding the links between genetic, epigenetic and non-genetic 

factors throughout the lifespan and across generations and their role in 

disease susceptibility and disease progression offer entirely new 

avenues and solutions to major problems in our society. To overcome the 

numerous challenges, we have come up with nine major conclusions to set 

the vision for future policies and research agendas at the European 

level.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{ISI:000333499100007,

title = {Sequencing and functional analysis of the genome of a nematode 

egg-parasitic fungus, Pochonia chlamydosporia},

author = { E. Larriba and M. D. L. A. Jaime and J. Carbonell-Caballero and A. Conesa and J. Dopazo and C. Nislow and J. Martin-Nieto and L. Vicente Lopez-Llorca},

url = {http://dx.doi.org/10.1016/j.fgb.2014.02.002},

doi = {10.1016/j.fgb.2014.02.002},

issn = {1087-1845},

year  = {2014},

date = {2014-04-01},

journal = {FUNGAL GENETICS AND BIOLOGY},

volume = {65},

pages = {69-80},

abstract = {Pochonia chlamydosporia is a worldwide-distributed soil fungus with a 

great capacity to infect and destroy the eggs and kill females of 

plant-parasitic nematodes. Additionally, it has the ability to colonize 

endophytically roots of economically-important crop plants, thereby 

promoting their growth and eliciting plant defenses. This multitrophic 

behavior makes P. chlamydosporia a potentially useful tool for 

sustainable agriculture approaches. We sequenced and assembled similar 

to 41 Mb of P. chlamydosporia genomic DNA and predicted 12,122 gene 

models, of which many were homologous to genes of fungal pathogens of 

invertebrates and fungal plant pathogens. Predicted genes (65%) were 

functionally annotated according to Gene Ontology, and 16% of them 

found to share homology with genes in the Pathogen Host Interactions 

(PHI) database. The genome of this fungus is highly enriched in genes 

encoding hydrolytic enzymes, such as proteases, glycoside hydrolases and 

carbohydrate esterases. We used RNA-Seq technology in order to identify 

the genes expressed during endophytic behavior of P. chlamydosporia when 

colonizing barley roots. Functional annotation of these genes showed 

that hydrolytic enzymes and transporters are expressed during 

endophytism. This structural and functional analysis of the P. 

chlamydosporia genome provides a starting point for understanding the 

molecular mechanisms involved in the multitrophic lifestyle of this 

fungus. The genomic information provided here should also prove useful 

for enhancing the capabilities of this fungus as a biocontrol agent of 

plant-parasitic nematodes and as a plant growth-promoting organism. (C) 

2014 Elsevier Inc. All rights reserved.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{ISI:000331407000009,

title = {Molecular interactions between sugar beet and Polymyxa betae during its 

life cycle},

author = { N. Desoignies and J. Carbonell and J. -S. Moreau and A. Conesa and J. Dopazo and A. Legreve},

url = {http://dx.doi.org/10.1111/aab.12095},

doi = {10.1111/aab.12095},

issn = {0003-4746},

year  = {2014},

date = {2014-03-01},

journal = {ANNALS OF APPLIED BIOLOGY},

volume = {164},

number = {2},

pages = {244-256},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{ISI:000333681300001,

title = {Data integration in the era of omics: current and future challenges},

author = { D. Gomez-Cabrero and I. Abugessaisa and D. Maier and A. Teschendorff and M. Merkenschlager and A. Gisel and E. Ballestar and E. Bongcam-Rudloff and A. Conesa and J. Tegner},

url = {http://dx.doi.org/10.1186/1752-0509-8-S2-I1},

doi = {10.1186/1752-0509-8-S2-I1},

issn = {1752-0509},

year  = {2014},

date = {2014-03-01},

journal = {BMC SYSTEMS BIOLOGY},

volume = {8},

number = {2},

abstract = {To integrate heterogeneous and large omics data constitutes not only a 

conceptual challenge but a practical hurdle in the daily analysis of 

omics data. With the rise of novel omics technologies and through 

large-scale consortia projects, biological systems are being further 

investigated at an unprecedented scale generating heterogeneous and 

often large data sets. These data-sets encourage researchers to develop 

novel data integration methodologies. In this introduction we review the 

definition and characterize current efforts on data integration in the 

life sciences. We have used a web-survey to assess current research 

projects on data-integration to tap into the views, needs and challenges 

as currently perceived by parts of the research community.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{ISI:000333681300002,

title = {The common ground of genomics and systems biology},

author = { A. Conesa and A. Mortazavi},

url = {http://dx.doi.org/10.1186/1752-0509-8-S2-S1},

doi = {10.1186/1752-0509-8-S2-S1},

issn = {1752-0509},

year  = {2014},

date = {2014-03-01},

journal = {BMC SYSTEMS BIOLOGY},

volume = {8},

number = {2},

abstract = {The rise of systems biology is intertwined with that of genomics, yet 

their primordial relationship to one another is ill-defined. We discuss 

how the growth of genomics provided a critical boost to the popularity 

of systems biology. We describe the parts of genomics that share common 

areas of interest with systems biology today in the areas of gene 

expression, network inference, chromatin state analysis, pathway 

analysis, personalized medicine, and upcoming areas of synergy as 

genomics continues to expand its scope across all biomedical fields.},

note = {High-Throughput Omics and Data Integration Workshop, Barcelona, SPAIN, FEB 13-15, 2013},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{ISI:000333681300008,

title = {Pathway network inference from gene expression data},

author = { I. Ponzoni and M. J. Nueda and S. Tarazona and S. Goetz and D. Montaner and J. S. Dussaut and J. Dopazo and A. Conesa},

url = {http://dx.doi.org/10.1186/1752-0509-8-S2-S7},

doi = {10.1186/1752-0509-8-S2-S7},

issn = {1752-0509},

year  = {2014},

date = {2014-03-01},

journal = {BMC SYSTEMS BIOLOGY},

volume = {8},

number = {2},

abstract = {Background: The development of high-throughput omics technologies 

enabled genome-wide measurements of the activity of cellular elements 

and provides the analytical resources for the progress of the Systems 

Biology discipline. Analysis and interpretation of gene expression data 

has evolved from the gene to the pathway and interaction level, i.e. 

from the detection of differentially expressed genes, to the 

establishment of gene interaction networks and the identification of 

enriched functional categories. Still, the understanding of biological 

systems requires a further level of analysis that addresses the 

characterization of the interaction between functional modules. 

Results: We present a novel computational methodology to study the 

functional interconnections among the molecular elements of a biological 

system. The PANA approach uses high-throughput genomics measurements and 

a functional annotation scheme to extract an activity profile from each 

functional block -or pathway-followed by machine-learning methods to 

infer the relationships between these functional profiles. The result is 

a global, interconnected network of pathways that represents the 

functional cross-talk within the molecular system. We have applied this 

approach to describe the functional transcriptional connections during 

the yeast cell cycle and to identify pathways that change their 

connectivity in a disease condition using an Alzheimer example. 

