InformationTheoretic Evaluation for Computational Biomedical Ontologies

InformationTheoretic Evaluation for Computational Biomedical Ontologies

by Clark

Produs indisponibil momentan. Pentru comenzi va rugam trimiteti mail la adresa depozit2@prior.ro sau contactati-ne la numarul de telefon 021 210 89 28 Vedeti mai jos alte produse similare disponibile.

Completati formularul de mai jos pentru a fi anuntat cand acest produs revine pe stoc.

Numele tau:
Email:
Cod produs/ISBN: 9783319041377

Disponibilitate: Acest produs nu este momentan in stoc

Autor: Clark

Editura: Springer

Limba: Engleza

Nr. pagini: 46

Coperta: Paperback

Dimensiuni: 22.6 x 14.7 x 0.8 cm

An aparitie: 2014

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.
ebookshop
An aparitie 2014
Autor Clark
Dimensiuni 22.6 x 14.7 x 0.8 cm
Editura Springer
Format Paperback
Limba Engleza
Nr pag 46

Clientii ebookshop.ro nu au adaugat inca opinii pentru acest produs. Fii primul care adauga o parere, folosind formularul de mai jos.

Spune-ne parerea ta despre acest produs

Nota acordata produsului:

Notificare prin e-mail cand apar comentarii noi
Scroll