SARS-CoV-2 virus RNA sequence classification and geographical analysis with convolutional neural networks approach

SARS-CoV-2 virus RNA sequence classification and geographical analysis with convolutional neural networks approach. Abstract Covid-19 infection, which spread to the whole world in December 2019 and is still active, caused more than 250 thousand deaths in the world today. Researches on this subject have been focused on analyzing the genetic structure of the virus, developing vaccines, the course of the disease, and its source. In this study, RNA sequences belonging to the SARS-CoV-2 virus are transformed into gene motifs with two basic image processing algorithms and classified with the convolutional neural network (CNN) models. The CNN models achieved an average of 98% Area Under Curve(AUC) value was achieved in RNA sequences classified as Asia, Europe, America, and Oceania. The resulting artificial neural network model was used for phylogenetic analysis of the variant of the virus isolated in Turkey. The classification results reached were compared with gene alignment values in the GISAID database, where SARS-CoV-2 virus records are kept all over the world. Our experimental results have revealed that now the detection of the geographic distribution of the virus with the CNN models might serve as an efficient method. Keywords: Deep Learning, Bioinformatics, Convolutional neural network, SARS-Cov-2, Pattern Classification Introduction Artificial intelligence practices and particularly deep learning studies are a widely used discipline in many research fields, including medicine and bioinformatics. The CNN models, especially in the field of medical imaging, are very successful in lesions and disease diagnosis. In addition to the success of deep learning methods in the fields of image processing, natural language processing, also has a lot of usage on a time scale with approaches such as Long-Short Term memory. In deep learning practices, low-level features such as DNA sequence, pathology images, and tomography scans can be learned from the data, by largely eliminating the need for engineering applications.