Enabling the Discovery and Virtual Screening of Potent and Safe Antimicrobial Peptides. Simultaneous Prediction of Antibacterial Activity and Cytotoxicity

Antimicrobial peptides
(AMPs) represent promising alternatives
to fight against bacterial pathogens. However, cellular toxicity remains
one of the main concerns in the early development of peptide-based
drugs. This work introduces the first multitasking (mtk) computational
model focused on performing simultaneous predictions of antibacterial
activities, and cytotoxicities of peptides. The model was created
from a data set containing 3592 cases, and it displayed accuracy higher
than 96% for classifying/predicting peptides in both training and
prediction (test) sets. The technique known as alanine scanning was
computationally applied to illustrate the calculation of the quantitative
contributions of the amino acids (in their respective positions of
the sequence) to the biological effects of a defined peptide. A small
library formed by 10 peptides was generated, where peptides were designed
by considering the interpretations of the different descriptors in
the mtk-computational model. All the peptides were predicted to exhibit
high antibacterial activities against multiple bacterial strains,
and low cytotoxicity against various cell types. The present mtk-computational
model can be considered a very useful tool to support high throughput
research for the discovery of potent and safe AMPs.