Publications

@article{cardozo2023dataset,

title = {Dataset of fundus images for the diagnosis of ocular toxoplasmosis},

author = {O. Cardozo and V. Ojeda and R. Parra and J. C. Mello-Román and J. L. Noguera Vázquez and M. García-Torres and F. Divina and S. Grillo and C. Villalba and J. Facon},

url = {https://www.sciencedirect.com/science/article/pii/S2352340923001749},

doi = {10.1016/j.dib.2023.109056},

year  = {2023},

date = {2023-01-01},

journal = {Data in Brief},

pages = {109056},

publisher = {Elsevier},

abstract = {Toxoplasmosis chorioretinitis is commonly diagnosed by an ophthalmologist through the evaluation of the fundus images of a patient. Early detection of these lesions may help to prevent blindness. In this article we present a data set of fundus images labeled into three categories: healthy eye, inactive and active chorioretinitis. The dataset was developed by three ophthalmologists with expertise in toxoplasmosis detection using fundus images. The dataset will be of great use to researchers working on ophthalmic image analysis using artificial intelligence techniques for the automatic detection of toxoplasmosis chorioretinitis.},

keywords = {bioinformatics},

pubstate = {published},

tppubtype = {article}

}

@article{vazquez2022systematic,

title = {A systematic review of the application of machine-learning algorithms in multiple sclerosis},

author = {M. Vázquez-Marrufo and E. Sarrias-Arrabal and M. García-Torres and R. Martín-Clemente and G. Izquierdo},

url = {https://www.sciencedirect.com/science/article/pii/S217358082200075X},

doi = {10.1016/j.nrleng.2020.10.013},

year  = {2023},

date = {2023-01-01},

journal = {Neurología (English Edition)},

publisher = {Elsevier},

abstract = {Introduction: The applications of artificial intelligence, and in particular automatic learning or “machine learning” (ML), constitute both a challenge and a great opportunity in numerous scientific, technical, and clinical disciplines. Specific applications in the study of multiple sclerosis (MS) have been no exception, and constitute an area of increasing interest in recent years. Objective: We present a systematic review of the application of ML algorithms in MS. Materials and methods: We used the PubMed search engine, which allows free access to the MEDLINE medical database, to identify studies including the keywords “machine learning” and “multiple sclerosis.” We excluded review articles, studies written in languages other than English or Spanish, and studies that were mainly technical and did not specifically apply to MS. The final selection included 76 articles, and 38 were rejected. Conclusions: After the review process, we established 4 main applications of ML in MS: 1) classifying MS subtypes; 2) distinguishing patients with MS from healthy controls and individuals with other diseases; 3) predicting progression and response to therapeutic interventions; and 4) other applications. Results found to date have shown that ML algorithms may offer great support for health professionals both in clinical settings and in research into MS.},

keywords = {bioinformatics},

pubstate = {published},

tppubtype = {article}

}

@article{delgado2022data,

title = {Data of transcriptional effects of the merbarone-mediated inhibition of TOP2},

author = {F. Delgado-Chaves and P. M. Martínez-García and A. Herrero-Ruiz and F. Gómez-Vela and F. Divina and S. Jimeno-González and F. Cortés-Ledesma},

url = {https://www.sciencedirect.com/science/article/pii/S235234092200693X},

doi = {10.1016/j.dib.2022.108499},

year  = {2022},

date = {2022-01-01},

journal = {Data in Brief},

volume = {44},

pages = {108499},

publisher = {Elsevier},

abstract = {Type II DNA topoisomerases relax topological stress by transiently gating DNA passage in a controlled cut-and-reseal mechanism that affects both DNA strands. Therefore, they are essential to overcome topological problems associated with DNA metabolism. Their aberrant activity results in the generation of DNA double-strand breaks, which can seriously compromise cell survival and genome integrity. Here, we profile the transcriptome of human-telomerase-immortalized retinal pigment epithelial 1 (RPE-1) cells when treated with merbarone, a drug that catalytically inhibits type II DNA topoisomerases. We performed RNA-Seq after 4 and 8 h of merbarone treatment and compared transcriptional profiles versus untreated samples. We report raw sequencing data together with lists of gene counts and differentially expressed genes.},

keywords = {bioinformatics},

pubstate = {published},

tppubtype = {article}

}

@article{aquino2022automatic,

title = {Automatic Diagnosis of Diabetic Retinopathy from Fundus Images Using Neuro-Evolutionary Algorithms},

author = {D. Aquino-Brítez and J.A. Gómez and J.L. Vázquez Noguera and M. García-Torres and J.C. Mello Román and P.E. Gardel-Sotomayor and V.E. Castillo Benitez and I. Castro Matto and D.P. Pinto-Roa and J. Facon and S.A. Grillo},

