Desenvolvimento de modelo multidimensional de predição de peptídeos antimicrobianos utilizando um sistema de inferência neuro-fuzzy adaptativo (ANFIS)

AUTOR(ES)
FONTE

IBICT - Instituto Brasileiro de Informação em Ciência e Tecnologia

DATA DE PUBLICAÇÃO

26/07/2012

RESUMO

Antimicrobial peptides (AMPs) are defense molecules widely distributed and represent a promising alternative for solving the problem of antibiotic resistance. Nevertheless, the experimental time needed to screen putative AMPs makes computational simulations based on peptide sequence analysis and/or molecular modeling extremely attractive. Artificial intelligence methods acting as simulation and prediction tools are of great importance in helping to efficiently discover and further novel AMPs design. Hitherto were not found prediction methods using as input information qualitative data from protein primary, secondary and tertiary structures altogether. Furthermore none of the main current prediction methods employ a neuro-fuzzy system as prediction tool. In the present study, state-of-the-art published outcomes using different prediction methods and databases were compared to an Adaptive Neuro-Fuzzy Inference System (ANFIS) model that uses peptide multidimensional information such as primary sequence, physicochemical characteristics and structural characteristics. Data from our study show that ANFIS obtained a global accuracy of 99.5% and a Mathews Correlation Coefficient (MCC) of 0.989, which proved it to be an efficient model for pattern recognition in antimicrobial peptide prediction. Moreover, a lower number of input parameters were needed for the ANFIS model, improving the speed and precision of prediction. In summary, due to the fuzzy nature of AMP structural and physicochemical properties, the ANFIS approach presented here can provide an efficient solution for screening putative AMP sequences and for exploration of properties characteristic of AMPs.

ASSUNTO(S)

sistemas difusos inteligência artificial biologia computacional genetica biotecnologia

ACESSO AO ARTIGO

Documentos Relacionados