Identification of biological properties in organisms using machine learning techniques on whole genome sequences

Abstract

The advance in technology and genome sequencing processes in the recent decades have made large volumes of biological data available to researchers from all over the world, which, due to the large scales, are difficult to analyze in their entirety. Therefore, it is intuitive to think of Artificial Intelligence to work with such information. In order to reduce the existing gap between the researchers and the Artificial Intelligence tools, a software was developed that allows the creation of a workspace for biological organisms, the processing of its corresponding genomes, and the creation and training of models of Machine Learning, everything using a simple (yet powerful) graphical interface.
The trained models are then analyzed to find which patterns determine the result of the property that is being investigated on the biological organism, finding in the process the genes with the greatest impact on the model’s predictions, allowing the researcher to subsequently analyze the desired genes in the laboratory, saving time and resources in the process.