Abstract
BackgroundHidden Markov Models (HMMs) provide an excellent means for structure identification and feature extraction on stochastic sequential data. An HMM-with-Duration (HMMwD) is an HMM that can also exactly model the hidden-label length (recurrence) distributions – while the regular HMM will impose a best-fit geometric distribution in its modeling/representation.ResultsA Novel, Fast, HMM-with-Duration (HMMwD) Implementation is presented, and experimental results are shown that demonstrate its performance on two-state synthetic data designed to model Nanopore Detector Data. The HMMwD experimental results are compared to (i) the ideal model and to (ii) the conventional HMM. Its accuracy is clearly an improvement over the standard HMM, and matches that of the ideal solution in many cases where the standard HMM does not. Computationally, the new HMMwD has all the speed advantages of the conventional (simpler) HMM implementation. In preliminary work shown here, HMM feature extraction is then used to establish the first pattern recognition-informed (PRI) sampling control of a Nanopore Detector Device (on a "live" data-stream).ConclusionThe improved accuracy of the new HMMwD implementation, at the same order of computational cost as the standard HMM, is an important augmentation for applications in gene structure identification and channel current analysis, especially PRI sampling control, for example, where speed is essential. The PRI experiment was designed to inherit the high accuracy of the well characterized and distinctive blockades of the DNA hairpin molecules used as controls (or blockade "test-probes"). For this test set, the accuracy inherited is 99.9%.
Highlights
It appears possible to obtain kinetic features directly from the channel blockade signals obtained during the capture of certain molecules in a nanopore detector, shown in Fig. 1, where individual blockade levels appear to correlate withBMC Bioinformatics 2007, 8(Suppl 7):S19 http://www.biomedcentral.com/1471-2105/8/S7/S19 binding or conformational states of the molecule [1,2,3]
Hidden Markov Models (HMMs) with Duration experimental tests Results for our new, implicit HMMwD, are presented in Figure 7 and in the figures in Additional Files 1–3, along with the comparative results from an explicit HMMwD that is used for comparative analysis
The explicit two-state HMMwD has 2n states, where n is the number of dwell bins in the quantization of the dwell-time distribution
Summary
It appears possible to obtain kinetic features directly from the channel blockade signals obtained during the capture of certain molecules in a nanopore detector, shown in Fig. 1 (see further details on the Detector in the Background), where individual blockade levels appear to correlate with (page number not for citation purposes)BMC Bioinformatics 2007, 8(Suppl 7):S19 http://www.biomedcentral.com/1471-2105/8/S7/S19 binding or conformational states of the molecule [1,2,3]. In [9,10,11,12,13], the nanopore detector was used to observe the conformational kinetics of the end regions of individual DNA hairpins (see Fig. 1, Lower Panel). DsDNA is too large to translocate, about ten base-pairs at one end can still be drawn into the large cisside vestibule This permits very sensitive experiments since the ends of "captured" dsDNA molecules can be observed for extensive periods of time to resolve features, allowing highly accurate classification of the captured end of dsDNA molecules [1,2,3,9,10,11,12,13]. For other references on Nanopore Detectors see the review of Nanopore Detectors presented in [14]; early work involving alpha-Hemolysin Nanopore Detectors can be found in [1,2,3,9,10,11,15,16,17,18,19,20,21,22,23,24,25]; rapidly growing research endeavors on Nanopore Detectors based on solid-state and other synthetic platforms can be found in [26,27,28,29,30,31,32,33,34,35,36]
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have