Implementation of Protein Sequence Classification for Globin family using Ensemble Learning

Feature Extraction from protein sequence is a very important taskin bioinformatics. The main focus of that work is protein sequencesclassificationthat can be used to improve drug discovery and identification of diseases for treating patients in the early stages of diagnosis. In this paper, we proposed a method which is used for feature extraction i.e. converting the protein sequence of hemoglobin in to feature vectors. The feature vectors are then given to the ensemble classifieras an input which uses various classifier to providebetter result/performance as compared to any constituent learning algorithm alone.