Machine learning-enhanced immunopeptidomics applied to T-cell epitope discovery for COVID-19 vaccines

Kevin A. Kovalchik; David J. Hamelin; Peter Kubiniok; Benoîte Bourdin; Fatima Mostefai; Raphaël Poujol; Bastien Paré; Shawn M. Simpson; John Sidney; Éric Bonneil; Mathieu Courcelles; Sunil Kumar Saini; Mohammad Shahbazy; Saketh Kapoor; Vigneshwar Rajesh; Maya Weitzen; Jean Christophe Grenier; Bayrem Gharsallaoui; Loïze Maréchal; Zhaoguan Wu; Christopher Savoie; Alessandro Sette; Pierre Thibault; Isabelle Sirois; Martin A. Smith; Hélène Decaluwe; Julie G. Hussin; Mathieu Lavallée-Adam; Etienne Caron

doi:10.1038/s41467-024-54734-9

Machine learning-enhanced immunopeptidomics applied to T-cell epitope discovery for COVID-19 vaccines

Kevin A. Kovalchik, David J. Hamelin, Peter Kubiniok, Benoîte Bourdin, Fatima Mostefai, Raphaël Poujol, Bastien Paré, Shawn M. Simpson, John Sidney, Éric Bonneil, Mathieu Courcelles, Sunil Kumar Saini, Mohammad Shahbazy, Saketh Kapoor, Vigneshwar Rajesh, Maya Weitzen, Jean Christophe Grenier, Bayrem Gharsallaoui, Loïze Maréchal, Zhaoguan WuChristopher Savoie, Alessandro Sette, Pierre Thibault, Isabelle Sirois, Martin A. Smith, Hélène Decaluwe, Julie G. Hussin^*, Mathieu Lavallée-Adam^*, Etienne Caron^*

^*Corresponding author for this work

Research output: Contribution to journal › Journal article › Research › peer-review

13 Downloads (Pure)

Abstract

Next-generation T-cell-directed vaccines for COVID-19 focus on establishing lasting T-cell immunity against current and emerging SARS-CoV-2 variants. Precise identification of conserved T-cell epitopes is critical for designing effective vaccines. Here we introduce a comprehensive computational framework incorporating a machine learning algorithm—MHCvalidator—to enhance mass spectrometry-based immunopeptidomics sensitivity. MHCvalidator identifies unique T-cell epitopes presented by the B7 supertype, including an epitope from a + 1-frameshift in a truncated Spike antigen, supported by ribosome profiling. Analysis of 100,512 COVID-19 patient proteomes shows Spike antigen truncation in 0.85% of cases, revealing frameshifted viral antigens at the population level. Our EpiTrack pipeline tracks global mutations of MHCvalidator-identified CD8 + T-cell epitopes from the BNT162b4 vaccine. While most vaccine epitopes remain globally conserved, an immunodominant A*01-associated epitope mutates in Delta and Omicron variants. This work highlights SARS-CoV-2 antigenic features and emphasizes the importance of continuous adaptation in T-cell vaccine development.

Original language	English
Article number	10316
Journal	Nature Communications
Volume	15
Issue number	1
Number of pages	22
ISSN	2041-1723
DOIs	https://doi.org/10.1038/s41467-024-54734-9
Publication status	Published - 2024

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

Access to Document

10.1038/s41467-024-54734-9

fulltextFinal published version, 3.64 MB

OpenUrl availability

Full text

Cite this

Kovalchik, K. A., Hamelin, D. J., Kubiniok, P., Bourdin, B., Mostefai, F., Poujol, R., Paré, B., Simpson, S. M., Sidney, J., Bonneil, É., Courcelles, M., Saini, S. K., Shahbazy, M., Kapoor, S., Rajesh, V., Weitzen, M., Grenier, J. C., Gharsallaoui, B., Maréchal, L., ... Caron, E. (2024). Machine learning-enhanced immunopeptidomics applied to T-cell epitope discovery for COVID-19 vaccines. Nature Communications, 15(1), Article 10316. https://doi.org/10.1038/s41467-024-54734-9

@article{24c2e0cf3da84681be24854396a9d0d9,

title = "Machine learning-enhanced immunopeptidomics applied to T-cell epitope discovery for COVID-19 vaccines",

abstract = "Next-generation T-cell-directed vaccines for COVID-19 focus on establishing lasting T-cell immunity against current and emerging SARS-CoV-2 variants. Precise identification of conserved T-cell epitopes is critical for designing effective vaccines. Here we introduce a comprehensive computational framework incorporating a machine learning algorithm—MHCvalidator—to enhance mass spectrometry-based immunopeptidomics sensitivity. MHCvalidator identifies unique T-cell epitopes presented by the B7 supertype, including an epitope from a + 1-frameshift in a truncated Spike antigen, supported by ribosome profiling. Analysis of 100,512 COVID-19 patient proteomes shows Spike antigen truncation in 0.85% of cases, revealing frameshifted viral antigens at the population level. Our EpiTrack pipeline tracks global mutations of MHCvalidator-identified CD8 + T-cell epitopes from the BNT162b4 vaccine. While most vaccine epitopes remain globally conserved, an immunodominant A*01-associated epitope mutates in Delta and Omicron variants. This work highlights SARS-CoV-2 antigenic features and emphasizes the importance of continuous adaptation in T-cell vaccine development.",

