On predicting secondary structure transition

Authors:
Raja Loganantharaj;Vivek Philip
Affiliations:
Bioinformatics Research Lab, University of Louisiana at Lafayette, USA.;Bioinformatics Research Lab, University of Louisiana at Lafayette, USA
Venue:
International Journal of Bioinformatics Research and Applications
Year:
2007

Citing 7
Cited 0

Simplifying decision trees

International Journal of Man-Machine Studies - Special Issue: Knowledge Acquisition for Knowledge-based Systems. Part 5
Artificial intelligence (3rd ed.)

Artificial intelligence (3rd ed.)
C4.5: programs for machine learning

C4.5: programs for machine learning
Artificial intelligence: a modern approach

Artificial intelligence: a modern approach
Bioinformatics: the machine learning approach

Bioinformatics: the machine learning approach
Random Forests

Machine Learning
Data Mining: Practical Machine Learning Tools and Techniques, Second Edition (Morgan Kaufmann Series in Data Management Systems)

Data Mining: Practical Machine Learning Tools and Techniques, Second Edition (Morgan Kaufmann Series in Data Management Systems)

Quantified Score

Hi-index	0.00

Visualization

Abstract

A function of a protein is dependent on its structure;therefore, predicting a protein structure from an amino acidsequence is an active area of research. To improve the accuracy ofvalidation of structures, we are studying the predictability ofsecondary structure transitions using the following machinelearning algorithms: naive Bayes, C4.5 decision tree, and randomforest. The annotated data sets from PDB that have agreement withDSSP and STRIDE are used for training and testing. We havedemonstrated that predicting structure transition with high degreeof certainty is possible and we were able to get as high as 97.5%of prediction accuracy.