Benchmarking Machine Learning Robustness In Covid-19 Genome Sequence Classification

This paper presents a framework for testing and benchmarking the robustness of machine learning models by simulating biological sequences with errors. It introduces several ways to perturb SARS-CoV-2 genome sequences to mimic the error profiles of common sequencing platforms such as Illumina and PacBio. Experiments on a wide array of ML models show that some simulation-based approaches with different levels of noise can improve the robustness of the models.