000 02931nam a22005535i 4500
001 978-3-319-04138-4
003 DE-He213
005 20200421112226.0
007 cr nn 008mamaa
008 140109s2014 gw | s |||| 0|eng d
020 _a9783319041384
_9978-3-319-04138-4
024 7 _a10.1007/978-3-319-04138-4
_2doi
050 4 _aQH324.2-324.25
072 7 _aPSA
_2bicssc
072 7 _aUB
_2bicssc
072 7 _aCOM014000
_2bisacsh
082 0 4 _a570.285
_223
100 1 _aClark, Wyatt Travis.
_eauthor.
245 1 0 _aInformation-Theoretic Evaluation for Computational Biomedical Ontologies
_h[electronic resource] /
_cby Wyatt Travis Clark.
264 1 _aCham :
_bSpringer International Publishing :
_bImprint: Springer,
_c2014.
300 _aVII, 46 p. 12 illus., 6 illus. in color.
_bonline resource.
336 _atext
_btxt
_2rdacontent
337 _acomputer
_bc
_2rdamedia
338 _aonline resource
_bcr
_2rdacarrier
347 _atext file
_bPDF
_2rda
490 1 _aSpringerBriefs in Computer Science,
_x2191-5768
505 0 _aIntroduction -- Methods -- Experiments and Results -- Discussion.
520 _aThe 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 _aComputer science.
650 0 _aHuman genetics.
650 0 _aHealth informatics.
650 0 _aAlgorithms.
650 0 _aPattern recognition.
650 0 _aBioinformatics.
650 1 4 _aComputer Science.
650 2 4 _aComputational Biology/Bioinformatics.
650 2 4 _aAlgorithm Analysis and Problem Complexity.
650 2 4 _aHuman Genetics.
650 2 4 _aPattern Recognition.
650 2 4 _aHealth Informatics.
710 2 _aSpringerLink (Online service)
773 0 _tSpringer eBooks
776 0 8 _iPrinted edition:
_z9783319041377
830 0 _aSpringerBriefs in Computer Science,
_x2191-5768
856 4 0 _uhttp://dx.doi.org/10.1007/978-3-319-04138-4
912 _aZDB-2-SCS
942 _cEBK
999 _c57669
_d57669