Conclusions: PANA is a useful tool to deepen in our understanding of the 

functional interdependences that operate within complex biological 

systems. We show the approach is algorithmically consistent and the 

inferred network is well supported by the available functional data. The 

method allows the dissection of the molecular basis of the functional 

connections and we describe the different regulatory mechanisms that 

explain the network's topology obtained for the yeast cell cycle data.},

note = {High-Throughput Omics and Data Integration Workshop, Barcelona, SPAIN, FEB 13-15, 2013},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{ISI:000333681300010,

title = {STATegra EMS: an Experiment Management System for complex 

next-generation omics experiments},

author = { R. Hernandez de Diego and N. Boix-Chova and D. Gomez-Cabrero and J. Tegner and I. Abugessaisa and A. Conesa},

url = {http://dx.doi.org/10.1186/1752-0509-8-S2-S9},

doi = {10.1186/1752-0509-8-S2-S9},

issn = {1752-0509},

year  = {2014},

date = {2014-03-01},

journal = {BMC SYSTEMS BIOLOGY},

volume = {8},

number = {2},

abstract = {High-throughput sequencing assays are now routinely used to study 

different aspects of genome organization. As decreasing costs and 

widespread availability of sequencing enable more laboratories to use 

sequencing assays in their research projects, the number of samples and 

replicates in these experiments can quickly grow to several dozens of 

samples and thus require standardized annotation, storage and management 

of preprocessing steps. As a part of the STATegra project, we have 

developed an Experiment Management System (EMS) for high throughput 

omics data that supports different types of sequencing-based assays such 

as RNA-seq, ChIP-seq, Methyl-seq, etc, as well as proteomics and 

metabolomics data. The STATegra EMS provides metadata annotation of 

experimental design, samples and processing pipelines, as well as 

storage of different types of data files, from raw data to ready-to-use 

measurements. The system has been developed to provide research 

laboratories with a freely-available, integrated system that offers a 

simple and effective way for experiment annotation and tracking of 

analysis procedures.},

note = {High-Throughput Omics and Data Integration Workshop, Barcelona, SPAIN, FEB 13-15, 2013},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{ISI:000331155800710,

title = {Methylation Microarray Analysis Identifies Differentially Methylated 

Genes in Serrated Compared to Conventional Colorectal Carcinomas},

author = { J. Garcia-Solano and E. Alcaraz-Mateos and J. Wilce and D. Torres-Moreno and M. C. Turpin-Sevilla and C. Navarre and A. Conesa and A. Tuomisto and P. Sirnio and M. J. Makinen and M. Perez-Guillermo and P. Conesa-Zamora},

issn = {0023-6837},

year  = {2014},

date = {2014-02-01},

journal = {LABORATORY INVESTIGATION},

volume = {94},

number = {1},

pages = {174A},

organization = {US & Canadian Acad Pathol; Dako; Biocare Med; Leica Biosystems; LabCorp 

Specialty Testing Grp, Integrated Oncol; GenomOncology; Nephropath; 

Ventana; Diagnost BioSystems},

note = {103rd Annual Meeting of the 

United-States-and-Canadian-Academy-of-Pathology (USCAP), San Diego, CA, MAR 01-07, 2014},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{ISI:000331502201024,

title = {Methylation Microarray Analysis Identifies Differentially Methylated 

Genes in Serrated Compared to Conventional Colorectal Carcinomas},

author = { J. Garica-Solano and E. Alcaraz-Mateos and J. Wilce and D. Torres-Moreno and M. C. Turpin-Sevilla and C. Navarre and A. Conesa and A. Tuomisto and P. Sirnio and M. J. Makinen and M. Perez-Guillermo and P. Conesa-Zamora},

issn = {0893-3952},

year  = {2014},

date = {2014-02-01},

journal = {MODERN PATHOLOGY},

volume = {27},

number = {2},

pages = {174A},

organization = {US & Canadian Acad Pathol; Dako; Biocare Med; Leica Biosystems; LabCorp 

Specialty Testing Grp, Integrated Oncol; GenomOncology; Nephropath; 

Ventana; Diagnost BioSystems},

note = {103rd Annual Meeting of the 

United-States-and-Canadian-Academy-of-Pathology (USCAP), San Diego, CA, MAR 01-07, 2014},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{ISI:000317907200122,

title = {Defining the Genomic Signature of Totipotency and Pluripotency during 

Early Human Development},

author = { A. Galan and P. Diaz-Gimeno and M. Eugenia Poo and D. Valbuena and E. Sanchez and V. Ruiz and J. Dopazo and D. Montaner and A. Conesa and C. Simon},

url = {http://dx.doi.org/10.1371/journal.pone.0062135},

doi = {10.1371/journal.pone.0062135},

issn = {1932-6203},

year  = {2013},

date = {2013-04-01},

journal = {PLOS ONE},

volume = {8},

number = {4},

abstract = {The genetic mechanisms governing human pre-implantation embryo 

development and the in vitro counterparts, human embryonic stem cells 

(hESCs), still remain incomplete. Previous global genome studies 

demonstrated that totipotent blastomeres from day-3 human embryos and 

pluripotent inner cell masses (ICMs) from blastocysts, display unique 

and differing transcriptomes. Nevertheless, comparative gene expression 

analysis has revealed that no significant differences exist between 

hESCs derived from blastomeres versus those obtained from ICMs, suggesting that pluripotent hESCs involve a new developmental 

progression. To understand early human stages evolution, we developed an 

undifferentiation network signature (UNS) and applied it to a 

differential gene expression profile between single blastomeres from 

day-3 embryos, ICMs and hESCs. This allowed us to establish a unique 

signature composed of highly interconnected genes characteristic of 

totipotency (61 genes), in vivo pluripotency (20 genes), and in vitro 

pluripotency (107 genes), and which are also proprietary according to 

functional analysis. This systems biology approach has led to an 

improved understanding of the molecular and signaling processes 

governing human pre-implantation embryo development, as well as enabling 

us to comprehend how hESCs might adapt to in vitro culture conditions.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{ISI:000311383600015,

title = {Expression profiling shows differential molecular pathways and provides 

potential new diagnostic biomarkers for colorectal serrated 

adenocarcinoma},

author = { P. Conesa-Zamora and J. Garcia-Solano and F. Garcia-Garcia and M. del Carmen Turpin and J. Trujillo-Santos and D. Torres-Moreno and I. Oviedo-Ramirez and R. Carbonell-Munoz and E. Munoz-Delgado and E. Rodriguez-Braun and A. Conesa and M. Perez-Guillermo},

url = {http://dx.doi.org/10.1002/ijc.27674},

doi = {10.1002/ijc.27674},

issn = {0020-7136},

year  = {2013},

date = {2013-01-01},

journal = {INTERNATIONAL JOURNAL OF CANCER},

volume = {132},

number = {2},

pages = {297-307},

abstract = {Serrated adenocarcinoma (SAC) is a recently recognized colorectal cancer 

