Application of boosting-based decision tree ensemble classifiers for discrimination of thermophilic and mesophilic proteins / 生物工程学报
Chinese Journal of Biotechnology
;
(12): 1026-1031, 2006.
Article
in Chinese
| WPRIM
| ID: wpr-325431
ABSTRACT
In this paper, the Boosting-based decision tree ensemble classifiers were applied to discriminate thermophilic and mesophilic proteins. Three methods, namely, self-consistency test, 5-fold cross-validation and independent testing with other dataset, were used to evaluate the performance and robust of the models. Logitboost, as a novel classifier in Boosting algorithm, performed better than Adaboost. The overall accuracy of the three methods was 100%, 88.4% and 89.5%, respectively. It was demonstrated that LogitBoost performed comparably or even better than that of neural network, a very powerful classifier widely used in biological literatures. The influence of protein size on discrimination was addressed. It is anticipated that the power in predicting many bio-macromolecular attributes will be further strengthened if the Boosting and some other existing algorithms can be effectively complemented with each other.
Full text:
Available
Index:
WPRIM (Western Pacific)
Main subject:
Algorithms
/
Decision Trees
/
Proteins
/
Chemistry
/
Classification
/
Neural Networks, Computer
/
Molecular Weight
Type of study:
Health economic evaluation
/
Prognostic study
Language:
Chinese
Journal:
Chinese Journal of Biotechnology
Year:
2006
Type:
Article
Similar
MEDLINE
...
LILACS
LIS