Study of Evolution By Automating Hardy Weinberg Equilibrium With Machine Learning Techniques In TensorFlow And Keras

Abstract

Evolution transpires in organism populations and includes population diversity, heredity and varying survival. One way to study evolution is to study how the frequency of a population’s allele varies from generation to generation. An allele is a type of gene variant. In other words, rather than looking at two parental species, evolution should be investigated by looking at the population as a whole. The only way to do this is therefore to investigate how allele frequencies shift in populations and how these shifts will predict what will happen to a population in the future. Throughout biology, there are basic equations which are used to model this theory basically termed as Hardy-Weinberg principle. This paper describes a new method that integrates Ecology and Engineering by automating the Hardy-Weinberg model using ADAM Optimization technique. The neural network trained based on Keras and Tensorflow has been deployed using python for the study of evolution. The developed model is tested with standard allele frequency database “ALFRED” to prove the efficiency.