doi = {10.3233/SHTI220166},

year  = {2022},

date = {2022-01-01},

journal = {Studies in Health Technology and Informatics},

volume = {290},

pages = {689--693},

abstract = {Due to the presence of high glucose levels, diabetes mellitus (DM) is a widespread disease that can damage blood vessels in the retina and lead to loss of the visual system. To combat this disease, called Diabetic Retinopathy (DR), retinography, using images of the fundus of the retina, is the most used method for the diagnosis of Diabetic Retinopathy. The Deep Learning (DL) area achieved high performance for the classification of retinal images and even achieved almost the same human performance in diagnostic tasks. However, the performance of DL architectures is highly dependent on the optimal configuration of the hyperparameters. In this article, we propose the use of Neuroevolutionary Algorithms to optimize the hyperparameters corresponding to the DL model for the diagnosis of DR. The results obtained prove that the proposed method outperforms the results obtained by the classical approach.},

keywords = {bioinformatics},

pubstate = {published},

tppubtype = {article}

}

@article{pulido2021,

title = {Serial co-expression analysis of host factors from SARS-CoV viruses highly converges with former high-throughput screenings and proposes key regulators},

author = {A. J. Pérez-Pulido and G. Asencio-Cortés and A. M. Brokate-Llanos and G. Brea-Calvo and M. R. Rodríguez-Griñolo and A. Garzón and M. J. Muñoz},

url = {https://academic.oup.com/bib/article/22/2/1038/6103172},

doi = {10.1093/bib/bbaa419},

year  = {2021},

date = {2021-01-01},

journal = {Briefings in Bioinformatics},

volume = {22},

number = {2},

pages = {1038--1052},

abstract = {The current genomics era is bringing an unprecedented growth in the amount of gene expression data, only comparable to the exponential growth of sequences in databases during the last decades. This data allow the design of secondary analyses that take advantage of this information to create new knowledge. One of these feasible analyses is the evaluation of the expression level for a gene through a series of different conditions or cell types. Based on this idea, we have developed Automatic and Serial Analysis of CO-expression, which performs expression profiles for a given gene along hundreds of heterogeneous and normalized transcriptomics experiments and discover other genes that show either a similar or an inverse behavior. It might help to discover co-regulated genes, and common transcriptional regulators in any biological model. The present severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) pandemic is an opportunity to test this novel approach due to the wealth of data that are being generated, which could be used for validating results. Thus, we have identified 35 host factors in the literature putatively involved in the infectious cycle of SARS-CoV viruses and searched for genes tightly co-expressed with them. We have found 1899 co-expressed genes whose assigned functions are strongly related to viral cycles. Moreover, this set of genes heavily overlaps with those identified by former laboratory.},

keywords = {bioinformatics},

pubstate = {published},

tppubtype = {article}

}

@article{parra2021trust,

title = {A Trust-Based Methodology to Evaluate Deep Learning Models for Automatic Diagnosis of Ocular Toxoplasmosis from Fundus Images},

author = {R. Parra and V. Ojeda and J.L. Vázquez Noguera and M. García-Torres and J.C. Mello-Román and C. Villalba and J. Facon and F. Divina and O. Cardozo and V. Castillo},

doi = {10.3390/diagnostics11111951},

year  = {2021},

date = {2021-01-01},

journal = {Diagnostics},

volume = {11},

number = {11},

pages = {1951},

publisher = {Multidisciplinary Digital Publishing Institute pubstate = published},

keywords = {bioinformatics, deep learning, pattern recognition},

pubstate = {published},

tppubtype = {article}

}

@article{martinez2021genome,

title = {Genome-wide prediction of topoisomerase II $beta$ binding by architectural factors and chromatin accessibility},

author = {P.M. Martínez-García and M. García-Torres and F. Divina and J. Terrón-Bautista and I. Delgado-Sainz and F. Gómez-Vela and F. Cortés-Ledesma},

doi = {10.1371/journal.pcbi.1007814},

year  = {2021},

date = {2021-01-01},

journal = {PLoS computational biology},

volume = {17},

number = {1},

pages = {e1007814},

publisher = {Public Library of Science San Francisco, CA USA pubstate = published},

keywords = {bioinformatics},

pubstate = {published},

tppubtype = {article}

}

@article{lopez2021multi,

title = {A multi-GPU biclustering algorithm for binary datasets},

author = {A. Lopez-Fernandez and D. Rodriguez-Baena and F. Gomez-Vela and F. Divina and M. Garcia-Torres},

