In this paper, we illustrate a system aimed at predicting protein secondary structures. Our proposal falls in the category of multiple experts, a machine learning technique that –under the assumption of absent or negative correlation in experts’ errors– may outperform monolithic classifier systems. The prediction activity results from the interaction of a population of experts, each integrating genetic and neural technologies. Roughly speaking, an expert of this kind embodies a genetic classifier designed to control the activation of a feedforward artificial neural network. Genetic and neural components (i.e., guard and embedded predictor, respectively) are devoted to perform different tasks and are supplied with different information: Each guard is aimed at (soft-) partitioning the input space, insomuch assuring both the diversity and the specialization of the corresponding embedded predictor, which in turn is devoted to perform the actual prediction. Guards deal with inputs that encode information strictly related with relevant domain knowledge, whereas embedded predictors process other relevant inputs, each consisting of a limited window of residues. To investigate the performance of the proposed approach, a system has been implemented and tested on the RS126 set of proteins. Experimental results point to the potential of the approach.
Weitere Kapitel dieses Buchs durch Wischen aufrufen
- A Multi-agent System for Protein Secondary Structure Prediction
- Springer Berlin Heidelberg