Topological AI forecasting of future dominating viral variants

TL;DR

This paper presents a topological AI approach that accurately predicts SARS-CoV-2 viral evolution, including mutation sites, infectivity, and variant dominance, well before experimental confirmation, aiding future pandemic preparedness.

Contribution

It introduces a novel topological AI framework that forecasts viral mutations and variant emergence with high accuracy, surpassing previous methods.

Findings

Predicted key mutation sites L452 and N501 in 2020.

Forecasted dominance of Omicron BA.4 and BA.5 in early 2022.

Accurately predicted impact of mutations on antibody efficacy.

Abstract

The understanding of the mechanisms of SARS-CoV-2 evolution and transmission is one of the greatest challenges of our time. By integrating artificial intelligence (AI), viral genomes isolated from patients, tens of thousands of mutational data, biophysics, bioinformatics, and algebraic topology, the SARS-CoV-2 evolution was revealed to be governed by infectivity-based natural selection. Two key mutation sites, L452 and N501 on the viral spike protein receptor-binding domain (RBD), were predicted in summer 2020, long before they occur in prevailing variants Alpha, Beta, Gamma, Delta, Kappa, Theta, Lambda, Mu, and Omicron. Recent studies identified a new mechanism of natural selection: antibody resistance. AI-based forecasting of Omicron's infectivity, vaccine breakthrough, and antibody resistance was later nearly perfectly confirmed by experiments. The replacement of dominant BA.1 by BA.2 in later March was predicted in early February. On May 1, 2022, persistent Laplacian-based AI projected Omicron BA.4 and BA.5 to become the new dominating COVID-19 variants. This prediction became reality in late June. Topological AI models offer accurate prediction of mutational impacts on the efficacy of monoclonal antibodies (mAbs).