Integrating Cellular Immune Biomarkers with Machine Learning to Identify Potential Correlates of Protection for a Trypanosoma cruzi Vaccine

Autores
Gamba, Juan Cruz; Borgna, Eliana Vanesa; Prochetto, Estefanía Soledad; Perez, Ana Rosa; Batista Duharte, Alexander; Marcipar, Iván; Gerard, Matias Fernandoi; Cabrera, Gabriel Gustavo
Año de publicación
2025
Idioma
inglés
Tipo de recurso
artículo
Estado
versión publicada
Descripción
Background: Chagas disease, caused by the protozoan parasite Trypanosoma cruzi (T. cruzi), remains a major public health concern in Latin America. No licensed vaccine exists to prevent or treat T. cruzi infection. Identifying correlates of protection (CoPs) could provide substitute endpoints to guide and accelerate vaccine development. Although most CoPs established to date are antibody-based, their utility has not been demonstrated in T. cruzi vaccine reports. Thus, this study aimed to explore alternative strategies considering the use of immune cells as potential CoPs. Methods: Mice were immunized with a vaccine candidate based on the T. cruzi trans-sialidase protein (TSf) and potentiated with 5-fluorouracil (5FU) to deplete myeloid-derived suppressor cells (MDSCs). Percentages of CD4+, CD8+, and CD11b+Gr-1+ cellular biomarkers were assessed by flow cytometry from the peripheral blood of immunized mice, which were subsequently challenged with a high dose of T. cruzi. A machine-learning (ML) model based on decision trees was applied to identify potential CoPs to predict survival by day 25 post-infection. Results: Individual biomarkers obtained from flow cytometry did not show strong predictive performance. In contrast, biomarker engineering led to a combination that integrated biomarkers rationally: summing the percentages of CD8+ and CD4+ cells and subtracting the percentage of CD11b+Gr-1+ MDSC-like cells (REB), enhanced the predictive capacity. Subsequent computational analysis and ML application led to the identification of a better and even improved potential Integrative CoP: 2 ∗ %CD8++ %CD4+ - %CD11b+ Gr1+(pICoP), which significantly improved the performance of a simple one-level decision-tree model, achieving an average accuracy of 0.86 and an average AUC-ROC of 0.87 for predicting survival in immunized and infected mice. Conclusions: Results presented herein provide evidence that integrating cellular immune biomarkers through rational biomarker engineering, together with ML analysis, could lead to the identification of potential CoPs for a T. cruzi vaccine.
Fil: Gamba, Juan Cruz. Universidad Nacional del Litoral. Facultad de Bioquímica y Ciencias Biológicas; Argentina. Consejo Nacional de Investigaciones Científicas y Técnicas. Centro Científico Tecnológico Conicet - Santa Fe; Argentina
Fil: Borgna, Eliana Vanesa. Universidad Nacional del Litoral. Facultad de Bioquímica y Ciencias Biológicas; Argentina. Consejo Nacional de Investigaciones Científicas y Técnicas. Centro Científico Tecnológico Conicet - Santa Fe; Argentina
Fil: Prochetto, Estefanía Soledad. Universidad Nacional del Litoral. Facultad de Bioquímica y Ciencias Biológicas; Argentina. Universidad Nacional del Litoral. Facultad de Ciencias Médicas; Argentina
Fil: Perez, Ana Rosa. Universidad Nacional de Rosario. Facultad de Ciencias Médicas; Argentina. Consejo Nacional de Investigaciones Científicas y Técnicas. Centro Científico Tecnológico Conicet - Rosario. Instituto de Inmunología Clinica y Experimental de Rosario. Universidad Nacional de Rosario. Facultad de Ciencias Médicas. Instituto de Inmunología Clinica y Experimental de Rosario; Argentina
Fil: Batista Duharte, Alexander. Universidad de Córdoba; España
Fil: Marcipar, Iván. Universidad Nacional del Litoral. Facultad de Bioquímica y Ciencias Biológicas; Argentina
