Better prediction of protein cellular localization sites with the k nearest neighbors classifier

Proc Int Conf Intell Syst Mol Biol. 1997;5:147-52.

Abstract

We have compared four classifiers on the problem of predicting the cellular localization sites of proteins in yeast and E. coli. A set of sequence derived features, such as regions of high hydrophobicity, were used for each classifier. The methods compared were a structured probabilistic model specifically designed for the localization problem, the k nearest neighbors classifier, the binary decision tree classifier, and the naïve Bayes classifier. The result of tests using stratified cross validation shows the k nearest neighbors classifier to perform better than the other methods. In the case of yeast this difference was statistically significant using a cross-validated paired t test. The result is an accuracy of approximately 60% for 10 yeast classes and 86% for 8 E. coli classes. The best previously reported accuracies for these datasets were 55% and 81% respectively.

Publication types

  • Comparative Study
  • Research Support, Non-U.S. Gov't

MeSH terms

  • Algorithms*
  • Bacterial Proteins / chemistry
  • Bacterial Proteins / classification
  • Bacterial Proteins / metabolism
  • Bayes Theorem
  • Binding Sites
  • Databases, Factual
  • Decision Trees
  • Escherichia coli / metabolism
  • Evaluation Studies as Topic
  • Fungal Proteins / chemistry
  • Fungal Proteins / classification
  • Fungal Proteins / metabolism
  • Proteins / chemistry
  • Proteins / classification*
  • Proteins / metabolism*
  • Saccharomyces cerevisiae / metabolism
  • Sequence Alignment
  • Software
  • Subcellular Fractions / metabolism

Substances

  • Bacterial Proteins
  • Fungal Proteins
  • Proteins