ROC analysis: applications to the classification of biological sequences and 3D structures

被引：122

作者：

Sonego, Paolo

Kocsor, Andras ^{[2
,3
]}

Pongor, Sandor ^{[1
,4
]}

机构：

[1] Int Ctr Genet Engn & Biotechnol, Prot Struct & Bioinformat Grp, I-34012 Trieste, Italy

[2] Univ Szeged, Szeged, Hungary

[3] Hungarian Acad Sci, Res Grp Artificial Intelligence, H-1051 Budapest, Hungary

[4] Hungarian Acad Sci, Bioinformat Grp, Biol Res Ctr, H-1051 Budapest, Hungary

来源：

BRIEFINGS IN BIOINFORMATICS | 2008年 / 9卷 / 03期

关键词：

protein similarity searching; classification; ROC analysis; performance assessment; function prediction;

D O I：

10.1093/bib/bbm064

中图分类号：

Q5 [生物化学];

学科分类号：

071010 ; 081704 ;

摘要：

ROC (receiver operator characteristics) analysis is a visual as well as numerical method used for assessing the performance of classification algorithms, such as those used for predicting structures and functions from sequence data. This review summarizes the fundamental concepts of ROC analysis and the interpretation of results using examples of sequence and structure comparison. We overview the available programs and provide evaluation guidelines for genomic/proteomic data, with particular regard to applications to large and heterogeneous databases used in bioinformatics.

引用

页码：198 / 209

页数：12

共 56 条

[1] BASIC LOCAL ALIGNMENT SEARCH TOOL [J].