doi = {10.1016/j.jpdc.2020.09.009},

year  = {2021},

date = {2021-01-01},

journal = {Journal of Parallel and Distributed Computing},

volume = {147},

pages = {209--219},

publisher = {Elsevier pubstate = published},

keywords = {bioinformatics, pattern recognition},

pubstate = {published},

tppubtype = {article}

}

@article{benitez2021dataset,

title = {Dataset from fundus images for the study of diabetic retinopathy},

author = {V.E. Castillo Benítez and I. Castro Matto and J.C. Mello Román and J.L. Vázquez Noguera and M. García-Torres and J. Ayala and D.P. Pinto-Roa and P.E. Gardel-Sotomayor and J. Facon and S.A. Grillo},

url = {https://www.sciencedirect.com/science/article/pii/S2352340921003528},

doi = {10.1016/j.dib.2021.107068},

year  = {2021},

date = {2021-01-01},

journal = {Data in Brief},

volume = {36},

pages = {107068},

publisher = {Elsevier},

abstract = {This article presents a database containing 757 color fundus images acquired at the Department of Ophthalmology of the Hospital de Clínicas, Facultad de Ciencias Médicas (FCM), Universidad Nacional de Asunción (UNA), Paraguay. Firstly, the retinal images were acquired with a clinical procedure presented in this paper. The acquisition of the retinographies was made through the Visucam 500 camera of the Zeiss brand. Next, two expert ophthalmologists have classified the dataset. These data can help physicians and researchers in the detection of cases of Non-Proliferative Diabetic Retinopathy (NPDR) and Proliferative Diabetic Retinopathy (PDR), in their different stages. The dataset generated will be useful for ophthalmologists and researchers to work on automatic detection algorithms for Diabetic Retinopathy (DR).},

keywords = {bioinformatics},

pubstate = {published},

tppubtype = {article}

}

@article{shin2021mathematical,

title = {A Mathematical Model for COVID-19 with Variable Transmissibility and Hospitalizations: A Case Study in Paraguay},

author = {H. Ho Shin and C. Sauer Ayala and P. Pérez-Estigarribia and S.A. Grillo and L. Segovia-Cabrera and M. García-Torres and C. Gaona and S. Irala and M.E. Pedrozo and G. Sequera and J.L. Vázquez Noguera and E. De Los Santos},

url = {https://www.mdpi.com/2076-3417/11/20/9726},

doi = {10.3390/app11209726},

year  = {2021},

date = {2021-01-01},

journal = {Applied Sciences},

volume = {11},

number = {20},

pages = {9726},

publisher = {Multidisciplinary Digital Publishing Institute},

abstract = {Forecasting the dynamics of the number of cases with coronavirus disease 2019 (COVID-19) in a given population is a challenging task due to behavioural changes which occur over short periods. Planning of hospital resources and containment measures in the near term require a scenario analysis and the use of predictive models to gain insight into possible outcomes for each scenario. In this paper, we present the SEIR-H epidemiological model for the spread dynamics in a given population and the impact of COVID-19 in the local health system. It was developed as an extension of the classic SEIR model to account for required hospital resources and behavioural changes of the population in response to containment measures. Time-varying parameters such as transmissibility are estimated using Bayesian methods, based on the database of reported cases with a moving time-window strategy. The assessment of the model offers reasonable results with estimated parameters and simulations, reflecting the observed dynamics in Paraguay. The proposed model can be used to simulate future scenarios and possible effects of containment strategies, to guide the public institution response based on the available resources in the local health system.},

keywords = {bioinformatics},

pubstate = {published},

tppubtype = {article}

}

@article{Delgado-Chaves20,

title = {Computational Analysis of the Global Effects of Ly6E in the Immune Response to Coronavirus Infection Using Gene Networks},

author = {F. M. Delgado-Chaves and F. Gómez-Vela and F. Divina and M. García-Torres and D. S. Rodríguez-Baena},

year  = {2020},

date = {2020-01-01},

journal = {Genes},

volume = {11},

number = {7},

pages = {831-864},

abstract = {Gene networks have arisen as a promising tool in the comprehensive modeling and analysis of complex diseases. Particularly in viral infections, the understanding of the host-pathogen mechanisms, and the immune response to these, is considered a major goal for the rational design of appropriate therapies. For this reason, the use of gene networks may well encourage therapy-associated research in the context of the coronavirus pandemic, orchestrating experimental scrutiny and reducing costs. In this work, gene co-expression networks were reconstructed from RNA-Seq expression data with the aim of analyzing the time-resolved effects of gene Ly6E in the immune response against the coronavirus responsible for murine hepatitis (MHV). Through the integration of differential expression analyses and reconstructed networks exploration, significant differences in the immune response to virus were observed in Ly6E∆HSC compared to wild type animals. Results show that Ly6E ablation at hematopoietic stem cells (HSCs) leads to a progressive impaired immune response in both liver and spleen. Specifically, depletion of the normal leukocyte mediated immunity and chemokine signaling is observed in the liver of Ly6E∆HSC mice. On the other hand, the immune response in the spleen, which seemed to be mediated by an intense chromatin activity in the normal situation, is replaced by ECM remodeling in Ly6E∆HSC mice. These findings, which require further experimental characterization, could be extrapolated to other coronaviruses and motivate the efforts towards novel antiviral approaches.},

