editorial distributed artificial intelligence models for knowledge...

EditorialDistributed Artificial Intelligence Models forKnowledge Discovery in Bioinformatics

Juan M. Corchado,1 Isabelle Bichindaritz,2 and Juan F. De Paz1

1Biomedical Research Institute of Salamanca/BISITE Research Group, University of Salamanca,Edificio I+D+i, 37008 Salamanca, Spain2Computer Science Department, State University of New York, Shineman Center 427, Oswego, NY 13126, USA

Correspondence should be addressed to Juan M. Corchado; [email protected]

Received 2 February 2015; Accepted 2 February 2015

Copyright © 2015 Juan M. Corchado et al. This is an open access article distributed under the Creative Commons AttributionLicense, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properlycited.

The increasing volume of existing information on biologicalprocesses and the use of large databases have significantlyincreased the accessibility of datasets to the scientific com-munity. This has enabled performing an analysis to facilitatethe extraction of relevant information or modeling and opti-mizing tasks in different processes. Parallel to the increasingvolumes of information is the emergence of new or adapteddistributed computing models such as grid computing andcloud computing. Together with new techniques of artificialintelligence, or more specifically knowledge discovery, thesemanagement systems are making it possible to perform amore efficient analysis of the information and are enablingthe creation of adaptive systems with learning ability.

In the area of distributed artificial intelligence modelsfor knowledge discovery in bioinformatics, ten interestingproposals are presented. These models analyze differentbiological aspects and simulate the process or user behaviorin the health care system. The main characteristics in theseproposals are the use of artificial intelligence techniques toanalyze the information and extract knowledge.

“Bladder Carcinoma Data with Clinical Risk Factors andMolecular Markers: A Cluster Analysis” provides interestingresearch about bladder cancer. The paper shows the hypoth-esis that the use of clinical and histopathological data withinformation about marker is useful to manage treatments ofnonmuscle invasive bladder cancers (NMIBC). The authorsapply data mining techniques such as hierarchical clustering

to create molecular cluster and risk groups. In their experi-ments, the authors analyze 45 patients with a new diagnosisof NMIBC.They create four groups of patients and categorizethe patients according to clinical characters and biologicalbehavior.

The authors of “A Linear-RBF Multikernel SVM to Clas-sify Big Text Corpora” use data mining techniques based onclassifiers to big text corpora. In particular, they implementa variant of support vector machine (SVM) to reduce thecomputational cost. The authors show a multikernel SVMwith automatic parameterization to improve the results ofSVM parameterized under a brute force search.The proposalis composed of a workflow with algorithms to process doc-uments, reduce the dimensionality of the data, and to apply/provide clustering, training, and prediction. The proposal isanalyzed according to the classification results and buildingtime in the dataset TREC Genomics 2005 corpus.

In “Analysis of Environmental Stress Factors Using anArtificial Growth System and Plant Fitness Optimization,”the authors analyze how some environment conditions canaccelerate the evolution process; in addition to modifyingthe environment conditions, it is possible to select genomicvariants. The authors analyze several factors for Pleurotusostreatus to improve quality and production. In order to carryout the analysis of the factors, the authors include severalIoT sensors to retrieve the information from the sensors.Theinformation is then processed with data mining techniques

Hindawi Publishing CorporationBioMed Research InternationalVolume 2015, Article ID 846785, 2 pageshttp://dx.doi.org/10.1155/2015/846785

2 BioMed Research International

in cloud system in order to predict plant growth and manageplant growth control.

“RecRWR: A Recursive Random Walk Method forImproved Identification of Diseases” proposes a newmethodto select the best disease targets for multiconcepts graphs.The proposal, referred to as recursive random walk withrestarts (RecRWR), includes multilayer networks, graphs,and weights calculation and has been tested with the OMIMdatabase with the area under ROC curves.

