1
|
Wang X, VanValkenberg A, Odom AR, Ellner JJ, Hochberg NS, Salgame P, Patil P, Johnson WE. Comparison of gene set scoring methods for reproducible evaluation of tuberculosis gene signatures. BMC Infect Dis 2024; 24:610. [PMID: 38902649 PMCID: PMC11191245 DOI: 10.1186/s12879-024-09457-z] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/29/2023] [Accepted: 05/31/2024] [Indexed: 06/22/2024] Open
Abstract
BACKGROUND Blood-based transcriptional gene signatures for tuberculosis (TB) have been developed with potential use to diagnose disease. However, an unresolved issue is whether gene set enrichment analysis of the signature transcripts alone is sufficient for prediction and differentiation or whether it is necessary to use the original model created when the signature was derived. Intra-method comparison is complicated by the unavailability of original training data and missing details about the original trained model. To facilitate the utilization of these signatures in TB research, comparisons between gene set scoring methods cross-data validation of original model implementations are needed. METHODS We compared the performance of 19 TB gene signatures across 24 transcriptomic datasets using both rrebuilt original models and gene set scoring methods. Existing gene set scoring methods, including ssGSEA, GSVA, PLAGE, Singscore, and Zscore, were used as alternative approaches to obtain the profile scores. The area under the ROC curve (AUC) value was computed to measure performance. Correlation analysis and Wilcoxon paired tests were used to compare the performance of enrichment methods with the original models. RESULTS For many signatures, the predictions from gene set scoring methods were highly correlated and statistically equivalent to the results given by the original models. In some cases, PLAGE outperformed the original models when considering signatures' weighted mean AUC values and the AUC results within individual studies. CONCLUSION Gene set enrichment scoring of existing gene sets can distinguish patients with active TB disease from other clinical conditions with equivalent or improved accuracy compared to the original methods and models. These data justify using gene set scoring methods of published TB gene signatures for predicting TB risk and treatment outcomes, especially when original models are difficult to apply or implement.
Collapse
Affiliation(s)
- Xutao Wang
- Department of Biostatistics, Boston University, Boston, MA, USA
- Division of Computational Biomedicine and Bioinformatics Program, Boston University, Boston, MA, USA
| | - Arthur VanValkenberg
- Division of Infectious Disease, Center for Data Science, Rutgers New Jersey Medical School, Newark, NJ, USA
| | - Aubrey R Odom
- Division of Computational Biomedicine and Bioinformatics Program, Boston University, Boston, MA, USA
| | - Jerrold J Ellner
- Department of Medicine, Center for Emerging Pathogens, Rutgers New Jersey Medical School, Newark, NJ, USA
| | - Natasha S Hochberg
- Boston Medical Center, Boston, MA, USA
- Section of Infectious Diseases, Boston University School of Medicine, Boston, MA, USA
| | - Padmini Salgame
- Department of Medicine, Center for Emerging Pathogens, Rutgers New Jersey Medical School, Newark, NJ, USA
| | - Prasad Patil
- Department of Biostatistics, Boston University, Boston, MA, USA
| | - W Evan Johnson
- Division of Infectious Disease, Center for Data Science, Rutgers New Jersey Medical School, Newark, NJ, USA.
- Department of Medicine, Center for Emerging Pathogens, Rutgers New Jersey Medical School, Newark, NJ, USA.
| |
Collapse
|
2
|
Balakrishnan V, Kehrabi Y, Ramanathan G, Paul SA, Tiong CK. Machine learning approaches in diagnosing tuberculosis through biomarkers - A systematic review. PROGRESS IN BIOPHYSICS AND MOLECULAR BIOLOGY 2023; 179:16-25. [PMID: 36931609 DOI: 10.1016/j.pbiomolbio.2023.03.001] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Subscribe] [Scholar Register] [Received: 12/09/2022] [Revised: 02/25/2023] [Accepted: 03/09/2023] [Indexed: 03/17/2023]
Abstract
Biomarker-based tests may facilitate Tuberculosis (TB) diagnosis, accelerate treatment initiation, and thus improve outcomes. This review synthesizes the literature on biomarker-based detection for TB diagnosis using machine learning. The systematic review approach follows the PRISMA guideline. Articles were sought using relevant keywords from Web of Science, PubMed, and Scopus, resulting in 19 eligible studies after a meticulous screening. All the studies were found to have focused on the supervised learning approach, with Support Vector Machine (SVM) and Random Forest emerging as the top two algorithms, with the highest accuracy, sensitivity and specificity reported to be 97.0%, 99.2%, and 98.0%, respectively. Further, protein-based biomarkers were widely explored, followed by gene-based such as RNA sequence and, Spoligotypes. Publicly available datasets were observed to be popularly used by the studies reviewed whilst studies targeting specific cohorts such as HIV patients or children gathering their own data from healthcare facilities, leading to smaller datasets. Of these, most studies used the leave one out cross validation technique to mitigate overfitting. The review shows that machine learning is increasingly assessed in research to improve TB diagnosis through biomarkers, as promising results were shown in terms of model's detection performance. This provides insights on the possible application of machine learning approaches to diagnose TB using biomarkers as opposed to the traditional methods that can be time consuming. Low-middle income settings, where access to basic biomarkers could be provided as compared to sputum-based tests that are not always available, could be a major application of such models.