keywords = {bioinformatics},

pubstate = {published},

tppubtype = {article}

}

@article{Vanhaeren20,

title = {A Comparative Study of Supervised Machine Learning Algorithms for the Prediction of Long-Range Chromatin Interactions},

author = {T. Vanhaeren and 

 F. Divina and 

 M. García-Torres and 

 F. Gómez-Vela and 

 W. Vanhoof and 

 P. M. Martínez-García},

year  = {2020},

date = {2020-01-01},

journal = {Genes},

volume = {11},

number = {9},

pages = {985},

abstract = {The role of three-dimensional genome organization as a critical regulator of gene expression has become increasingly clear over the last decade. Most of our understanding of this association comes from the study of long range chromatin interaction maps provided by Chromatin Conformation Capture-based techniques, which have greatly improved in recent years. Since these procedures are experimentally laborious and expensive, in silico prediction has emerged as an alternative strategy to generate virtual maps in cell types and conditions for which experimental data of chromatin interactions is not available. Several methods have been based on predictive models trained on one-dimensional (1D) sequencing features, yielding promising results. However, different approaches vary both in the way they model chromatin interactions and in the machine learning-based strategy they rely on, making it challenging to carry out performance comparison of existing methods. In this study, we use publicly available 1D sequencing signals to model cohesin-mediated chromatin interactions in two human cell lines and evaluate the prediction performance of six popular machine learning algorithms: decision trees, random forests, gradient boosting, support vector machines, multi-layer perceptron and deep learning. Our approach accurately predicts long-range interactions and reveals that gradient boosting significantly outperforms the other five methods, yielding accuracies of about 95%. We show that chromatin features in close genomic proximity to the anchors cover most of the predictive information, as has been previously reported. Moreover, we demonstrate that gradient boosting models trained with different subsets of chromatin features, unlike the other methods tested, are able to produce accurate predictions. In this regard, and besides architectural proteins, transcription factors are shown to be highly informative. Our study provides a framework for the systematic prediction of long-range chromatin interactions, identifies gradient boosting as the best suited algorithm for this task and highlights cell-type specific binding of transcription factors at the anchors as important determinants of chromatin wiring mediated by cohesin},

keywords = {bioinformatics},

pubstate = {published},

tppubtype = {article}

}

@article{Genes2019,

title = {Computational Inference of Gene Co-Expression Networks for the identification of Lung Carcinoma Biomarkers: An Ensemble Approach},

author = {F. M Delgado-Chaves and F. Gómez-Vela and M. García-Torres and F. Divina and J.L. Vázquez Noguera},

url = {https://www.mdpi.com/2073-4425/10/12/962},

doi = {https://doi.org/10.3390/genes10120962},

year  = {2019},

date = {2019-01-01},

journal = {Genes},

volume = {10},

number = {12},

pages = {962},

abstract = {Gene Networks (GN), have emerged as an useful tool in recent years for the analysis of different diseases in the field of biomedicine. In particular, GNs have been widely applied for the study and analysis of different types of cancer. In this context, Lung carcinoma is among the most common cancer types and its short life expectancy is partly due to late diagnosis. For this reason, lung cancer biomarkers that can be easily measured are highly demanded in biomedical research. In this work, we present an application of gene co-expression networks in the modelling of lung cancer gene regulatory networks, which ultimately served to the discovery of new biomarkers. For this, a robust GN inference was performed from microarray data concomitantly using three different co-expression measures. Results identified a major cluster of genes involved in SRP-dependent co-translational protein target to membrane, as well as a set of 28 genes that were exclusively found in networks generated from cancer samples. Amongst potential biomarkers, genes NCKAP1L and DMD are highlighted due to their implications in a considerable portion of lung and bronchus primary carcinomas. These findings demonstrate the potential of GN reconstruction in the rational prediction of biomarkers.},

keywords = {bioinformatics},

pubstate = {published},

tppubtype = {article}

}

@article{Entropy2019,

title = {Ensemble and Greedy Approach for the Reconstruction of Large Gene Co-Expression Networks},

author = {F. Gómez-Vela and F. M Delgado-Chaves and D.S. Rodríguez-Baena and M. García-Torres and F. Divina},

