A multi-level approach to SCOP fold recognition


Conference Paper

The classification of proteins based on their structure can play an important role in the deduction or discovery of protein function. However, the relatively low number of solved protein structures and the unknown relationship between structure and sequence requires an alternative method of representation for classification to be effective. Further-more, the large number of potential folds causes problems for many classification strategies, increasing the likelihood that the classifier will reach a local optima while trying to distinguish between all of the possible structural categories. Here we present a hierarchical strategy for structural classification that first partitions proteins based on their SCOP class before attempting to assign a protein fold. Using a well-known dataset derived from the 27 most-populated SCOP folds and several sequence-based descriptor properties as input features, we test a number of classification methods, including Naïve Bayes and Boosted C4.5. Our strategy achieves an average fold recognition of 74%, which is significantly higher than the 56-60% previously reported in the literature, indicating the effectiveness of a multi-level approach. © 2005 IEEE.

Full Text

Duke Authors

Cited Authors

  • Marsolo, K; Parthasarathy, S; Ding, C

Published Date

  • December 1, 2005

Published In

  • Proceedings Bibe 2005: 5th Ieee Symposium on Bioinformatics and Bioengineering

Volume / Issue

  • 2005 /

Start / End Page

  • 57 - 64

International Standard Book Number 10 (ISBN-10)

  • 0769524761

International Standard Book Number 13 (ISBN-13)

  • 9780769524764

Digital Object Identifier (DOI)

  • 10.1109/BIBE.2005.5

Citation Source

  • Scopus