Document Detail

A probabilistic model for secondary structure prediction from protein chemical shifts.
MedLine Citation:
PMID:  23292699     Owner:  NLM     Status:  Publisher    
Protein chemical shifts encode detailed structural information that is di_cult and computationally costly to describe at a fundamental level. Statistical and machine learning approaches have been used to infer correlations between chemical shifts and secondary structure from experimental chemical shifts. These methods range from simple statistics such as the chemical shift index to complex methods using neural networks. Notwithstanding their higher accuracy, more complex approaches tend to obscure the relationship between secondary structure and chemical shift and often involve many parameters that need to be trained. We present hidden Markov models (HMM) with Gaussian emission probabilities to model the dependence between protein chemical shifts and secondary structure. The continuous emission probabilities are modeled as conditional probabilities for a given amino acid and secondary structure type. Using these distributions as outputs of _rst and second order HMMs we achieve a prediction accuracy of 82.3%, which is competitive with existing methods for predicting secondary structure from protein chemical shifts. Incorporation of sequence-based secondary structure prediction into our HMM improves the prediction accuracy to 84.0%. Our _ndings suggest that an HMM with correlated Gaussian distributions conditioned on the secondary structure provide an adequate generative model of chemical shifts. Proteins 2012. © 2012 Wiley Periodicals, Inc.
Martin Mechelke; Michael Habeck
Related Documents :
23978849 - The effect of photosynthesis time scales on microalgae productivity.
2676569 - Floating norms as a means to describe individual skeletal patterns.
3382869 - The measurement of total filtration of diagnostic x-ray tubes.
24324539 - Correction: analysis of the proteinaceous components of the organic matrix of calcitic ...
24923709 - Review of collagen i hydrogels for bioengineered tissue microenvironments: characteriza...
23729869 - Coupled particulate and continuum model for nanoparticle targeted delivery.
23689869 - Cross-sensor iris recognition through kernel learning.
17187829 - Application of fuzzy-logic models for metabolic control analysis.
12626479 - Invited review: identifying new mouse models of cardiovascular disease: a review of hig...
Publication Detail:
Type:  JOURNAL ARTICLE     Date:  2013-1-5
Journal Detail:
Title:  Proteins     Volume:  -     ISSN:  1097-0134     ISO Abbreviation:  Proteins     Publication Date:  2013 Jan 
Date Detail:
Created Date:  2013-1-7     Completed Date:  -     Revised Date:  -    
Medline Journal Info:
Nlm Unique ID:  8700181     Medline TA:  Proteins     Country:  -    
Other Details:
Languages:  ENG     Pagination:  -     Citation Subset:  -    
Copyright Information:
Copyright © 2012 Wiley Periodicals, Inc.
Department of Protein Evolution, Max Planck Institute for Developmental Biology, Spemannstr. 35, 72076 Tüubingen, Germany.
Export Citation:
APA/MLA Format     Download EndNote     Download BibTex
MeSH Terms

From MEDLINE®/PubMed®, a database of the U.S. National Library of Medicine

Previous Document:  Patterns of physical activity participation across the cancer trajectory in colorectal cancer surviv...
Next Document:  Multicolor Hybrid Upconversion Nanoparticles and Their Improved Performance as Luminescence Temperat...