This research presents using Hidden Markov Models to resolve DNA basecalling problems.
This paper proposes Hidden Markov Models (HMMs) as an approach to the DNA basecalling problem. The authors model the state emission densities using Artificial Neural Networks, and provide a modified Baum-Welch re-estimation procedure to perform training. Moreover, the authors develop a method that exploits consensus sequences to label training data, thus minimizing the need for hand-labeling. The results demonstrate the potential of these models and suggest further research. The authors also perform a careful study of the basecalling errors and propose alternative HMM topologies that might further improve performance. The authors conclude by suggesting further research directions.
Similar Publications
- Smokeless Powder Residue Analysis by Capillary Electrophoresis
- Influence of Structural and Compositional Heterogeneities on Nanoscale Thermal Transport and Magnetization Dynamics
- Unveiling the Effect of Shape Anisotropy of Plasmonic Tungsten Oxide Nanostructures for Enhanced Electrocatalytic Hydrogen Evolution