(CRC) subtype accounting for 7.5 to 8.7% of CRCs. It has been shown 

that SAC has a poorer prognosis and has different molecular and 

immunohistochemical features compared with conventional carcinoma (CC) 

but, to date, only one previous study has analyzed its mRNA expression 

profile by microarray. Using a different microarray platform, we have 

studied the molecular signature of 11 SACs and compared it with that of 

15 matched CC with the aim of discerning the functions which 

characterize SAC biology and validating, at the mRNA and protein level, the most differentially expressed genes which were also tested using a 

validation set of 70 SACs and 70 CCs to assess their diagnostic and 

prognostic values. Microarray data showed a higher representation of 

morphogenesis-, hypoxia-, cytoskeleton- and vesicle transport-related 

functions and also an overexpression of fascin1 (actin-bundling protein 

associated with invasion) and the antiapoptotic gene hippocalcin in SAC 

all of which were validated both by quantitative real-time PCR (qPCR) 

and immunohistochemistry. Fascin1 expression was statistically 

associated with KRAS mutation with 88.6% sensitivity and 85.7% 

specificity for SAC diagnosis and the positivity of fascin1 or hippocalcin was highly suggestive of SAC diagnosis (sensitivity = 

100%). Evaluation of these markers in CRCs showing histological and 

molecular characteristics of high-level microsatellite instability 

(MSI-H) also helped to distinguish SACs from MSI-H CRCs. Molecular 

profiling demonstrates that SAC shows activation of distinct signaling 

pathways and that immunohistochemical fascin1 and hippocalcin expression 

can be reliably used for its differentiation from other CRC subtypes.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{ISI:000309754300355,

title = {METHYLATION STATUS IN NEUROBLASTOMA AND ITS PROGNOSTIC VALUE},

author = { Y. Yanez and E. Grau and A. Canete and A. Conesa and A. Gonzalez Neira and V. Castel},

issn = {1545-5009},

year  = {2012},

date = {2012-12-01},

journal = {PEDIATRIC BLOOD & CANCER},

volume = {59},

number = {6, SI},

pages = {1053-1054},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{ISI:000308289400005,

title = {Microarray analysis of Etrog citron (Citrus medica L.) reveals changes 

in chloroplast, cell wall, peroxidase and symporter activities in 

response to viroid infection},

author = { S. Rizza and A. Conesa and J. Juarez and A. Catara and L. Navarro and N. Duran-Vila and G. Ancillo},

url = {http://dx.doi.org/10.1111/j.1364-3703.2012.00794.x},

doi = {10.1111/j.1364-3703.2012.00794.x},

issn = {1464-6722},

year  = {2012},

date = {2012-10-01},

journal = {MOLECULAR PLANT PATHOLOGY},

volume = {13},

number = {8},

pages = {852-864},

abstract = {Viroids are small (246401 nucleotides), single-stranded, circular RNA 

molecules that infect several crop plants and can cause diseases of 

economic importance. Citrus are the hosts in which the largest number of 

viroids have been identified. Citrus exocortis viroid (CEVd), the causal 

agent of citrus exocortis disease, induces considerable losses in citrus 

crops. Changes in the gene expression profile during the early 

(pre-symptomatic) and late (post-symptomatic) stages of Etrog citron 

infected with CEVd were investigated using a citrus cDNA microarray. 

MaSigPro analysis was performed and, on the basis of gene expression 

profiles as a function of the time after infection, the differentially 

expressed genes were classified into five clusters. FatiScan analysis 

revealed significant enrichment of functional categories for each 

cluster, indicating that viroid infection triggers important changes in 

chloroplast, cell wall, peroxidase and symporter activities.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{ISI:000309881200016,

title = {Qualimap: evaluating next-generation sequencing alignment data},

author = { F. Garcia-Alcalde and K. Okonechnikov and J. Carbonell and L. M. Cruz and S. Goetz and S. Tarazona and J. Dopazo and T. F. Meyer and A. Conesa},

url = {http://dx.doi.org/10.1093/bioinformatics/bts503},

doi = {10.1093/bioinformatics/bts503},

issn = {1367-4803},

year  = {2012},

date = {2012-10-01},

journal = {BIOINFORMATICS},

volume = {28},

number = {20},

pages = {2678-2679},

abstract = {Motivation: The sequence alignment/map (SAM) and the binary 

alignment/map (BAM) formats have become the standard method of 

representation of nucleotide sequence alignments for next-generation 

sequencing data. SAM/BAM files usually contain information from tens to 

hundreds of millions of reads. Often, the sequencing technology, protocol and/or the selected mapping algorithm introduce some unwanted 

biases in these data. The systematic detection of such biases is a 

non-trivial task that is crucial to drive appropriate downstream 

analyses. 

Results: We have developed Qualimap, a Java application that supports 

user-friendly quality control of mapping data, by considering sequence 

features and their genomic properties. Qualimap takes sequence alignment 

data and provides graphical and statistical analyses for the evaluation 

of data. Such quality-control data are vital for highlighting problems 

in the sequencing and/or mapping processes, which must be addressed 

prior to further analyses.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{ISI:000310262500003,

title = {Development, Characterization and Experimental Validation of a 

Cultivated Sunflower (Helianthus annuus L.) Gene Expression 

Oligonucleotide Microarray},

author = { P. Fernandez and M. Soria and D. Blesa and J. DiRienzo and S. Moschen and M. Rivarola and B. Jose Clavijo and S. Gonzalez and L. Peluffo and D. Principi and G. Dosio and L. Aguirrezabal and F. Garcia-Garcia and A. Conesa and E. Hopp and J. Dopazo and R. Amelia Heinz and N. Paniego},

url = {http://dx.doi.org/10.1371/journal.pone.0045899},

doi = {10.1371/journal.pone.0045899},

issn = {1932-6203},

year  = {2012},

date = {2012-10-01},

journal = {PLOS ONE},

volume = {7},

number = {10},

abstract = {Oligonucleotide-based microarrays with accurate gene coverage represent 

a key strategy for transcriptional studies in orphan species such as 

sunflower, H. annuus L., which lacks full genome sequences. The goal of 

this study was the development and functional annotation of a 

comprehensive sunflower unigene collection and the design and validation 

of a custom sunflower oligonucleotide-based microarray. A large scale 

EST (>130,000 ESTs) curation, assembly and sequence annotation was 

performed using Blast2GO (www.blast2go.de). The EST assembly comprises 

41,013 putative transcripts (12,924 contigs and 28,089 singletons). The 

resulting Sunflower Unigen Resource (SUR version 1.0) was used to design 

an oligonucleotide-based Agilent microarray for cultivated sunflower. 

This microarray includes a total of 42,326 features: 1,417 Agilent 

controls, 74 control probes for sunflower replicated 10 times (740 

controls) and 40,169 different non-control probes. Microarray 

performance was validated using a model experiment examining the 

induction of senescence by water deficit. Pre-processing and 

differential expression analysis of Agilent microarrays was performed 

using the Bioconductor limma package. The analyses based on p-values 

calculated by eBayes (p<0.01) allowed the detection of 558 

differentially expressed genes between water stress and control 

conditions; from these, ten genes were further validated by qPCR. 