“Gene Knockout Identification Using an Extension ofBees Hill Flux Balance Analysis” is an interesting paper thatpresents an extension of Bees Hill Flux Balance Analysis(BHFBA) integrated within the framework of the OptKnockand Hill Climbing algorithm in a local search to extract geneknockout in order to maximize the production of the desiredmetabolite. The proposal has been analyzed with differentdatabases and compares the execution time, growth rate,and production yield. The authors validate that the BHFBAimproves the performance due to the inclusion of the HillClimbing algorithm.

In “Using the eServices Platform for Detecting BehaviorPatterns Deviation in the Elderly Assisted Living: A CaseStudy,” the authors present the eServices platform (ElderlySupport Service Platform). The platform detects any devi-ation in the behavioral pattern followed by elderly peopleand is able to predict dangerous situations. The system wasmodeled with the CRISP-DM methodology and was testedwith synthetic data based on real data and expert knowledge.The authors incorporate several data mining techniques suchas decision trees, cluster, or ROC curves in order to validatethe results.

“Agent-Based Spatiotemporal Simulation of Biomolec-ular Systems within the Open Source MASON Frame-work” presents a tool for biomolecular reaction modellingin the multiagent simulator of neighborhoods framework(MASON). The tool describes the interaction among themolecules. The system is worth considering to analyze theeffect of different factors in simulations. The system is testedin several scenarios based on enzymatic activity. The resultsarea is compared with studies performed in laboratories.

“A Distributed Multiagent System Architecture for BodyArea Networks Applied to Healthcare Monitoring” presentsan architecture based on a multiagent system to monitorthe parameters of several users with biomedical sensors. Theagents incorporate the BDI (belief, desire, and intention)model and data mining techniques to analyze the data of thesensors. The system is able to detect movements, activities,and postures. Its accuracy is confirmed and presented in theresults taken from the tests performed in several cases.

“Modelling the Longevity of Dental Restorations bymeans of a CBR System” presents a case based reasoning(CBR) system to analyze dental restorations with differentmaterials. The system applies the steps of the CBR cycle inwhich it integrates several datamining algorithms to performin the retrieved phase. It also includes a mixture of expertswith neural networks and Bayesian networks in the reusephase to predict the longevity of dental restorations. Thesystem is tested with the data of patients and the results areshown in the paper.

Finally, “aCGH-MAS: Analysis of aCGH by means ofMultiagent System” proposes a multiagent system to analyzedata of CGH (comparative genomic hybridization) arrays.The agents incorporate several layers to perform visualizationand analysis and to manage information processes. Thesystem proposes different visualizations to facilitate the visualanalysis and to access the information in databases.Moreover,the multiagent system provides several data mining tech-niques to carry out the analysis. The system is tested withseveral kinds of CGH arrays and the results are shown in thepaper.

Acknowledgments

We would like to thank all the contributing authors for theirparticipation in this special issue and the reviewers for theirhard and very valuable work and support. We would alsolike to thank the journal’s editorial staff for their work andassistance.

Juan M. CorchadoIsabelle Bichindaritz

Juan F. De Paz

Submit your manuscripts athttp://www.hindawi.com

Hindawi Publishing Corporationhttp://www.hindawi.com Volume 2014

Anatomy Research International

PeptidesInternational Journal of


Hindawi Publishing Corporation http://www.hindawi.com

International Journal of

Volume 2014

Zoology


Molecular Biology International

GenomicsInternational Journal of


The Scientific World JournalHindawi Publishing Corporation http://www.hindawi.com Volume 2014


BioinformaticsAdvances in

Marine BiologyJournal of



Signal TransductionJournal of


BioMed Research International

Evolutionary BiologyInternational Journal of



Biochemistry Research International

ArchaeaHindawi Publishing Corporationhttp://www.hindawi.com Volume 2014


Genetics Research International


Advances in

Virolog y

Hindawi Publishing Corporationhttp://www.hindawi.com

Nucleic AcidsJournal of

Volume 2014

Stem CellsInternational



Enzyme Research


International Journal of

Microbiology

editorial distributed artificial intelligence models for knowledge...

Documents