Design of artificial neural network and its applications to the analysis of alcoholism data

Li, Wentian; Haghighi, F.; Falk, Catherine T.

doi:10.1002/gepi.1370170738

Cited by 13 publications

(13 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…[28] Several research groups have used NNs for genetic studies because of their potential for detecting gene-gene or gene-environment interactions in addition to main effects. [31][32][33][34][35][36][37][38][39][40][41][42][43] These studies had varying levels of success because of the challenges associated with designing the appropriate NN architecture. Ritchie et al [44] proposed a novel NN technique that uses evolutionary algorithms (see section 1) to optimise both the inputs and the architecture of NNs.…”

Section: Optimisation and Evolutionmentioning

confidence: 99%

Machine Learning for Detecting Gene-Gene Interactions

McKinney

Reif

Ritchie

et al. 2006

Applied Bioinformatics

224

137

View full text Add to dashboard Cite

Complex interactions among genes and environmental factors are known to play a role in common human disease aetiology. There is a growing body of evidence to suggest that complex interactions are 'the norm' and, rather than amounting to a small perturbation to classical Mendelian genetics, interactions may be the predominant effect. Traditional statistical methods are not well suited for detecting such interactions, especially when the data are high dimensional (many attributes or independent variables) or when interactions occur between more than two polymorphisms. In this review, we discuss machine-learning models and algorithms for identifying and characterising susceptibility genes in common, complex, multifactorial human diseases. We focus on the following machine-learning methods that have been used to detect gene-gene interactions: neural networks, cellular automata, random forests, and multifactor dimensionality reduction. We conclude with some ideas about how these methods and others can be integrated into a comprehensive and flexible framework for data mining and knowledge discovery in human genetics.

show abstract

Section: Optimisation and Evolutionmentioning

confidence: 99%

Machine Learning for Detecting Gene-Gene Interactions

McKinney

Reif

Ritchie

et al. 2006

Applied Bioinformatics

224

137

View full text Add to dashboard Cite

show abstract

“…Another encoding scheme that has been used involves representing the data according to identity-by-descent (IBD) sharing, such that x = 1 for sharing an allele, x = -1 for not sharing the allele, and x = 0 for uninformative. This coding scheme has been the more common type of encoding for linkage analysis with NN [ 19 - 22 , 24 ]. Finally, NPL scores (a measure of allele sharing used in non-parametric linkage analysis) could also be used as inputs (predictors) of the NN [ 25 ].…”

Section: Neural Network In Genetic Epidemiologymentioning

confidence: 99%

Neural networks for genetic epidemiology: past, present, and future

Motsinger‐Reif

Ritchie

2008

BioData Mining

View full text Add to dashboard Cite

During the past two decades, the field of human genetics has experienced an information explosion. The completion of the human genome project and the development of high throughput SNP technologies have created a wealth of data; however, the analysis and interpretation of these data have created a research bottleneck. While technology facilitates the measurement of hundreds or thousands of genes, statistical and computational methodologies are lacking for the analysis of these data. New statistical methods and variable selection strategies must be explored for identifying disease susceptibility genes for common, complex diseases. Neural networks (NN) are a class of pattern recognition methods that have been successfully implemented for data mining and prediction in a variety of fields. The application of NN for statistical genetics studies is an active area of research. Neural networks have been applied in both linkage and association analysis for the identification of disease susceptibility genes.In the current review, we consider how NN have been used for both linkage and association analyses in genetic epidemiology. We discuss both the successes of these initial NN applications, and the questions that arose during the previous studies. Finally, we introduce evolutionary computing strategies, Genetic Programming Neural Networks (GPNN) and Grammatical Evolution Neural Networks (GENN), for using NN in association studies of complex human diseases that address some of the caveats illuminated by previous work.

show abstract

“…The conclusion that there are perhaps 20 or so markers that best explain the German Asthma data set may not stand true for other data sets, or may be altered if any one of the following conditions are changed: (i) if the independent variable is not the mean IBD (using mean IBD implies that the maternal and paternal IBD is treated equally and additively); (ii) if the mean IBDs from different markers are not combined additively (additivity is equivalent to a linear hyperplane used in the discrimination, instead of a nonlinear surface such as those used in artificial neural networks [Li et al, 1999]); and (iii) if genetic heterogeneity is assumed (tree-based discriminations, and conditional approaches that separate main and minor effects, may provide a solution to this issue). Clearly, for such a small data set, a best model can be obtained by chance.…”

Section: Discussionmentioning

confidence: 96%

Marker Selection by Akaike Information Criterion and Bayesian Information Criterion

Nyholt

2001

Genetic Epidemiology

Self Cite

View full text Add to dashboard Cite

We carried out a discriminant analysis with identity by descent (IBD) at each marker as inputs, and the sib pair type (affected-affected versus affected-unaffected) as the output. Using simple logistic regression for this discriminant analysis, we illustrate the importance of comparing models with different number of parameters. Such model comparisons are best carried out using either the Akaike information criterion (AIC) or the Bayesian information criterion (BIC). When AIC (or BIC) stepwise variable selection was applied to the German Asthma data set, a group of markers were selected which provide the best fit to the data (assuming an additive effect). Interestingly, these 25-26 markers were not identical to those with the highest (in magnitude) single-locus lod scores.

show abstract

Design of artificial neural network and its applications to the analysis of alcoholism data

Cited by 13 publications

References 8 publications

Machine Learning for Detecting Gene-Gene Interactions

Machine Learning for Detecting Gene-Gene Interactions

Neural networks for genetic epidemiology: past, present, and future

Marker Selection by Akaike Information Criterion and Bayesian Information Criterion

Contact Info

Product

Resources

About