Over-represented ontologies were identified using FatiScan in the 

Babelomics suite. This work generated a curated and trustable sunflower 

unigene collection, and a custom, validated sunflower 

oligonucleotide-based microarray using Agilent technology. Both the 

curated unigene collection and the validated oligonucleotide microarray 

provide key resources for sunflower genome analysis, transcriptional 

studies, and molecular breeding for crop improvement.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{ISI:000310368300003,

title = {Early gene expression events in the laminar abscission zone of 

abscission-promoted citrus leaves after a cycle of water 

stress/rehydration: involvement of CitbHLH1},

author = { J. Agusti and J. Gimeno and P. Merelo and R. Serrano and M. Cercos and A. Conesa and M. Talon and F. R. Tadeo},

url = {http://dx.doi.org/10.1093/jxb/ers270},

doi = {10.1093/jxb/ers270},

issn = {0022-0957},

year  = {2012},

date = {2012-10-01},

journal = {JOURNAL OF EXPERIMENTAL BOTANY},

volume = {63},

number = {17},

pages = {6079-6091},

abstract = {Leaf abscission is a common response of plants to drought stress. Some 

species, such as citrus, have evolved a specific behaviour in this 

respect, keeping their leaves attached to the plant body during water 

stress until this is released by irrigation or rain. This study 

successfully reproduced this phenomenon under controlled conditions (24h 

of water stress followed by 24h of rehydration) and used it to construct 

a suppression subtractive hybridization cDNA library enriched in genes 

involved in the early stages of rehydration-promoted leaf abscission 

after water stress. Sequencing of the library yielded 314 unigenes, which were spotted onto nylon membranes. Membrane hybridization with 

petiole (Pet)- and laminar abscission zone (LAZ)-enriched RNA samples 

corresponding to early steps in leaf abscission revealed an almost 

exclusive preferential gene expression programme in the LAZ. The data 

identified major processes such as protein metabolism, cell-wall 

modification, signalling, control of transcription and vesicle 

production, and transport as the main biological processes activated in 

LAZs during the early steps of rehydration-promoted leaf abscission 

after water stress. Based on these findings, a model for the early steps 

of citrus leaf abscission is proposed. In addition, it is suggested that 

CitbHLH1, the putative citrus orthologue of Arabidopsis BIGPETAL, may 

play major roles in the control of abscission-related events in citrus 

abscission zones.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{ISI:000305420000014,

title = {ARSyN: a method for the identification and removal of systematic noise 

in multifactorial time course microarray experiments},

author = { M. J. Nueda and A. Ferrer and A. Conesa},

url = {http://dx.doi.org/10.1093/biostatistics/kxr042},

doi = {10.1093/biostatistics/kxr042},

issn = {1465-4644},

year  = {2012},

date = {2012-07-01},

journal = {BIOSTATISTICS},

volume = {13},

number = {3},

pages = {553-566},

abstract = {Transcriptomic profiling experiments that aim to the identification of 

responsive genes in specific biological conditions are commonly set up 

under defined experimental designs that try to assess the effects of 

factors and their interactions on gene expression. Data from these 

controlled experiments, however, may also contain sources of unwanted 

noise that can distort the signal under study, affect the residuals of 

applied statistical models, and hamper data analysis. Commonly, normalization methods are applied to transcriptomics data to remove 

technical artifacts, but these are normally based on general assumptions 

of transcript distribution and greatly ignore both the characteristics 

of the experiment under consideration and the coordinative nature of 

gene expression. In this paper, we propose a novel methodology, ARSyN, for the preprocessing of microarray data that takes into account these 2 

last aspects. By combining analysis of variance (ANOVA) modeling of gene 

expression values and multivariate analysis of estimated effects, the 

method identifies the nonstructured part of the signal associated to the 

experimental factors (the noise within the signal) and the structured 

variation of the ANOVA errors (the signal of the noise). By removing 

these noise fractions from the original data, we create a filtered data 

set that is rich in the information of interest and includes only the 

random noise required for inferential analysis. In this work, we focus 

on multifactorial time course microarray (MTCM) experiments with 2 

factors: one quantitative such as time or dosage and the other 

qualitative, as tissue, strain, or treatment. However, the method can be 

used in other situations such as experiments with only one factor or 

more complex designs with more than 2 factors. The filtered data 

obtained after applying ARSyN can be further analyzed with the 

appropriate statistical technique to obtain the biological information 

required. To evaluate the performance of the filtering strategy, we have 

applied different statistical approaches for MTCM analysis to several 

real and simulated data sets, studying also the efficiency of these 

techniques. By comparing the results obtained with the original and 

ARSyN filtered data and also with other filtering techniques, we can 

conclude that the proposed method increases the statistical power to 

detect biological signals, especially in cases where there are high 

levels of structural noise. Software for ARSyN is freely available at 

http://www.ua.es/personal/mj.nueda.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{ISI:000305069800421,

title = {Regulatory proteins in the opportunistic human pathogen Aspergillus 

fumigatus},

author = { C. J. Lin and H. Irmer and S. Tarazona and P. Olbermann and S. Krappmann and A. Conesa and G. Braus},

issn = {0933-7407},

year  = {2012},

date = {2012-06-01},

journal = {MYCOSES},

volume = {55},

number = {4, SI},

pages = {135-136},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{ISI:000311518100001,

title = {Identification of yeast genes that confer resistance to chitosan 

oligosaccharide (COS) using chemogenomics},

author = { M. D. L. A. Jaime and L. Vicente Lopez-Llorca and A. Conesa and A. Y. Lee and M. Proctor and L. E. Heisler and M. Gebbia and G. Giaever and J. T. Westwood and C. Nislow},

url = {http://dx.doi.org/10.1186/1471-2164-13-267},

doi = {10.1186/1471-2164-13-267},

issn = {1471-2164},

year  = {2012},

date = {2012-06-01},

journal = {BMC GENOMICS},

volume = {13},

abstract = {Background: Chitosan oligosaccharide (COS), a deacetylated derivative of 

chitin, is an abundant, and renewable natural polymer. COS has higher 

antimicrobial properties than chitosan and is presumed to act by 

disrupting/permeabilizing the cell membranes of bacteria, yeast and 

fungi. COS is relatively non-toxic to mammals. By identifying the 

molecular and genetic targets of COS, we hope to gain a better 

understanding of the antifungal mode of action of COS. 

Results: Three different chemogenomic fitness assays, haploinsufficiency 

(HIP), homozygous deletion (HOP), and multicopy suppression (MSP) 

profiling were combined with a transcriptomic analysis to gain insight 

in to the mode of action and mechanisms of resistance to chitosan 

oligosaccharides. The fitness assays identified 39 yeast deletion 

strains sensitive to COS and 21 suppressors of COS sensitivity. The 

genes identified are involved in processes such as RNA biology 

(transcription, translation and regulatory mechanisms), membrane 

functions (e.g. signalling, transport and targeting), membrane 

structural components, cell division, and proteasome processes. The 

transcriptomes of control wild type and 5 suppressor strains 

overexpressing ARL1, BCK2, ERG24, MSG5, or RBA50, were analyzed in the 

presence and absence of COS. Some of the up-regulated transcripts in the 

suppressor overexpressing strains exposed to COS included genes involved 

in transcription, cell cycle, stress response and the Ras signal 

transduction pathway. Down-regulated transcripts included those encoding 

protein folding components and respiratory chain proteins. The 

COS-induced transcriptional response is distinct from previously 

described environmental stress responses (i.e. thermal, salt, osmotic 

and oxidative stress) and pre-treatment with these well characterized 

environmental stressors provided little or any resistance to COS. 

