Publications

@article{Lopez-Fernandez2024b,

title = {Optimized Python library for reconstruction of ensemble?based gene co?expression networks using multi?GPU},

author = {A. Lopez-Fernandez and F. Gómez-Vela and Dulcenombre M. Saz-Navarro and F. M. Delgado and D. Rodríguez-Baena},

url = {https://link.springer.com/article/10.1007/s11227-024-06127-4},

doi = {10.1007/s11227-024-06127-4},

issn = {1573-0484},

year  = {2024},

date = {2024-05-11},

journal = {The Journal of Supercomputing},

abstract = {Gene co-expression networks are valuable tools for discovering biologically relevant information within gene expression data. However, analysing large datasets presents challenges due to the identification of nonlinear gene–gene associations and the need to process an ever-growing number of gene pairs and their potential network connections. These challenges mean that some experiments are discarded because the techniques do not support these intense workloads. This paper presents pyEnGNet, a Python library that can generate gene co-expression networks in High-performance computing environments. To do this, pyEnGNet harnesses CPU and multi-GPU parallel computing resources, efficiently handling large datasets. These implementations have optimised memory management and processing, delivering timely results. We have used synthetic datasets to prove the runtime and intensive workload improvements. In addition, pyEnGNet was used in a real-life study of patients after allogeneic stem cell transplantation with invasive aspergillosis and was able to detect biological perspectives in the study.},

keywords = {Big Data, Bioinformatics, Data Mining, Gene co-expression network, GPU, High-Performance Computing},

pubstate = {published},

tppubtype = {article}

}

@article{Figueroa-Martinez2024,

title = {Computational Ensemble Gene Co-Expression Networks for the Analysis of Cancer Biomarkers},

author = {J. Figueroa-Martinez and Dulcenombre M. Saz-Navarro and A. Lopez-Fernandez and D. Rodríguez-Baena and F. Gómez-Vela},

url = {https://www.mdpi.com/2227-9709/11/2/14},

doi = {10.3390/informatics11020014},

issn = {2227-9709},

year  = {2024},

date = {2024-03-26},

journal = {Informatics},

volume = {11},

number = {2},

pages = {14},

abstract = {Gene networks have become a powerful tool for the comprehensive examination of gene expression patterns. Thanks to these networks generated by means of inference algorithms, it is possible to study different biological processes and even identify new biomarkers for such diseases. These biomarkers are essential for the discovery of new treatments for genetic diseases such as cancer. In this work, we introduce an algorithm for genetic network inference based on an ensemble method that improves the robustness of the results by combining two main steps: first, the evaluation of the relationship between pairs of genes using three different co-expression measures, and, subsequently, a voting strategy. The utility of this approach was demonstrated by applying it to a human dataset encompassing breast and prostate cancer-associated stromal cells. Two gene networks were computed using microarray data, one for breast cancer and one for prostate cancer. The results obtained revealed, on the one hand, distinct stromal cell behaviors in breast and prostate cancer and, on the other hand, a list of potential biomarkers for both diseases. In the case of breast tumor, ST6GAL2, RIPOR3, COL5A1, and DEPDC7 were found, and in the case of prostate tumor, the genes were GATA6-AS1, ARFGEF3, PRR15L, and APBA2. These results demonstrate the usefulness of the ensemble method in the field of biomarker discovery.},

keywords = {Bioinformatics, Biomarkers, Breast cancer, Gene co-expression network, Prostate cancer, Stromal tissue},

pubstate = {published},

tppubtype = {article}

}

@article{Lopez-Fernandez2024,

title = {bioScience: A new python science library for high-performance computing bioinformatics analytics},

author = {A. Lopez-Fernandez and F. Gómez-Vela and J. González-Domínguez and P. Bidare-Divakarachari},

url = {https://www.sciencedirect.com/science/article/pii/S2352711024000372},

doi = {10.1016/j.softx.2024.101666},

issn = {2352-7110},

year  = {2024},

date = {2024-02-19},

journal = {SoftwareX},

volume = {26},

pages = {101666},

abstract = {BioScience is an advanced Python library designed to satisfy the growing data analysis needs in the field of bioinformatics by leveraging High-Performance Computing (HPC). This library encompasses a vast multitude of functionalities, from loading specialized gene expression datasets (microarrays, RNA-Seq, etc.) to preprocessing techniques and data mining algorithms suitable for this type of datasets. BioScience is distinguished by its capacity to manage large amounts of biological data, providing users with efficient and scalable tools for the analysis of genomic and transcriptomic data through the use of parallel architectures for clusters composed of CPUs and GPUs.},

keywords = {Bioinformatics, Data analysis, Data Mining, Data science, High-Performance Computing},

pubstate = {published},

tppubtype = {article}

}

@article{Saz-Navarro2024,

title = {CyEnGNet—App: A new Cytoscape app for the reconstruction of large co-expression networks using an ensemble approach},

author = {Dulcenombre M. Saz-Navarro and A. Lopez-Fernandez and F. Gómez-Vela and D. Rodríguez-Baena},

url = {https://www.sciencedirect.com/science/article/pii/S2352711024000050},

doi = {10.1016/j.softx.2024.101634},

issn = {2352-7110},

year  = {2024},

date = {2024-01-18},

urldate = {2024-01-18},

journal = {SoftwareX},

volume = {25},

pages = {101634},

abstract = {The construction of gene co-expression networks is an essential tool in Bioinformatics for discovering useful biological knowledge. There are a multitude of methodologies related to the construction of this type of network, and one of them is EnGNet, which carries out a joint and greedy approach to the reconstruction of large gene coexpression networks. This work introduces CyEnGNet-App, a Cytoscape application designed to integrate and leverage the EnGNet algorithm. The application allows dynamic interaction and visualisation of gene networks and integration with other Cytoscape applications. CyEnGNet-App is a valuable addition to the field of Bioinformatics, improving the reconstruction of genetic networks and providing a more accessible and efficient user experience in Cytoscape.},

keywords = {Bioinformatics, Cytoscape, Gene networks, Network analysis, Visualisation},

