Identification of hidden Markov models for ion channel currents .III. Bandlimited, sampled data

For pt.II. see ibid., vol.46, p.1916-29 (1998). Hidden Markov models (HMMs) have been used to model single channel currents as recorded with the patch clamp technique from living cells. Continuous time patch-clamp recordings are typically passed through an antialiasing filter and sampled before analysis. In this paper, an adaptation of the Baum-Welch weighted least squares (BW-WLS) algorithm called the H-noise algorithm is presented to estimate the HMM and noise model parameters from bandlimited, sampled data. The effects of the antialiasing filter and the correlated background noise are considered in a metastate or vector HMM framework. The "correlated emission probability", which plays a central role in the algorithm, is redefined to consider the noise correlation in successive filtered, sampled data points. The performance of the H-noise algorithm is demonstrated with simulated data.