Katya Rodríguez

Classification of DNA microarrays using artificial neural networks and ABC algorithm

Graphical abstractDisplay Omitted HighlightsABC algorithm discovered the best set of genes to classify correctly cancer samples.With less than 1% of information is possible to classify with an accuracy of 93.2%.Multilayer perceptron performs better than radial basis function network. DNA microarray is an efficient new technology that allows to analyze, at the same time, the expression level of millions of genes. The gene expression level indicates the synthesis of different messenger ribonucleic acid (mRNA) molecule in a cell. Using this gene expression level, it is possible to diagnose diseases, identify tumors, select the best treatment to resist illness, detect mutations among other processes. In order to achieve that purpose, several computational techniques such as pattern classification approaches can be applied. The classification problem consists in identifying different classes or groups associated with a particular disease (e.g., various types of cancer, in terms of the gene expression level). However, the enormous quantity of genes and the few samples available, make difficult the processes of learning and recognition of any classification technique. Artificial neural networks (ANN) are computational models in artificial intelligence used for classifying, predicting and approximating functions. Among the most popular ones, we could mention the multilayer perceptron (MLP), the radial basis function neural network (RBF) and support vector machine (SVM). The aim of this research is to propose a methodology for classifying DNA microarray. The proposed method performs a feature selection process based on a swarm intelligence algorithm to find a subset of genes that best describe a disease. After that, different ANN are trained using the subset of genes. Finally, four different datasets were used to validate the accuracy of the proposal and test the relevance of genes to correctly classify the samples of the disease.

Classification of DNA Microarrays Using Artificial Bee Colony (ABC) Algorithm

DNA microarrays are a powerful technique in genetic science due to the possibility to analyze the gene expression level of millions of genes at the same time. Using this technique, it is possible to diagnose diseases, identify tumours, select the best treatment to resist illness, detect mutations and prognosis purpose. However, the main problem that arises when DNA microarrays are analyzed with computational intelligent techniques is that the number of genes is too big and the samples are too few. For these reason, it is necessary to apply pre-processing techniques to reduce the dimensionality of DNA microarrays. In this paper, we propose a methodology to select the best set of genes that allow classifying the disease class of a gene expression with a good accuracy using Artificial Bee Colony (ABC) algorithm and distance classifiers. The results are compared against Principal Component Analysis (PCA) technique and others from the literature.

Designing artificial neural networks using differential evolution for classifying DNA microarrays

The information obtained from the analysis of DNA microarrays is relevant to identify and predict illness, improve treatments, and to determine which genes are responsible to provoke a specific disease. However, the enormous quantity of genes and the few samples to be analyzed affect the performance of any classifier. For this reason, it is necessary to develop a methodology that combines a robust feature selection technique with a classification algorithm for classifying DNA microarrays. In this paper, we combine a feature selection technique based on the Artificial Bee Colony algorithm with an Artificial Neural Network (ANN). Furthermore, this ANN is automatically designed by a Differential Evolution (DE) algorithm that optimizes the synaptic weights, the architecture, and the transfer functions at the same time. To test the accuracy of the proposed methodology, we use the Leukemia AML-ALL dataset.

Generalized neurons and its application in DNA microarray classification

The DNA Microarray classification is an important task in bioinformatics and medicine area. The genetic expression in DNA microarrays present the opportunity to determine for example, which genes are involved with a particular disease, identify tumors, select the best treatment, etc. Several computational intelligence technique such as artificial neural networks can be used to identify different groups of genes associated with a particular disease. However, the enormous quantity of genes and the few samples available demand the use of more robust artificial neural networks. The purpose of this research is focused on showing how a generalize neuron (GN) can be applied in the DNA microarray classification task. In order to do that, the proposed methodology first, select the set of genes that best describe the disease applying the artificial bee colony algorithm. After that, the genes found during the first stage are used to train a GN. The GN is trained with the differential evolution algorithm. Finally, the accuracy of the proposed methodology is tested classifying two type of cancer using DNA microarrays: the acute lymphocytic leukemia and the acute myeloid leukemia.

Session details: Late breaking abstracts workshop

Two-page abstracts describing late-breaking developments in the field of genetic and evolutionary computation have been solicited for the Late-Breaking Abstracts (LBA) Workshop at GECCO 2012. As in previous years, the LBA Workshop has received an overwhelming response from the research community. Out of 28 submitted abstracts, 24 abstracts have finally been accepted after a brief, but nevertheless careful, examination of the workshop chairs. We would like to express our sincere thanks to all authors who submitted their abstracts. The accepted abstracts span a wide range of GECCO-related topics such as evolutionary game theory, evolutionary robotics and combinatorial as well as real-value optimization. We have tried our best to cluster the accepted abstracts into meaningful sessions, and genuinely hope you enjoy the Workshop and find the GECCO 2012 Proceedings of use for your work now and your future projects and activities.