Abstract
BACKGROUND: In the past, large numbers of methods have been developed for predicting the secondary structure of proteins. Best of the author knowledge no method has been specifically developed for predicting the secondary structure of peptides. We analyzed the secondary structure of peptides and proteins; it was observed that the same peptide in protein adopts different secondary structures. Considering the wide application of peptides in the therapeutic market, we made attempt to develop a method called PEP2D for predicting the secondary structure of peptides. RESULTS: In this study, 3107 unique peptides have been used to train, test and evaluate peptide secondary structure prediction models. It was observed that regular secondary structure content (e.g., helix, beta-sheet) increased with length of peptides. Firstly, models based on various machine-learning techniques have been developed using binary profile of peptides and achieved maximum overall accuracy (Q3) 79.5%. The performance of models further improved from 79.5% to 83.5% using evolutionary information in the form of PSSM profile. We also evaluate the performance of protein secondary structure prediction method PSIPRED on our dataset and achieved maximum accuracy 76.9%; particularly poor (Q3 71.4%) for small peptides having a length less than 10 residues. Overall, PEP2D has a better prediction of beta-sheets (Q3 74%) and coil region (Q3 87%) of peptides as compare to PSIPRED (Q3 54.4% for beta-sheet and Q3 77.9% for coil). We also measure the performance of PSIPRED and PEP2D in terms of segment overlap (SOV); achieved 69.3 and 76.7 respectively. CONCLUSION: Our observations indicate that there is a need for developing a separate method for predicting the secondary structure of peptides. It was also observed that models based on PSSM profile perform poor on small peptides in comparison to long peptides. Based on our study, we developed a method for predicting the secondary structure of peptides. In order to provide service to the user, a webserver/standalone has been developed (https://webs.iiitd.edu.in/raghava/pep2d/).
