Use of artificial neural networks with Monte Carlo simulation applied to the protein folding problem / Uso de redes neurais artificiais na simulação Monte Carlo aplicado ao problema de dobramento de proteínas

AUTOR(ES)
DATA DE PUBLICAÇÃO

2006

RESUMO

This work proposes a new strategy to optimize the Monte Carlo method (MC) applied to the protein folding problem. This strategy is based on the information obtained from Artificial Neural Networks (ANNs), trained to predict the protein secondary structure. The work presents, initially, background knowledge about proteins and their structure. Follows an introduction to the MC method, Neural Networks and to the prediction of secondary structure using PHD/PROF programs. Then, a survey about tridimensional protein structure is presented. Other concepts,such as information gain in the context of hybrid systems, are also presented. Based on state-of-the art results, a new method is proposed using the predictions produced by the PROF program, available on-line and with a performance higher than 76% for secundary structure prediction, for the reduction of the MC search space. The MC method is presented with the secondary structure prediction based on ANNs (MC-RNA) and applied to four diferent proteins obtained from the list of target proteins in the CASP experiments. For these proteins, an improvement in performance is shown in relation to the conventional MC method. Additionaly to the MC method an to the new MC-RNA method, a validation method MC-DSSP was developed using real informations and a priori knowledge about the secondary structure. The method MC-DSSP was also applied to the four test proteins to demonstrate the influence of the quality in the secondary structure prediction on the tertiary structure prediction. In all tests with the three methods MC-DSSP, MC-RNA and MC, a higher score in terms of tertiary structure prediction was obtained with the MC-RNA method than with the MC method, for the same computer power. In the same way, the MC-DSSP method, which uses exact information about the secondary structure, reached better prediction for the tridimensinal prediction than the other methods, showing the importance of a good quality in the secondary structure for the prediction of the tertiary structure

ASSUNTO(S)

protein folding bioinformática ciencia da computacao redes neurais artificiais monte carlo monte carlo dobramento de proteínas artificial neural networks bioinformatics

ACESSO AO ARTIGO

Documentos Relacionados