DNA-based prediction of eye color in Latin American population applying Machine Learning models

Abstract

Reduction in the costs of DNA sequencing and genotyping allows for the increased availability of databases which can be useful for analyzing the relationship between the human genetic code and visible characteristics, diseases, and behaviors, among others. The aim of this study is to improve the prediction of eye color from genotype by means of several Machine Learning models, using a dataset of 308 volunteers from Buenos Aires, Argentina. The results achieved are competitive and demonstrate the usefulness of artificial intelligence (AI) in the fields of genetics and its application in areas such as health, biometrics and forensics.