Supervised Feature Ranking Using a Genetic Algorithm Optimized Artificial Neural Network

Abstract

A genetic algorithm optimized artificial neural network GNW has been designed to rank features for two diversified multivariate data sets. The dimensions of these data sets are 85 × 24 and 62 × 25 for 24 or 25 molecular descriptors being computed for 85 matrix metalloproteinase-1 inhibitors or 62 hepatitis C virus NS3 protease inhibitors, respectively. Each molecular descriptor computed is treated as a feature and input into an input layer node of the artificial neural network. To optimize the artificial neural network by the genetic algorithm, each interconnected weight between input and hidden or between hidden and output layer nodes is binary encoded as a 16 bits string in a chromosome, and the chromosome is evolved by crossover and mutation operations. Each input layer node and its associated weights of the trained GNW are systematically omitted once (the self-depleted weights), and the corresponding weight adjustments due to the omission are computed to keep the overall network behavior unchanged. The primary feature ranking index defined as the sum of self-depleted weights and the corresponding weight adjustments computed is found capable of separating good from bad features for some artificial data sets of known feature rankings tested. The final feature indexes used to rank the data sets are computed as a sum of the weighted frequency of each feature being ranked in a particular rank for each data set being partitioned into numerous clusters. The two data sets are also clustered by a standard K-means method and trained by a support vector machine (SVM) for feature ranking using the computed F-scores as feature ranking index. It is found that GNW outperforms the SVM method on three artificial as well as the matrix metalloproteinase-1 inhibitor data sets studied. A clear-cut separation of good from bad features is offered by the GNW but not by the SVM method for a feature pool of known feature ranking.

An Anchor-Dependent Molecular Docking Process for Docking Small Flexible Molecules into Rigid Protein Receptors

“…The searching range of all the rotatable bonds was set between 180 and −180. There was a certain population of chromosomes generated within each generation, and two out of them were selected by a roulette wheel mechanism for crossover operation. We proceeded with two-points crossover on the two chromosomes randomly selected by first picking out two crossover sites randomly.…”

Multi‐Objective Feature Selection in QSAR Using a Machine Learning Approach

“…Many FS strategies use evolutionary algorithms [6,23,24], given that they allow a stochastic and parallel search of the possible solutions of a problem, and hence they are able to escape from local minima. There are also other approaches based on stepwise strategies which perform a greedy search of the best subsets of variables [22].…”

Effects of SVM parameter optimization on discrimination and calibration for post-procedural PCI mortality

“…They have been compared to other methods, such as logistic regression, [9][10][11][12] k-nearest neighbors, [13] and neural networks. [9,[12][13][14] The results have been heterogeneous, but in many published reports SVMs have been found to be equivalent to more traditional types of models. [9,10,15,16] In some domains, SVMs were claimed to have outperformed other methodologies.…”