pubstate = {published},

tppubtype = {article}

}

@article{Lopez-Fernandez2020,

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

author = {A. Lopez-Fernandez and D. Rodríguez-Baena and F. Gómez-Vela and F. Divina and M. García-Torres},

url = {https://www.sciencedirect.com/science/article/pii/S0743731520303701},

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

issn = {0743-7315},

year  = {2021},

date = {2021-01-01},

journal = {Journal of Parallel and Distributed Computing},

volume = {147},

pages = {209-219},

abstract = {Graphics Processing Units technology (GPU) and CUDA architecture are one of the most used options to adapt machine learning techniques to the huge amounts of complex data that are currently generated. Biclustering techniques are useful for discovering local patterns in datasets. Those of them that have been implemented to use GPU resources in parallel have improved their computational performance. However, this fact does not guarantee that they can successfully process large datasets. There are some important issues that must be taken into account, like the data transfers between CPU and GPU memory or the balanced distribution of workload between the GPU resources. In this paper, a GPU version of one of the fastest biclustering solutions, BiBit, is presented. This implementation, named gBiBit, has been designed to take full advantage of the computational resources offered by GPU devices. Either using a single GPU device or in its multi-GPU mode, gBiBit is able to process large binary datasets. The experimental results have shown that gBiBit improves the computational performance of BiBit, a CPU parallel version and an early GPU version, called ParBiBit and CUBiBit, respectively. gBiBit source code is available at https://github.com/aureliolfdez/gbibit.},

keywords = {Biclustering, Big Data, CUDA, GPU},

pubstate = {published},

tppubtype = {article}

}

@article{Lopez-Fernandez2020b,

title = {gMSR: A Multi-GPU Algorithm to Accelerate a Massive Validation of Biclusters},

author = {A. Lopez-Fernandez and D. Rodríguez-Baena and F. Gómez-Vela},

url = {https://www.mdpi.com/2079-9292/9/11/1782},

doi = {10.3390/electronics9111782},

issn = {2079-9292},

year  = {2020},

date = {2020-10-27},

journal = {Electronics},

volume = {9},

number = {11},

pages = {1782},

abstract = {Nowadays, Biclustering is one of the most widely used machine learning techniques to discover local patterns in datasets from different areas such as energy consumption, marketing, social networks or bioinformatics, among them. Particularly in bioinformatics, Biclustering techniques have become extremely time-consuming, also being huge the number of results generated, due to the continuous increase in the size of the databases over the last few years. For this reason, validation techniques must be adapted to this new environment in order to help researchers focus their efforts on a specific subset of results in an efficient, fast and reliable way. The aforementioned situation may well be considered as Big Data context. In this sense, multiple machine learning techniques have been implemented by the application of Graphic Processing Units (GPU) technology and CUDA architecture to accelerate the processing of large databases. However, as far as we know, this technology has not yet been applied to any bicluster validation technique. In this work, a multi-GPU version of one of the most used bicluster validation measure, Mean Squared Residue (MSR), is presented. It takes advantage of all the hardware and memory resources offered by GPU devices. Because of to this, gMSR is able to validate a massive number of biclusters in any Biclustering-based study within a Big Data context.},

keywords = {Biclustering, Biclustering validation, CUDA, GPU, MSR},

pubstate = {published},

tppubtype = {article}

}

@article{Delgado2020,

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

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

url = {https://www.mdpi.com/2073-4425/11/7/831},

doi = {10.3390/genes11070831},

issn = {2073-4425},

year  = {2020},

date = {2020-07-21},

journal = {Genes},

volume = {11},

number = {7},

pages = {831},

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 = {Data Mining, Gene Network, murine coronavirus, Systems biology, Viral infection},

pubstate = {published},

tppubtype = {article}

}

@article{Aram2020,

title = {The integration of heterogeneous information from diverse disciplines regarding persons and goods},

author = {B. Aram and A. Lopez-Fernandez and D. Muñiz-Amian},

doi = {10.1093/llc/fqaa021},

year  = {2020},

date = {2020-06-24},

journal = {Digital Scholarship in the Humanities},

abstract = {This article presents a relational database capable of integrating data from a variety of types of written sources as well as material remains. In response to historical research questions, information from such diverse sources as documentary, bioanthropological, isotopic, and DNA analyses has been assessed, homogenized, and situated in time and space. Multidisciplinary ontologies offer complementary and integrated perspectives regarding persons and goods. While responding to specific research questions about the impact of globalization on the isthmus of Panama during the sixteenth and seventeenth centuries, the data model and user interface promote the ongoing interrogation of diverse information about complex, changing societies. To this end, the application designed makes it possible to search, consult, and download data that researchers have contributed from anywhere in the world.},

keywords = {Databases, Digital Humanities},

pubstate = {published},

tppubtype = {article}

}

@article{Rodríguez-Baena2020,

title = {Identifying livestock behavior patterns based on accelerometer dataset},

author = {D. Rodríguez-Baena and F. Gómez-Vela and M. García-Torres and F. Divina and C. D. Barranco and N. Díaz-Díaz and M. Jiménez and G. Montalvo},

url = {http://www.sciencedirect.com/science/article/pii/S1877750318311359},

doi = {10.1016/j.jocs.2020.101076},

issn = {1877-7503},

year  = {2020},

date = {2020-03-01},

journal = {Journal of Computational Science},

volume = {41},

pages = {101076},

abstract = {In large livestock farming it would be beneficial to be able to automatically detect behaviors in animals. In fact, this would allow to estimate the health status of individuals, providing valuable insight to stock raisers. Traditionally this process has been carried out manually, relying only on the experience of the breeders. Such an approach is effective for a small number of individuals. However, in large breeding farms this may not represent the best approach, since, in this way, not all the animals can be effectively monitored all the time. Moreover, the traditional approach heavily rely on human experience, which cannot be always taken for granted. To this aim, in this paper, we propose a new method for automatically detecting activity and inactivity time periods of animals, as a behavior indicator of livestock. In order to do this, we collected data with sensors located in the body of the animals to be analyzed. In particular, the reliability of the method was tested with data collected on Iberian pigs and calves. Results confirm that the proposed method can help breeders in detecting activity and inactivity periods for large livestock farming.},

