The structural class is an important feature in characterizing the overall topological folding type of a protein or the domains therein. Prediction of protein structural classification has attracted the attention and efforts from many investigators. In this paper a novel predictor, the AdaBoost Learner, was introduced to deal with this problem. The essence of the AdaBoost Learner is that a combination of many 'weak' learning algorithms, each performing just slightly better than a random guessing algorithm, will generate a 'strong' learning algorithm. Demonstration thru jackknife cross-validation on two working datasets constructed by previous investigators indicated that AdaBoost outperformed other predictors such as SVM (support vector machine), a powerful algorithm widely used in biological literatures. It has not escaped our notice that AdaBoost may hold a high potential for improving the quality in predicting the other protein features as well, such as subcellular location and receptor type, among many others. Or at the very least, it will play a complementary role to many of the existing algorithms in this regard.
[1]
H D Dakin,et al.
On Amino-acids.
,
1918,
The Biochemical journal.
[2]
Andreas Christmann,et al.
Support vector machines
,
2008,
Data Mining and Knowledge Discovery Handbook.
[3]
Thomas G. Dietterich.
What is machine learning?
,
2020,
Archives of Disease in Childhood.
[4]
Vladimir Vapnik,et al.
Statistical learning theory
,
1998
.
[5]
M. Nadeau.
Proteins : Structure , Function , and Genetics
,
.
[6]
Nello Cristianini,et al.
Support vector machines
,
2009
.
[7]
김삼묘,et al.
“Bioinformatics” 특집을 내면서
,
2000
.
[8]
Heekuck Oh,et al.
Neural Networks for Pattern Recognition
,
1993,
Adv. Comput..