Fil: Gerard, Matias Fernandoi. Consejo Nacional de Investigaciones Científicas y Técnicas. Centro Científico Tecnológico Conicet - Santa Fe. Instituto de Investigación en Señales, Sistemas e Inteligencia Computacional. Universidad Nacional del Litoral. Facultad de Ingeniería y Ciencias Hídricas. Instituto de Investigación en Señales, Sistemas e Inteligencia Computacional; Argentina
Fil: Cabrera, Gabriel Gustavo. Universidad Nacional del Litoral. Facultad de Bioquímica y Ciencias Biológicas; Argentina
Materia
Trypanosoma cruzi
Chagas disease
Correlate of protection
Decision tree
Machine learning
Myeloid-derived suppressor cells
Vaccine
Nivel de accesibilidad
acceso abierto
Condiciones de uso
https://creativecommons.org/licenses/by-nc-sa/2.5/ar/
Repositorio
CONICET Digital (CONICET)
Institución
Consejo Nacional de Investigaciones Científicas y Técnicas
OAI Identificador
oai:ri.conicet.gov.ar:11336/282676
Acceder
id CONICETDig_c325ec908559722deb9d53ae0d27c064
oai_identifier_str oai:ri.conicet.gov.ar:11336/282676
network_acronym_str CONICETDig
repository_id_str 3498
network_name_str CONICET Digital (CONICET)
spelling Integrating Cellular Immune Biomarkers with Machine Learning to Identify Potential Correlates of Protection for a Trypanosoma cruzi VaccineGamba, Juan CruzBorgna, Eliana VanesaProchetto, Estefanía SoledadPerez, Ana RosaBatista Duharte, AlexanderMarcipar, IvánGerard, Matias FernandoiCabrera, Gabriel GustavoTrypanosoma cruziChagas diseaseCorrelate of protectionDecision treeMachine learningMyeloid-derived suppressor cellsVaccinehttps://purl.org/becyt/ford/3.1https://purl.org/becyt/ford/3Background: Chagas disease, caused by the protozoan parasite Trypanosoma cruzi (T. cruzi), remains a major public health concern in Latin America. No licensed vaccine exists to prevent or treat T. cruzi infection. Identifying correlates of protection (CoPs) could provide substitute endpoints to guide and accelerate vaccine development. Although most CoPs established to date are antibody-based, their utility has not been demonstrated in T. cruzi vaccine reports. Thus, this study aimed to explore alternative strategies considering the use of immune cells as potential CoPs. Methods: Mice were immunized with a vaccine candidate based on the T. cruzi trans-sialidase protein (TSf) and potentiated with 5-fluorouracil (5FU) to deplete myeloid-derived suppressor cells (MDSCs). Percentages of CD4+, CD8+, and CD11b+Gr-1+ cellular biomarkers were assessed by flow cytometry from the peripheral blood of immunized mice, which were subsequently challenged with a high dose of T. cruzi. A machine-learning (ML) model based on decision trees was applied to identify potential CoPs to predict survival by day 25 post-infection. Results: Individual biomarkers obtained from flow cytometry did not show strong predictive performance. In contrast, biomarker engineering led to a combination that integrated biomarkers rationally: summing the percentages of CD8+ and CD4+ cells and subtracting the percentage of CD11b+Gr-1+ MDSC-like cells (REB), enhanced the predictive capacity. Subsequent computational analysis and ML application led to the identification of a better and even improved potential Integrative CoP: 2 ∗ %CD8++ %CD4+ - %CD11b+ Gr1+(pICoP), which significantly improved the performance of a simple one-level decision-tree model, achieving an average accuracy of 0.86 and an average AUC-ROC of 0.87 for predicting survival in immunized and infected mice. Conclusions: Results presented herein provide evidence that integrating cellular immune biomarkers through rational biomarker engineering, together with ML analysis, could lead to the identification of potential CoPs for a T. cruzi vaccine.Fil: Gamba, Juan Cruz. Universidad Nacional del Litoral. Facultad