Systems immunologist applying machine learning to understand human immunology and how vaccines work. Co-developer of SIMON, an open-source platform for the application of machine learning to biological and clinical data.
Machine learning holds considerable promise for understanding complex biological processes such a... more Machine learning holds considerable promise for understanding complex biological processes such as vaccine responses. Capturing interindividual variability is essential to increase the statistical power necessary for building more accurate predictive models. However, available approaches have difficulty coping with incomplete datasets which is often the case when combining studies. Additionally, there are hundreds of algorithms available and no simple way to find the optimal one. In this study, we developed Sequential Iterative Modeling “OverNight” (SIMON), an automated machine learning system that compares results from 128 different algorithms and is particularly suitable for datasets containing many missing values. We applied SIMON to data from five clinical studies of seasonal influenza vaccination. The results reveal previously unrecognized CD4+ and CD8+ T cell subsets strongly associated with a robust Ab response to influenza Ags. These results demonstrate that SIMON can greatly speed up the choice of analysis modalities. Hence, it is a highly useful approach for data-driven hypothesis generation from disparate clinical datasets. Our strategy could be used to gain biological insight from ever-expanding heterogeneous datasets that are publicly available.
Machine learning has the potential to identify novel biological factors underlying successful ant... more Machine learning has the potential to identify novel biological factors underlying successful antibody responses to influenza vaccines. The first attempts have revealed a high level of complexity in establishing influenza immunity, and many different cellular and molecular components are involved. Of note is that the previously identified correlates of protection fail to account for the majority of individual responses across different age groups and influenza seasons. Challenges remain from the small sample sizes in most studies and from often limited data sets, such as transcriptomic data. Here we report the creation of a unified database, FluPRINT, to enable large-scale studies exploring the cellular and molecular underpinnings of successful antibody responses to influenza vaccines. Over 3,000 parameters were considered, including serological responses to influenza strains, serum cytokines, cell phenotypes, and cytokine stimulations. FluPRINT, facilitates the application of machine learning algorithms for data mining. The data are publicly available and represent a resource to uncover new markers and mechanisms that are important for influenza vaccine immunogenicity.
Development of an effective vaccine against human cytomegalovirus (HCMV) is a need of utmost medi... more Development of an effective vaccine against human cytomegalovirus (HCMV) is a need of utmost medical importance. Generally, it is believed that a live attenuated vaccine would best provide protective immunity against this tenacious pathogen. Here, we propose a strategy for an HCMV vaccine that aims at the simultaneous activation of innate and adaptive immune responses. An HCMV strain expressing the host ligand ULBP2 for the NKG2D receptor was found to be susceptible to control by natural killer (NK) cells, and preserved the ability to stimulate HCMV-specific T cells. Infection with the ULBP2-expressing HCMV strain caused diminished cell surface levels of MHC class I molecules. While expression of the NKG2D ligand increased the cytolytic activity of NK cells, NKG2D engagement in CD8+ T cells provided co-stimulation and compensated for lower MHC class I expression. Altogether , our data indicate that triggering of both arms of the immune system is a promising approach applicable to the generation of a live attenuated HCMV vaccine. Human cytomegalovirus (CMV) is a major cause of morbidity and mortality in congenitally infected newborns and immunocompromised individuals, indicating an utmost need for a vaccine to protect these vulnerable groups. Recent experimental studies in animal models, including non-human primates, have shown that attenuated CMVs trigger a potent immune response and are attractive vaccine candidates. However, an effective CMV vaccine is still not available. Here, we demonstrate that rational engineering of a live attenuated human CMV vaccine candidate is feasible. We equipped a CMV strain with an immunostimulatory molecule that is a ligand for an activating receptor present on both Natural Killer cells and CD8+ T cells. Moreover, we deleted several immunoevasins
Machine learning holds considerable promise for understanding complex biological processes such a... more Machine learning holds considerable promise for understanding complex biological processes such as vaccine responses. Capturing interindividual variability is essential to increase the statistical power necessary for building more accurate predictive models. However, available approaches have difficulty coping with incomplete datasets which is often the case when combining studies. Additionally, there are hundreds of algorithms available and no simple way to find the optimal one. In this study, we developed Sequential Iterative Modeling “OverNight” (SIMON), an automated machine learning system that compares results from 128 different algorithms and is particularly suitable for datasets containing many missing values. We applied SIMON to data from five clinical studies of seasonal influenza vaccination. The results reveal previously unrecognized CD4+ and CD8+ T cell subsets strongly associated with a robust Ab response to influenza Ags. These results demonstrate that SIMON can greatly speed up the choice of analysis modalities. Hence, it is a highly useful approach for data-driven hypothesis generation from disparate clinical datasets. Our strategy could be used to gain biological insight from ever-expanding heterogeneous datasets that are publicly available.
Machine learning has the potential to identify novel biological factors underlying successful ant... more Machine learning has the potential to identify novel biological factors underlying successful antibody responses to influenza vaccines. The first attempts have revealed a high level of complexity in establishing influenza immunity, and many different cellular and molecular components are involved. Of note is that the previously identified correlates of protection fail to account for the majority of individual responses across different age groups and influenza seasons. Challenges remain from the small sample sizes in most studies and from often limited data sets, such as transcriptomic data. Here we report the creation of a unified database, FluPRINT, to enable large-scale studies exploring the cellular and molecular underpinnings of successful antibody responses to influenza vaccines. Over 3,000 parameters were considered, including serological responses to influenza strains, serum cytokines, cell phenotypes, and cytokine stimulations. FluPRINT, facilitates the application of machine learning algorithms for data mining. The data are publicly available and represent a resource to uncover new markers and mechanisms that are important for influenza vaccine immunogenicity.
Development of an effective vaccine against human cytomegalovirus (HCMV) is a need of utmost medi... more Development of an effective vaccine against human cytomegalovirus (HCMV) is a need of utmost medical importance. Generally, it is believed that a live attenuated vaccine would best provide protective immunity against this tenacious pathogen. Here, we propose a strategy for an HCMV vaccine that aims at the simultaneous activation of innate and adaptive immune responses. An HCMV strain expressing the host ligand ULBP2 for the NKG2D receptor was found to be susceptible to control by natural killer (NK) cells, and preserved the ability to stimulate HCMV-specific T cells. Infection with the ULBP2-expressing HCMV strain caused diminished cell surface levels of MHC class I molecules. While expression of the NKG2D ligand increased the cytolytic activity of NK cells, NKG2D engagement in CD8+ T cells provided co-stimulation and compensated for lower MHC class I expression. Altogether , our data indicate that triggering of both arms of the immune system is a promising approach applicable to the generation of a live attenuated HCMV vaccine. Human cytomegalovirus (CMV) is a major cause of morbidity and mortality in congenitally infected newborns and immunocompromised individuals, indicating an utmost need for a vaccine to protect these vulnerable groups. Recent experimental studies in animal models, including non-human primates, have shown that attenuated CMVs trigger a potent immune response and are attractive vaccine candidates. However, an effective CMV vaccine is still not available. Here, we demonstrate that rational engineering of a live attenuated human CMV vaccine candidate is feasible. We equipped a CMV strain with an immunostimulatory molecule that is a ligand for an activating receptor present on both Natural Killer cells and CD8+ T cells. Moreover, we deleted several immunoevasins
Uploads
Papers by Adriana Tomic