ABSTRACT
Genetic mutations give rise to a quasispecies of drug/vaccine-resistant and virulent organisms. These organisms are classified as strains or variants depending on the extent of their phenotypic manifestation. Thus, there is a thin dichotomy between SARS-CoV-2 strains and their associated variants. This paper sought to comprehensively review the successes achieved in the classification of SARS-CoV-2 strains based on genomic sequences (GSs) using deep learning architectures, thereby stimulating further research on the variants identified recently. Selective screening and analysis of research articles centered on deep learning architectures employed for SARS-CoV-2 detection based on GS information were carried out. This incorporated the use of relevant key/search terms and logical/Boolean operators to scan through the Scopus repository. To provide a foundation for future investigations on the classification of SARS-CoV-2 strains, meticulous analysis of the three key aspects, such as , methodology, and conclusion, was implemented. Despite the high level of intra-species similarity, this article presents new studies that use deep learning technology to detect SARS-CoV-2 strains on the premise of the primary sequence of nucleotides in their genome. Manually searching through specific genes for mutations to identify variants after sequencing can be very laborious. This is where the use of computational acumen comes into play. Deep learning, an offshoot of machine learning, has been utilized in various literature to tackle such problems. Rapid identification of SARS-CoV-2 variant after sequencing aids quick response by clinicians to administer relevant drugs and save lives. Also, governments utilize this information to map out strategies for the timely containment of the spread of an identified variant with elevated virulence. The deep learning models reported in this paper show the remarkable predictive results achieved in identifying SARS-CoV-2 strains. However, no work has been done on the identification of recent variants reported globally. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.