Binary classification of chalcone derivatives with LDA or KNN based on their antileishmanial activity and molecular descriptors selected using the Successive Projections Algorithm feature-selection technique

Mohammad Goodarzi, Wouter Saeys, Mario Cesar Ugulino De Araujo, Roberto Kawakami Harrop Galvão, Yvan Vander Heyden

Research output: Contribution to journalArticle

17 Citations (Scopus)

Abstract

Chalcones are naturally occurring aromatic ketones, which consist of an α-, β-unsaturated carbonyl system joining two aryl rings. These compounds are reported to exhibit several pharmacological activities, including antiparasitic, antibacterial, antifungal, anticancer, immunomodulatory, nitric oxide inhibition and anti-inflammatory effects. In the present work, a Quantitative Structure-Activity Relationship (QSAR) study is carried out to classify chalcone derivatives with respect to their antileishmanial activity (active/inactive) on the basis of molecular descriptors. For this purpose, two techniques to select descriptors are employed, the Successive Projections Algorithm (SPA) and the Genetic Algorithm (GA). The selected descriptors are initially employed to build Linear Discriminant Analysis (LDA) models. An additional investigation is then carried out to determine whether the results can be improved by using a non-parametric classification technique (One Nearest Neighbour, 1NN). In a case study involving 100 chalcone derivatives, the 1NN models were found to provide better rates of correct classification than LDA, both in the training and test sets. The best result was achieved by a SPA-1NN model with six molecular descriptors, which provided correct classification rates of 97% and 84% for the training and test sets, respectively.

Original languageEnglish (US)
Pages (from-to)189-195
Number of pages7
JournalEuropean Journal of Pharmaceutical Sciences
Volume51
Issue number1
DOIs
StatePublished - Jan 1 2014

Fingerprint

Chalcone
Discriminant Analysis
Chalcones
Antiparasitic Agents
Quantitative Structure-Activity Relationship
Ketones
Nitric Oxide
Anti-Inflammatory Agents
Pharmacology

Keywords

  • Antileishmanial activity
  • Genetic Algorithm
  • Linear Discriminant Analysis
  • One Nearest Neighbour
  • Successive Projections Algorithm

ASJC Scopus subject areas

  • Pharmaceutical Science

Cite this

Binary classification of chalcone derivatives with LDA or KNN based on their antileishmanial activity and molecular descriptors selected using the Successive Projections Algorithm feature-selection technique. / Goodarzi, Mohammad; Saeys, Wouter; De Araujo, Mario Cesar Ugulino; Galvão, Roberto Kawakami Harrop; Vander Heyden, Yvan.

In: European Journal of Pharmaceutical Sciences, Vol. 51, No. 1, 01.01.2014, p. 189-195.

Research output: Contribution to journalArticle

@article{ae6c3db0553c4d13a601a5a6d9236852,
title = "Binary classification of chalcone derivatives with LDA or KNN based on their antileishmanial activity and molecular descriptors selected using the Successive Projections Algorithm feature-selection technique",
abstract = "Chalcones are naturally occurring aromatic ketones, which consist of an α-, β-unsaturated carbonyl system joining two aryl rings. These compounds are reported to exhibit several pharmacological activities, including antiparasitic, antibacterial, antifungal, anticancer, immunomodulatory, nitric oxide inhibition and anti-inflammatory effects. In the present work, a Quantitative Structure-Activity Relationship (QSAR) study is carried out to classify chalcone derivatives with respect to their antileishmanial activity (active/inactive) on the basis of molecular descriptors. For this purpose, two techniques to select descriptors are employed, the Successive Projections Algorithm (SPA) and the Genetic Algorithm (GA). The selected descriptors are initially employed to build Linear Discriminant Analysis (LDA) models. An additional investigation is then carried out to determine whether the results can be improved by using a non-parametric classification technique (One Nearest Neighbour, 1NN). In a case study involving 100 chalcone derivatives, the 1NN models were found to provide better rates of correct classification than LDA, both in the training and test sets. The best result was achieved by a SPA-1NN model with six molecular descriptors, which provided correct classification rates of 97{\%} and 84{\%} for the training and test sets, respectively.",
keywords = "Antileishmanial activity, Genetic Algorithm, Linear Discriminant Analysis, One Nearest Neighbour, Successive Projections Algorithm",
author = "Mohammad Goodarzi and Wouter Saeys and {De Araujo}, {Mario Cesar Ugulino} and Galv{\~a}o, {Roberto Kawakami Harrop} and {Vander Heyden}, Yvan",
year = "2014",
month = "1",
day = "1",
doi = "10.1016/j.ejps.2013.09.019",
language = "English (US)",
volume = "51",
pages = "189--195",
journal = "European Journal of Pharmaceutical Sciences",
issn = "0928-0987",
publisher = "Elsevier",
number = "1",

