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

Learning from prepandemic data to forecast viral escape DOI Creative Commons
Nicole N. Thadani, Sarah F. Gurev, Pascal Notin

et al.

Nature, Journal Year: 2023, Volume and Issue: 622(7984), P. 818 - 825

Published: Oct. 11, 2023

Abstract Effective pandemic preparedness relies on anticipating viral mutations that are able to evade host immune responses facilitate vaccine and therapeutic design. However, current strategies for evolution prediction not available early in a pandemic—experimental approaches require polyclonal antibodies test against 1–16 , existing computational methods draw heavily from strain prevalence make reliable predictions of variants concern 17–19 . To address this, we developed EVEscape, generalizable modular framework combines fitness deep learning model historical sequences with biophysical structural information. EVEscape quantifies the escape potential at scale has advantage being applicable before surveillance sequencing, experimental scans or three-dimensional structures antibody complexes available. We demonstrate trained 2020, is as accurate high-throughput variation SARS-CoV-2 other viruses including influenza, HIV understudied such Lassa Nipah. provide continually revised scores all strains predict probable further forecast emerging tool continuing development ( evescape.org ).

Language: Английский

Citations

79
Fitness effects of mutations to SARS-CoV-2 proteins DOI Creative Commons
Jesse D. Bloom, Richard A. Neher

Virus Evolution, Journal Year: 2023, Volume and Issue: 9(2)

Published: July 1, 2023

Knowledge of the fitness effects mutations to SARS-CoV-2 can inform assessment new variants, design therapeutics resistant escape, and understanding functions viral proteins. However, experimentally measuring is challenging: we lack tractable lab assays for many proteins, comprehensive deep mutational scanning has been applied only two Here, develop an approach that leverages millions publicly available sequences estimate mutations. We first calculate how independent occurrences each mutation are expected be observed along phylogeny in absence selection. then compare these observations actual effect mutation. These estimates correlate well with measurements. For most genes, synonymous nearly neutral, stop-codon deleterious, amino acid have a range effects. some accessory proteins under little no provide interactive visualizations all (https://jbloomlab.github.io/SARS2-mut-fitness/). The framework describe applicable any virus which number sufficiently large neutral observed.

Language: Английский

Citations

73
Convergent evolution of SARS-CoV-2 XBB lineages on receptor-binding domain 455–456 synergistically enhances antibody evasion and ACE2 binding DOI Creative Commons
Fanchong Jian, Leilei Feng, Sijie Yang

et al.

PLoS Pathogens, Journal Year: 2023, Volume and Issue: 19(12), P. e1011868 - e1011868

Published: Dec. 20, 2023

Severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) XBB lineages have achieved dominance worldwide and keep on evolving. Convergent evolution of the receptor-binding domain (RBD) L455F F456L is observed, resulting in variants with substantial growth advantages, such as EG.5, FL.1.5.1, XBB.1.5.70, HK.3. Here, we show that neutralizing antibody (NAb) evasion drives convergent F456L, while epistatic shift caused by enables subsequent convergence through ACE2 binding enhancement further immune evasion. evade RBD-targeting Class 1 public NAbs, reducing neutralization efficacy breakthrough infection (BTI) reinfection convalescent plasma. Importantly, single substitution significantly dampens receptor binding; however, combination forms an adjacent residue flipping, which leads to enhanced NAbs resistance affinity. The perturbed mode exceptional NAb evasion, revealed structural analyses. Our results indicate flexibility contributed epistasis cannot be underestimated, potential SARS-CoV-2 RBD remains high.

Language: Английский

Citations

72
Immune evasion and ACE2 binding affinity contribute to SARS-CoV-2 evolution DOI
Wentai Ma, Haoyi Fu, Fanchong Jian

et al.

Nature Ecology & Evolution, Journal Year: 2023, Volume and Issue: 7(9), P. 1457 - 1466

Published: July 13, 2023

Language: Английский

Citations

55
A pan-influenza antibody inhibiting neuraminidase via receptor mimicry DOI Creative Commons

Corey Momont,

Ha V. Dang, Fabrizia Zatta

et al.

Nature, Journal Year: 2023, Volume and Issue: 618(7965), P. 590 - 597

Published: May 31, 2023

Rapidly evolving influenza A viruses (IAVs) and B (IBVs) are major causes of recurrent lower respiratory tract infections. Current vaccines elicit antibodies predominantly to the highly variable head region haemagglutinin their effectiveness is limited by viral drift1 suboptimal immune responses2. Here we describe a neuraminidase-targeting monoclonal antibody, FNI9, that potently inhibits enzymatic activity all group 1 2 IAVs, as well Victoria/2/87-like, Yamagata/16/88-like ancestral IBVs. FNI9 broadly neutralizes seasonal IAVs IBVs, including immune-evading H3N2 strains bearing an N-glycan at position 245, shows synergistic when combined with anti-haemagglutinin stem-directed antibodies. Structural analysis reveals D107 in heavy chain complementarity-determinant 3 mimics interaction sialic acid carboxyl three conserved arginine residues (R118, R292 R371) neuraminidase catalytic site. demonstrates potent prophylactic against lethal IAV IBV infections mice. The unprecedented breadth potency antibody supports its development for prevention illness pandemic viruses.

