This paper presents the application of special unsupervised neural networks (self-organizing maps) to different domains, as sleep apnea discovery, protein sequences analysis and tumor classification. An enhancement of the original algorithm, as well as the introduction of several hierachical...

In this paper, hidden Markov models (HMMs) are discussed in the context of molecular biological sequence analysis. The statistics relevant in the HMM approach are described in detail. An HMM based method is used to analyze two proteins that contain short protein repeats (SPRs). As a benchmark, a...

These report presents two methods for the identification of signal peptides and their cleavage sites. The first method is based on based neural networks and the second on hidden Markov models. The transmembrane protein topology can also be identified by a method based on hidden Markov models,...

We propose a new Markov switching model with time varying probabilities for the transitions. The novelty of our model is that the transition probabilities evolve over time by means of an observation driven model. The innovation of the time varying probability is generated by the score of the...