Collapse
Affiliation(s)
- Vimala Balakrishnan
- Faculty of Computer Science and Information Technology, Universiti Malaya, 50603, Kuala Lumpur, Malaysia.
| | - Yousra Kehrabi
- Department of Infectious Diseases, Hôpital Bichat-Claude Bernard, Assistance Publique Hôpitaux de Paris, Paris, France
| | - Ghayathri Ramanathan
- Faculty of Computer Science and Information Technology, Universiti Malaya, 50603, Kuala Lumpur, Malaysia
| | - Scott Arjay Paul
- School of Biosciences, Faculty of Health and Medical Sciences, Taylor's University, Subang Jaya, Malaysia
| | - Chiong Kian Tiong
- Faculty of Medicine, Universiti Malaya, 50603, Kuala Lumpur, Malaysia
| |
Collapse
|
3
|
Tateosian NL, Morelli MP, Pellegrini JM, García VE. Beyond the Clinic: The Activation of Diverse Cellular and Humoral Factors Shapes the Immunological Status of Patients with Active Tuberculosis. Int J Mol Sci 2023; 24:5033. [PMID: 36902461 PMCID: PMC10002939 DOI: 10.3390/ijms24055033] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/11/2023] [Revised: 02/24/2023] [Accepted: 02/27/2023] [Indexed: 03/08/2023] Open
Abstract
Mycobacterium tuberculosis (Mtb), the etiologic agent of tuberculosis (TB), has killed nearly one billion people in the last two centuries. Nowadays, TB remains a major global health problem, ranking among the thirteen leading causes of death worldwide. Human TB infection spans different levels of stages: incipient, subclinical, latent and active TB, all of them with varying symptoms, microbiological characteristics, immune responses and pathologies profiles. After infection, Mtb interacts with diverse cells of both innate and adaptive immune compartments, playing a crucial role in the modulation and development of the pathology. Underlying TB clinical manifestations, individual immunological profiles can be identified in patients with active TB according to the strength of their immune responses to Mtb infection, defining diverse endotypes. Those different endotypes are regulated by a complex interaction of the patient's cellular metabolism, genetic background, epigenetics, and gene transcriptional regulation. Here, we review immunological categorizations of TB patients based on the activation of different cellular populations (both myeloid and lymphocytic subsets) and humoral mediators (such as cytokines and lipid mediators). The analysis of the participating factors that operate during active Mtb infection shaping the immunological status or immune endotypes of TB patients could contribute to the development of Host Directed Therapy.
Collapse
Affiliation(s)
- Nancy Liliana Tateosian
- Departamento de Química Biológica, Facultad de Ciencias Exactas y Naturales, Universidad de Buenos Aires, Intendente Güiraldes 2160, Pabellón II, 4°piso, Ciudad Universitaria, Buenos Aires C1428EGA, Argentina
- Instituto de Química Biológica de la Facultad de Ciencias Exactas y Naturales (IQUIBICEN), Facultad de Ciencias Exactas y Naturales, Universidad de Buenos Aires, Consejo Nacional de Investigaciones Científicas y Técnicas, Intendente Güiraldes 2160, Pabellón II, 4°piso, Ciudad Universitaria, Buenos Aires C1428EGA, Argentina
| | - María Paula Morelli
- Departamento de Química Biológica, Facultad de Ciencias Exactas y Naturales, Universidad de Buenos Aires, Intendente Güiraldes 2160, Pabellón II, 4°piso, Ciudad Universitaria, Buenos Aires C1428EGA, Argentina
- Instituto de Química Biológica de la Facultad de Ciencias Exactas y Naturales (IQUIBICEN), Facultad de Ciencias Exactas y Naturales, Universidad de Buenos Aires, Consejo Nacional de Investigaciones Científicas y Técnicas, Intendente Güiraldes 2160, Pabellón II, 4°piso, Ciudad Universitaria, Buenos Aires C1428EGA, Argentina
| | - Joaquín Miguel Pellegrini
- Centre d’Immunologie de Marseille Luminy, INSERM, CNRS, Aix-Marseille Université, Parc Scientifique et Technologique de Luminy, Case 906, CEDEX 09, 13288 Marseille, France
| | - Verónica Edith García
- Departamento de Química Biológica, Facultad de Ciencias Exactas y Naturales, Universidad de Buenos Aires, Intendente Güiraldes 2160, Pabellón II, 4°piso, Ciudad Universitaria, Buenos Aires C1428EGA, Argentina
