Chemoinformatics for rational discovery of safe antibacterial drugs: Simultaneous predictions of biological activity against streptococci and toxicological profiles in laboratory animals

• Type: Article in International Scientific Journal
• Date: 2013

Authors

Alejandro Speck Planche (Author) Other; Valeria V Kleandrova (Author) Other; Cordeiro, MNDS (Author) FCUP

Journal

Title: Bioorganic and Medicinal Chemistry

Vol. 21

Pages: 2727-2732

ISSN: 0968-0896

Publisher: Elsevier

Indexing

ISI Web of Knowledge - 48 Citations

Scopus - 54 Citations

Scientific classification

FOS: Natural sciences > Chemical sciences

Other information

Authenticus ID: P-005-0QT

DOI: 10.1016/j.bmc.2013.03.015

Abstract (EN): Streptococci are a group of Gram-positive bacteria which are responsible for causing many diverse diseases in humans and other animals worldwide. The high prevalence of resistance of these bacteria to current antibacterial drugs is an alarming problem for the scientific community. The battle against streptococci by using antimicrobial chemotherapies will depend on the design of new chemicals with high inhibitory activity, having also as low toxicity as possible. Multi-target approaches based on quantitative-structure activity relationships (mt-QSAR) have played a very important role, providing a better knowledge about the molecular patterns related with the appearance of different pharmacological profiles including antimicrobial activity. Until now, almost all mt-QSAR models have considered the study of biological activity or toxicity separately. In the present study, we develop by the first time, a unified multitasking (mtk) QSAR model for the simultaneous prediction of anti-streptococci activity and toxic effects against biological models like Mus musculus and Rattus norvegicus. The mtk-QSAR model was created by using artificial neural networks (ANN) analysis for the classification of compounds as positive (high biological activity and/or low toxicity) or negative (otherwise) under diverse sets of experimental conditions. Our mtk-QSAR model, correctly classified more than 97% of the cases in the whole database (more than 11,500 cases), serving as a promising tool for the virtual screening of potent and safe anti-streptococci drugs.

Language: English

Type (Professor's evaluation): Scientific

No. of pages: 6