Pub. Date:
Springer International Publishing
Information-Theoretic Evaluation for Computational Biomedical Ontologies

Information-Theoretic Evaluation for Computational Biomedical Ontologies

by Wyatt Travis Clark


Current price is , Original price is $54.99. You

Temporarily Out of Stock Online

Please check back later for updated availability.

5 New & Used Starting at $9.98


The development of effective methods for the prediction of ontological annotations is an important goal in computational biology, yet evaluating their performance is difficult due to problems caused by the structure of biomedical ontologies and incomplete annotations of genes. This work proposes an information-theoretic framework to evaluate the performance of computational protein function prediction. A Bayesian network is used, structured according to the underlying ontology, to model the prior probability of a protein's function. The concepts of misinformation and remaining uncertainty are then defined, that can be seen as analogs of precision and recall. Finally, semantic distance is proposed as a single statistic for ranking classification models. The approach is evaluated by analyzing three protein function predictors of gene ontology terms. The work addresses several weaknesses of current metrics, and provides valuable insights into the performance of protein function prediction tools.

Product Details

ISBN-13: 9783319041377
Publisher: Springer International Publishing
Publication date: 01/10/2014
Series: SpringerBriefs in Computer Science
Edition description: 2014
Pages: 46
Product dimensions: 6.10(w) x 9.25(h) x 0.01(d)

Table of Contents



Experiments and Results


Customer Reviews

Most Helpful Customer Reviews

See All Customer Reviews