Protein & Peptide Letters

Prof. Ben M. Dunn  
Department of Biochemistry and Molecular Biology
University of Florida
College of Medicine
P.O. Box 100245
Gainesville, FL
USA
Email: bdunn@ufl.edu

Back

Function Prediction of Hypothetical Proteins Without Sequence Similarity to Proteins of Known Function (SUPPLEMENTARY MATERIALS)

Author(s): S. Kannan, A. M. Hauth and G. Burger

Affiliation: Center Robert Cedergren for Bioinformatics and Genomics, Departement de Biochimie, Universite de Montreal, 2900 Edouard-Montpetit, Montreal, Quebec, H3T 1J4, Canada.

Keywords: Ab initio protein function prediction, sequence-similarity-free, machine learning, decision trees, mitochondrionencoded hypothetical proteins, domain-specific validation

Abstract:

Function prediction by sequence-similarity based methods identifies only ∼50% of the proteins deduced from newly sequenced genomes. We have developed an approach to annotate the ‘leftover proteins’ i.e., those which cannot be assigned function using sequence similarity. Our method (MOPS) is pan-taxonomic, predicting fine-grained molecular function (rather than a broad functional category) with high performance. In addition, we developed a validation scheme that assesses predictions using domain-specific knowledge.

Reprint ePrint Rights & PermissionsPrintExport

Article Details

VOLUME: 15
ISSUE: 10
Page: [1107 - 1116]
Pages: 10
DOI: 10.2174/092986608786071085