Machine learning in bioinformatics

Larrañaga, Pedro; Calvo, B.; Santana, Roberto; Bielza, Concha; Galdiano, Josu; Inza, Iñaki; Lozano, José A.; Armañanzas, Rubén; Santafé, Guzmán; Pérez, Aritz; Robles, Víctor

doi:10.1093/bib/bbk007

Cited by 743 publications

(443 citation statements)

References 228 publications

Supporting

Mentioning

433

Contrasting

Unclassified

Order By: Relevance

“…Supervised methods utilize a prior knowledge about the system by developing classification models based on known spectra [62,[64][65][66]. These methods include Linear DA (LDA), Direct LDA (DLDA), Heteroscedastic LDA (HLDA), Nonparametric DA (NDA), Kernel-based LDA (K-LDA), SIMCA, PLS-DA and Multivariate Analysis of Variance (MANOVA) [67][68][69][70][71][72][73][74].…”

Section: Identification Of Unknown Body Fluidsmentioning

confidence: 99%

Discriminant Analysis of Raman Spectra for Body Fluid Identification for Forensic Purposes

Sikirzhytski

Virkler

Lednev

et al. 2010

AIP Conference Proceedings

View full text Add to dashboard Cite

Detection and identification of blood, semen and saliva stains, the most common body fluids encountered at a crime scene, are very important aspects of forensic science today. This study targets the development of a nondestructive, confirmatory method for body fluid identification based on Raman spectroscopy coupled with advanced statistical analysis. Dry traces of blood, semen and saliva obtained from multiple donors were probed using a confocal Raman microscope with a 785-nm excitation wavelength under controlled laboratory conditions. Results demonstrated the capability of Raman spectroscopy to identify an unknown substance to be semen, blood or saliva with high confidence.

show abstract

Section: Identification Of Unknown Body Fluidsmentioning

confidence: 99%

Discriminant Analysis of Raman Spectra for Body Fluid Identification for Forensic Purposes

Sikirzhytski

Virkler

Lednev

et al. 2010

AIP Conference Proceedings

View full text Add to dashboard Cite

show abstract

“…Thus, the sum of the probabilities of all the transitions from a given states to all other states must be 1. Markov and HMMs are gaining popularity in bioinformatics research for nucleotide sequence analysis [10,12]. For prokaryotes gene identification, Borodovsky [15] effectively applied this HMM technique.…”

Section: Literature Surveymentioning

confidence: 99%

“…In this context, Biological data mining plays an important role to supply data to overcome provoking challenges in the process of research and development, thus enabling various possibilities in this direction [1]. Although the field of bioinformatics is originally aimed to extract information embedded within the three billion bases of human DNA, the field has further evolved to understand its capability and capacity for studying information contents and information flow of biological systems and processes.…”

Section: Introductionmentioning

confidence: 99%

Splice Site Recognition Using Lower Dimensional LHMM Features and SVM Classifier

Sahu¹

2017

IJRASET

View full text Add to dashboard Cite

“…The conditional probabilities learnt through the phenotype statistical distribution in the database will be used to report interactions among genes not only based on their individual expression levels, but also on their behaviour through the different conditions. This fact involves the addition of the probabilistic relationship that associates the sample class (or phenotype) with each relevant gene or feature under the study, that is, a supervised-class experimental design [18,19]. Our new proposal belongs to these supervised studies, stressing the search of robust results by means of a hierarchy of supervised Bayesian classifiers.…”

Section: Introductionmentioning

confidence: 99%

Detecting reliable gene interactions by a hierarchy of Bayesian network classifiers

Armañanzas

Inza

Larrañaga

2008

Computer Methods and Programs in Biomedicine

Self Cite

View full text Add to dashboard Cite

The main purpose of a gene interaction network is to map the relationships of the genes that are out of sight when a genomic study is tackled. DNA microarrays allow the measure of gene expression of thousands of genes at the same time. These data constitute the numeric seed for the induction of the gene networks. In this paper, we propose a new approach to build gene networks by means of Bayesian classifiers, variable selection and bootstrap resampling. The interactions induced by the Bayesian classifiers are based both on the expression levels Keywords:an d on the phenotype information of the supervised variable. Feature selection and bootBayesian network classifiers strap resampling add reliability and robustness to the overall process removing the false Robust arc identification positive findings. The consensus among all the induced models produces a hierarchy of Gene interactions dependences and, thus, of variables. Biologists can define the depth level of the model hierar-DNA microarrays chy so the set of interactions and genes involved can vary from a sparse to a dense set. ExperKnowledge discovery imental results show how these networks perform well on classification tasks. The biological validation matches previous biological findings and opens new hypothesis for future studies.

show abstract

Machine learning in bioinformatics

Cited by 743 publications

References 228 publications

Discriminant Analysis of Raman Spectra for Body Fluid Identification for Forensic Purposes

Discriminant Analysis of Raman Spectra for Body Fluid Identification for Forensic Purposes

Splice Site Recognition Using Lower Dimensional LHMM Features and SVM Classifier

Detecting reliable gene interactions by a hierarchy of Bayesian network classifiers

Contact Info

Product

Resources

About