The Highest Expected Reward Decoding for HMMs with Application to Recombination Detection

Abstract. Hidden Markov models are traditionally decoded by the Viterbi algorithm which finds the highest probability state path in the model. In recent years, several limitations of the Viterbi decoding have been demonstrated, and new algorithms have been developed to address them (Kall et al., 2005; Brejova et al., 2007; Gross et al., 2007; Brown and Truszkowski, 2010). In this paper, we propose a new efficient highest expected reward decoding algorithm (HERD) that allows for uncertainty in boundaries of individual sequence features. We demonstrate usefulness of our approach on jumping HMMs for recombination detection in viral genomes.

• Type: Journal
• Year: 2010
• Where: CORR
• Authors: Michal Nánási, Tomás Vinar, Brona Brejová
• Keywords: CORR 2010, Education, Et Al, Gross Et Al, Hidden Markov Models