Rational drug design for anti-cancer chemotherapy: Multi-target QSAR models for the in silico discovery of anti-colorectal cancer agents

Alejandro Speck-Planche, Valeria V. Kleandrova, Feng Luan, M. Natália D.S. Cordeiro

Producción científica: Contribución a una revistaArtículorevisión exhaustiva

99 Citas (Scopus)

Resumen

The discovery of new and more potent anti-cancer agents constitutes one of the most active fields of research in chemotherapy. Colorectal cancer (CRC) is one of the most studied cancers because of its high prevalence and number of deaths. In the current pharmaceutical design of more efficient anti-CRC drugs, the use of methodologies based on Chemoinformatics has played a decisive role, including Quantitative-Structure-Activity Relationship (QSAR) techniques. However, until now, there is no methodology able to predict anti-CRC activity of compounds against more than one CRC cell line, which should constitute the principal goal. In an attempt to overcome this problem we develop here the first multi-target (mt) approach for the virtual screening and rational in silico discovery of anti-CRC agents against ten cell lines. Here, two mt-QSAR classification models were constructed using a large and heterogeneous database of compounds. The first model was based on linear discriminant analysis (mt-QSAR-LDA) employing fragment-based descriptors while the second model was obtained using artificial neural networks (mt-QSAR-ANN) with global 2D descriptors. Both models correctly classified more than 90% of active and inactive compounds in training and prediction sets. Some fragments were extracted from the molecules and their contributions to anti-CRC activity were calculated using mt-QSAR-LDA model. Several fragments were identified as potential substructural features responsible for the anti-CRC activity and new molecules designed from those fragments with positive contributions were suggested and correctly predicted by the two models as possible potent and versatile anti-CRC agents.

Idioma originalInglés
Páginas (desde-hasta)4848-4855
Número de páginas8
PublicaciónBioorganic and Medicinal Chemistry
Volumen20
N.º15
DOI
EstadoPublicada - 1 ago. 2012
Publicado de forma externa

Huella

Profundice en los temas de investigación de 'Rational drug design for anti-cancer chemotherapy: Multi-target QSAR models for the in silico discovery of anti-colorectal cancer agents'. En conjunto forman una huella única.

Citar esto