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

• Published in: Briefings in bioinformatics Vol. 23; no. 3
• Main Authors: Li, Jing, Wu, Ya-Nan, Zhang, Sen, Kang, Xiao-Ping, Jiang, Tao
• Format: Journal Article
• Language: English
• Published: England Oxford University Press 13.05.2022; Oxford Publishing Limited (England)
• Subjects: Adaptation; Artificial neural networks; Biodiversity; Composition; Coronaviruses; COVID-19; Deep learning; DNA-directed RNA polymerase; Genetic diversity; Genotypes; Glycoproteins; Machine learning; Mutation; Neural networks; Pathogenicity; Pathogens; Phenotypes; Problem Solving Protocol; Representations; Ribonucleic acid; Risk assessment; RNA; RNA polymerase; RNA viruses; RNA-directed RNA polymerase; Severe acute respiratory syndrome; Severe acute respiratory syndrome coronavirus 2; Three dimensional models; Viruses; SARS-CoV-2; 3D convolutional neural networks; dinucleotide composition representation; variants of concern; human adaptation
• ISSN: 1467-5463; 1477-4054
• DOI: 10.1093/bib/bbac036

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.