期刊名称：International Journal of Computer Trends and Technology
电子版ISSN：2231-2803
出版年度：2016
卷号：34
期号：3
页码：139-143
DOI：10.14445/22312803/IJCTT-V34P125
出版社：Seventh Sense Research Group
摘要：Drug discovery process, Disease detection and Prediction of molecular class are the area of great significance for carrying out research. In past few decades some precise approaches were used to enhance the accuracy of Human protein Function (HPF) prediction. This research study is primarily concentrated on such approach of HPF prediction with sequence derived features (SDF) using decision trees and there variants implemented using C5 and C4.5 algorithms like See5 and SIPINA. More sequence derived features were identified and incorporated. The training data was improved with these incorporated features. The Sequence data was evolved from HPRD (Human protein reference database) in terms of number of sequences and the features used to extract the relation towards a specific class which enhancing power of training data. Multiple techniques were examined for accuracy in prediction and a widespread comparison was done amongst them incorporating with previous research results, and prescribed the overall accuracy of See5 with 64% and SIPINA with 88%.
