Predicting Protein Secondary Structure Based on Compound Pyramid Model

Biological processes have produced the ultimate intelligent system, and now we are trying to understand biology by building intelligent systems. Protein Secondary structure prediction is essential for the tertiary structure modeling, and it is the one of the major challenge of bioinformatics. In this paper, we proposed a new type of intelligent system to predict the protein secondary structure, and it contain a Compound Pyramid Model (CPM) which is gradually enhanced, multi-layered. This model is composed of four independent coordination´s layers by intelligent interfaces, synthesizes several methods. The model penetrates the whole domain knowledge, and the effective attributes are chosen by Causal Cellular Automata, and the high pure structure database is constructed for training. An optimized accuracy (Q3) for the RS126 and CB513 dataset of 83.99% and 85.58%, respectively, could be obtained. And the CASP8´s sequences, the results are found to be superior to those produced by other methods, such as PSIPRED,SSPRO,SAM-T02,PHD Expert, PROF, JPRED, and so on. The result shows that our method has strong generalization ability.