keywords = {Livestock activity, Pattern recognition, Time series processing},

pubstate = {published},

tppubtype = {article}

}

@article{Gómez-Vela2019,

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

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

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

doi = {10.3390/e21121139},

year  = {2019},

date = {2019-11-01},

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 = {Ensemble networks, Gene Network},

pubstate = {published},

tppubtype = {article}

}

@article{Díaz-Montaña2019,

title = {Development and use of a Cytoscape app for GRNCOP2},

author = {J. J. Díaz-Montaña and N. Díaz-Díaz and C. D. Barranco and I. Ponzoni},

url = {http://www.sciencedirect.com/science/article/pii/S0169260718313592},

doi = {10.1016/j.cmpb.2019.05.030},

issn = {0169-2607},

year  = {2019},

date = {2019-08-01},

journal = {Computer Methods and Programs in Biomedicine},

volume = {177},

pages = {211-218},

abstract = {Background and Objective: Gene regulatory networks (GRNs) are essential for understanding most molecular processes. In this context, the so-called model-free approaches have an advantage modeling the complex topologies behind these dynamic molecular networks, since most GRNs are difficult to map correctly by any other mathematical model. Abstract model-free approaches, also known as rule-based extraction methods, offer valuable benefits when performing data-driven analysis; such as requiring the least amount of data and simplifying the inference of large models at a faster analysis speed. In particular, GRNCOP2 is a combinatorial optimization method with an adaptive criterion for the discretization of gene expression data and high performance, in contrast to other rule-based extraction methods for discovering GRNs. However, the analysis of the large relational structures of the networks inferred by GRNCOP2 requires the support of effective tools for interactive network visualization and topological analysis of the extracted associations. This need motivated the possibility of integrating GRNCOP2 in the Cytoscape ecosystem in order to benefit from Cytoscapes core functionality, as well as all the other apps in its ecosystem.



Methods: In this paper, we introduce the implementation of a GRNCOP2 Cytoscape app. This incorporation to Cytoscape platform includes new functionality for GRN visualizations, dynamic user-interaction and integration with other apps for topological analysis of the networks.



Results: In order to demonstrate the usefulness of integrating GRNCOP2 in Cytoscape, the new app was used to tackle a novel use case for GRNCOP2: the analysis of crosstalk between pathways. In this regard, datasets associated with Alzheimer’s disease (AD) were analyzed using GRNCOP2 app and other apps of the Cytoscape ecosystem by performing a topological analysis of the AD progression and its synchronization with the Ubiquitin Mediated Proteolysis pathway. Finally, the biological relevance of the findings achieved by this new app were evaluated by searching for evidence in the literature.



Conclusions: The proposed crosstalk analysis with the new GRNCOP2 app focused on assessing the phase of the Alzheimer’s disease progression where the coordination with the Ubiquitin Mediated Proteolysis pathway increase, and identifying the genes that explain the signalling between these cellular processes. Both questions were explored by topological contrastive analysis of the GRNs generated for the GRNCOP2 app, where several facilities of Cytoscape were exploited. The topological patterns inferred by this new App have been consistent with biological evidence reported in the scientic literature, illustrating the effectiveness of using this new GRNCOP2 App in pathway analysis.



Availability: The GRNCOP2 App is freely available at the official Cytoscape app store: http://apps.cytoscape.org/apps/grncop2},

keywords = {Cytoscape},

pubstate = {published},

tppubtype = {article}

}

@article{Delgado2019,

title = {Computational methods for Gene Regulatory Networks reconstruction and analysis: A review},

author = {F. M. Delgado and F. Gómez-Vela},

url = {http://www.sciencedirect.com/science/article/pii/S0933365718303865},

doi = {10.1016/j.artmed.2018.10.006},

issn = {0933-3657},

year  = {2019},

date = {2019-04-01},

journal = {Artificial Intelligence in Medicine},

volume = {95},

pages = {133-145},

abstract = {In the recent years, the vast amount of genetic information generated by new-generation approaches, have led to the need of new data handling methods. The integrative analysis of diverse-nature gene information could provide a much-sought overview to study complex biological systems and processes. In this sense, Gene Regulatory Networks (GRN) arise as an increasingly-promising tool for the modelling and analysis of biological processes. This review is an attempt to summarize the state of the art in the field of GRNs. Essential points in the field are addressed, thereof: (a) the type of data used for network generation, (b) machine learning methods and tools used for network generation, (c) model optimization and (d) computational approaches used for network validation. This survey is intended to provide an overview of the subject for readers to improve their knowledge in the field of GRN for future research.},

keywords = {Gene Network, Systems biology},

pubstate = {published},

tppubtype = {article}

}

@article{Medina2017,

title = {Indexing techniques to improve the performance of necessity-based fuzzy queries using classical indexing of RDBMS},

author = {J. M. Medina and C. D. Barranco and O. Pons},

url = {http://www.sciencedirect.com/science/article/pii/S0165011417303482},

doi = {10.1016/j.fss.2017.09.008},

issn = {0165-0114},

year  = {2018},

date = {2018-11-01},

journal = {Fuzzy Sets and Systems},

volume = {351},

pages = {90-107},

abstract = {It is widely known that the most effective way to implement a fuzzy database is to use a classical Relational Database Management System (RDBMS) as the basis. All these systems provide several kinds of indexing methods to improve the execution time of classical queries, but they are useless when directly applied to fuzzy queries. For this reason, in this work we propose and evaluate several fuzzy indexing techniques implemented over the indexing techniques available on classical RDBMS in order to enhance flexible queries when based on the necessity measure. As the results show, the best evaluated fuzzy indexing techniques can be implemented on top of classical RDBMS.},

keywords = {Fuzzy databases},

pubstate = {published},

tppubtype = {article}

}

@article{Gómez-Vela2018,

title = {Structure Optimization for Large Gene Networks Based on Greedy Strategy},