Conclusions: Overexpression of the ARL1 gene, a member of the Ras 

superfamily that regulates membrane trafficking, provides protection 

against COS-induced cell membrane permeability and damage. We found that 

the ARL1 COS-resistant over-expression strain was as sensitive to 

Amphotericin B, Fluconazole and Terbinafine as the wild type cells and 

that when COS and Fluconazole are used in combination they act in a 

synergistic fashion. The gene targets of COS identified in this study 

indicate that COS's mechanism of action is different from other commonly 

studied fungicides that target membranes, suggesting that COS may be an 

effective fungicide for drug-resistant fungal pathogens.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{ISI:000301295900020,

title = {Mining of miRNAs and potential targets from gene oriented clusters of 

transcripts sequences of the anti-malarial plant, Artemisia annua},

author = { A. L. Perez-Quintero and G. Sablok and T. V. Tatarinova and A. Conesa and J. Kuo and C. Lopez},

url = {http://dx.doi.org/10.1007/s10529-011-0808-0},

doi = {10.1007/s10529-011-0808-0},

issn = {0141-5492},

year  = {2012},

date = {2012-04-01},

journal = {BIOTECHNOLOGY LETTERS},

volume = {34},

number = {4},

pages = {737-745},

abstract = {miRNAs involved in the biosynthesis of artemisinin, an anti-malarial 

compound form the plant Artemisia annua, have been identified using 

computational approaches to find conserved pre-miRNAs in available A. 

annua UniGene collections. Eleven pre-miRNAs were found from nine 

families. Targets predicted for these miRNAs were mainly transcription 

factors for conserved miRNAs. No target genes involved in artemisinin 

biosynthesis were found. However, miR390 was predicted to target a gene 

involved in the trichome development, which is the site of synthesis of 

artemisinin and could be a candidate for genetic transformation aiming 

to increase the content of artemisinin. Phylogenetic analyses were 

carried out to determinate the relation between A. annua and other plant 

pre-miRNAs: the pre-miRNA-based phylogenetic trees failed to correspond 

to known phylogenies, suggesting that pre-miRNA primary sequences may be 

too variable to accurately predict phylogenetic relations.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{ISI:000305345200011,

title = {Transcriptome Profiling of the Intoxication Response of Tenebrio molitor 

Larvae to Bacillus thuringiensis Cry3Aa Protoxin},

author = { B. Oppert and S. E. Dowd and P. Bouffard and L. Li and A. Conesa and M. D. Lorenzen and M. Toutges and J. Marshall and D. L. Huestis and J. Fabrick and C. Oppert and J. L. Jurat-Fuentes},

url = {http://dx.doi.org/10.1371/journal.pone.0034624},

doi = {10.1371/journal.pone.0034624},

issn = {1932-6203},

year  = {2012},

date = {2012-04-01},

journal = {PLOS ONE},

volume = {7},

number = {4},

abstract = {Bacillus thuringiensis (Bt) crystal (Cry) proteins are effective against 

a select number of insect pests, but improvements are needed to increase 

efficacy and decrease time to mortality for coleopteran pests. To gain 

insight into the Bt intoxication process in Coleoptera, we performed 

RNA-Seq on cDNA generated from the guts of Tenebrio molitor larvae that 

consumed either a control diet or a diet containing Cry3Aa protoxin. 

Approximately 134,090 and 124,287 sequence reads from the control and 

Cry3Aa-treated groups were assembled into 1,318 and 1,140 contigs, respectively. Enrichment analyses indicated that functions associated 

with mitochondrial respiration, signalling, maintenance of cell 

structure, membrane integrity, protein recycling/synthesis, and glycosyl 

hydrolases were significantly increased in Cry3Aa-treated larvae, whereas functions associated with many metabolic processes were reduced, especially glycolysis, tricarboxylic acid cycle, and fatty acid 

synthesis. Microarray analysis was used to evaluate temporal changes in 

gene expression after 6, 12 or 24 h of Cry3Aa exposure. Overall, microarray analysis indicated that transcripts related to allergens, chitin-binding proteins, glycosyl hydrolases, and tubulins were induced, and those related to immunity and metabolism were repressed in 

Cry3Aa-intoxicated larvae. The 24 h microarray data validated most of 

the RNA-Seq data. Of the three intoxication intervals, larvae 

demonstrated more differential expression of transcripts after 12 h 

exposure to Cry3Aa. Gene expression examined by three different methods 

in control vs. Cry3Aa-treated larvae at the 24 h time point indicated 

that transcripts encoding proteins with chitin-binding domain 3 were the 

most differentially expressed in Cry3Aa-intoxicated larvae. Overall, the 

data suggest that T. molitor larvae mount a complex response to Cry3Aa 

during the initial 24 h of intoxication. Data from this study represent 

the largest genetic sequence dataset for T. molitor to date. 

Furthermore, the methods in this study are useful for comparative 

analyses in organisms lacking a sequenced genome.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{ISI:000209459000044,

title = {Transdifferentiation of MALME-3M and MCF-7 Cells toward Adipocyte-like 

Cells is Dependent on Clathrin-mediated Endocytosis},

author = { J. Carcel-Trullols and C. Aguilar-Gallardo and F. Garcia-Alcalde and M. Angel Pardo-Cea and J. Dopazo and A. Conesa and C. Simon},

url = {http://dx.doi.org/10.1186/2193-1801-1-44},

doi = {10.1186/2193-1801-1-44},

issn = {2193-1801},

year  = {2012},

date = {2012-01-01},

journal = {SPRINGERPLUS},

volume = {1},

abstract = {Enforced cell transdifferentiation of human cancer cells is a promising 

alternative to conventional chemotherapy. We previously identified 

albumin-associated lipid-and, more specifically, saturated fatty 

acid-induced transdifferentiation programs in human cancer cells 

(HCCLs). In this study, we further characterized the adipocyte-like 

cells, resulting from the transdifferentiation of human cancer cell 

lines MCF-7 and MALME-3M, and proposed a common mechanistic approach for 

these transdifferentiating programs. We showed the loss of pigmentation 

in MALME-3M cells treated with albumin-associated lipids, based on 

electron microscopic analysis, and the overexpression of perilipin 2 

(PLIN2) by western blotting in MALME-3M and MCF-7 cells treated with 

unsaturated fatty acids. Comparing the gene expression profiles of naive 

melanoma MALME-3M cells and albumin-associated lipid-treated cells, based on RNA sequencing, we confirmed the transcriptional upregulation 

