A statical algorithm for protein secondary structure prediction, using a specifically adapted neural network, is proposed; the only information needed for prediction is the primary structure of a protein. Since a neural net is often considered as the 'optimum' among the statistical algorithms in pattern recognition problems, with this neural net we think to get closer to 70% of correctly predicted protein secondary structure, which is often considered the limit for this kind of predictive algorithm.
Protein secondary structure prediction and neural networks
GIACOMINI, MAURO;RUGGIERO, CARMELINA;SACILE, ROBERTO
1991-01-01
Abstract
A statical algorithm for protein secondary structure prediction, using a specifically adapted neural network, is proposed; the only information needed for prediction is the primary structure of a protein. Since a neural net is often considered as the 'optimum' among the statistical algorithms in pattern recognition problems, with this neural net we think to get closer to 70% of correctly predicted protein secondary structure, which is often considered the limit for this kind of predictive algorithm.File in questo prodotto:
Non ci sono file associati a questo prodotto.
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.