2011 | OriginalPaper | Chapter
Identifying Oligomeric Proteins Based on a Self-constructed Dataset
Authors : Tong Wang, Wenan Tan, Lihua Hu
Published in: Advanced Research on Computer Education, Simulation and Modeling
Publisher: Springer Berlin Heidelberg
Activate our intelligent search to find suitable subject content or patents.
Select sections of text to find matching patents with Artificial Intelligence. powered by
Select sections of text to find additional relevant content using AI-assisted search. powered by
Oligomeric proteins are very common in nature. They can be divided into two classes: homo-oligomers and hetero-oligomers. In this paper, a new method for the prediction of oligomeric protein types is proposed based on a self-constructed dataset. This stringent benchmark data set were screened strictly in which none of proteins has ≥60% pairwise sequence identity to any other in the same subset. DC (Dipeptide Composition) is used as sequence encoding scheme for the construction of decision system. A supervised linear DR (Dimensionality Reduction) algorithm, the so-called LDA (Linear Discriminant Analysis) is introduced to reduce the decision system, which can be used to classify new objects. The results thus obtained in predicting the types of oligomeric proteins are quite encouraging.