of some key adipogenic gene markers and also an alternative splicing of 

the adipogenic master regulator PPARG, that is probably related to the 

reported up regulated expression of the protein. Most importantly, these 

results also showed the upregulation of genes responsible for Clathrin 

(CLTC) and other adaptor-related proteins. An increase in CLTC 

expression in the transdifferentiated cells was confirmed by western 

blotting. Inactivation of CLTC by chlorpromazine (CHP), an inhibitor of 

CTLC mediated endocytosis (CME), and gene silencing by siRNAs, partially 

reversed the accumulation of neutral lipids observed in the 

transdifferentiated cells. These findings give a deeper insight into the 

phenotypic changes observed in HCCL to adipocyte-like 

transdifferentiation and point towards CME as a key pathway in distinct 

transdifferentiation programs.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{ISI:000298300800012,

title = {Histone modifications and expression of DAM6 gene in peach are modulated 

during bud dormancy release in a cultivar-dependent manner},

author = { C. Leida and A. Conesa and G. Llacer and M. Luisa Badenes and G. Rios},

url = {http://dx.doi.org/10.1111/j.1469-8137.2011.03863.x},

doi = {10.1111/j.1469-8137.2011.03863.x},

issn = {0028-646X},

year  = {2012},

date = {2012-01-01},

journal = {NEW PHYTOLOGIST},

volume = {193},

number = {1},

pages = {67-80},

abstract = {Bud dormancy release in many woody perennial plants responds to the 

seasonal accumulation of chilling stimulus. MADS-box transcription 

factors encoded by DORMANCY ASSOCIATED MADS-box (DAM) genes in peach 

(Prunus persica) are implicated in this pathway, but other regulatory 

factors remain to be identified. In addition, the regulation of DAM gene 

expression is not well known at the molecular level. A microarray 

hybridization approach was performed to identify genes whose expression 

correlates with the bud dormancy-related behaviour in 10 different peach 

cultivars. Histone modifications in DAM6 gene were investigated by 

chromatin immunoprecipitation in two different cultivars. The expression 

of DAM4DAM6 and several genes related to abscisic acid and drought 

stress response correlated with the dormancy behaviour of peach 

cultivars. The trimethylation of histone H3 at K27 in the DAM6 promoter, coding region and the second large intron was preceded by a decrease in 

acetylated H3 and trimethylated H3K4 in the region of translation start, coinciding with repression of DAM6 during dormancy release. Analysis of 

chromatin modifications reinforced the role of epigenetic mechanisms in 

DAM6 regulation and bud dormancy release, and highlighted common 

features with the vernalization process in Arabidopsis thaliana and 

cereals.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{ISI:000299712500014,

title = {Variable selection for multifactorial genomic data},

author = { S. Tarazona and S. Prado-Lopez and J. Dopazo and A. Ferrer and A. Conesa},

url = {http://dx.doi.org/10.1016/j.chemolab.2011.10.012},

doi = {10.1016/j.chemolab.2011.10.012},

issn = {0169-7439},

year  = {2012},

date = {2012-01-01},

journal = {CHEMOMETRICS AND INTELLIGENT LABORATORY SYSTEMS},

volume = {110},

number = {1},

pages = {113-122},

abstract = {Dimension reduction techniques are used to explore genomic data. Due to 

the large number of variables (genes) included in this kind of studies, variable selection methods are needed to identify the most responsive 

genes in order to get a better interpretation of the results or to 

conduct more specific experiments. These methods should be consistent 

with the amount of signal in the data. For this purpose, we introduce a 

novel selection strategy called minAS and also adapt other existing 

strategies, such us Gamma approximation, resampling techniques, etc. All 

of them are based on studying the distribution of statistics measuring 

the importance of the variables in the model. These strategies have been 

applied to the ASCA-genes analysis framework and more generally to 

dimension reduction techniques as PCA. The performance of the different 

strategies was evaluated using simulated data. The best performing 

methods were then applied on an experimental dataset containing the 

transcriptomic profiles of human embryonic stem cells cultured under 

different oxygen concentrations. The ability of the methods to extract 

relevant biological information from the data is discussed. (C) 2011 

Elsevier B.V. All rights reserved.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{ISI:000297242100015,

title = {Large-scale transcriptional profiling and functional assays reveal 

important roles for Rho-GTPase signalling and SCL during haematopoietic 

differentiation of human embryonic stem cells},

author = { S. Yung and M. Ledran and I. Moreno-Gimeno and A. Conesa and D. Montaner and J. Dopazo and I. Dimmick and N. J. Slater and L. Marenah and P. J. Real and I. Paraskevopoulou and V. Bisbal and D. Burks and M. Santibanez-Koref and R. Moreno and J. Mountford and P. Menendez and L. Armstrong and M. Lako},

url = {http://dx.doi.org/10.1093/hmg/ddr431},

doi = {10.1093/hmg/ddr431},

issn = {0964-6906},

year  = {2011},

date = {2011-12-01},

journal = {HUMAN MOLECULAR GENETICS},

volume = {20},

number = {24},

pages = {4932-4946},

abstract = {Understanding the transcriptional cues that direct differentiation of 

human embryonic stem cells (hESCs) and human-induced pluripotent stem 

cells to defined and functional cell types is essential for future 

clinical applications. In this study, we have compared transcriptional 

profiles of haematopoietic progenitors derived from hESCs at various 

developmental stages of a feeder-and serum-free differentiation method 

and show that the largest transcriptional changes occur during the first 

4 days of differentiation. Data mining on the basis of molecular 

function revealed Rho-GTPase signalling as a key regulator of 

differentiation. Inhibition of this pathway resulted in a significant 

reduction in the numbers of emerging haematopoietic progenitors 

throughout the differentiation window, thereby uncovering a previously 

unappreciated role for Rho-GTPase signalling during human haematopoietic 

development. Our analysis indicated that SCL was the 11th most 

upregulated transcript during the first 4 days of the hESC 

differentiation process. Overexpression of SCL in hESCs promoted 

differentiation to meso-endodermal lineages, the emergence of 

haematopoietic and erythro-megakaryocytic progenitors and accelerated 

erythroid differentiation. Importantly, intrasplenic transplantation of 

SCL-overexpressing hESC-derived haematopoietic cells enhanced recovery 

from induced acute anaemia without significant cell engraftment, suggesting a paracrine-mediated effect.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{ISI:000297918600020,

title = {Differential expression in RNA-seq: A matter of depth},

author = { S. Tarazona and F. Garcia-Alcalde and J. Dopazo and A. Ferrer and A. Conesa},

url = {http://dx.doi.org/10.1101/gr.124321.111},

doi = {10.1101/gr.124321.111},

issn = {1088-9051},

year  = {2011},

date = {2011-12-01},

journal = {GENOME RESEARCH},

volume = {21},

number = {12},

pages = {2213-2223},

abstract = {Next-generation sequencing (NGS) technologies are revolutionizing genome 

