HOME > 상세정보

상세정보

Information-theoretic evaluation for computational biomedical ontologies [electronic resource]

Information-theoretic evaluation for computational biomedical ontologies [electronic resource]

자료유형
E-Book(소장)
개인저자
Clark, Wyatt Travis.
서명 / 저자사항
Information-theoretic evaluation for computational biomedical ontologies [electronic resource] / Wyatt Travis Clark.
발행사항
Cham :   Springer International Publishing :   Imprint: Springer,   2014.  
형태사항
1 online resource (vii, 46 p.) : ill. (some col.).
총서사항
Springer briefs in computer science,2191-5768
ISBN
9783319041384
요약
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.
일반주기
Title from e-Book title page.  
내용주기
Introduction -- Methods -- Experiments and Results -- Discussion.
서지주기
Includes bibliographical references and index.
이용가능한 다른형태자료
Issued also as a book.  
일반주제명
Computational Biology. Algorithms. Biological Ontologies. Proteins --physiology.
바로가기
URL
000 00000nam u2200205 a 4500
001 000046047769
005 20201006091713
006 m d
007 cr
008 200916s2014 sz a ob 001 0 eng d
020 ▼a 9783319041384
040 ▼a 211009 ▼c 211009 ▼d 211009
050 4 ▼a QH324.2-324.25
082 0 0 ▼a 610.285 ▼2 23
084 ▼a 610.285 ▼2 DDCK
090 ▼a 610.285
100 1 ▼a Clark, Wyatt Travis.
245 1 0 ▼a Information-theoretic evaluation for computational biomedical ontologies ▼h [electronic resource] / ▼c Wyatt Travis Clark.
260 ▼a Cham : ▼b Springer International Publishing : ▼b Imprint: Springer, ▼c 2014.
300 ▼a 1 online resource (vii, 46 p.) : ▼b ill. (some col.).
490 1 ▼a Springer briefs in computer science, ▼x 2191-5768
500 ▼a Title from e-Book title page.
504 ▼a Includes bibliographical references and index.
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.
530 ▼a Issued also as a book.
538 ▼a Mode of access: World Wide Web.
650 1 2 ▼a Computational Biology.
650 2 2 ▼a Algorithms.
650 2 2 ▼a Biological Ontologies.
650 2 2 ▼a Proteins ▼x physiology.
830 0 ▼a SpringerBriefs in computer science.
856 4 0 ▼u https://oca.korea.ac.kr/link.n2s?url=http://dx.doi.org/10.1007/978-3-319-04138-4
945 ▼a KLPA
991 ▼a E-Book(소장)

소장정보

No. 소장처 청구기호 등록번호 도서상태 반납예정일 예약 서비스
No. 1 소장처 중앙도서관/e-Book 컬렉션/ 청구기호 CR 610.285 등록번호 E14033828 도서상태 대출불가(열람가능) 반납예정일 예약 서비스 M

관련분야 신착자료