A methodology for detecting relevant single nucleotide polymorphism in prostate cancer with multivariate adaptive regression splines and backpropagation artificial neural networks.
Juan Enrique Sánchez LasherasCarmen González-DonquilesPaulino José García NietoJosé Juan Jiménez MoleonDolores Salas-TrejoSergio Luis Suárez GómezAntonio J. Molina de la TorreJoaquín González-NuevoLaura BonaveraJorge Carballido-LandeiraFrancisco Javier de Cos JuezPublished in: Neural Comput. Appl. (2020)
Keyphrases
- back propagation
- artificial neural networks
- prostate cancer
- multivariate adaptive regression splines
- neural network
- feed forward
- feed forward neural networks
- hidden layer
- multilayer perceptron
- backpropagation neural networks
- human genome
- genome wide
- computer aided
- genetic algorithm
- mr images
- single nucleotide polymorphisms
- computational approaches
- medical image analysis
- activation function
- backpropagation neural network
- feedforward neural networks
- fuzzy logic
- high throughput
- learning algorithm
- radial basis function
- multi layer perceptron
- feature extraction
- pairwise
- high dimensional