Machine learning-driven identification of serotype-independent pneumococcal vaccine candidates using samples from human infection challenge studies

Aug 6, 2026

Upload by Aria

Identifying conserved, immunogenic proteins that protect against Streptococcus pneumoniae colonization can enable serotype-independent vaccines. Using a controlled human infection challenge model, no single IgG or individual cytokine/chemokine response correlated significantly with protection, indicating protection emerges from coordinated multi-antigen immunity. Independent Random Forest models were trained on humoral and cellular datasets. The humoral model prioritized PdB, SP1069, and SP0899 IgG responses, while the cellular model linked MCP-1 responses to SP1069 and SP0899, and IL-17A to SP0648-3, with additional baseline IFN-γ, RANTES, and anti-protein IgG associated with lower colonization density.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages11

Reading Time28 min

AccessFree to download

Introduction

Pneumonia and pneumococcal colonization

Current pneumococcal vaccines and limitations

Rationale for serotype-independent protein antigens

Vaccine 75 (2026) 128280 Contents lists available at ScienceDirect Vaccine journal [homepage:](homepage: www.elsevier.com/locate/vaccine)[ www.elsevier.com/locate/vaccine](homepage: www.elsevier.com/locate/vaccine) | Machine learning-driven identification of serotype-independent pneumococcal vaccine candidates using samples from human infection challenge studies | | | | | --- | --- | --- | --- | | Katerina S. Cheliotis a,b,1, Patricia Gonzalez-Dias a,c,o,1, Esther L. German a,d,
Andr´e N.A. Gonçalves a,c,o, Elena Mitsi a,c,o, Elissavet Nikolaou a,e,f, Sherin Pojar a,g,
Eliane N. Miyajih, Rafaella Tostesh, Jesús Rein´e a,c,o, Andrea M. Collins a,i, Helder I. Nakayaj,k, Stephen B. Gordon a,l, Ying-Jie Lum, Shaun H. Pennington a, Andrew J. Pollard c,o,
Richard Malley m, Simon P. Jochemsn, Britta Urbana,c,o,2, Carla Sol´orzano a,c,o,2,*, Daniela M. Ferreira a,c,*,2
a Department of Clinical Sciences, Liverpool School of Tropical Medicine, Liverpool, United Kingdom b City St George's, University of London, London, United Kingdom
c Oxford Vaccine Group, Department of Paediatrics, University of Oxford, Oxford, United Kingdom d London School of Hygiene and Tropical Medicine, London, United Kingdom
e Infection, Immunity and Global Health, Murdoch Children's Research Institute, Melbourne, Victoria, Australia
f Department of Microbiology and Immunology, The University of Melbourne at the Peter Doherty Institute for Infection and Immunity, Melbourne, Victoria, Australia g BioGrad Limited, Liverpool, United Kingdom
h Laborat´orio de Bacteriologia, Instituto Butantan, S˜ao Paulo, Brazil
i Liverpool University Foundation Hospitals Trust, Liverpool, United Kingdom
j Department of Clinical and Toxicological Analyses, School of Pharmaceutical Sciences, University of S˜ao Paulo, S˜ao Paulo, Brazil, 05508 k Hospital Israelita Albert Einstein, S˜ao Paulo, Brazil
l Centre for Inflammation Research, University of Edinburgh, Edinburgh, United Kingdom m Boston Children's Hospital, Harvard, Medical School, MA, USA
n Leiden University Center for Infectious Diseases (LUCID), Leiden University Medical Center, Leiden, Netherlands
o NIHR Oxford Biomedical Research Centre, Oxford, United Kingdom | | | | | A R T I C L E I N F O | | A B S T R A C T | | | Keywords:
Streptococcus pneumoniae Controlled human infection model Correlates of protection Serotype-independent vaccine Machine learning
Vaccine antigen discovery Systems vaccinology
Immune responses | | Identifying conserved, immunogenic proteins that confer protection against Streptococcus pneumoniae (pneumococcus) colonization could enable development of serotype-independent vaccines.
In our controlled human infection model, no individual IgG or cytokine/chemokine response correlated significantly with protection against colonization with pneumococcus, suggesting that effective immunity reflects a coordinated, multi-antigen response. To capture these complex patterns, we trained independent Random Forest models on humoral and cellular datasets. The humoral model identified IgG responses to PdB, SP1069, and SP0899 as predictive of protection. The cellular model revealed that MCP-1 responses to SP1069 and SP0899, and IL-17A production in response to SP0648-3, were associated with protection. Elevated baseline IFN-γ, RANTES, and anti-protein IgG levels were linked to reduced colonization density.
We highlight SP1069 and SP0899 as potential serotype-independent vaccine candidates and demonstrate the utility of machine learning to identify immune correlates of protection. | | * Corresponding authors at: Oxford Vaccine Group, Department of Paediatrics, University of Oxford, Oxford, United Kingdom. E-mail address: [carla.solorzanogonzalez@paediatrics.ox.ac.uk](carla.solorzanogonzalez@paediatrics.ox.ac.uk) (C. Sol´orzano). 1 Joint first authors. 2 Joint senior authors. [https://doi.org/10.1016/j.vaccine.2026.128280](https://doi.org/10

FAQs

Why is serotype-independent pneumococcal vaccine development important?

Current vaccines protect only against a limited set of pneumococcal serotypes, leading to serotype replacement and persistent disease burden. Serotype-independent approaches could provide broader protection.

What did the controlled human infection model show about immune correlates of protection?

No individual IgG or single cytokine/chemokine response correlated significantly with protection against colonization, suggesting protection depends on coordinated responses across multiple antigens.

Which immune signatures were identified as associated with protection?

The humoral model highlighted IgG responses to PdB, SP1069, and SP0899. The cellular model associated MCP-1 responses to SP1069 and SP0899 and IL-17A production in response to SP0648-3 with protection.

Aug 6, 2026

Upload by Aria