Publications

@article{Ugidos2022.10.09.511458b,

title = {MAMBA: a model-driven, constraint-based multiomic integration method},

author = {Manuel Ugidos and Carme Nu no-Cabanes and Sonia Tarazona and Alberto Ferrer and Lars Keld Nielsen and Susana Rodr'iguez-Navarro and Igor Mar'in de Mas and Ana Conesa},

url = {https://www.biorxiv.org/content/early/2022/10/10/2022.10.09.511458},

doi = {10.1101/2022.10.09.511458},

year  = {2022},

date = {2022-01-01},

journal = {bioRxiv},

publisher = {Cold Spring Harbor Laboratory},

abstract = {The inclusion of omic data into constraint-based modeling (CBM) has improved metabolic network characterization of biological models. However, the integration of semi-quantitative metabolomic data into CBM remains challenging. Here, we present MAMBA (Metabolic Adjustment via Multiomic Blocks Aggregation), a CBM approach that enables the use of semi-quantitative metabolomic data together with a gene-centric omic data type (e.g. transcriptomics, ChIP-seq or chromatin accessibility data, among others), and the combination of different time points and conditions. MAMBA outperformed other methods in terms of metabolic network characterization and metabolite prediction accuracy. As a case study, we applied MAMBA to a yeast multiomic dataset with time series design where two different yeast strains where exposed to heat stress. MAMBA captured known biology of heat stress in yeast and identified novel affected metabolic pathways. MAMBA was implemented as an integer linear programming (ILP) problem to guarantee efficient computation, and coded for MATLAB (freely available at github.com/ConesaLab/MAMBA).Competing Interest StatementThe authors have declared no competing interest.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{pmid36137106,

title = {Machine-learning-derived predictive score for early estimation of COVID-19 mortality risk in hospitalized patients},

author = {Alba González-Cebrián and Joan Borràs-Ferrís and Juan Pablo Ordovás-Baines and Marta Hermenegildo-Caudevilla and Mónica Climente-Marti and Sonia Tarazona and Raffaele Vitale and Daniel Palací-López and Jesús Francisco Sierra-Sánchez and Javier Saez de la Fuente and Alberto Ferrer},

doi = {10.1371/journal.pone.0274171},

issn = {1932-6203},

year  = {2022},

date = {2022-01-01},

journal = {PLoS One},

volume = {17},

number = {9},

pages = {e0274171},

abstract = {The clinical course of COVID-19 is highly variable. It is therefore essential to predict as early and accurately as possible the severity level of the disease in a COVID-19 patient who is admitted to the hospital. This means identifying the contributing factors of mortality and developing an easy-to-use score that could enable a fast assessment of the mortality risk using only information recorded at the hospitalization. A large database of adult patients with a confirmed diagnosis of COVID-19 (n = 15,628; with 2,846 deceased) admitted to Spanish hospitals between December 2019 and July 2020 was analyzed. By means of multiple machine learning algorithms, we developed models that could accurately predict their mortality. We used the information about classifiers' performance metrics and about importance and coherence among the predictors to define a mortality score that can be easily calculated using a minimal number of mortality predictors and yielded accurate estimates of the patient severity status. The optimal predictive model encompassed five predictors (age, oxygen saturation, platelets, lactate dehydrogenase, and creatinine) and yielded a satisfactory classification of survived and deceased patients (area under the curve: 0.8454 with validation set). These five predictors were additionally used to define a mortality score for COVID-19 patients at their hospitalization. This score is not only easy to calculate but also to interpret since it ranges from zero to eight, along with a linear increase in the mortality risk from 0% to 80%. A simple risk score based on five commonly available clinical variables of adult COVID-19 patients admitted to hospital is able to accurately discriminate their mortality probability, and its interpretation is straightforward and useful.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{Turpin-Sevilla2021-vy,

title = {Global methylome scores correlate with histological subtypes of  colorectal carcinoma and show different associations with common  clinical and molecular features},

author = {María Del Carmen Turpín-Sevilla and Fernando Pérez-Sanz and José García-Solano and Patricia Sebastián-León and Javier Trujillo-Santos and Pablo Carbonell and Eduardo Estrada and Anne Tuomisto and Irene Herruzo and Lochlan J Fennell and Markus J Mäkinen and Edith Rodríguez-Braun and Vicki L J Whitehall and Ana Conesa and Pablo Conesa-Zamora},

url = {https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8533997/pdf/cancers-13-05165.pdf},

doi = {10.3390/cancers13205165},

year  = {2021},

date = {2021-10-01},

urldate = {2021-10-01},

journal = {Cancers (Basel)},

volume = {13},

number = {20},

pages = {5165},

publisher = {MDPI AG},

abstract = {BACKGROUND: The typical methylation patterns associated with 

 cancer are hypermethylation at gene promoters and global genome 

 hypomethylation. Aberrant CpG island hypermethylation at 

 promoter regions and global genome hypomethylation have not been 

 associated with histological colorectal carcinomas (CRC) 