author = {F. Gómez-Vela and D. Rodríguez-Baena and J. L. Vázquez-Noguera},

url = {https://www.hindawi.com/journals/cmmm/2018/9674108/},

doi = {10.1155/2018/9674108},

year  = {2018},

date = {2018-06-01},

journal = {Computational and Mathematical Methods in Medicine},

volume = {2018},

abstract = {In the last few years, gene networks have become one of most important tools to model biological processes. Among other utilities, these networks visually show biological relationships between genes. However, due to the large amount of the currently generated genetic data, their size has grown to the point of being unmanageable. To solve this problem, it is possible to use computational approaches, such as heuristics-based methods, to analyze and optimize gene network’s structure by pruning irrelevant relationships. In this paper we present a new method, called GeSOp, to optimize large gene network structures. The method is able to perform a considerably prune of the irrelevant relationships comprising the input network. To do so, the method is based on a greedy heuristic to obtain the most relevant subnetwork. The performance of our method was tested by means of two experiments on gene networks obtained from different organisms. The first experiment shows how GeSOp is able not only to carry out a significant reduction in the size of the network, but also to maintain the biological information ratio. In the second experiment, the ability to improve the biological indicators of the network is checked. Hence, the results presented show that GeSOp is a reliable method to optimize and improve the structure of large gene networks.},

keywords = {Gene Network, Soft Computing},

pubstate = {published},

tppubtype = {article}

}

@article{Lopez-Fernandez2018,

title = {BIGO: A web application to analyse gene enrichment analysis results},

author = {A. Lopez-Fernandez and D. Rodríguez-Baena and F. Gómez-Vela and N. Díaz-Díaz},

url = {http://www.sciencedirect.com/science/article/pii/S147692711730823X},

doi = {10.1016/j.compbiolchem.2018.06.006},

issn = {1476-9271},

year  = {2018},

date = {2018-05-01},

journal = {Computational biology and chemistry},

volume = {76},

pages = {169-178},

abstract = {Background and objective

Gene enrichment tools enable the analysis of the relationships between genes with biological annotations stored in biological databases. The results obtained by these tools are usually difficult to analyse. Therefore, researchers require new tools with friendly user interfaces available on all types of devices and new methods to make the analysis of the results easier.



Methods

In this work, we present the BIGO Web tool. BIGO is a friendly Web tool to perform enrichment analyses of a collection of gene sets. On the basis of the obtained enrichment analysis results, BIGO combines the biological terms to organize them and graphically represents the relationships between gene sets to make the interpretations of the results easier.



Results

BIGO offers useful services that provide the opportunity to focus on a concrete subset of results by discarding too general biological terms or to obtain useful knowledge by means of the visual analysis of the functional connections between the sets of genes being analysed.



Conclusions

BIGO is a web tool with a novel and modern design that provides the possibility to improve the analysis tasks applied to gene enrichment results.},

keywords = {Bioinformatics, Biological validation, Gene enrichment analysis},

pubstate = {published},

tppubtype = {article}

}

@article{Díaz-Montaña2018,

title = {GNC–app: A new Cytoscape app to rate gene networks biological coherence using gene–gene indirect relationships},

author = {J. J. Díaz-Montaña and F. Gómez-Vela and N. Díaz-Díaz},

url = {http://www.sciencedirect.com/science/article/pii/S0303264717303258},

doi = {10.1016/j.biosystems.2018.01.007},

issn = {0303-2647},

year  = {2018},

date = {2018-04-01},

journal = {Biosystems},

volume = {166},

pages = {61-65},

abstract = {Motivation

Gene networks are currently considered a powerful tool to model biological processes in the Bioinformatics field. A number of approaches to infer gene networks and various software tools to handle them in a visual simplified way have been developed recently. However, there is still a need to assess the inferred networks in order to prove their relevance.



Results

In this paper, we present the new GNC-app for Cytoscape. GNC-app implements the GNC methodology for assessing the biological coherence of gene association networks and integrates it into Cytoscape. Implemented de novo, GNC-app significantly improves the performance of the original algorithm in order to be able to analyse large gene networks more efficiently. It has also been integrated in Cytoscape to increase the tool accessibility for non-technical users and facilitate the visual analysis of the results. This integration allows the user to analyse not only the global biological coherence of the network, but also the biological coherence at the gene–gene relationship level. It also allows the user to leverage Cytoscape capabilities as well as its rich ecosystem of apps to perform further analyses and visualizations of the network using such data.



Availability

The GNC-app is freely available at the official Cytoscape app store: http://apps.cytoscape.org/apps/gnc.},

keywords = {Cytoscape, Gene Network},

pubstate = {published},

tppubtype = {article}

}

@article{Díaz-Montaña2017,

title = {GFD-Net: A novel semantic similarity methodology for the analysis of gene networks},

author = {J. J. Díaz-Montaña and N. Díaz-Díaz and F. Gómez-Vela},

url = {http://www.sciencedirect.com/science/article/pii/S1532046417300382},

doi = {10.1016/j.jbi.2017.02.013},

issn = {1532-0464},

year  = {2017},

date = {2017-04-01},

journal = {Journal of Biomedical Informatics},

volume = {68},

pages = {71-82},

abstract = {Since the popularization of biological network inference methods, it has become crucial to create methods to validate the resulting models. Here we present GFD-Net, the first methodology that applies the concept of semantic similarity to gene network analysis. GFD-Net combines the concept of semantic similarity with the use of gene network topology to analyze the functional dissimilarity of gene networks based on Gene Ontology (GO). The main innovation of GFD-Net lies in the way that semantic similarity is used to analyze gene networks taking into account the network topology. GFD-Net selects a functionality for each gene (specified by a GO term), weights each edge according to the dissimilarity between the nodes at its ends and calculates a quantitative measure of the network functional dissimilarity, i.e. a quantitative value of the degree of dissimilarity between the connected genes. The robustness of GFD-Net as a gene network validation tool was demonstrated by performing a ROC analysis on several network repositories. Furthermore, a well-known network was analyzed showing that GFD-Net can also be used to infer knowledge. The relevance of GFD-Net becomes more evident in Section “GFD-Net applied to the study of human diseases” where an example of how GFD-Net can be applied to the study of human diseases is presented. GFD-Net is available as an open-source Cytoscape app which offers a user-friendly interface to configure and execute the algorithm as well as the ability to visualize and interact with the results(http://apps.cytoscape.org/apps/gfdnet).},

