A new approach using geometric moments of distance matrix image for risk type prediction of human papillomaviruses

摘要

High-risk types of human papillomaviruses (HPVs) cause cervical cancer, and the second most common tumor in women worldwide, and the HPV E6 protein is one of two viral oncoproteins that is expressed in virtually all HPV-positive cancers. Therefore, how can we identify whether it is a risk type of HPVs by means of E6 properties is very useful and necessary to the diagnosis and the remedy of cervical cancer. Using the pseudo amino acid (PseAA) composition to represent the sample of a protein can incorporate a considerable amount of sequence pattern information so as to improve the prediction quality for the classification of risk type. In this paper, based on the characters of hydrophobicity, hydrophilicity, side-chain mass, we present a novel approach — protein distance matrix image(DMI) to classify HPV risk types from E6 protein sequences. Based on the protein DMI, two geometric moments were extracted from each of the protein sequences concerned are adopted for its PseAA. It was demonstrated thru the jackknife cross-validation test that the overall success rate are 100%. The results showed that bioinformatics based on theoretical approaches can direct and simplify experimental studies.