Applications of Bioinformatics Databases to Predict the Secondary Structure

A computing engine, innovative structure prediction parameters (ISPP) has been developed using Python programming. The proposed computing engine has several utilities to enable structural biologists to predict the secondary structural elements from amino acid sequence using Bioinformatics Databases (25% threshold of 3693 non-homologous proteins). Information about the secondary structure of a protein sequence can greatly assist biologists in the generation and testing of hypotheses, as well as design of experiments. The sequential information of proteins has been increasing many folds than their three-dimensional counterpart. In this paper, structure prediction parameters using chi square value with respect to a-helix, B-strand and random structures were generated for the 20 amino acid singlets, 400 amino acid doublets and 8000 amino acid triplets. An innovative method, ISPBD (Innovative Structure Prediction using Bioinformatics Databases), was developed to predict the secondary structure of the proteins from amino acid sequences using the generated structure prediction parameters. The result clearly indicates that the average value of the percentage of prediction accuracy for a-helix by ISPBD, SSPDP, NNPREDICT, DSC, NNSSP and PHD methods was found to be 61%, 57%, 44%, 55%, 59% and 67%. The average percentage value of prediction for B-strand is 70%, 69%, 21% 34%, 56% and 53% respectively by ISPBD, SSPDP, NNPREDICT, DSC, NNSSP and PHD methods. This clearly indicates that for helical prediction my method (ISPBD) has comparable prediction accuracy as that of SSPDP,PHD method but much better prediction than DSC, NNSSP and NNPREDICT. The method (ISPBD) can be used as a candidature for secondary structure prediction from amino acid sequence.