Integrating DNA sequence features for more accurate prediction of replication origins in some double-stranded DNA viral genomes

Abstract

Replication origins are considered important sites for understanding the molecular mechanisms involved in DNA replication. The aim of this study was to integrate DNA sequence features for more accurate prediction of replication origins in some double-stranded DNA viral genomes. Several sequence features, which are related to replication origins, were explored and quantified according to some score schemes. Then generalized additive models (GAM) with various covariates were built up, which were fitted by window scores of sequence features in herpesvirus and caudovirus genomes with known replication origins. The best model was chosen by AUC criterion and stepwise model selection procedure, and cross-validation method was employed to assess the prediction performance of the model. The prediction accuracy of GAM approach surpassed that of existing computational approaches. The GAM approach appears promising to identify replication origins in herpesviruses and caudoviruses.