keywords = {Gene Network},

pubstate = {published},

tppubtype = {article}

}

@article{Medina2016,

title = {Evaluation of Indexing Strategies for Possibilistic Queries Based on Indexing Techniques Available in Traditional RDBMS},

author = {J. M. Medina and C. D. Barranco and O. Pons},

url = {https://onlinelibrary.wiley.com/doi/abs/10.1002/int.21820

https://onlinelibrary.wiley.com/doi/pdf/10.1002/int.21820},

doi = {10.1002/int.21820},

year  = {2016},

date = {2016-10-18},

journal = {International Journal of Intelligent Systems},

volume = {31},

number = {12},

pages = {1135-1165},

abstract = {A common way to implement a fuzzy database is on top of a classical relational database management systems (RDBMS). Given that almost all RDBMS provide indexing mechanisms to enhance classical query processing performance, finding ways to use these mechanisms to enhance the performance of flexible query processing is of enormous interest. This work proposes and evaluates a set of indexing strategies, implemented exclusively on top of classical RDBMS indexing structures, designed to improve flexible query processing performance, focusing in the case of possibilities queries. Results show the best indexing strategies for different data a query scenarios, offering effective ways to implement fuzzy data indexes on top of a classical RDBMS.},

keywords = {Fuzzy databases},

pubstate = {published},

tppubtype = {article}

}

@article{Gómez-Vela2016,

title = {Incorporating biological knowledge for construction of fuzzy networks of gene associations},

author = {F. Gómez-Vela and C. D. Barranco and N. Díaz-Díaz },

url = {http://www.sciencedirect.com/science/article/pii/S1568494616300011},

doi = {10.1016/j.asoc.2016.01.014},

issn = {1568-4946},

year  = {2016},

date = {2016-05-01},

journal = {Applied Soft Computing},

volume = {42},

pages = {144-155},

abstract = {Gene association networks have become one of the most important approaches to modelling of biological processes by means of gene expression data. According to the literature, co-expression-based methods are the main approaches to identification of gene association networks because such methods can identify gene expression patterns in a dataset and can determine relations among genes. These methods usually have two fundamental drawbacks. Firstly, they are dependent on quality of the input dataset for construction of reliable models because of the sensitivity to data noise. Secondly, these methods require that the user select a threshold to determine whether a relation is biologically relevant. Due to these shortcomings, such methods may ignore some relevant information. We present a novel fuzzy approach named FyNE (Fuzzy NEtworks) for modelling of gene association networks. FyNE has two fundamental features. Firstly, it can deal with data noise using a fuzzy-set-based protocol. Secondly, the proposed approach can incorporate prior biological knowledge into the modelling phase, through a fuzzy aggregation function. These features help to gain some insights into doubtful gene relations. The performance of FyNE was tested in four different experiments. Firstly, the improvement offered by FyNE over the results of a co-expression-based method in terms of identification of gene networks was demonstrated on different datasets from different organisms. Secondly, the results produced by FyNE showed its low sensitivity to noise data in a randomness experiment. Additionally, FyNE could infer gene networks with a biological structure in a topological analysis. Finally, the validity of our proposed method was confirmed by comparing its performance with that of some representative methods for identification of gene networks},

keywords = {Gene Network},

pubstate = {published},

tppubtype = {article}

}

@article{Díaz-Montaña2016,

title = {Web-based Gene Pathogenicity Analysis (WGPA): a web platform to interpret gene pathogenicity from personal genome data},

author = {J. J. Díaz-Montaña and O. J. L. Rackham and N. Díaz-Díaz and E. Petretto},

url = {https://doi.org/10.1093/bioinformatics/btv598},

doi = {10.1093/bioinformatics/btv598},

isbn = {1367-4803},

year  = {2016},

date = {2016-02-14},

journal = {Bioinformatics},

volume = {32},

number = {4},

pages = {635-637},

abstract = {As the volume of patient-specific genome sequences increases the focus of biomedical research is switching from the detection of disease-mutations to their interpretation. To this end a number of techniques have been developed that use mutation data collected within a population to predict whether individual genes are likely to be disease-causing or not. As both sequence data and associated analysis tools proliferate, it becomes increasingly difficult for the community to make sense of these data and their implications. Moreover, no single analysis tool is likely to capture all relevant genomic features that contribute to the gene’s pathogenicity. Here, we introduce Web-based Gene Pathogenicity Analysis (WGPA), a web-based tool to analyze genes impacted by mutations and rank them through the integration of existing prioritization tools, which assess different aspects of gene pathogenicity using population-level sequence data. Additionally, to explore the polygenic contribution of mutations to disease, WGPA implements gene set enrichment analysis to prioritize disease-causing genes and gene interaction networks, therefore providing a comprehensive annotation of personal genomes data in disease.},

keywords = {Gene analysis},

pubstate = {published},

tppubtype = {article}

}

@article{García-Torres2016,

title = {High-dimensional feature selection via feature grouping: A Variable Neighborhood Search approach},

author = {M. García-Torres and F. Gómez-Vela and B. Melián-Batista and J. M. Moreno-Vega},

url = {http://www.sciencedirect.com/science/article/pii/S0020025515005460},

doi = {10.1016/j.ins.2015.07.041},

issn = {0020-0255},

year  = {2016},

date = {2016-01-01},

journal = {Information Sciences},

volume = {326},

pages = {102-118},

abstract = {In recent years, advances in technology have led to increasingly high-dimensional datasets. This increase of dimensionality along with the presence of irrelevant and redundant features make the feature selection process challenging with respect to efficiency and effectiveness. In this context, approximate algorithms are typically applied since they provide good solutions in a reasonable time. On the other hand, feature grouping has arisen as a powerful approach to reduce dimensionality in high-dimensional data. Recently, some authors have focused their attention on developing methods that combine feature grouping and feature selection to improve the model. In this paper, we propose a feature selection strategy that utilizes feature grouping to increase the effectiveness of the search. As feature selection strategy, we propose a Variable Neighborhood Search (VNS) metaheuristic. Then, we propose to group the input space into subsets of features by using the concept of Markov blankets. To the best of our knowledge, this is the first time in which the Markov blanket is used for grouping features. We test the performance of VNS by conducting experiments on several high-dimensional datasets from two different domains: microarray and text mining. We compare VNS with popular and competitive techniques. Results show that VNS is a competitive strategy capable of finding a small size of features with similar predictive power than that obtained with other algorithms used in this study.},

