Baseline gene signatures of reactogenicity to Ebola vaccination - a machine learning approach across multiple cohorts

Aug 3, 2026

Upload by Maeve

Focus on baseline molecular predictors of vaccine reactogenicity in Ebola vaccination, integrating prevaccination gene expression profiles with adverse events observed within 14 days after dosing. A machine learning framework was developed and applied to expression data from 343 blood samples across four phase I cohorts spanning Switzerland, USA, Gabon, and Kenya. Analysis highlighted 22 key genes linked to common transient adverse events, supporting mechanistic interpretation and advancing personalized vaccinology and vaccine safety assessment.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages10

Reading Time25 min

AccessFree to download

Introduction

Methods

Results and Discussion

Key genes linked to adverse events

Keywords

TYPE Original Research PUBLISHED 08 November 2023 DOI 10.3389/fimmu.2023.1259197 OPEN ACCESS EDITED BY Francesco Pappalardo, University of Catania, Italy REVIEWED BY Elke Bergmann-Leitner, Walter Reed Army Institute of Research, United States Saranya Sridhar, Sanoﬁ Pasteur, United Kingdom *CORRESPONDENCE Helder I. Nakaya [helder.nakaya@einstein.br](helder.nakaya@einstein.br) RECEIVED 15 July 2023 ACCEPTED 23 October 2023 PUBLISHED 08 November 2023 CITATION Gonzalez Dias Carvalho PC, Dominguez Crespo Hirata T, Mano Alves LY, Moscardini IF, do Nascimento APB, Costa-Martins AG, Sorgi S, Harandi AM, Ferreira DM, Vianello E, Haks MC, Ottenhoff THM, Santoro F, Martinez-Murillo P, Huttner A, Siegrist C-A, Medaglini D and Nakaya HI (2023) Baseline gene signatures of reactogenicity to Ebola vaccination: a machine learning approach across multiple cohorts. Front. Immunol. 14:1259197 . doi: 10.3389/fimmu.2023.1259197 COPYRIGHT © 2023 Gonzalez Dias Carvalho, Dominguez Crespo Hirata, Mano Alves, Moscardini, do Nascimento, Costa-Martins, Sorgi, Harandi, Ferreira, Vianello, Haks, Ottenhoff, Santoro, Martinez-Murillo, Huttner, Siegrist, Medaglini and Nakaya. This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY) . The use, distribution or reproduction in other forums is permitted, provided the original author(s) and the copyright owner(s) are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms. Baseline gene signatures of reactogenicity to Ebola vaccination: a machine learning approach across multiple cohorts Patrícia Conceição Gonzalez Dias Carvalho 1,2 , Thiago Dominguez Crespo Hirata 3, Leandro Yukio Mano Alves 3, Isabelle Franco Moscardini 4, Ana Paula Barbosa do Nascimento 5, Andr´e G. Costa-Martins 3,6, Sara Sorgi 7, Ali M. Harandi 8,9, Daniela M. Ferreira 1,2, Eleonora Vianello 10, Mariëlle C. Haks 10, Tom H. M. Ottenhoff 10, Francesco Santoro 7, Paola Martinez-Murillo 11, for VSV-EBOVAC Consortia, for VSV-EBOPLUS Consortia, Angela Huttner 11,12, Claire-Anne Siegrist 11, Donata Medaglini 13 and Helder I. Nakaya 14,15* 1Oxford Vaccine Group, University of Oxford, Oxford, United Kingdom, 2 Department of Clinical Sciences, Liverpool School of Tropical Medicine, Liverpool, United Kingdom, 3 Department of Clinical and Toxicological Analyses, School of Pharmaceutical Sciences, University of São Paulo, São Paulo, Brazil, 4 Microbiotec Srl, Siena, Italy, 5 Division of Infectious Diseases, Cincinnati Children ’s Hospital Medical Center, Cincinnati, OH, United States, 6Artiﬁcial Intelligence and Analytics Department, Institute for Technological Research, São Paulo, Brazil, 7 Laboratory of Molecular Microbiology and Biotechnology (LAMMB), Department of Medical Biotechnologies, University of Siena, Siena, Italy, 8 Department of Microbiology and Immunology, Institute of Biomedicine, Sahlgrenska Academy, University of Gothenburg, Gothenburg, Sweden, 9Vaccine Evaluation Center, BC Children ’s Hospital Research Institute, University of British Columbia, Vancouver, BC, Canada, 10 Department of Infectious Diseases, Leiden University Medical Center, Leiden, Netherlands, 11Centre for Vaccinology, Faculty of Medicine, University of Geneva, Geneva, Switzerland, 12 Infectious Diseases Service, Geneva University Hospitals, Geneva, Switzerland, 13 Department of Medical Biotechnologies, University of Siena, Siena, Italy, 14Scientiﬁc Platform Pasteur-University of São Paulo, São Paulo, Brazil, 15 Hospital Israelita Albert Einstein, São Paulo, Brazil Introduction: The rVSVDG-ZEBOV-GP (Ervebo®) vaccine is both immunogenic and protective against Ebola. However, the vaccine can cause a broad range of transient adverse reactions, from headache to arthritis. Identifying baseline reactogenicity sig

FAQs

What data are used to predict Ebola vaccine reactogenicity?

Prevaccination gene expression data are integrated with adverse events occurring within 14 days post-vaccination.

How many cohorts and samples support the analysis?

The study analyzes 144 genes across 343 blood samples from participants in four phase I clinical trial cohorts.

What was the main outcome of the machine learning approach?

The approach identified 22 key genes associated with adverse events such as local reactions, fatigue, headache, myalgia, fever, chills, arthralgia, nausea, and arthritis.

Aug 3, 2026

Upload by Maeve