Mutation prediction of Infectious viruses based on Different Machine learning approaches

In general, the ability to predict the evolution of a pathogen enhances our ability to control, prevent, and treatdiseases. Usually, only mutations that can escape the host immune system and affect the severity can sustainand spread throughout generations. Several different pandemics have happened through the years. Forexample, the ۱۹۱۸ influenza pandemic was one of the most severe in recent history, and the H۱N۱ viruscaused it. By mutation prediction, pandemics can be recognized before they happen. VariationalAutoEncoders (VAEs) and Generative Adversarial Networks (GANs) generate new samples from our datain machine learning. Sequence-to-Sequence (Seq۲seq) networks are primarily used in translation tasks togenerate a new sample from the previous one. The method that we use is a combination of GAN networksand sequence to sequence networks. We create a Seq۲seq network as a Generator of our model with the helpof Long Short Term Memories (LSTMs) and then use a discriminator to distinguish whether the sequencesare fake or real. The most challenging task is that GANs are not good in sequential data, and Seq۲seq hassome problems in the long length of sequences. For the result, we find out which sequence is more possiblefor the mutant in the future, and we can use these results for preventing a future pandemic.

کلیدواژه ها:

Machine Learning ، GANs ، Deep Learning ، Sequence Generating