url = {https://www.mdpi.com/1099-4300/21/12/1139},

doi = {https://doi.org/10.3390/e21121139},

year  = {2019},

date = {2019-01-01},

journal = {Entropy},

volume = {21},

number = {12},

pages = {1139},

abstract = {Gene networks have become a powerful tool in the comprehensive analysis of gene expression. Due to the increasing amount of available data, computational methods for networks generation must deal with the so-called curse of dimensionality in the quest for the reliability of the obtained results. In this context, ensemble strategies have significantly improved the precision of results by combining different measures or methods. On the other hand, structure optimization techniques are also important in the reduction of the size of the networks, not only improving their topology but also keeping a positive prediction ratio. In this work, we present Ensemble and Greedy networks (EnGNet), a novel two-step method for gene networks inference. First, EnGNet uses an ensemble strategy for co-expression networks generation. Second, a greedy algorithm optimizes both the size and the topological features of the network. Not only do achieved results show that this method is able to obtain reliable networks, but also that it significantly improves topological features. Moreover, the usefulness of the method is proven by an application to a human dataset on post-traumatic stress disorder, revealing an innate immunity-mediated response to this pathology. These results are indicative of the method’s potential in the field of biomarkers discovery and characterization.},

keywords = {bioinformatics},

pubstate = {published},

tppubtype = {article}

}

@article{MG2019,

title = {Pangenome of Acinetobacter baumannii uncovers two groups of genomes, one of them with genes involved in CRISPR/Cas defence systems associated with the absence of plasmids and exclusive genes for biofilm formation},

author = {E.L. Mangas and A. Rubio and R. Álvarez-Marín and G. Labrador-Herrera and J. Pachón and M. Eugenia Pachón-Ibáñez and F. Divina and A.J. Pérez-Pulido},

url = {https://www.microbiologyresearch.org/content/journal/mgen/10.1099/mgen.0.000309},

doi = {https://doi.org/10.1099/mgen.0.000309},

year  = {2019},

date = {2019-01-01},

journal = {Microbial Genomics},

pages = {mgen000309},

abstract = {Acinetobacter baumannii is an opportunistic bacterium that causes hospital-acquired infections with a high mortality and morbidity, since there are strains resistant to virtually any kind of antibiotic. The chase to find novel strategies to fight against this microbe can be favoured by knowledge of the complete catalogue of genes of the species, and their relationship with the specific characteristics of different isolates. In this work, we performed a genomics analysis of almost 2500 strains. Two different groups of genomes were found based on the number of shared genes. One of these groups rarely has plasmids, and bears clustered regularly interspaced short palindromic repeat (CRISPR) sequences, in addition to CRISPR-associated genes (cas genes) or restriction-modification system genes. This fact strongly supports the lack of plasmids. Furthermore, the scarce plasmids in this group also bear CRISPR sequences, and specifically contain genes involved in prokaryotic toxin–antitoxin systems that could either act as the still little known CRISPR type IV system or be the precursors of other novel CRISPR/Cas systems. In addition, a limited set of strains present a new cas9-like gene, which may complement the other cas genes in inhibiting the entrance of new plasmids into the bacteria. Finally, this group has exclusive genes involved in biofilm formation, which would connect CRISPR systems to the biogenesis of these bacterial resistance structures.},

keywords = {bioinformatics},

pubstate = {published},

tppubtype = {article}

}

@article{Gutierrez-Aviles2018,

title = {TRIQ: a new method to evaluate triclusters},

author = {D. Gutiérrez-Avilés and R. Giráldez and F. J. Gil-Cumbreras and C. Rubio-Escudero},

url = {https://biodatamining.biomedcentral.com/articles/10.1186/s13040-018-0177-5},

doi = {10.1186/s13040-018-0177-5},

year  = {2018},

date = {2018-01-01},

journal = {BioData Mining},

volume = {11},

number = {1},

pages = {15},

abstract = {Triclustering has shown to be a valuable tool for the analysis of microarray data since its appearance as an improvement of classical clustering and biclustering techniques. The standard for validation of triclustering is based on three different measures: correlation, graphic similarity of the patterns and functional annotations for the genes extracted from the Gene Ontology project (GO).},

keywords = {bioinformatics, time series},

pubstate = {published},

tppubtype = {article}

}

@article{BIODM2018,

title = {Pairwise gene GO-based measures for biclustering of high-dimensional expression data},

