An Information-Theoretic Definition of Similarity
ICML '98 Proceedings of the Fifteenth International Conference on Machine Learning
Semantic similarity over the gene ontology: family correlation and selecting disjunctive ancestors
Proceedings of the 14th ACM international conference on Information and knowledge management
An introduction to ROC analysis
Pattern Recognition Letters - Special issue: ROC analysis in pattern recognition
ROCR: visualizing classifier performance in R
Bioinformatics
Using information content to evaluate semantic similarity in a taxonomy
IJCAI'95 Proceedings of the 14th international joint conference on Artificial intelligence - Volume 1
| Hi-index | 0.00 |
Background - Because of the importance of protein interactions in organisms, researchers are interested in the functional similarity between interacted proteins. Gene ontology semantic similarity provides a novel way to measure the similarity between gene products, including proteins. Various methods have been proposed for calculating the semantic similarity between GO terms and gene products, therefore evaluating these measurements on protein interaction data is helpful and necessary for related studies. Results - 35 different definitions of GO semantic similarity are evaluated by receiver operating characteristic analysis, information gain and Chi-square on core PPIs of four organisms, human, rat, mouse and fruit fly, from DIP database. Conclusions - For the identification of interacted proteins, CoutoEnriched is the best definition of the similarity between GO terms, and there is no significant difference between most methods calculating the semantic similarity between two sets of GO terms.