de Bioquímica y Ciencias Biológicas; Argentina. Consejo Nacional de Investigaciones Científicas y Técnicas. Centro Científico Tecnológico Conicet - Santa Fe; ArgentinaFil: Borgna, Eliana Vanesa. Universidad Nacional del Litoral. Facultad de Bioquímica y Ciencias Biológicas; Argentina. Consejo Nacional de Investigaciones Científicas y Técnicas. Centro Científico Tecnológico Conicet - Santa Fe; ArgentinaFil: Prochetto, Estefanía Soledad. Universidad Nacional del Litoral. Facultad de Bioquímica y Ciencias Biológicas; Argentina. Universidad Nacional del Litoral. Facultad de Ciencias Médicas; ArgentinaFil: Perez, Ana Rosa. Universidad Nacional de Rosario. Facultad de Ciencias Médicas; Argentina. Consejo Nacional de Investigaciones Científicas y Técnicas. Centro Científico Tecnológico Conicet - Rosario. Instituto de Inmunología Clinica y Experimental de Rosario. Universidad Nacional de Rosario. Facultad de Ciencias Médicas. Instituto de Inmunología Clinica y Experimental de Rosario; ArgentinaFil: Batista Duharte, Alexander. Universidad de Córdoba; EspañaFil: Marcipar, Iván. Universidad Nacional del Litoral. Facultad de Bioquímica y Ciencias Biológicas; ArgentinaFil: Gerard, Matias Fernandoi. Consejo Nacional de Investigaciones Científicas y Técnicas. Centro Científico Tecnológico Conicet - Santa Fe. Instituto de Investigación en Señales, Sistemas e Inteligencia Computacional. Universidad Nacional del Litoral. Facultad de Ingeniería y Ciencias Hídricas. Instituto de Investigación en Señales, Sistemas e Inteligencia Computacional; ArgentinaFil: Cabrera, Gabriel Gustavo. Universidad Nacional del Litoral. Facultad de Bioquímica y Ciencias Biológicas; ArgentinaMDPI2025-08info:eu-repo/semantics/articleinfo:eu-repo/semantics/publishedVersionhttp://purl.org/coar/resource_type/c_6501info:ar-repo/semantics/articuloapplication/pdfapplication/pdfapplication/pdfapplication/pdfhttp://hdl.handle.net/11336/282676Gamba, Juan Cruz; Borgna, Eliana Vanesa; Prochetto, Estefanía Soledad; Perez, Ana Rosa; Batista Duharte, Alexander; et al.; Integrating Cellular Immune Biomarkers with Machine Learning to Identify Potential Correlates of Protection for a Trypanosoma cruzi Vaccine; MDPI; Vaccines; 13; 9; 8-2025; 1-252076-393XCONICET DigitalCONICETenginfo:eu-repo/semantics/altIdentifier/url/https://www.mdpi.com/2076-393X/13/9/915info:eu-repo/semantics/altIdentifier/doi/10.3390/vaccines13090915info:eu-repo/semantics/openAccesshttps://creativecommons.org/licenses/by-nc-sa/2.5/ar/reponame:CONICET Digital (CONICET)instname:Consejo Nacional de Investigaciones Científicas y Técnicas2026-05-06T16:42:58Zoai:ri.conicet.gov.ar:11336/282676instacron:CONICETInstitucionalhttp://ri.conicet.gov.ar/Organismo científico-tecnológicoNo correspondehttp://ri.conicet.gov.ar/oai/requestdasensio@conicet.gov.ar; lcarlino@conicet.gov.arArgentinaNo correspondeNo correspondeNo correspondeopendoar:34982026-05-06 16:42:58.855CONICET Digital (CONICET) - Consejo Nacional de Investigaciones Científicas y Técnicasfalse
dc.title.none.fl_str_mv Integrating Cellular Immune Biomarkers with Machine Learning to Identify Potential Correlates of Protection for a Trypanosoma cruzi Vaccine
title Integrating Cellular Immune Biomarkers with Machine Learning to Identify Potential Correlates of Protection for a Trypanosoma cruzi Vaccine
spellingShingle Integrating Cellular Immune Biomarkers with Machine Learning to Identify Potential Correlates of Protection for a Trypanosoma cruzi Vaccine
Gamba, Juan Cruz
Trypanosoma cruzi
Chagas disease
Correlate of protection
Decision tree
Machine learning
Myeloid-derived suppressor cells
Vaccine
title_short Integrating Cellular Immune Biomarkers with Machine Learning to Identify Potential Correlates of Protection for a Trypanosoma cruzi Vaccine