}

TY - JOUR

T1 - Binary classification of chalcone derivatives with LDA or KNN based on their antileishmanial activity and molecular descriptors selected using the Successive Projections Algorithm feature-selection technique

AU - Goodarzi, Mohammad

AU - Saeys, Wouter

AU - De Araujo, Mario Cesar Ugulino

AU - Galvão, Roberto Kawakami Harrop

AU - Vander Heyden, Yvan

PY - 2014/1/1

Y1 - 2014/1/1

N2 - Chalcones are naturally occurring aromatic ketones, which consist of an α-, β-unsaturated carbonyl system joining two aryl rings. These compounds are reported to exhibit several pharmacological activities, including antiparasitic, antibacterial, antifungal, anticancer, immunomodulatory, nitric oxide inhibition and anti-inflammatory effects. In the present work, a Quantitative Structure-Activity Relationship (QSAR) study is carried out to classify chalcone derivatives with respect to their antileishmanial activity (active/inactive) on the basis of molecular descriptors. For this purpose, two techniques to select descriptors are employed, the Successive Projections Algorithm (SPA) and the Genetic Algorithm (GA). The selected descriptors are initially employed to build Linear Discriminant Analysis (LDA) models. An additional investigation is then carried out to determine whether the results can be improved by using a non-parametric classification technique (One Nearest Neighbour, 1NN). In a case study involving 100 chalcone derivatives, the 1NN models were found to provide better rates of correct classification than LDA, both in the training and test sets. The best result was achieved by a SPA-1NN model with six molecular descriptors, which provided correct classification rates of 97% and 84% for the training and test sets, respectively.

AB - Chalcones are naturally occurring aromatic ketones, which consist of an α-, β-unsaturated carbonyl system joining two aryl rings. These compounds are reported to exhibit several pharmacological activities, including antiparasitic, antibacterial, antifungal, anticancer, immunomodulatory, nitric oxide inhibition and anti-inflammatory effects. In the present work, a Quantitative Structure-Activity Relationship (QSAR) study is carried out to classify chalcone derivatives with respect to their antileishmanial activity (active/inactive) on the basis of molecular descriptors. For this purpose, two techniques to select descriptors are employed, the Successive Projections Algorithm (SPA) and the Genetic Algorithm (GA). The selected descriptors are initially employed to build Linear Discriminant Analysis (LDA) models. An additional investigation is then carried out to determine whether the results can be improved by using a non-parametric classification technique (One Nearest Neighbour, 1NN). In a case study involving 100 chalcone derivatives, the 1NN models were found to provide better rates of correct classification than LDA, both in the training and test sets. The best result was achieved by a SPA-1NN model with six molecular descriptors, which provided correct classification rates of 97% and 84% for the training and test sets, respectively.

KW - Antileishmanial activity

KW - Genetic Algorithm

KW - Linear Discriminant Analysis

KW - One Nearest Neighbour

KW - Successive Projections Algorithm

UR - http://www.scopus.com/inward/record.url?scp=84885814075&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84885814075&partnerID=8YFLogxK

U2 - 10.1016/j.ejps.2013.09.019

DO - 10.1016/j.ejps.2013.09.019

M3 - Article

C2 - 24090733

AN - SCOPUS:84885814075

VL - 51

SP - 189

EP - 195

JO - European Journal of Pharmaceutical Sciences

JF - European Journal of Pharmaceutical Sciences

SN - 0928-0987

IS - 1

ER -