author = {J. A. Nepomuceno and A. Troncoso and J. S. Aguilar-Ruiz},

url = {https://www.ncbi.nlm.nih.gov/pubmed/29610579},

doi = {10.1186/s13040-018-0165-9},

year  = {2018},

date = {2018-01-01},

journal = {BioData Mining},

volume = {11},

number = {4},

abstract = {BACKGROUND: Biclustering algorithms search for groups of genes that share the same behavior under a subset of samples in gene expression data. Nowadays, the biological knowledge available in public repositories can be used to drive these algorithms to find biclusters composed of groups of genes functionally coherent. On the other hand, a distance among genes can be defined according to their information stored in Gene Ontology (GO). Gene pairwise GO semantic similarity measures report a value for each pair of genes which establishes their functional similarity. A scatter search-based algorithm that optimizes a merit function that integrates GO information is studied in this paper. This merit function uses a term that addresses the information through a GO measure. RESULTS: The effect of two possible different gene pairwise GO measures on the performance of the algorithm is analyzed. Firstly, three well known yeast datasets with approximately one thousand of genes are studied. Secondly, a group of human datasets related to clinical data of cancer is also explored by the algorithm. Most of these data are high-dimensional datasets composed of a huge number of genes. The resultant biclusters reveal groups of genes linked by a same functionality when the search procedure is driven by one of the proposed GO measures. Furthermore, a qualitative biological study of a group of biclusters show their relevance from a cancer disease perspective. CONCLUSIONS: It can be concluded that the integration of biological information improves the performance of the biclustering process. The two different GO measures studied show an improvement in the results obtained for the yeast dataset. However, if datasets are composed of a huge number of genes, only one of them really improves the algorithm performance. This second case constitutes a clear option to explore interesting datasets from a clinical point of view.},

keywords = {bioinformatics},

pubstate = {published},

tppubtype = {article}

}

@article{PO:EP-2018,

title = {The Blessing of Dimensionality: Feature Selection Outperforms Functional Connectivity-based Feature Transformation to Classify ADHD Subjects from EEG Patterns of Phase Synchronisation},

author = {E. Pereda and M. García-Torres and B. Melián and S. Ma~nas and L. Méndez and J. González},

url = {https://journals.plos.org/plosone/article?id=10.1371/journal.pone.0201660},

doi = {10.1371/journal.pone.0201660},

year  = {2018},

date = {2018-01-01},

journal = {PLoS ONE},

volume = {13},

number = {8},

keywords = {bioinformatics},

pubstate = {published},

tppubtype = {article}

}

@article{Gutierrez-Aviles2015,

title = {MSL: A Measure to Evaluate Three-dimensional Patterns in Gene Expression Data},

author = {D. Gutiérrez-Avilés and C. Rubio-Escudero},

url = {https://journals.sagepub.com/doi/10.4137/EBO.S25822},

doi = {10.4137/EBO.S25822},

year  = {2015},

date = {2015-01-01},

journal = {Evolutionary Bioinformatics},

volume = {11},

pages = {121—135},

abstract = {icroarray technology is highly used in biological research environments due to its ability to monitor the RNA concentration levels. The analysis of the data generated represents a computational challenge due to the characteristics of these data. Clustering techniques are widely applied to create groups of genes that exhibit a similar behavior. Biclustering relaxes the constraints for grouping, allowing genes to be evaluated only under a subset of the conditions. Triclustering appears for the analysis of longitudinal experiments in which the genes are evaluated under certain conditions at several time points. These triclusters provide hidden information in the form of behavior patterns from temporal experiments with microarrays relating subsets of genes, experimental conditions, and time points. We present an evaluation measure for triclusters called Multi Slope Measure, based on the similarity among the angles of the slopes formed by each profile formed by the genes, conditions, and times of the tricluster.},

keywords = {bioinformatics, time series},

pubstate = {published},

tppubtype = {article}

}

@article{ASC2015,

title = {Scatter Search-based identification of local patterns with positive and negative correlations in gene expression data},

author = {J. A. Nepomuceno and A. Troncoso and J. S. Aguilar-Ruiz},

url = {https://www.sciencedirect.com/science/article/pii/S1568494615003683},

doi = {10.1016/j.asoc.2015.06.019},

year  = {2015},

date = {2015-01-01},

journal = {Applied Soft Computing},

volume = {35},

pages = {637-651},

abstract = {This paper presents a scatter search approach based on linear correlations among genes to find biclusters, which include both shifting and scaling patterns and negatively correlated patterns contrarily to most of correlation-based algorithms published in the literature. The methodology established here for comparison is based on a priori biological information stored in the well-known repository Gene Ontology (GO). In particular, the three existing categories in GO, Biological Process, Cellular Components and Molecular Function, have been used. The performance of the proposed algorithm has been compared to other benchmark biclustering algorithms, specifically a group of classical biclustering algorithms and two algorithms that use correlation-based merit functions. The proposed algorithm outperforms the benchmark algorithms and finds patterns based on negative correlations. Although these patterns contain important relationship among genes, they are not found by most of biclustering algorithms. The experimental study also shows the importance of the size in a bicluster in addition to the value of its correlation. In particular, the size of a bicluster has an influence over its enrichment in a GO term.},

keywords = {bioinformatics},

pubstate = {published},

tppubtype = {article}

}

@article{Marquez-Chamorro2015,

title = {Soft computing methods for the prediction of protein tertiary structures: A survey},

author = {A. E. Marquez-Chamorro and G. Asencio-Cortes and C. E. Santiesteban-Toca and J. S. Aguilar-Ruiz},

