Predicting the antigenic evolution of SARS-COV-2 with deep learning DOI Creative Commons
Wenkai Han, Ningning Chen, Xinzhou Xu

et al.

Nature Communications, Journal Year: 2023, Volume and Issue: 14(1)

Published: June 13, 2023

The relentless evolution of SARS-CoV-2 poses a significant threat to public health, as it adapts immune pressure from vaccines and natural infections. Gaining insights into potential antigenic changes is critical but challenging due the vast sequence space. Here, we introduce Machine Learning-guided Antigenic Evolution Prediction (MLAEP), which combines structure modeling, multi-task learning, genetic algorithms predict viral fitness landscape explore via in silico directed evolution. By analyzing existing variants, MLAEP accurately infers variant order along evolutionary trajectories, correlating with corresponding sampling time. Our approach identified novel mutations immunocompromised COVID-19 patients emerging variants like XBB1.5. Additionally, predictions were validated through vitro neutralizing antibody binding assays, demonstrating that predicted exhibited enhanced evasion. profiling predicting changes, aids vaccine development enhances preparedness against future variants.

Language: Английский

Key mechanistic features of the trade-off between antibody escape and host cell binding in the SARS-CoV-2 Omicron variant spike proteins DOI Creative Commons
Weiwei Li, Zepeng Xu, Tianhui Niu

et al.

The EMBO Journal, Journal Year: 2024, Volume and Issue: 43(8), P. 1484 - 1498

Published: March 11, 2024

Abstract Since SARS-CoV-2 Omicron variant emerged, it is constantly evolving into multiple sub-variants, including BF.7, BQ.1, BQ.1.1, XBB, XBB.1.5 and the recently emerged BA.2.86 JN.1. Receptor binding immune evasion are recognized as two major drivers for evolution of receptor domain (RBD) spike (S) protein. However, underlying mechanism interplay between factors remains incompletely understood. Herein, we determined structures human ACE2 complexed with XBB RBDs. Based on ACE2/RBD these sub-variants a comparison known complex structures, found that R346T substitution in RBD enhanced upon an interaction residue R493, but not Q493, via involving long-range conformation changes. Furthermore, R493Q F486V exert balanced impact, through which capability was somewhat compromised to achieve optimal binding. We propose “two-steps-forward one-step-backward” model describe such compromise affinity during sub-variants.

Language: Английский

Citations

21
Deep mutational scanning of H5 hemagglutinin to inform influenza virus surveillance DOI Creative Commons
Bernadeta Dadonaite, Jenny Ahn, Jordan T. Ort

et al.

PLoS Biology, Journal Year: 2024, Volume and Issue: 22(11), P. e3002916 - e3002916

Published: Nov. 12, 2024

H5 influenza is considered a potential pandemic threat. Recently, viruses belonging to clade 2.3.4.4b have caused large outbreaks in avian and multiple nonhuman mammalian species. Previous studies identified molecular phenotypes of the viral hemagglutinin (HA) protein that contribute humans, including cell entry, receptor preference, HA stability, reduced neutralization by polyclonal sera. However, prior experimental work has only measured how these are affected handful >10,000 different possible amino-acid mutations HA. Here, we use pseudovirus deep mutational scanning measure all affect each phenotype. We identify allow better bind α2-6-linked sialic acids show some already carry stabilize also sera from mice ferrets vaccinated against or infected with viruses. These antigenic maps enable rapid assessment when new strains acquired may create mismatches candidate vaccine virus, mutation present recent HAs causes change. Overall, systematic nature combined safety pseudoviruses enables comprehensive measurements phenotypic effects can inform real-time interpretation variation observed during surveillance influenza.

Language: Английский

Citations

21
Evolving antibody response to SARS-CoV-2 antigenic shift from XBB to JN.1 DOI Creative Commons
Fanchong Jian, Jing Wang, Ayijiang Yisimayi

et al.

bioRxiv (Cold Spring Harbor Laboratory), Journal Year: 2024, Volume and Issue: unknown

Published: April 22, 2024

Abstract The continuous evolution of SARS-CoV-2, particularly the emergence BA.2.86/JN.1 lineage replacing XBB lineages, necessitates re-evaluation current vaccine compositions. Here, we provide a comprehensive analysis humoral immune response to and JN.1 human exposures, emphasizing need for JN.1-lineage-based boosters. We demonstrate antigenic distinctiveness lineages in SARS-CoV-2-naive individuals but not those with prior vaccinations or infections, infection elicits superior plasma neutralization titers against its subvariants. highlight strong evasion receptor binding capability KP.3, supporting foreseeable prevalence. Extensive BCR repertoire, isolating ∼2000 RBD-specific monoclonal antibodies (mAbs) their targeting epitopes characterized by deep mutational scanning (DMS), underscores systematic superiority JN.1-elicited memory B cells (MBCs). Notably, Class 1 IGHV3-53/3-66-derived neutralizing (NAbs) contribute majorly within wildtype (WT)-reactive NAbs JN.1. However, KP.2 KP.3 evade substantial subset them, even induced JN.1, advocating booster updates optimized enrichment. JN.1-induced Omicron-specific also high potency across all Omicron lineages. Escape hotspots these have mainly been mutated RBD, resulting higher barrier escape, considering probable recovery previously escaped NAbs. Additionally, prevalence broadly reactive IGHV3-53/3-66- encoding MBCs, competing suggests inhibitory role on de novo activation naive cells, potentially explaining heavy imprinting mRNA-vaccinated individuals. These findings delineate evolving antibody shift from importance developing lineage, especially KP.3-based boosters, enhance immunity future SARS-CoV-2 variants.

Language: Английский

Citations

20
Molecular basis of convergent evolution of ACE2 receptor utilization among HKU5 coronaviruses DOI
Young‐Jun Park, Chen Liu, Jimin Lee

et al.

Cell, Journal Year: 2025, Volume and Issue: unknown

Published: Feb. 1, 2025

Language: Английский

Citations

5
Predicting the antigenic evolution of SARS-COV-2 with deep learning DOI Creative Commons
Wenkai Han, Ningning Chen, Xinzhou Xu

et al.

Nature Communications, Journal Year: 2023, Volume and Issue: 14(1)

Published: June 13, 2023

The relentless evolution of SARS-CoV-2 poses a significant threat to public health, as it adapts immune pressure from vaccines and natural infections. Gaining insights into potential antigenic changes is critical but challenging due the vast sequence space. Here, we introduce Machine Learning-guided Antigenic Evolution Prediction (MLAEP), which combines structure modeling, multi-task learning, genetic algorithms predict viral fitness landscape explore via in silico directed evolution. By analyzing existing variants, MLAEP accurately infers variant order along evolutionary trajectories, correlating with corresponding sampling time. Our approach identified novel mutations immunocompromised COVID-19 patients emerging variants like XBB1.5. Additionally, predictions were validated through vitro neutralizing antibody binding assays, demonstrating that predicted exhibited enhanced evasion. profiling predicting changes, aids vaccine development enhances preparedness against future variants.

Language: Английский

Citations

35