 subsets. Using Illumina's 450 k Infinium Human Methylation 

 beadchip, the methylome of 82 CRCs were analyzed, comprising 

 different histological subtypes: 40 serrated adenocarcinomas 

 (SAC), 32 conventional carcinomas (CC) and 10 CRCs showing 

 histological and molecular features of microsatellite 

 instability (hmMSI-H), and, additionally, 35 normal adjacent 

 mucosae. Scores reflecting the overall methylation at 250 bp, 1 

 kb and 2 kb from the transcription starting site (TSS) were 

 studied. RESULTS: SAC has an intermediate methylation pattern 

 between CC and hmMSI-H for the three genome locations. In 

 addition, the shift from promoter hypermethylation to genomic 

 hypomethylation occurs at a small sequence between 250 bp and 1 

 Kb from the gene TSS, and an asymmetric distribution of 

 methylation was observed between both sides of the CpG islands 

 (N vs. S shores). CONCLUSION: These findings show that different 

 histological subtypes of CRC have a particular global 

 methylation pattern depending on sequence distance to TSS and 

 highlight the so far underestimated importance of CpGs 

 aberrantly hypomethylated in the clinical phenotype of CRCs.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@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{pmid34132490,

title = {Precise transcriptional control of cellular quiescence by BRAVO/WOX5 complex in Arabidopsis roots},

author = {Isabel Betegón-Putze and Josep Mercadal and Nadja Bosch and Ainoa Planas-Riverola and Mar Marquès-Bueno and Josep Vilarrasa-Blasi and David Frigola and Rebecca C Burkart and Cristina Martínez and Ana Conesa and Rosangela Sozzani and Yvonne Stahl and Salomé Prat and Marta Ibañes and Ana I Caño-Delgado},

doi = {10.15252/msb.20209864},

issn = {1744-4292},

year  = {2021},

date = {2021-06-01},

journal = {Mol Syst Biol},

volume = {17},

number = {6},

pages = {e9864},

abstract = {Understanding stem cell regulatory circuits is the next challenge in plant biology, as these cells are essential for tissue growth and organ regeneration in response to stress. In the Arabidopsis primary root apex, stem cell-specific transcription factors BRAVO and WOX5 co-localize in the quiescent centre (QC) cells, where they commonly repress cell division so that these cells can act as a reservoir to replenish surrounding stem cells, yet their molecular connection remains unknown. Genetic and biochemical analysis indicates that BRAVO and WOX5 form a transcription factor complex that modulates gene expression in the QC cells to preserve overall root growth and architecture. Furthermore, by using mathematical modelling we establish that BRAVO uses the WOX5/BRAVO complex to promote WOX5 activity in the stem cells. Our results unveil the importance of transcriptional regulatory circuits in plant stem cell development.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{Planell2021-dy,

title = {STATegra: Multi-omics data integration - A conceptual scheme  with a bioinformatics pipeline},

author = {Nuria Planell and Vincenzo Lagani and Patricia Sebastian-Leon and Frans Kloet and Ewoud Ewing and Nestoras Karathanasis and Arantxa Urdangarin and Imanol Arozarena and Maja Jagodic and Ioannis Tsamardinos and Sonia Tarazona and Ana Conesa and Jesper Tegner and David Gomez-Cabrero},

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

doi = {10.3389/fgene.2021.620453},

year  = {2021},

date = {2021-03-01},

urldate = {2021-03-01},

journal = {Front. Genet.},

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{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{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{pmid33994920,

title = {Mutant PRPF8 Causes Widespread Splicing Changes in Spliceosome Components in Retinitis Pigmentosa Patient iPSC-Derived RPE Cells},

author = {Ángeles Arzalluz-Luque and Jose Luis Cabrera and Heli Skottman and Alberto Benguria and Arantxa Bolinches-Amorós and Nicolás Cuenca and Vincenzo Lupo and Ana Dopazo and Sonia Tarazona and Bárbara Delás and Miguel Carballo and Beatriz Pascual and Imma Hernan and Slaven Erceg and Dunja Lukovic},

doi = {10.3389/fnins.2021.636969},

issn = {1662-4548},

year  = {2021},

date = {2021-01-01},

journal = {Front Neurosci},

volume = {15},

pages = {636969},

abstract = {Retinitis pigmentosa (RP) is a rare, progressive disease that affects photoreceptors and retinal pigment epithelial (RPE) cells with blindness as a final outcome. Despite high medical and social impact, there is currently no therapeutic options to slow down the progression of or cure the disease. The development of effective therapies was largely hindered by high genetic heterogeneity, inaccessible disease tissue, and unfaithful model organisms. The fact that components of ubiquitously expressed splicing factors lead to the retina-specific disease is an additional intriguing question. Herein, we sought to correlate the retinal cell-type-specific disease phenotype with the splicing profile shown by a patient with autosomal recessive RP, caused by a mutation in pre-mRNA splicing factor 8 (PRPF8). In order to get insight into the role of PRPF8 in homeostasis and disease, we capitalize on the ability to generate patient-specific RPE cells and reveal differentially expressed genes unique to RPE cells. We found that spliceosomal complex and ribosomal functions are crucial in determining cell-type specificity through differential expression and alternative splicing (AS) and that PRPF8 mutation causes global changes in splice site selection and exon inclusion that particularly affect genes involved in these cellular functions. This finding corroborates the hypothesis that retinal tissue identity is conferred by a specific splicing program and identifies retinal AS events as a framework toward the design of novel therapeutic opportunities.},

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-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{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}

}