Computer Aided Multi Parameter Antigen Design: Impact of Synthetic Peptide Vaccines from Soybean Mosaic Virus

Abstract

The potyvirus coat protein (CP) is involved in aphid transmission, cell-to-cell movement and virus assembly, not only by binding to viral RNA, but also by self-interaction or interactions with other factors. Peptide fragments of genome coatprotein can be used to select nonamers for use in rational vaccine design and to increase the understanding of roles of the immune system in infectious diseases. For development of MHC binder prediction method, an elegant machine learning technique support vector machine (SVM) has been used. SVM has been trained on the binary input of single amino acid sequence. The MHC peptide binding is predicted using neural networks trained on C terminals of known epitopes. SVM has been trained on the binary input of single amino acid sequence. The average accuracy of SVM based method for 42 alleles is ~80%. In this analysis, we found the MHCII-IAb peptide regions, 880- YKTAKDLLT, 2577- PILAPDGTI, 1438- KVTKVDGRT, 2647- TWLYDTLST, (optimal score is 1.506); MHCII-IAd peptide regions 2079-GSFIITNGH, 1911-FIHLYGVEP, 1306-GSSNIVVMT, 695-AAYMLTVFH, (optimal score is 0.893); MHCII-IAg7 peptide regions 2962-SDAAEAYIE, 2891-WYNAVKDEY, 1544-FIATEAAFL, 1123- KIVAFMALL (optimal score is 1.915); MHCII- RT1.B peptide regions 1114-KTATQLQLE, 413-STAENASLQ, 162-TKERRATSQ, 1112-QAKTATQLQ, (optimal score is 1.807); which are represent predicted binders from genome polyprotein. Computer aided multi parameter antigen design was used to developed synthetic peptide vaccines from Soybean mosaic virus.