Cargando…

Information-Theoretic Evaluation for Computational Biomedical Ontologies

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...

Descripción completa

Detalles Bibliográficos
Clasificación:Libro Electrónico
Autor principal: Clark, Wyatt Travis (Autor)
Autor Corporativo: SpringerLink (Online service)
Formato: Electrónico eBook
Idioma:Inglés
Publicado: Cham : Springer International Publishing : Imprint: Springer, 2014.
Edición:1st ed. 2014.
Colección:SpringerBriefs in Computer Science,
Temas:
Acceso en línea:Texto Completo

MARC

LEADER 00000nam a22000005i 4500
001 978-3-319-04138-4
003 DE-He213
005 20220126094416.0
007 cr nn 008mamaa
008 140109s2014 sz | s |||| 0|eng d
020 |a 9783319041384  |9 978-3-319-04138-4 
024 7 |a 10.1007/978-3-319-04138-4  |2 doi 
050 4 |a QH324.2-324.25 
072 7 |a PS  |2 bicssc 
072 7 |a UY  |2 bicssc 
072 7 |a COM014000  |2 bisacsh 
072 7 |a PSAX  |2 thema 
082 0 4 |a 570.285  |2 23 
082 0 4 |a 570.113  |2 23 
100 1 |a Clark, Wyatt Travis.  |e author.  |4 aut  |4 http://id.loc.gov/vocabulary/relators/aut 
245 1 0 |a Information-Theoretic Evaluation for Computational Biomedical Ontologies  |h [electronic resource] /  |c by Wyatt Travis Clark. 
250 |a 1st ed. 2014. 
264 1 |a Cham :  |b Springer International Publishing :  |b Imprint: Springer,  |c 2014. 
300 |a VII, 46 p. 12 illus., 6 illus. in color.  |b online resource. 
336 |a text  |b txt  |2 rdacontent 
337 |a computer  |b c  |2 rdamedia 
338 |a online resource  |b cr  |2 rdacarrier 
347 |a text file  |b PDF  |2 rda 
490 1 |a SpringerBriefs in Computer Science,  |x 2191-5776 
505 0 |a Introduction -- Methods -- Experiments and Results -- Discussion. 
520 |a 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. 
650 0 |a Bioinformatics. 
650 0 |a Algorithms. 
650 0 |a Medical genetics. 
650 0 |a Pattern recognition systems. 
650 0 |a Medical informatics. 
650 1 4 |a Computational and Systems Biology. 
650 2 4 |a Algorithms. 
650 2 4 |a Medical Genetics. 
650 2 4 |a Automated Pattern Recognition. 
650 2 4 |a Health Informatics. 
710 2 |a SpringerLink (Online service) 
773 0 |t Springer Nature eBook 
776 0 8 |i Printed edition:  |z 9783319041377 
776 0 8 |i Printed edition:  |z 9783319041391 
830 0 |a SpringerBriefs in Computer Science,  |x 2191-5776 
856 4 0 |u https://doi.uam.elogim.com/10.1007/978-3-319-04138-4  |z Texto Completo 
912 |a ZDB-2-SCS 
912 |a ZDB-2-SXCS 
950 |a Computer Science (SpringerNature-11645) 
950 |a Computer Science (R0) (SpringerNature-43710)