GEARS: Evolving Classifier using Genetic Algorithm and Ensemble Learning by Inducing Sequence Data and Preference Associative Rules

Indeed machine learning models have played a significant role in bioinformatics to classify protein and DNA sequences. But large number of these models; have been evolved by learning amino acid sequence data. We are developing a new approach to evolve classification model(s) by learning amino acid sequence data and associative classification rules based on amino acid’s preference through genetic evolution. Implementation of this approach is a new machine learning simulator called GEARS (Genetic Evolution of Classifiers by Learning Residue Rules and Sequence). We hypothesized that classification model(s); learned by GEARS will reduce the false negative and positive predictions. This study reports the conceptual framework and architecture of GEARS along with its application to post translational modification. Tool Development for Automatic Mitigation of IT Risks in an Enterprise Mr. Abdul Mateen and Dr. Sohail Asghar Shaheed Zulfikar Ali Bhutto Institute of Science and Technology, Islamabad, Pakistan. [email protected]