Analysis of Proteasome Inhibition Prediction Using Atom-Based Quadratic Indices Enhanced by Machine Learning Classification Techniques

Author(s): Gerardo M. Casanola-Martin, Huong Le-Thi-Thu, Yovani Marrero-Ponce, Juan A Castillo- Garit, Francisco Torrens, Facundo Perez-Gimenez, Concepcion Abad

Journal Name: Letters in Drug Design & Discovery

Volume 11 , Issue 6 , 2014

Become EABM
Become Reviewer
Call for Editor

Graphical Abstract:


In this work the use of 2D atom-based quadratic indices is shown in the prediction of proteasome inhibition. Machine learning approaches such as support vector machine, artificial neural network, random forest and k-nearest neighbor were used as main techniques to carry out two quantitative structure-activity relationship (QSAR) studies. First, a database consisting of active and non-active classes was predicted with model performances above 85% and 80% in learning and test series, respectively. Second a regression-based model was developed which allow to estimate the EC50 with Q2 values of 52.89 and 50.19, in training and prediction sets, respectively, were developed. These results provided new approaches on proteasome inhibitor identification encouraged by virtual screenings procedures.

Keywords: Atom-based quadratic index, Classification and regression model, Machine learning, Proteasome inhibition, QSAR, TOMOCOMD-CARDD software.

Rights & PermissionsPrintExport Cite as

Article Details

Year: 2014
Published on: 27 May, 2014
Page: [705 - 711]
Pages: 7
DOI: 10.2174/1570180811666140122001144
Price: $65

Article Metrics

PDF: 13