Deep learning based on biologically interpretable genome representation predicts two types of human adaptation of SARS-CoV-2 variants

Abstract

Explosively emerging SARS-CoV-2 variants challenge current nomenclature schemes based on genetic diversity and biological significance. Genomic composition-based machine learning methods have recently performed well in identifying phenotype-genotype relationships. We introduced a framework involving dinucleotide (DNT) composition representation (DCR) to parse the general human adaptation of RNA viruses and applied a three-dimensional convolutional neural network (3D CNN) analysis to learn the human adaptation of other existing coronaviruses (CoVs) and predict the adaptation of SARS-CoV-2 variants of concern (VOCs). A markedly separable, linear DCR distribution was observed in two major genes-receptor-binding glycoprotein and RNA-dependent RNA polymerase (RdRp)-of six families of single-stranded (ssRNA) viruses. Additionally, there was a general host-specific distribution of both the spike proteins and RdRps of CoVs. The 3D CNN based on spike DCR predicted a dominant type II adaptation of most Beta, Delta and Omicron VOCs, with high transmissibility and low pathogenicity. Type I adaptation with opposite transmissibility and pathogenicity was predicted for SARS-CoV-2 Alpha VOCs (77%) and Kappa variants of interest (58%). The identified adaptive determinants included D1118H and A570D mutations and local DNTs. Thus, the 3D CNN model based on DCR features predicts SARS-CoV-2, a major type II human adaptation and is qualified to predict variant adaptation in real time, facilitating the risk-assessment of emerging SARS-CoV-2 variants and COVID-19 control.

Keywords: 3D convolutional neural networks; SARS-CoV-2; dinucleotide composition representation; human adaptation; variants of concern.