keywords = {Feature selection, Metaheuristic},

pubstate = {published},

tppubtype = {article}

}

@article{Gómez-Vela2015,

title = {Gene network coherence based on prior knowledge using direct and indirect relationships},

author = {F. Gómez-Vela and J. A. Lagares and N. Díaz-Díaz},

url = {http://www.sciencedirect.com/science/article/pii/S1476927115000481},

doi = {10.1016/j.compbiolchem.2015.03.002},

issn = {1476-9271},

year  = {2015},

date = {2015-06-01},

journal = {Computational Biology and Chemistry},

volume = {56},

pages = {142-151},

abstract = {Gene networks (GNs) have become one of the most important approaches for modeling biological processes. They are very useful to understand the different complex biological processes that may occur in living organisms. Currently, one of the biggest challenge in any study related with GN is to assure the quality of these GNs. In this sense, recent works use artificial data sets or a direct comparison with prior biological knowledge. However, these approaches are not entirely accurate as they only take into account direct gene–gene interactions for validation, leaving aside the weak (indirect) relationships. We propose a new measure, named gene network coherence (GNC), to rate the coherence of an input network according to different biological databases. In this sense, the measure considers not only the direct gene–gene relationships but also the indirect ones to perform a complete and fairer evaluation of the input network. Hence, our approach is able to use the whole information stored in the networks. A GNC JAVA-based implementation is available at: http://fgomezvela.github.io/GNC/. The results achieved in this work show that GNC outperforms the classical approaches for assessing GNs by means of three different experiments using different biological databases and input networks. According to the results, we can conclude that the proposed measure, which considers the inherent information stored in the direct and indirect gene–gene relationships, offers a new robust solution to the problem of GNs biological validation.},

keywords = {Biological knowledge, Gene Network},

pubstate = {published},

tppubtype = {article}

}

@article{Medina2014,

title = {A Fuzzy Temporal Object-Relational Database: Model and Implementation},

author = {J. M. Medina and J. E. Pons and C. D. Barranco and O. Pons},

url = {https://onlinelibrary.wiley.com/doi/abs/10.1002/int.21666

https://onlinelibrary.wiley.com/doi/pdf/10.1002/int.21666},

doi = {10.1002/int.21666},

year  = {2014},

date = {2014-06-24},

journal = {International Journal of Intelligent Systems},

volume = {29},

number = {9},

pages = {836-863},

abstract = {Abstract In real world, some data have a specific temporal validity that must be appropiately managed. To deal with this kind of data, several proposals of temporal databases have been introduced. Moreover, time can also be affected by imprecision, vagueness, and/or uncertainty, since human beings manage time using temporal indications and temporal notions, which may also be imprecise. For this reason, information systems require appropriate support to accomplish this task. In this work, we present a novel possibilistic valid time model for fuzzy databases including the data structures, the integrity constraints, and the DML. Together with this model, we also present its implementation by means of a fuzzy valid time support module on top of a fuzzy object-relational database system. The integration of these modules allows to perform queries that combines fuzzy valid time constraints together with fuzzy predicates. Besides, the model and implementation proposed support the crisp valid time model as a particular case of the fuzzy valid time support provided.},

keywords = {Fuzzy databases},

pubstate = {published},

tppubtype = {article}

}

@article{Rodríguez-Baena2013,

title = {Extracting and validating biclusters from binary datasets},

author = {D. Rodríguez-Baena},

doi = {10.3233/AIC-130570},

year  = {2013},

date = {2013-05-01},

journal = {AI Communications},

volume = {26},

number = {4},

pages = {417-418},

abstract = {This work proposes a novel algorithm to extract biclusters from binary datasets: the Bit-Pattern Biclustering Algorithm (BiBit). The selective search performed by BiBit, based on a very fast bits words processing technique, provides very satisfactory results in quality and computational cost. Besides, a new software tool, named CarGene (Characterization of Genes), that helps scientists to validate sets of genes using biological knowledge is introduced too.},

keywords = {Biclustering, Binary dataset, Biological validation},

pubstate = {published},

tppubtype = {article}

}

@article{Barranco2013,

title = {Building a Fuzzy Valid Time Support Module on a Fuzzy Object-Relational Database},

author = {C. D. Barranco and J. M. Medina and J. E. Pons and O. Pons},

doi = {10.1007/978-3-642-40769-7_39},

isbn = {978-3-642-40769-7},

year  = {2013},

date = {2013-05-01},

journal = {Flexible Query Answering Systems},

pages = {447-458},

abstract = {In this work we present the implementation of a Fuzzy Valid Time Support Module on top of a Fuzzy Object-Relational Database System, based on a model to deal with imprecision in valid-time databases. The integration of these modules allows to perform queries that combines fuzzy valid time constraints with fuzzy predicates. Both modules can be deployed in Oracle Relational Database Management System 10.2 and higher. The module implements the mechanisms that overload the SQL sentences: Insert, Update, Delete and Select to allow fuzzy temporal handling. The implementation described supports the crisp valid time model as a particular case of its fuzzy valid time support provided.},