author = "Kovalchik, {Kevin A.} and Hamelin, {David J.} and Peter Kubiniok and Beno{\^i}te Bourdin and Fatima Mostefai and Rapha{\"e}l Poujol and Bastien Par{\'e} and Simpson, {Shawn M.} and John Sidney and {\'E}ric Bonneil and Mathieu Courcelles and Saini, {Sunil Kumar} and Mohammad Shahbazy and Saketh Kapoor and Vigneshwar Rajesh and Maya Weitzen and Grenier, {Jean Christophe} and Bayrem Gharsallaoui and Lo{\"i}ze Mar{\'e}chal and Zhaoguan Wu and Christopher Savoie and Alessandro Sette and Pierre Thibault and Isabelle Sirois and Smith, {Martin A.} and H{\'e}l{\`e}ne Decaluwe and Hussin, {Julie G.} and Mathieu Lavall{\'e}e-Adam and Etienne Caron",

note = "Publisher Copyright: {\textcopyright} The Author(s) 2024.",

year = "2024",

doi = "10.1038/s41467-024-54734-9",

language = "English",

volume = "15",

journal = "Nature Communications",

issn = "2041-1723",

publisher = "Nature Publishing Group",

number = "1",

}

Kovalchik, KA, Hamelin, DJ, Kubiniok, P, Bourdin, B, Mostefai, F, Poujol, R, Paré, B, Simpson, SM, Sidney, J, Bonneil, É, Courcelles, M, Saini, SK, Shahbazy, M, Kapoor, S, Rajesh, V, Weitzen, M, Grenier, JC, Gharsallaoui, B, Maréchal, L, Wu, Z, Savoie, C, Sette, A, Thibault, P, Sirois, I, Smith, MA, Decaluwe, H, Hussin, JG, Lavallée-Adam, M & Caron, E 2024, 'Machine learning-enhanced immunopeptidomics applied to T-cell epitope discovery for COVID-19 vaccines', Nature Communications, vol. 15, no. 1, 10316. https://doi.org/10.1038/s41467-024-54734-9

TY - JOUR

T1 - Machine learning-enhanced immunopeptidomics applied to T-cell epitope discovery for COVID-19 vaccines

AU - Kovalchik, Kevin A.

AU - Hamelin, David J.

AU - Kubiniok, Peter

AU - Bourdin, Benoîte

AU - Mostefai, Fatima

AU - Poujol, Raphaël

AU - Paré, Bastien

AU - Simpson, Shawn M.

AU - Sidney, John

AU - Bonneil, Éric

AU - Courcelles, Mathieu

AU - Saini, Sunil Kumar

AU - Shahbazy, Mohammad

AU - Kapoor, Saketh

AU - Rajesh, Vigneshwar

AU - Weitzen, Maya

AU - Grenier, Jean Christophe

AU - Gharsallaoui, Bayrem

AU - Maréchal, Loïze

AU - Wu, Zhaoguan

AU - Savoie, Christopher

AU - Sette, Alessandro

AU - Thibault, Pierre

AU - Sirois, Isabelle

AU - Smith, Martin A.

AU - Decaluwe, Hélène

AU - Hussin, Julie G.

AU - Lavallée-Adam, Mathieu

AU - Caron, Etienne

PY - 2024

Y1 - 2024

N2 - Next-generation T-cell-directed vaccines for COVID-19 focus on establishing lasting T-cell immunity against current and emerging SARS-CoV-2 variants. Precise identification of conserved T-cell epitopes is critical for designing effective vaccines. Here we introduce a comprehensive computational framework incorporating a machine learning algorithm—MHCvalidator—to enhance mass spectrometry-based immunopeptidomics sensitivity. MHCvalidator identifies unique T-cell epitopes presented by the B7 supertype, including an epitope from a + 1-frameshift in a truncated Spike antigen, supported by ribosome profiling. Analysis of 100,512 COVID-19 patient proteomes shows Spike antigen truncation in 0.85% of cases, revealing frameshifted viral antigens at the population level. Our EpiTrack pipeline tracks global mutations of MHCvalidator-identified CD8 + T-cell epitopes from the BNT162b4 vaccine. While most vaccine epitopes remain globally conserved, an immunodominant A*01-associated epitope mutates in Delta and Omicron variants. This work highlights SARS-CoV-2 antigenic features and emphasizes the importance of continuous adaptation in T-cell vaccine development.

AB - Next-generation T-cell-directed vaccines for COVID-19 focus on establishing lasting T-cell immunity against current and emerging SARS-CoV-2 variants. Precise identification of conserved T-cell epitopes is critical for designing effective vaccines. Here we introduce a comprehensive computational framework incorporating a machine learning algorithm—MHCvalidator—to enhance mass spectrometry-based immunopeptidomics sensitivity. MHCvalidator identifies unique T-cell epitopes presented by the B7 supertype, including an epitope from a + 1-frameshift in a truncated Spike antigen, supported by ribosome profiling. Analysis of 100,512 COVID-19 patient proteomes shows Spike antigen truncation in 0.85% of cases, revealing frameshifted viral antigens at the population level. Our EpiTrack pipeline tracks global mutations of MHCvalidator-identified CD8 + T-cell epitopes from the BNT162b4 vaccine. While most vaccine epitopes remain globally conserved, an immunodominant A*01-associated epitope mutates in Delta and Omicron variants. This work highlights SARS-CoV-2 antigenic features and emphasizes the importance of continuous adaptation in T-cell vaccine development.

U2 - 10.1038/s41467-024-54734-9

DO - 10.1038/s41467-024-54734-9

M3 - Journal article

C2 - 39609459

AN - SCOPUS:85210556528

SN - 2041-1723

VL - 15

JO - Nature Communications

JF - Nature Communications

IS - 1

M1 - 10316

ER -

Machine learning-enhanced immunopeptidomics applied to T-cell epitope discovery for COVID-19 vaccines

Abstract

UN SDGs

Access to Document

OpenUrl availability

Fingerprint

Cite this