Prediction of Molecular Bioactivity for Drug Design Using a Decision Tree Algorithm

Abstract

Abstract. A machine learning-based approach to the prediction of molecular bioactivity in new drugs is proposed. Two important aspects are considered for the task: feature subset selection and cost-sensitive classification. These are to cope with the huge number of features and unbalanced samples in a dataset of drug candidates. We designed a pattern classifier with such capabilities based on information theory and re-sampling techniques. Experimental results demonstrate the feasibility of the proposed approach. In particular, the classification accuracy of our approach was higher than that of the winner of KDD Cup 2001 competition.

A variable selection method based on Tabu search for logistic regression models

“…Extensive research into variable selection has been carried out over the past four decades. Many studies on variable selection are related to medicine and biology, such as those by Sierra et al (2001), Ganster et al (2001), Inza et al (2000), Lee et al (2003), Shy and Suganthan (2003) and Tamoto et al (2004).…”

Predicting Corporate Failure: The GRASP-LOGIT Model

“…Over the past four decades, extensive research into feature selection has been conducted. Some of these works are Ganster et al (2001), Lee et al (2003), Crone and Finlay (2012) and Mangalova and Agafonov (2014). Besides, the problem of selecting variables from a large candidate pool abounds in areas such as discriminant analysis (Pacheco et al, 2006), linear regression , Arslan, 2012 and logistic regression (Pacheco et al, 2009;Matsui, 2014).…”

Analysis of new variable selection methods for discriminant analysis

“…Extensive research into variable selection has been carried out over the past four decades. Many studies on variable selection are related to medicine and biology, such as Sierra et al (2001), Ganster et al (2001), Inza et al (2000), Lee et al (2003), Shy and Suganthan (2003), and Tamoto et al (2004).…”