keywords = {Fuzzy databases},

pubstate = {published},

tppubtype = {article}

}

@article{Díaz-Díaz2013,

title = {Genes functional coherence based on actual biological knowledge},

author = {N. Díaz-Díaz},

url = {https://content.iospress.com/articles/ai-communications/aic553},

doi = {10.3233/AIC-130553},

year  = {2013},

date = {2013-01-02},

journal = {AI Communications},

volume = {26},

number = {2},

pages = {247-249},

abstract = {This work proposes two new approaches to establish the quality of genetic model based on current biological knowledge. First, it is developed a KEGG-based tool that provides a friendly graphical environment to analyze gene-enrichment. Moreover, a novel GO-based dissimilarity measure is proposed for evaluating groups of genes based on the most relevant functions of the whole set. To found this function, an heuristic approach based on Voronoi diagram has been presented.},

keywords = {Biological validation, Gene enrichment analysis},

pubstate = {published},

tppubtype = {article}

}

@article{Medina2012,

title = {On Modeling the Behavior of Comparators for Complex Fuzzy Objects in a Fuzzy Object-Relational Database Management System},

author = {J. M. Medina and C. D. Barranco and J. R. Campaña and S. J. Castillo},

doi = {10.1080/18756891.2012.718159},

issn = {1875-6883},

year  = {2012},

date = {2012-08-01},

journal = {International Journal of Computational Intelligence Systems},

volume = {5},

number = {4},

pages = {762-774},

abstract = {This paper proposes a parameterized definition for fuzzy comparators on complex fuzzy datatypes like fuzzy collections with conjunctive semantics and fuzzy objects. This definition and its implementation on a Fuzzy Object-Relational Database Management System (FORDBMS) provides the designer with a powerful tool to adapt the behavior of these operators to the semantics of the considered application.},

keywords = {Fuzzy databases},

pubstate = {published},

tppubtype = {article}

}

@article{Medina2012b,

title = {On the Use of a Fuzzy Object-Relational Database for Flexible Retrieval of Medical Images},

author = {J. M. Medina and S. J. Castillo and C. D. Barranco and J. R. Campaña},

doi = {10.1109/TFUZZ.2012.2201726},

issn = {1941-0034},

year  = {2012},

date = {2012-08-01},

journal = {IEEE Transactions on Fuzzy Systems},

volume = {20},

number = {4},

pages = {786-803},

abstract = {This paper introduces a novel approach to medical image retrieval using a fuzzy object-relational database management system (FORDBMS). The system stores medical images along with information about the content of the image, such as the presence or absence of certain indicators of pathologies. It allows us to flexibly retrieve them on the basis of these indicators, making it possible to obtain images from patients with similar diagnosis and thus, following a common visual pattern. To illustrate the capabilities of the FORDBMS, this paper focuses on X-ray images of patients suffering from scoliosis (a medical condition in which the patient's spine is curved) from which spine descriptions are obtained. Then queries are performed to obtain a set of images with a certain curvature pattern. Results show high accuracy when evaluated by medical experts. Compared with other ad hoc content-based image retrieval systems, the one presented here is easily adaptable to other application domains, customizable, and very scalable.},

keywords = {Fuzzy databases},

pubstate = {published},

tppubtype = {article}

}

@article{Barranco2012,

title = {An impact ordering approach for indexing fuzzy sets},

author = {C. D. Barranco and S. Helmer},

url = {http://www.sciencedirect.com/science/article/pii/S0165011411000558},

doi = {10.1016/j.fss.2011.01.014},

issn = {0165-0114},

year  = {2012},

date = {2012-06-01},

journal = {Fuzzy Sets and Systems},

volume = {196},

pages = {33-46},

abstract = {We propose an approach for indexing fuzzy data based on inverted files that speeds up retrieval considerably by stopping the traversal of postings lists early. This is possible because the entries in the postings lists are organized in a way that guarantees that there are no matching items beyond a certain point in a list. Consequently, we can reduce the number of false positives significantly, leading to an increase in retrieval performance. We have implemented our approach and evaluated it experimentally, including a test on skewed and real-world data, comparing it to an approach that has previously been shown to be superior to other methods.},

keywords = {Fuzzy databases},

pubstate = {published},

tppubtype = {article}

}

@article{Gómez-Vela2011b,

title = {Pattern Recognition in Biological Time Series},

author = {F. Gómez-Vela and F. Martínez-Álvarez and C. D. Barranco and N. Díaz-Díaz and D. Rodríguez-Baena and J. Aguilar-Ruiz},

doi = {10.1007/978-3-642-25274-7_17},

isbn = {978-3-642-25274-7},

year  = {2011},

date = {2011-11-01},

journal = {Advances in Artificial Intelligence},

pages = {164-172},

abstract = {Knowledge extraction from gene expression data has been one of the main challenges in the bioinformatics field during the last few years. In this context, a particular kind of data, data retrieved in a temporal basis (also known as time series), provide information about the way a gene can be expressed during time. This work presents an exhaustive analysis of last proposals in this area, particularly focusing on those proposals using non--supervised machine learning techniques (i.e. clustering, biclustering and regulatory networks) to find relevant patterns in gene expression.},

keywords = {Biclustering, Clustering, Gene Network},

pubstate = {published},

tppubtype = {article}

}

@article{Aguilar-Ruiz2011,

title = {CarGene: Characterisation of sets of genes based on metabolic pathways analysis},

author = {J. Aguilar-Ruiz and D. Rodríguez-Baena and N. Díaz-Díaz and I. A. Nepomuceno-Chamorro},

doi = {10.1504/IJDMB.2011.043033},

year  = {2011},

date = {2011-10-12},

journal = {International Journal of Data Mining and Bioinformatics},

volume = {5},

number = {5},

pages = {558-573},

abstract = {The great amount of biological information provides scientists with an incomparable framework for testing the results of new algorithms. Several tools have been developed for analysing gene-enrichment and most of them are Gene Ontology-based tools. We developed a Kyoto Encyclopedia of Genes and Genomes (Kegg)-based tool that provides a friendly graphical environment for analysing gene-enrichment. The tool integrates two statistical corrections and simultaneously analysing the information about many groups of genes in both visual and textual manner. We tested the usefulness of our approach on a previous analysis (Huttenshower et al.). Furthermore, our tool is freely available (http://www.upo.es/eps/bigs/cargene.html).},

