MRFy: Remote Homology Detection for Beta-Structural Proteins Using Markov Random Fields and Stochastic Search

Author

Daniels, Noah M. ; Gallant, Andrew ; Ramsey, Norman ; Cowen, Lenore J.

Author_Institution

Math. Dept. & Comput. Sci. & Artificial Intell. Lab., Massachusetts Inst. of Technol., Cambridge, MA, USA

Volume

12

Issue

1

fYear

2015

fDate

Jan.-Feb. 1 2015

Firstpage

4

Lastpage

16

Abstract

We introduce MRFy, a tool for protein remote homology detection that captures beta-strand dependencies in the Markov random field. Over a set of 11 SCOP beta-structural superfamilies, MRFy shows a 14 percent improvement in mean Area Under the Curve for the motif recognition problem as compared to HMMER, 25 percent improvement as compared to RAPTOR, 14 percent improvement as compared to HHPred, and a 18 percent improvement as compared to CNFPred and RaptorX. MRFy was implemented in the Haskell functional programming language, and parallelizes well on multi-core systems. MRFy is available, as source code as well as an executable, from http://mrfy.cs.tufts.edu/.

Keywords

Markov processes; bioinformatics; functional languages; functional programming; molecular biophysics; molecular configurations; proteins; source code (software); CNFPred; HHPred; HMMER; Haskell functional programming language; MRFy; Markov random fields; RAPTOR; RaptorX; SCOP beta-structural superfamilies; area under-the-curve; beta-strand dependencies; beta-structural proteins; motif recognition problem; multicore systems; protein remote homology detection; remote homology detection; source code; stochastic search; Computational modeling; Hidden Markov models; Markov processes; Search problems; Simulated annealing; Viterbi algorithm; Protein structure prediction; remote homology detection; structural bioinformatics;

fLanguage

English

Journal_Title

Computational Biology and Bioinformatics, IEEE/ACM Transactions on

Publisher

ieee

ISSN

1545-5963

Type

jour

DOI

10.1109/TCBB.2014.2344682

Filename

6868971