research, and in particular, their application to transcriptomics 

(RNA-seq) is increasingly being used for gene expression profiling as a 

replacement for microarrays. However, the properties of RNA-seq data 

have not been yet fully established, and additional research is needed 

for understanding how these data respond to differential expression 

analysis. In this work, we set out to gain insights into the 

characteristics of RNA-seq data analysis by studying an important 

parameter of this technology: the sequencing depth. We have analyzed how 

sequencing depth affects the detection of transcripts and their 

identification as differentially expressed, looking at aspects such as 

transcript biotype, length, expression level, and fold-change. We have 

evaluated different algorithms available for the analysis of RNA-seq and 

proposed a novel approach-NOISeq-that differs from existing methods in 

that it is data-adaptive and nonparametric. Our results reveal that most 

existing methodologies suffer from a strong dependency on sequencing 

depth for their differential expression calls and that this results in a 

considerable number of false positives that increases as the number of 

reads grows. In contrast, our proposed method models the noise 

distribution from the actual data, can therefore better adapt to the 

size of the data set, and is more effective in controlling the rate of 

false discoveries. This work discusses the true potential of RNA-seq for 

studying regulation at low expression ranges, the noise within RNA-seq 

data, and the issue of replication.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{ISI:000297983800001,

title = {Fortunella margarita Transcriptional Reprogramming Triggered by 

Xanthomonas citri subsp citri},

author = { A. A. Khalaf and Jr. Gmitter and A. Conesa and J. Dopazo and G. A. Moore},

url = {http://dx.doi.org/10.1186/1471-2229-11-159},

doi = {10.1186/1471-2229-11-159},

issn = {1471-2229},

year  = {2011},

date = {2011-11-01},

journal = {BMC PLANT BIOLOGY},

volume = {11},

abstract = {Background: Citrus canker disease caused by the bacterial pathogen 

Xanthomonas citri subsp. citri (Xcc) has become endemic in areas where 

high temperature, rain, humidity, and windy conditions provide a 

favourable environment for the dissemination of the bacterium. Xcc is 

pathogenic on many commercial citrus varieties but appears to elicit an 

incompatible reaction on the citrus relative Fortunella margarita Swing 

(kumquat), in the form of a very distinct delayed necrotic response. We 

have developed subtractive libraries enriched in sequences expressed in 

kumquat leaves during both early and late stages of the disease. The 

isolated differentially expressed transcripts were subsequently 

sequenced. Our results demonstrate how the use of microarray expression 

profiling can help assign roles to previously uncharacterized genes and 

elucidate plant pathogenesis-response related mechanisms. This can be 

considered to be a case study in a citrus relative where high throughput 

technologies were utilized to understand defence mechanisms in 

Fortunella and citrus at the molecular level. 

Results: cDNAs from sequenced kumquat libraries (ESTs) made from 

subtracted RNA populations, healthy vs. infected, were used to make this 

microarray. Of 2054 selected genes on a customized array, 317 were 

differentially expressed (P < 0.05) in Xcc challenged kumquat plants 

compared to mock-inoculated ones. This study identified components of 

the incompatible interaction such as reactive oxygen species (ROS) and 

programmed cell death (PCD). Common defence mechanisms and a number of 

resistance genes were also identified. In addition, there were a 

considerable number of differentially regulated genes that had no 

homologues in the databases. This could be an indication of either a 

specialized set of genes employed by kumquat in response to canker 

disease or new defence mechanisms in citrus. 

Conclusion: Functional categorization of kumquat Xcc-responsive genes 

revealed an enhanced defence-related metabolism as well as a number of 

resistant response-specific genes in the kumquat transcriptome in 

response to Xcc inoculation. Gene expression profile(s) were analyzed to 

assemble a comprehensive and inclusive image of the molecular 

interaction in the kumquat/Xcc system. This was done in order to 

elucidate molecular mechanisms associated with the development of the 

hypersensitive response phenotype in kumquat leaves. These data will be 

used to perform comparisons among citrus species to evaluate means to 

enhance the host immune responses against bacterial diseases.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{ISI:000292249800002,

title = {Profiling the venom gland transcriptomes of Costa Rican snakes by 454 

pyrosequencing},

author = { J. Durban and P. Juarez and Y. Angulo and B. Lomonte and M. Flores-Diaz and A. Alape-Giron and M. Sasa and L. Sanz and J. M. Gutierrez and J. Dopazo and A. Conesa and J. J. Calvete},

url = {http://dx.doi.org/10.1186/1471-2164-12-259},

doi = {10.1186/1471-2164-12-259},

issn = {1471-2164},

year  = {2011},

date = {2011-05-01},

journal = {BMC GENOMICS},

volume = {12},

abstract = {Background: A long term research goal of venomics, of applied importance 

for improving current antivenom therapy, but also for drug discovery, is 

to understand the pharmacological potential of venoms. Individually or 

combined, proteomic and transcriptomic studies have demonstrated their 

feasibility to explore in depth the molecular diversity of venoms. In 

the absence of genome sequence, transcriptomes represent also valuable 

searchable databases for proteomic projects. 

Results: The venom gland transcriptomes of 8 Costa Rican taxa from 5 

genera (Crotalus, Bothrops, Atropoides, Cerrophidion, and Bothriechis) 

of pitvipers were investigated using high-throughput 454 pyrosequencing. 

100,394 out of 330,010 masked reads produced significant hits in the 

available databases. 5.165,220 nucleotides (8.27%) were masked by 

RepeatMasker, the vast majority of which corresponding to class I 

(retroelements) and class II (DNA transposons) mobile elements. BLAST 

hits included 79,991 matches to entries of the taxonomic suborder 

Serpentes, of which 62,433 displayed similarity to documented venom 

proteins. Strong discrepancies between the transcriptome-computed and 

the proteome-gathered toxin compositions were obvious at first sight. 

Although the reasons underlaying this discrepancy are elusive, since no 

clear trend within or between species is apparent, the data indicate 

that individual mRNA species may be translationally controlled in a 

species-dependent manner. The minimum number of genes from each toxin 

family transcribed into the venom gland transcriptome of each species 

was calculated from multiple alignments of reads matched to a 

full-length reference sequence of each toxin family. Reads encoding ORF 

regions of Kazal-type inhibitor-like proteins were uniquely found in 

Bothriechis schlegelii and B. lateralis transcriptomes, suggesting a 

genus-specific recruitment event during the early-Middle Miocene. A 

transcriptome-based cladogram supports the large divergence between A. 

mexicanus and A. picadoi, and a closer kinship between A. mexicanus and 

C. godmani. 

Conclusions: Our comparative next-generation sequencing (NGS) analysis 

reveals taxon-specific trends governing the formulation of the venom 

arsenal. Knowledge of the venom proteome provides hints on the 

translation efficiency of toxin-coding transcripts, contributing thereby 

to a more accurate interpretation of the transcriptome. The application 

of NGS to the analysis of snake venom transcriptomes, may represent the 

tool for opening the door to systems venomics.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{ISI:000289162000005,

title = {B2G-FAR, a species-centered GO annotation repository},

author = { S. Goetz and R. Arnold and P. Sebastian-Leon and S. Martin-Rodriguez and P. Tischler and M. Jehl and J. Dopazo and T. Rattei and A. Conesa},

url = {http://dx.doi.org/10.1093/bioinformatics/btr059},

doi = {10.1093/bioinformatics/btr059},

issn = {1367-4803},

year  = {2011},

date = {2011-04-01},

journal = {BIOINFORMATICS},

volume = {27},

number = {7},

pages = {919-924},

abstract = {Motivation: Functional genomics research has expanded enormously in the 

last decade thanks to the cost reduction in high-throughput technologies 

and the development of computational tools that generate, standardize 

and share information on gene and protein function such as the Gene 

Ontology ( GO). Nevertheless, many biologists, especially working with 

non-model organisms, still suffer from non-existing or low-coverage 

functional annotation, or simply struggle retrieving, summarizing and 

querying these data. 

