Predicting human miRNA target genes using a novel evolutionary methodology

Handle URI:
http://hdl.handle.net/10754/564489
Title:
Predicting human miRNA target genes using a novel evolutionary methodology
Authors:
Aigli, Korfiati; Kleftogiannis, Dimitrios A. ( 0000-0003-1086-821X ) ; Konstantinos, Theofilatos; Spiros, Likothanassis; Athanasios, Tsakalidis; Seferina, Mavroudi
Abstract:
The discovery of miRNAs had great impacts on traditional biology. Typically, miRNAs have the potential to bind to the 3'untraslated region (UTR) of their mRNA target genes for cleavage or translational repression. The experimental identification of their targets has many drawbacks including cost, time and low specificity and these are the reasons why many computational approaches have been developed so far. However, existing computational approaches do not include any advanced feature selection technique and they are facing problems concerning their classification performance and their interpretability. In the present paper, we propose a novel hybrid methodology which combines genetic algorithms and support vector machines in order to locate the optimal feature subset while achieving high classification performance. The proposed methodology was compared with two of the most promising existing methodologies in the problem of predicting human miRNA targets. Our approach outperforms existing methodologies in terms of classification performances while selecting a much smaller feature subset. © 2012 Springer-Verlag.
KAUST Department:
Computer, Electrical and Mathematical Sciences and Engineering (CEMSE) Division; Computer Science Program
Publisher:
Springer Science + Business Media
Journal:
Artificial Intelligence: Theories and Applications
Conference/Event name:
7th Hellenic Conference on Artificial Intelligence, SETN 2012
Issue Date:
2012
DOI:
10.1007/978-3-642-30448-4_37
Type:
Conference Paper
ISSN:
03029743
ISBN:
9783642304477
Appears in Collections:
Conference Papers; Computer Science Program; Computer, Electrical and Mathematical Sciences and Engineering (CEMSE) Division

Full metadata record

DC FieldValue Language
dc.contributor.authorAigli, Korfiatien
dc.contributor.authorKleftogiannis, Dimitrios A.en
dc.contributor.authorKonstantinos, Theofilatosen
dc.contributor.authorSpiros, Likothanassisen
dc.contributor.authorAthanasios, Tsakalidisen
dc.contributor.authorSeferina, Mavroudien
dc.date.accessioned2015-08-04T07:02:18Zen
dc.date.available2015-08-04T07:02:18Zen
dc.date.issued2012en
dc.identifier.isbn9783642304477en
dc.identifier.issn03029743en
dc.identifier.doi10.1007/978-3-642-30448-4_37en
dc.identifier.urihttp://hdl.handle.net/10754/564489en
dc.description.abstractThe discovery of miRNAs had great impacts on traditional biology. Typically, miRNAs have the potential to bind to the 3'untraslated region (UTR) of their mRNA target genes for cleavage or translational repression. The experimental identification of their targets has many drawbacks including cost, time and low specificity and these are the reasons why many computational approaches have been developed so far. However, existing computational approaches do not include any advanced feature selection technique and they are facing problems concerning their classification performance and their interpretability. In the present paper, we propose a novel hybrid methodology which combines genetic algorithms and support vector machines in order to locate the optimal feature subset while achieving high classification performance. The proposed methodology was compared with two of the most promising existing methodologies in the problem of predicting human miRNA targets. Our approach outperforms existing methodologies in terms of classification performances while selecting a much smaller feature subset. © 2012 Springer-Verlag.en
dc.publisherSpringer Science + Business Mediaen
dc.subjectevolutionary computationen
dc.subjectgenetic algorithmsen
dc.subjectMachine Learning classificationen
dc.subjectmiRNA targetsen
dc.subjectmiRNAsen
dc.subjectmultiobjective optimizationen
dc.subjectSupport Vector Machinesen
dc.titlePredicting human miRNA target genes using a novel evolutionary methodologyen
dc.typeConference Paperen
dc.contributor.departmentComputer, Electrical and Mathematical Sciences and Engineering (CEMSE) Divisionen
dc.contributor.departmentComputer Science Programen
dc.identifier.journalArtificial Intelligence: Theories and Applicationsen
dc.conference.date28 May 2012 through 31 May 2012en
dc.conference.name7th Hellenic Conference on Artificial Intelligence, SETN 2012en
dc.conference.locationLamiaen
dc.contributor.institutionDepartment of Computer Engineering and Informatics, University of Patras, Greeceen
kaust.authorKleftogiannis, Dimitrios A.en
All Items in KAUST are protected by copyright, with all rights reserved, unless otherwise indicated.