en
2004
2004-01-01
426-437
The Most Probable Labeling Problem in HMMs and Its Application to Bioinformatics
chapters
2019-04-16T08:26
https://link.springer.com/10.1007%2F978-3-540-30219-3_36
chapter
Hidden Markov models (HMMs) are often used for biological sequence annotation. Each sequence element is represented by states with the same label. A sequence should be annotated with the labeling of highest probability. Computing this most probable labeling was shown NP-hard by Lyngsø and Pedersen [9]. We improve this result by proving the problem NP-hard for a fixed HMM. High probability labelings are often found by heuristics, such as taking the labeling corresponding to the most probable state path. We introduce an efficient algorithm that computes the most probable labeling for a wide class of HMMs, including models previously used for transmembrane protein topology prediction and coding region detection.
true
https://scigraph.springernature.com/explorer/license/
Brown
Daniel G.
Brejová
Broňa
Berlin, Heidelberg
Springer Berlin Heidelberg
Tomáš
Vinař
Junhyong
Kim
01e70e0e0ea4c0b5480a9daa993a8a83623aba1b5d8c0e2bd6028d3d20c7951f
readcube_id
Jonassen
Inge
10.1007/978-3-540-30219-3_36
doi
978-3-540-23018-2
978-3-540-30219-3
Algorithms in Bioinformatics
Springer Nature - SN SciGraph project
Information and Computing Sciences
School of Computer Science, University of Waterloo, N2L 3G1, Waterloo, ON, Canada
University of Waterloo
pub.1000399524
dimensions_id
Computation Theory and Mathematics