title_full Integrating Cellular Immune Biomarkers with Machine Learning to Identify Potential Correlates of Protection for a Trypanosoma cruzi Vaccine
title_fullStr Integrating Cellular Immune Biomarkers with Machine Learning to Identify Potential Correlates of Protection for a Trypanosoma cruzi Vaccine
title_full_unstemmed Integrating Cellular Immune Biomarkers with Machine Learning to Identify Potential Correlates of Protection for a Trypanosoma cruzi Vaccine
title_sort Integrating Cellular Immune Biomarkers with Machine Learning to Identify Potential Correlates of Protection for a Trypanosoma cruzi Vaccine
dc.creator.none.fl_str_mv Gamba, Juan Cruz
Borgna, Eliana Vanesa
Prochetto, Estefanía Soledad
Perez, Ana Rosa
Batista Duharte, Alexander
Marcipar, Iván
Gerard, Matias Fernandoi
Cabrera, Gabriel Gustavo
author Gamba, Juan Cruz
author_facet Gamba, Juan Cruz
Borgna, Eliana Vanesa
Prochetto, Estefanía Soledad
Perez, Ana Rosa
Batista Duharte, Alexander
Marcipar, Iván
Gerard, Matias Fernandoi
Cabrera, Gabriel Gustavo
author_role author
author2 Borgna, Eliana Vanesa
Prochetto, Estefanía Soledad
Perez, Ana Rosa
Batista Duharte, Alexander
Marcipar, Iván
Gerard, Matias Fernandoi
Cabrera, Gabriel Gustavo
author2_role author
author
author
author
author
author
author
dc.subject.none.fl_str_mv Trypanosoma cruzi
Chagas disease
Correlate of protection
Decision tree
Machine learning
Myeloid-derived suppressor cells
Vaccine
topic Trypanosoma cruzi
Chagas disease
Correlate of protection
Decision tree
Machine learning
Myeloid-derived suppressor cells
Vaccine
purl_subject.fl_str_mv https://purl.org/becyt/ford/3.1
https://purl.org/becyt/ford/3
dc.description.none.fl_txt_mv Background: Chagas disease, caused by the protozoan parasite Trypanosoma cruzi (T. cruzi), remains a major public health concern in Latin America. No licensed vaccine exists to prevent or treat T. cruzi infection. Identifying correlates of protection (CoPs) could provide substitute endpoints to guide and accelerate vaccine development. Although most CoPs established to date are antibody-based, their utility has not been demonstrated in T. cruzi vaccine reports. Thus, this study aimed to explore alternative strategies considering the use of immune cells as potential CoPs. Methods: Mice were immunized with a vaccine candidate based on the T. cruzi trans-sialidase protein (TSf) and potentiated with 5-fluorouracil (5FU) to deplete myeloid-derived suppressor cells (MDSCs). Percentages of CD4+, CD8+, and CD11b+Gr-1+ cellular biomarkers were assessed by flow cytometry from the peripheral blood of immunized mice, which were subsequently challenged with a high dose of T. cruzi. A machine-learning (ML) model based on decision trees was applied to identify potential CoPs to predict survival by day 25 post-infection. Results: Individual biomarkers obtained from flow cytometry did not show strong predictive performance. In contrast, biomarker engineering led to a combination that integrated biomarkers rationally: summing the percentages of CD8+ and CD4+ cells and subtracting the percentage of CD11b+Gr-1+ MDSC-like cells (REB), enhanced the predictive capacity. Subsequent computational analysis and ML application led to the identification of a better and even improved potential Integrative CoP: 2 ∗ %CD8++ %CD4+ - %CD11b+ Gr1+(pICoP), which significantly improved the performance of a simple one-level decision-tree model, achieving an average accuracy of 0.86 and an average AUC-ROC of 0.87 for predicting survival in immunized and infected mice. Conclusions: Results presented herein provide evidence that integrating cellular immune biomarkers through rational biomarker engineering, together with ML analysis, could lead to the identification of potential CoPs for a T. cruzi vaccine.
