Journal Article

Machine learning prediction of malaria vaccine efficacy based on antibody profiles

Mordmüller, Benjamin, Hoffman, Stephen L., Campo, Joseph J., Reuter, Bernhard, Pfeifer, Nico, Fendel, Rolf, Felgner, Philip L., Kremsner, Peter G., Wistuba-Hamprecht, Jacqueline

2024

Overview

Immunization through repeated direct venous inoculation of Plasmodium falciparum (Pf) sporozoites (PfSPZ) under chloroquine chemoprophylaxis, using the PfSPZ Chemoprophylaxis Vaccine (PfSPZ-CVac), induces high-level protection against controlled human malaria infection (CHMI). Humoral and cellular immunity contribute to vaccine efficacy but only limited information about the implicated Pf-specific antigens is available. Here, we examined Pf-specific antibody profiles, measured by protein arrays representing the full Pf proteome, of 40 placebo- and PfSPZ-immunized malaria-naïve volunteers from an earlier published PfSPZ-CVac dose-escalation trial. For this purpose, we both utilized and adapted supervised machine learning methods to identify predictive antibody profiles at two different time points: after immunization and before CHMI. We developed an adapted multitask support vector machine (SVM) approach and compared it to standard methods, i.e. single-task SVM, regularized logistic regression and random forests. Our results show, that the multitask SVM approach improved the classification performance to discriminate the protection status based on the underlying antibody-profiles while combining time- and dose-dependent data in the prediction model. Additionally, we developed the new f E ature di S tance ex P lainabilit Y (ESPY) method to quantify the impact of single antigens on the non-linear multitask SVM model and make it more interpretable. In conclusion, our multitask SVM model outperforms the studied standard approaches in regard of classification performance. Moreover, with our new explanation method ESPY, we were able to interpret the impact of Pf-specific antigen antibody responses that predict sterile protective immunity against CHMI after immunization. The identified Pf-specific antigens may contribute to a better understanding of immunity against human malaria and may foster vaccine development.

• Publisher: Public Library of Science,Public Library of Science (PLoS)
• Subject: Antibodies / Antibodies, Protozoan - blood / Antibodies, Protozoan - immunology / Antigens / Biology and Life Sciences / Cell-mediated immunity / Chloroquine / Classification / Computational Biology - methods / Effectiveness / Health aspects / Humans / Humoral immunity / Identification methods / Immunity / Immunization / Inoculation / Learning algorithms / Machine Learning / Malaria / Malaria vaccine / Malaria Vaccines - immunology / Malaria, Falciparum - immunology / Malaria, Falciparum - parasitology / Malaria, Falciparum - prevention & control / Medicine and Health Sciences / Methods / Parasites / Patient outcomes / Physical Sciences / Plasmodium falciparum / Plasmodium falciparum - immunology / Prediction models / Protein arrays / Proteins / Proteomes / Research and Analysis Methods / Sporozoites / Supervised learning / Support Vector Machine / Support vector machines / Treatment outcome / Vaccine development / Vaccine Efficacy / Vaccines / Vector-borne diseases / Viral antibodies