Results: The Blast2GO Functional Annotation Repository (B2G-FAR) is a 

bioinformatics resource envisaged to provide functional information for 

otherwise uncharacterized sequence data and offers data mining tools to 

analyze a larger repertoire of species than currently available. This 

new annotation resource has been created by applying the Blast2GO 

functional annotation engine in a strongly high-throughput manner to the 

entire space of public available sequences. The resulting repository 

contains GO term predictions for over 13.2 million non-redundant protein 

sequences based on BLAST search alignments from the SIMAP database. We 

generated GO annotation for approximately 150 000 different taxa making 

available 2000 species with the highest coverage through B2G-FAR. A 

second section within B2G-FAR holds functional annotations for 17 

non-model organism Affymetrix GeneChips. 

Conclusions: B2G-FAR provides easy access to exhaustive functional 

annotation for 2000 species offering a good balance between quality and 

quantity, thereby supporting functional genomics research especially in 

the case of non-model organisms.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{ISI:000288020600040,

title = {Modeling Human Endometrial Decidualization from the Interaction between 

Proteome and Secretome},

author = { T. Garrido-Gomez and F. Dominguez and J. Antonio Lopez and E. Camafeita and A. Quinonero and J. Antonio Martinez-Conejero and A. Pellicer and A. Conesa and C. Simon},

url = {http://dx.doi.org/10.1210/jc.2010-1825},

doi = {10.1210/jc.2010-1825},

issn = {0021-972X},

year  = {2011},

date = {2011-03-01},

journal = {JOURNAL OF CLINICAL ENDOCRINOLOGY & METABOLISM},

volume = {96},

number = {3},

pages = {706-716},

abstract = {Context: Decidualization of the human endometrium, which involves 

morphological and biochemical modifications of the endometrial stromal 

cells (ESCs), is a prerequisite for adequate trophoblast invasion and 

placenta formation. 

Objective: This study aims to investigate the proteome and secretome of 

in vitro decidualized ESCs. These data were combined with published 

genomic information and integrated to model the human decidualization 

interactome. 

Design: Prospective experimental case-control study. 

Setting: A private research foundation. 

Patients: Sixteen healthy volunteer ovum donors. 

Intervention: Endometrial samples were obtained, and ESCs were isolated 

and decidualized in vitro. 

Main Outcome Measures: Two-dimensional difference in-gel 

electrophoresis, matrix-assisted laser 

desorption/ionization-time-of-flight mass spectrometry, Western blot, human protein cytokine array, ELISA, and bioinformatics analysis were 

performed. 

Results: The proteomic analysis revealed 60 differentially expressed 

proteins (36 over-and 24 underexpressed) in decidualized versus control 

ESCs, including known decidualization markers (cathepsin B) and new 

biomarkers (transglutaminase 2, peroxiredoxin 4, and the ACTB protein). 

In the secretomic analysis, a total of 13 secreted proteins (11 up-and 2 

down-regulated) were identified, including well-recognized markers (IGF 

binding protein-1 and prolactin) and novel ones (myeloid progenitor 

inhibitory factor-1 and platelet endothelial cell adhesion molecule-1). 

These proteome/secretome profiles have been integrated into a 

decidualization interactome model. 

Conclusions: Proteomic and secretomic have been used as hypothesis-free 

approaches together with complex bioinformatics to model the human 

decidual interactome for the first time. We confirm previous knowledge, describe new molecules, and we have built up a model for human in vitro 

decidualization as invaluable tool for the diagnosis, therapy, and 

interpretation of biological phenomena. (J Clin Endocrinol Metab 96: 

706-716, 2011)},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{ISI:000285626300021,

title = {Paintomics: a web based tool for the joint visualization of 

transcriptomics and metabolomics data},

author = { F. Garcia-Alcalde and F. Garcia-Lopez and J. Dopazo and A. Conesa},

url = {http://dx.doi.org/10.1093/bioinformatics/btq594},

doi = {10.1093/bioinformatics/btq594},

issn = {1367-4803},

year  = {2011},

date = {2011-01-01},

journal = {BIOINFORMATICS},

volume = {27},

number = {1},

pages = {137-139},

abstract = {Motivation: The development of the omics technologies such as 

transcriptomics, proteomics and metabolomics has made possible the 

realization of systems biology studies where biological systems are 

interrogated at different levels of biochemical activity (gene 

expression, protein activity and/or metabolite concentration). An 

effective approach to the analysis of these complex datasets is the 

joined visualization of the disparate biomolecular data on the framework 

of known biological pathways. 

Results: We have developed the Paintomics web server as an easy-to-use 

bioinformatics resource that facilitates the integrated visual analysis 

of experiments where transcriptomics and metabolomics data have been 

measured on different conditions for the same samples. Basically, Paintomics takes complete transcriptomics and metabolomics datasets, together with lists of significant gene or metabolite changes, and 

paints this information on KEGG pathway maps.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{ISI:000284658300011,

title = {A multiway approach to data integration in systems biology based on 

Tucker3 and N-PLS},

author = { A. Conesa and J. M. Prats-Montalban and S. Tarazona and M. Jose Nueda and A. Ferrer},

url = {http://dx.doi.org/10.1016/j.chemolab.2010.06.004},

doi = {10.1016/j.chemolab.2010.06.004},

issn = {0169-7439},

year  = {2010},

date = {2010-11-01},

journal = {CHEMOMETRICS AND INTELLIGENT LABORATORY SYSTEMS},

volume = {104},

number = {1, SI},

pages = {101-111},

abstract = {This paper discusses the potential of multi-way projection methods for 

analysing multifactorial data structures to identify underlying 

components of variability that interconnect different blocks of omics 

variables. We explore their suitability for explorative and variable 

selection analysis of systems biology data where different types of 

biological parameters are studied together. These methodologies were 

applied to the integrative analysis of a functional genomics dataset 

where transcriptomics, metabolomics and physiological data are 

available. Our results show that multiway methods are suited to 

accommodate multifactorial omics experiments and to analyse 

relationships between different biochemical layers. Additionally, strategies are presented for variable selection in the context of omics 

data and for interpreting results at the level of cellular pathways. (C) 

2010 Elsevier B.V. All rights reserved.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}