doi = {10.1016/j.asoc.2015.06.024},

issn = {1568-4946},

year  = {2015},

date = {2015-01-01},

journal = {Applied Soft Computing},

number = {35},

pages = {398-410},

abstract = {The problem of protein structure prediction (PSP) represents one of the most important challenges in computational biology. Determining the three dimensional structure of proteins is necessary to understand their functions at molecular level. The most representative soft computing approaches for solving the protein tertiary structure prediction problem are summarized in this paper. These approaches have been categorized following the type of methodology. A total of 90 relevant works published in last 15 years in the field of protein structure prediction have been reported, including the best competitors in last CASP editions. However, despite large research effort in last decades, a considerable scope for further improvement still remains in this area.},

keywords = {bioinformatics},

pubstate = {published},

tppubtype = {article}

}

@article{CMPB2015,

title = {Integrating biological knowledge based on functional annotations for biclustering of gene expression data},

author = {J. A. Nepomuceno and A. Troncoso and J. S. Aguilar-Ruiz},

url = {https://www.sciencedirect.com/science/article/pii/S0169260715000450},

doi = {10.1016/j.cmpb.2015.02.010},

year  = {2015},

date = {2015-00-00},

journal = {Computers Methods and Programs in Biomedicine},

volume = {119},

number = {3},

pages = {163-180},

abstract = {Gene expression data analysis is based on the assumption that co-expressed genes imply co-regulated genes. This assumption is being reformulated because the co-expression of a group of genes may be the result of an independent activation with respect to the same experimental condition and not due to the same regulatory regime. For this reason, traditional techniques are recently being improved with the use of prior biological knowledge from open-access repositories together with gene expression data. Biclustering is an unsupervised machine learning technique that searches patterns in gene expression data matrices. A scatter search-based biclustering algorithm that integrates biological information is proposed in this paper. In addition to the gene expression data matrix, the input of the algorithm is only a direct annotation file that relates each gene to a set of terms from a biological repository where genes are annotated. Two different biological measures, FracGO and SimNTO, are proposed to integrate this information by means of its addition to-be-optimized fitness function in the scatter search scheme. The measure FracGO is based on the biological enrichment and SimNTO is based on the overlapping among GO annotations of pairs of genes. Experimental results evaluate the proposed algorithm for two datasets and show the algorithm performs better when biological knowledge is integrated. Moreover, the analysis and comparison between the two different biological measures is presented and it is concluded that the differences depend on both the data source and how the annotation file has been built in the case GO is used. It is also shown that the proposed algorithm obtains a greater number of enriched biclusters than other classical biclustering algorithms typically used as benchmark and an analysis of the overlapping among biclusters reveals that the biclusters obtained present a low overlapping. The proposed methodology is a general-purpose algorithm which allows the integration of biological information from several sources and can be extended to other biclustering algorithms based on the optimization of a merit function.},

keywords = {bioinformatics},

pubstate = {published},

tppubtype = {article}

}

@article{Gutierrez-Aviles2014,

title = {Mining 3D Patterns from Gene Expression Temporal Data: A New Tricluster Evaluation Measure},

author = {D. Gutiérrez-Avilés and C. Rubio-Escudero},

url = {http://www.hindawi.com/journals/tswj/2014/624371/},

doi = {10.1155/2014/624371},

year  = {2014},

date = {2014-01-01},

journal = {The Scientific World Journal},

volume = {2014},

pages = {1-16},

abstract = {Microarrays have revolutionized biotechnological research. The analysis of new data generated represents a computational challenge due to the characteristics of these data. Clustering techniques are applied to create groups of genes that exhibit a similar behavior. Biclustering emerges as a valuable tool for microarray data analysis since it relaxes the constraints for grouping, allowing genes to be evaluated only under a subset of the conditions. However, if a third dimension appears in the data, triclustering is the appropriate tool for the analysis. This occurs in longitudinal experiments in which the genes are evaluated under conditions at several time points. All clustering, biclustering, and triclustering techniques guide their search for solutions by a measure that evaluates the quality of clusters. We present an evaluation measure for triclusters called Mean Square Residue 3D. This measure is based on the classic biclustering measure Mean Square Residue. Mean Square Residue 3D has been applied to both synthetic and real data and it has proved to be capable of extracting groups of genes with homogeneous patterns in subsets of conditions and times, and these groups have shown a high correlation level and they are also related to their functional annotations extracted from the Gene Ontology project.},

keywords = {bioinformatics, time series},

pubstate = {published},

tppubtype = {article}

}

@article{Marquez-Chamorro2014,

title = {Evolutionary decision rules for predicting protein contact maps},

author = {A. E. Marquez-Chamorro and G. Asencio-Cortes and F. Divina and J. S. Aguilar-Ruiz},

