Prediction of the Risk Types of Human Papillomaviruses by Support Vector Machines

Abstract. Infection by high-risk human papillomaviruses (HPVs) is associated with the development of cervical cancers. Classification of risk types is important to understand the mechanisms in infection and to develop novel instruments for medical examination such as DNA microarrays. In this paper, we classify the risk type of HPVs by using the protein sequences. Our approach is based on the hidden Markov model and the Support Vector Machines. The former searches informative subsequence positions and the latter computes efficiently to classify protein sequences. In the experiments, the proposed classifier was compared with previous methods in accuracy and F-cost, also the prediction result of four unknown types is presented.

• Type: Conference
• Year: 2004
• Where: PRICAI
• Authors: Je-Gun Joung, Sok June Oh, Byoung-Tak Zhang
• Keywords: Artificial Intelligence, Hidden Markov Model, PRICAI 2004, Protein Sequences, Risk Type