Language: Английский

Citations

51
The landscape of antibody binding affinity in SARS-CoV-2 Omicron BA.1 evolution DOI Creative Commons
Alief Moulana, Thomas Dupic, Angela M. Phillips

et al.

eLife, Journal Year: 2023, Volume and Issue: 12

Published: Feb. 13, 2023

The Omicron BA.1 variant of SARS-CoV-2 escapes convalescent sera and monoclonal antibodies that are effective against earlier strains the virus. This immune evasion is largely a consequence mutations in receptor binding domain (RBD), major antigenic target SARS-CoV-2. Previous studies have identified several key RBD leading to escape from most antibodies. However, little known about how these interact with each other RBD. Here, we systematically map interactions by measuring affinity all possible combinations 15 (2 =32,768 genotypes) 4 (LY-CoV016, LY-CoV555, REGN10987, S309) distinct epitopes. We find can lose diverse acquiring few large-effect reduce others through small-effect mutations. our results also reveal alternative pathways antibody does not include every mutation. Moreover, epistatic shown constrain decline S309 but only modestly shape landscapes Together previous work on ACE2 landscape, suggest mediated groups mutations, whose deleterious effects compensated another group (most notably Q498R N501Y).

Language: Английский

Citations

50
Spike deep mutational scanning helps predict success of SARS-CoV-2 clades DOI Creative Commons
Bernadeta Dadonaite,

Jack Brown,

Teagan McMahon

et al.

Nature, Journal Year: 2024, Volume and Issue: 631(8021), P. 617 - 626

Published: July 3, 2024

SARS-CoV-2 variants acquire mutations in the spike protein that promote immune evasion

Language: Английский

Citations

50
Deep-learning-enabled protein–protein interaction analysis for prediction of SARS-CoV-2 infectivity and variant evolution DOI
Guangyu Wang, Xiaohong Liu, Kai Wang

et al.

Nature Medicine, Journal Year: 2023, Volume and Issue: 29(8), P. 2007 - 2018

Published: July 31, 2023

Language: Английский

Citations

44
Unsupervised evolution of protein and antibody complexes with a structure-informed language model DOI
Varun R. Shanker, Theodora U. J. Bruun, Brian Hie

et al.

Science, Journal Year: 2024, Volume and Issue: 385(6704), P. 46 - 53

Published: July 4, 2024

Large language models trained on sequence information alone can learn high-level principles of protein design. However, beyond sequence, the three-dimensional structures proteins determine their specific function, activity, and evolvability. Here, we show that a general model augmented with structure backbone coordinates guide evolution for diverse without need to individual functional tasks. We also demonstrate ESM-IF1, which was only single-chain structures, be extended engineer complexes. Using this approach, screened about 30 variants two therapeutic clinical antibodies used treat severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) infection. achieved up 25-fold improvement in neutralization 37-fold affinity against antibody-escaped viral concern BQ.1.1 XBB.1.5, respectively. These findings highlight advantage integrating structural identify efficient trajectories requiring any task-specific training data.

Language: Английский

Citations

31
Mutations in the SARS-CoV-2 spike receptor binding domain and their delicate balance between ACE2 affinity and antibody evasion DOI Creative Commons

Song Xue,

Yuru Han, Fan Wu

et al.

Protein & Cell, Journal Year: 2024, Volume and Issue: 15(6), P. 403 - 418

Published: March 4, 2024

Intensive selection pressure constrains the evolutionary trajectory of SARS-CoV-2 genomes and results in various novel variants with distinct mutation profiles. Point mutations, particularly those within receptor binding domain (RBD) spike (S) protein, lead to functional alteration both engagement monoclonal antibody (mAb) recognition. Here, we review data RBD point mutations possessed by major discuss their individual effects on ACE2 affinity immune evasion. Many single amino acid substitutions epitopes crucial for evasion capacity may conversely weaken affinity. However, this weakened effect could be largely compensated specific epistatic such as N501Y, thus maintaining overall protein all variants. The predominant direction evolution lies neither promoting nor evading mAb neutralization but a delicate balance between these two dimensions. Together, interprets how efficiently resist meanwhile is maintained, emphasizing significance comprehensive assessment mutations.

Language: Английский

Citations

25