Information-Theoretic Evaluation for Computational Biomedical Ontologies

Nonfiction, Computers, Advanced Computing, Computer Science, Programming, Science & Nature, Science
Cover of the book Information-Theoretic Evaluation for Computational Biomedical Ontologies by Wyatt Travis Clark, Springer International Publishing
View on Amazon View on AbeBooks View on Kobo View on B.Depository View on eBay View on Walmart
Author: Wyatt Travis Clark ISBN: 9783319041384
Publisher: Springer International Publishing Publication: January 9, 2014
Imprint: Springer Language: English
Author: Wyatt Travis Clark
ISBN: 9783319041384
Publisher: Springer International Publishing
Publication: January 9, 2014
Imprint: Springer
Language: English

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.

View on Amazon View on AbeBooks View on Kobo View on B.Depository View on eBay View on Walmart

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.

More books from Springer International Publishing

Cover of the book Reforming the Art of Living by Wyatt Travis Clark
Cover of the book Rethinking Media Development through Evaluation by Wyatt Travis Clark
Cover of the book Advances in Geometry and Lie Algebras from Supergravity by Wyatt Travis Clark
Cover of the book Voting Experiments by Wyatt Travis Clark
Cover of the book Lipids in Protein Misfolding by Wyatt Travis Clark
Cover of the book Information Theoretic Security by Wyatt Travis Clark
Cover of the book From Robot to Human Grasping Simulation by Wyatt Travis Clark
Cover of the book Optimum Design and Manufacture of Wood Products by Wyatt Travis Clark
Cover of the book Textbook of Pediatric Gastroenterology, Hepatology and Nutrition by Wyatt Travis Clark
Cover of the book Advances in Conceptual Modeling by Wyatt Travis Clark
Cover of the book High-Mountain Atmospheric Research by Wyatt Travis Clark
Cover of the book Surgery of the Spine and Spinal Cord by Wyatt Travis Clark
Cover of the book Separation Hydrometallurgy of Rare Earth Elements by Wyatt Travis Clark
Cover of the book Excel 2013 for Health Services Management Statistics by Wyatt Travis Clark
Cover of the book Cinematic Philosophy by Wyatt Travis Clark
We use our own "cookies" and third party cookies to improve services and to see statistical information. By using this website, you agree to our Privacy Policy