Fil: Gamba, Juan Cruz. Universidad Nacional del Litoral. Facultad de Bioquímica y Ciencias Biológicas; Argentina. Consejo Nacional de Investigaciones Científicas y Técnicas. Centro Científico Tecnológico Conicet - Santa Fe; Argentina
Fil: Borgna, Eliana Vanesa. Universidad Nacional del Litoral. Facultad de Bioquímica y Ciencias Biológicas; Argentina. Consejo Nacional de Investigaciones Científicas y Técnicas. Centro Científico Tecnológico Conicet - Santa Fe; Argentina
Fil: Prochetto, Estefanía Soledad. Universidad Nacional del Litoral. Facultad de Bioquímica y Ciencias Biológicas; Argentina. Universidad Nacional del Litoral. Facultad de Ciencias Médicas; Argentina
Fil: Perez, Ana Rosa. Universidad Nacional de Rosario. Facultad de Ciencias Médicas; Argentina. Consejo Nacional de Investigaciones Científicas y Técnicas. Centro Científico Tecnológico Conicet - Rosario. Instituto de Inmunología Clinica y Experimental de Rosario. Universidad Nacional de Rosario. Facultad de Ciencias Médicas. Instituto de Inmunología Clinica y Experimental de Rosario; Argentina
Fil: Batista Duharte, Alexander. Universidad de Córdoba; España
Fil: Marcipar, Iván. Universidad Nacional del Litoral. Facultad de Bioquímica y Ciencias Biológicas; Argentina
Fil: Gerard, Matias Fernandoi. Consejo Nacional de Investigaciones Científicas y Técnicas. Centro Científico Tecnológico Conicet - Santa Fe. Instituto de Investigación en Señales, Sistemas e Inteligencia Computacional. Universidad Nacional del Litoral. Facultad de Ingeniería y Ciencias Hídricas. Instituto de Investigación en Señales, Sistemas e Inteligencia Computacional; Argentina
Fil: Cabrera, Gabriel Gustavo. Universidad Nacional del Litoral. Facultad de Bioquímica y Ciencias Biológicas; Argentina
description Background: Chagas disease, caused by the protozoan parasite Trypanosoma cruzi (T. cruzi), remains a major public health concern in Latin America. No licensed vaccine exists to prevent or treat T. cruzi infection. Identifying correlates of protection (CoPs) could provide substitute endpoints to guide and accelerate vaccine development. Although most CoPs established to date are antibody-based, their utility has not been demonstrated in T. cruzi vaccine reports. Thus, this study aimed to explore alternative strategies considering the use of immune cells as potential CoPs. Methods: Mice were immunized with a vaccine candidate based on the T. cruzi trans-sialidase protein (TSf) and potentiated with 5-fluorouracil (5FU) to deplete myeloid-derived suppressor cells (MDSCs). Percentages of CD4+, CD8+, and CD11b+Gr-1+ cellular biomarkers were assessed by flow cytometry from the peripheral blood of immunized mice, which were subsequently challenged with a high dose of T. cruzi. A machine-learning (ML) model based on decision trees was applied to identify potential CoPs to predict survival by day 25 post-infection. Results: Individual biomarkers obtained from flow cytometry did not show strong predictive performance. In contrast, biomarker engineering led to a combination that integrated biomarkers rationally: summing the percentages of CD8+ and CD4+ cells and subtracting the percentage of CD11b+Gr-1+ MDSC-like cells (REB), enhanced the predictive capacity. Subsequent computational analysis and ML application led to the identification of a better and even improved potential Integrative CoP: 2 ∗ %CD8++ %CD4+ - %CD11b+ Gr1+(pICoP), which significantly improved the performance of a simple one-level decision-tree model, achieving an average accuracy of 0.86 and an average AUC-ROC of 0.87 for predicting survival in immunized and infected mice. Conclusions: Results presented herein provide evidence that integrating cellular immune biomarkers through rational biomarker engineering, together with ML analysis, could lead to the identification of potential CoPs for a T. cruzi vaccine.
