Weka Machine Learning for Predicting the Phospholipidosis Inducing Potential

Abstract

Abstract:The drug discovery and development process is lengthy and expensive, and bringing a drug to market may take up to 18 years and may cost up to 2 billion $US. The extensive use of computer-assisted drug design techniques may considerably increase the chances of finding valuable drug candidates, thus decreasing the drug discovery time and costs. The most important computational approach is represented by structure-activity relationships that can discriminate between sets of chemicals that are active/inactive towards a certain biological receptor. An adverse effect of some cationic amphiphilic drugs is phospholipidosis that manifests as an intracellular accumulation of phospholipids and formation of concentric lamellar bodies. Here we present structure-activity relationships (SAR) computed with a wide variety of machine learning algorithms trained to identify drugs that have phospholipidosis inducing potential. All SAR models are developed with the machine learning software Weka, and include both classical algorithms, such as k-nearest neighbors and decision trees, as well as recently introduced methods, such as support vector machines and artificial immune systems. The best predictions are obtained with support vector machines, followed by a perceptron artificial neural network, logistic regression, and k-nearest neighbors.

Comparative Study of Classification Algorithms Using Molecular Descriptors in Toxicological DataBases

“…A selection algorithm was also used to identify three necessary attributes for the compounds discrimination and the leave-one-out cross-validation was the evaluated procedure. Again in [24] the problem is to predict potential toxicity of compounds depending on their physico-chemicals properties. It was used a wide variety of machine learning algorithms with Weka (machine learning software), including classical algorithms, such as k-nearest neighbours and decision trees, as well as support vector machines and artificial immune systems.…”

Conotoxins: Review and Docking Studies to determine potentials of Conotoxin as an Anticancer Drug Molecule

“…Some recent issues guestedited by González-Díaz et al review many of these techniques. See for instance, papers published in Current Topics in Medicinal Chemistry in 2008 [14][15][16][17][18][19][20][21][22][23], Current Proteomics in 2009, and Current Drug Metabolism [24][25][26][27][28][29][30][31] or Current Pharmaceutical Design in 2010 [32][33][34][35][36][37][38][39][40]. In this work we review computational chemistry and bioinformatics methods used to study an interesting class of peptides called conotoxins, and their possible interaction with HERG channels.…”

Application of Bioinformatics for the Search of Novel Anti-Viral Therapies: Rational Design of Anti-Herpes Agents

“…Nowadays, it is almost impossible to have clear ideas about biochemical or biological processes or phenomena without use of Bioinformatics, which is concerned in the application of statistics and computer science to the field of molecular biology and it has been determinant for the better understanding of processes related to Medicinal Chemistry [7][8][9][10][11][12][13][14][15][16], Proteomics [17][18][19][20][21][22][23], Drug Metabolism [24][25][26][27][28][29][30][31][32], or Pharmaceutical Design [33][34][35][36][37][38][39][40][41][42]. This review is focused on the role of Bioinformatics toward the design of compounds with anti-herpetic activity.…”