Neural networks ensemble for automatic DNA microarray spot classification

In this work, a new step for the DNA microarray image analysis pipeline is proposed using neural computing techniques. We perform the classification of the spots into morphology-derived classes in order to assist the segmentation procedure that is traditionally performed after the gridding process. Our method consists of extracting multiple features from each individual spot area (or cell-derived from the gridding process) that are then reduced to a presumably optimal subset using a feature selection process, the sequential forward selection algorithm. Classification is then realized by means of a neural network ensemble with a tree-like structure, made up of seven multi-layer perceptron networks. The architecture of each neural network has been obtained through an exhaustive automatic searching process that optimizes the size of the network as a function of the classification error rate. The neural ensemble classifier is tested on two sub-grids extracted from real microarray DNA images and is shown to achieve high accuracy rates over the seven different classes of spot. In addition, a dataset with more than 1000 samples of classes of spot has been generated and made freely available.