publishDate 2025
dc.date.none.fl_str_mv 2025-08
dc.type.none.fl_str_mv info:eu-repo/semantics/article
info:eu-repo/semantics/publishedVersion
http://purl.org/coar/resource_type/c_6501
info:ar-repo/semantics/articulo
format article
status_str publishedVersion
dc.identifier.none.fl_str_mv http://hdl.handle.net/11336/282676
Gamba, Juan Cruz; Borgna, Eliana Vanesa; Prochetto, Estefanía Soledad; Perez, Ana Rosa; Batista Duharte, Alexander; et al.; Integrating Cellular Immune Biomarkers with Machine Learning to Identify Potential Correlates of Protection for a Trypanosoma cruzi Vaccine; MDPI; Vaccines; 13; 9; 8-2025; 1-25
2076-393X
CONICET Digital
CONICET
url http://hdl.handle.net/11336/282676
identifier_str_mv Gamba, Juan Cruz; Borgna, Eliana Vanesa; Prochetto, Estefanía Soledad; Perez, Ana Rosa; Batista Duharte, Alexander; et al.; Integrating Cellular Immune Biomarkers with Machine Learning to Identify Potential Correlates of Protection for a Trypanosoma cruzi Vaccine; MDPI; Vaccines; 13; 9; 8-2025; 1-25
2076-393X
CONICET Digital
CONICET
dc.language.none.fl_str_mv eng
language eng
dc.relation.none.fl_str_mv info:eu-repo/semantics/altIdentifier/url/https://www.mdpi.com/2076-393X/13/9/915
info:eu-repo/semantics/altIdentifier/doi/10.3390/vaccines13090915
dc.rights.none.fl_str_mv info:eu-repo/semantics/openAccess
https://creativecommons.org/licenses/by-nc-sa/2.5/ar/
eu_rights_str_mv openAccess
rights_invalid_str_mv https://creativecommons.org/licenses/by-nc-sa/2.5/ar/
dc.format.none.fl_str_mv application/pdf
application/pdf
application/pdf
application/pdf
dc.publisher.none.fl_str_mv MDPI
publisher.none.fl_str_mv MDPI
dc.source.none.fl_str_mv reponame:CONICET Digital (CONICET)
instname:Consejo Nacional de Investigaciones Científicas y Técnicas
reponame_str CONICET Digital (CONICET)
collection CONICET Digital (CONICET)
instname_str Consejo Nacional de Investigaciones Científicas y Técnicas
repository.name.fl_str_mv CONICET Digital (CONICET) - Consejo Nacional de Investigaciones Científicas y Técnicas
repository.mail.fl_str_mv dasensio@conicet.gov.ar; lcarlino@conicet.gov.ar
_version_ 1864650368537853952
score 12.637756

Publicaciones similares