doi = {10.1007/s10044-012-0297-3},

issn = {1433-7541},

year  = {2014},

date = {2014-01-01},

journal = {Pattern Analysis and Applications},

volume = {4},

number = {17},

pages = {725-737},

abstract = {Protein structure prediction is currently one of the main open challenges in Bioinformatics. The protein contact map is an useful, and commonly used, representation for protein 3D structure and represents binary proximities (contact or non-contact) between each pair of amino acids of a protein. In this work, we propose a multi-objective evolutionary approach for contact map prediction based on physico-chemical properties of amino acids. The evolutionary algorithm produces a set of decision rules that identifies contacts between amino acids. The rules obtained by the algorithm impose a set of conditions based on amino acid properties to predict contacts. We present results obtained by our approach on four different protein data sets. A statistical study was also performed to extract valid conclusions from the set of prediction rules generated by our algorithm. Results obtained confirm the validity of our proposal.},

keywords = {bioinformatics},

pubstate = {published},

tppubtype = {article}

}

@article{GUTIERREZAVILES201442,

title = {TriGen: A genetic algorithm to mine triclusters in temporal gene expression data},

author = {D. Gutiérrez-Avilés and C. Rubio-Escudero and F. Martínez-Álvarez and J.C. Riquelme},

url = {http://www.sciencedirect.com/science/article/pii/S0925231213011004},

doi = {10.1016/j.neucom.2013.03.061},

year  = {2014},

date = {2014-01-01},

journal = {Neurocomputing},

volume = {132},

pages = {42-53},

abstract = {Analyzing microarray data represents a computational challenge due to the characteristics of these data. Clustering techniques are widely applied to create groups of genes that exhibit a similar behavior under the conditions tested. Biclustering emerges as an improvement of classical clustering since it relaxes the constraints for grouping genes to be evaluated only under a subset of the conditions and not under all of them. However, this technique is not appropriate for the analysis of longitudinal experiments in which the genes are evaluated under certain conditions at several time points. We present the TriGen algorithm, a genetic algorithm that finds triclusters of gene expression that take into account the experimental conditions and the time points simultaneously. We have used TriGen to mine datasets related to synthetic data, yeast (Saccharomyces cerevisiae) cell cycle and human inflammation and host response to injury experiments. TriGen has proved to be capable of extracting groups of genes with similar patterns in subsets of conditions and times, and these groups have shown to be related in terms of their functional annotations extracted from the Gene Ontology.},

keywords = {bioinformatics},

pubstate = {published},

tppubtype = {article}

}

@article{IS:GT-2013,

title = {Comparison of metaheuristic strategies for peakbin selection in proteomic mass spectrometry data},

author = {M. García-Torres and R. Arma{~n}anzas and C. Bielza and P. Larra~naga},

url = {https://www.sciencedirect.com/science/article/pii/S0020025510006195},

doi = {10.1016/j.ins.2010.12.013},

year  = {2013},

date = {2013-01-01},

journal = {Information Sciences},

volume = {222},

pages = {229-246},

keywords = {bioinformatics, feature selection},

pubstate = {published},

tppubtype = {article}

}

@article{BIODM2011,

title = {Biclustering of Gene Expression Data by Correlation-Based Scatter Search},

author = {J. A. Nepomuceno and A. Troncoso and J. S. Aguilar-Ruiz},

url = {https://link.springer.com/article/10.1186/1756-0381-4-3},

doi = {10.1186/1756-0381-4-3},

year  = {2011},

date = {2011-01-01},

journal = {BioData Mining},

volume = {4},

number = {3},

abstract = {Background: The analysis of data generated by microarray technology is very useful to understand how the genetic information becomes functional gene products. Biclustering algorithms can determine a group of genes which are co-expressed under a set of experimental conditions. Recently, new biclustering methods based on metaheuristics have been proposed. Most of them use the Mean Squared Residue as merit function but interesting and relevant patterns from a biological point of view such as shifting and scaling patterns may not be detected using this measure. However, it is important to discover this type of patterns since commonly the genes can present a similar behavior although their expression levels vary in different ranges or magnitudes. Methods: Scatter Search is an evolutionary technique that is based on the evolution of a small set of solutions which are chosen according to quality and diversity criteria. This paper presents a Scatter Search with the aim of finding biclusters from gene expression data. In this algorithm the proposed fitness function is based on the linear correlation among genes to detect shifting and scaling patterns from genes and an improvement method is included in order to select just positively correlated genes. Results: The proposed algorithm has been tested with three real data sets such as Yeast Cell Cycle dataset, human B-cells lymphoma dataset and Yeast Stress dataset, finding a remarkable number of biclusters with shifting and scaling patterns. In addition, the performance of the proposed method and fitness function are compared to that of CC, OPSM, ISA, BiMax, xMotifs and Samba using Gene the Ontology Database.},

keywords = {bioinformatics},

pubstate = {published},

tppubtype = {article}

}