keywords = {Pathways analysis},

pubstate = {published},

tppubtype = {article}

}

@article{Díaz-Díaz2011c,

title = {GO-based Functional Dissimilarity of Gene Sets},

author = {N. Díaz-Díaz and J. Aguilar-Ruiz},

doi = {10.1186/1471-2105-12-360},

year  = {2011},

date = {2011-09-01},

journal = {BMC Bioinformatics},

volume = {12},

number = {360},

abstract = {Background

The Gene Ontology (GO) provides a controlled vocabulary for describing the functions of genes and can be used to evaluate the functional coherence of gene sets. Many functional coherence measures consider each pair of gene functions in a set and produce an output based on all pairwise distances. A single gene can encode multiple proteins that may differ in function. For each functionality, other proteins that exhibit the same activity may also participate. Therefore, an identification of the most common function for all of the genes involved in a biological process is important in evaluating the functional similarity of groups of genes and a quantification of functional coherence can helps to clarify the role of a group of genes working together.



Results

To implement this approach to functional assessment, we present GFD (GO-based Functional Dissimilarity), a novel dissimilarity measure for evaluating groups of genes based on the most relevant functions of the whole set. The measure assigns a numerical value to the gene set for each of the three GO sub-ontologies.



Conclusions

Results show that GFD performs robustly when applied to gene set of known functionality (extracted from KEGG). It performs particularly well on randomly generated gene sets. An ROC analysis reveals that the performance of GFD in evaluating the functional dissimilarity of gene sets is very satisfactory. A comparative analysis against other functional measures, such as GS2 and those presented by Resnik and Wang, also demonstrates the robustness of GFD.},

keywords = {Biological validation},

pubstate = {published},

tppubtype = {article}

}

@article{Rodríguez-Baena2011,

title = {A biclustering algorithm for extracting bit-patterns from binary datasets},

author = {D. Rodríguez-Baena and A. J. Pérez-Pulido and J. Aguilar-Ruiz},

url = {https://doi.org/10.1093/bioinformatics/btr464

https://academic.oup.com/bioinformatics/article-pdf/27/19/2738/16900447/btr464.pdf},

doi = {10.1093/bioinformatics/btr464},

issn = {1367-4803},

year  = {2011},

date = {2011-08-08},

journal = {Bioinformatics},

volume = {27},

number = {19},

pages = {2738-2745},

abstract = {Motivation: Binary datasets represent a compact and simple way to store data about the relationships between a group of objects and their possible properties. In the last few years, different biclustering algorithms have been specially developed to be applied to binary datasets. Several approaches based on matrix factorization, suffix trees or divide-and-conquer techniques have been proposed to extract useful biclusters from binary data, and these approaches provide information about the distribution of patterns and intrinsic correlations.



Results: A novel approach to extracting biclusters from binary datasets, BiBit, is introduced here. The results obtained from different experiments with synthetic data reveal the excellent performance and the robustness of BiBit to density and size of input data. Also, BiBit is applied to a central nervous system embryonic tumor gene expression dataset to test the quality of the results. A novel gene expression preprocessing methodology, based on expression level layers, and the selective search performed by BiBit, based on a very fast bit-pattern processing technique, provide very satisfactory results in quality and computational cost. The power of biclustering in finding genes involved simultaneously in different cancer processes is also shown. Finally, a comparison with Bimax, one of the most cited binary biclustering algorithms, shows that BiBit is faster while providing essentially the same results.},

keywords = {Biclustering, Binary dataset},

pubstate = {published},

tppubtype = {article}

}

@article{Barranco2009,

title = {Indexing Fuzzy numerical Data with a B+ Tree for Fast Retrieval Using Necessity-Measured Flexible conditions.},

author = {C. D. Barranco and J. R. Campaña and J. M. Medina},

url = {https://doi.org/10.1142/S0218488509006005},

doi = {10.1142/S0218488509006005},

year  = {2009},

date = {2009-11-01},

journal = {International Journal of Uncertainty, Fuzziness and Knowledge-Based Systems},

volume = {17},

pages = {1-23},

abstract = {This paper proposes an indexing procedure for improving the performance of query processing on a fuzzy database. It focuses on the case when a necessity-measured atomic flexible condition is imposed on the values of a fuzzy numerical attribute. The proposal is to apply a classical indexing structure for numerical crisp data, a B+-tree combined with a Hilbert curve. The use of such a common indexing technique makes its incorporation into current systems straightforward. The efficiency of the proposal is compared with that of another indexing procedure for similar fuzzy data and flexible query types. Experimental results reveal that the performance of the proposed method is similar and more stable than that of its competitor.},

keywords = {Fuzzy data},

pubstate = {published},

tppubtype = {article}

}

@article{Alves2009,

title = {Gene association analysis: a survey of frequent pattern mining from gene expression data},

author = {R. Alves and D. Rodríguez-Baena and J. Aguilar-Ruiz},

url = {https://doi.org/10.1093/bib/bbp042

https://academic.oup.com/bib/article-pdf/11/2/210/573238/bbp042.pdf},

doi = {10.1093/bib/bbp042},

issn = {1467-5463},

year  = {2009},

date = {2009-10-08},

journal = {Briefings in Bioinformatics},

volume = {11},

number = {2},

pages = {210-224},

abstract = {Establishing an association between variables is always of interest in genomic studies. Generation of DNA microarray gene expression data introduces a variety of data analysis issues not encountered in traditional molecular biology or medicine. Frequent pattern mining (FPM) has been applied successfully in business and scientific data for discovering interesting association patterns, and is becoming a promising strategy in microarray gene expression analysis. We review the most relevant FPM strategies, as well as surrounding main issues when devising efficient and practical methods for gene association analysis (GAA). We observed that, so far, scalability achieved by efficient methods does not imply biological soundness of the discovered association patterns, and vice versa. Ideally, GAA should employ a balanced mining model taking into account best practices employed by methods reviewed in this survey. Integrative approaches, in which biological knowledge plays an important role within the mining process, are becoming more reliable.},

keywords = {Gene expression analysis, Pattern recognition},

pubstate = {published},

tppubtype = {article}

}