- Instituto de Química Biológica de la Facultad de Ciencias Exactas y Naturales (IQUIBICEN), Facultad de Ciencias Exactas y Naturales, Universidad de Buenos Aires, Consejo Nacional de Investigaciones Científicas y Técnicas, Intendente Güiraldes 2160, Pabellón II, 4°piso, Ciudad Universitaria, Buenos Aires C1428EGA, Argentina
| |
Collapse
|
4
|
Ashenafi S, Brighenti S. Reinventing the human tuberculosis (TB) granuloma: Learning from the cancer field. Front Immunol 2022; 13:1059725. [PMID: 36591229 PMCID: PMC9797505 DOI: 10.3389/fimmu.2022.1059725] [Citation(s) in RCA: 5] [Impact Index Per Article: 2.5] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/01/2022] [Accepted: 11/30/2022] [Indexed: 12/23/2022] Open
Abstract
Tuberculosis (TB) remains one of the deadliest infectious diseases in the world and every 20 seconds a person dies from TB. An important attribute of human TB is induction of a granulomatous inflammation that creates a dynamic range of local microenvironments in infected organs, where the immune responses may be considerably different compared to the systemic circulation. New and improved technologies for in situ quantification and multimodal imaging of mRNA transcripts and protein expression at the single-cell level have enabled significantly improved insights into the local TB granuloma microenvironment. Here, we review the most recent data on regulation of immunity in the TB granuloma with an enhanced focus on selected in situ studies that enable spatial mapping of immune cell phenotypes and functions. We take advantage of the conceptual framework of the cancer-immunity cycle to speculate how local T cell responses may be enhanced in the granuloma microenvironment at the site of Mycobacterium tuberculosis infection. This includes an exploratory definition of "hot", immune-inflamed, and "cold", immune-excluded TB granulomas that does not refer to the level of bacterial replication or metabolic activity, but to the relative infiltration of T cells into the infected lesions. Finally, we reflect on the current knowledge and controversy related to reactivation of active TB in cancer patients treated with immune checkpoint inhibitors such as PD-1/PD-L1 and CTLA-4. An understanding of the underlying mechanisms involved in the induction and maintenance or disruption of immunoregulation in the TB granuloma microenvironment may provide new avenues for host-directed therapies that can support standard antibiotic treatment of persistent TB disease.
Collapse
Affiliation(s)
- Senait Ashenafi
- Department of Medicine Huddinge, Center for Infectious Medicine (CIM), Karolinska Institutet, ANA Futura, Huddinge, Sweden,Department of Pathology, School of Medicine, College of Health Sciences, Tikur Anbessa Specialized Hospital and Addis Ababa University, Addis Ababa, Ethiopia
| | - Susanna Brighenti
- Department of Medicine Huddinge, Center for Infectious Medicine (CIM), Karolinska Institutet, ANA Futura, Huddinge, Sweden,*Correspondence: Susanna Brighenti,
| |
Collapse
|
5
|
Ntoumi F, Petersen E, Mwaba P, Aklillu E, Mfinanga S, Yeboah-Manu D, Maeurer M, Zumla A. Blue Skies research is essential for ending the Tuberculosis pandemic and advancing a personalized medicine approach for holistic management of Respiratory Tract infections. Int J Infect Dis 2022; 124 Suppl 1:S69-S74. [PMID: 35301102 PMCID: PMC8920086 DOI: 10.1016/j.ijid.2022.03.012] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Download PDF] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/07/2022] [Accepted: 03/08/2022] [Indexed: 12/14/2022] Open
Abstract
OBJECTIVES Investments into 'Blue Skies' fundamental TB research in low- and middle-income countries (LMICs) have not been forthcoming. We highlight why blue skies research will be essential for achieving global TB control and eradicating TB. METHODS We review the historical background to early TB discovery research and give examples of where investments into basic science and fundamental 'blue skies research' are delivering novel data and approaches to advance diagnosis, management and holistic care for patients with active and latent TB infection. FINDINGS The COVID-19 pandemic has shown that making available adequate funding for priority investments into 'Blue skies research' to delineate scientific understanding of a new infectious diseases threat to global health security can lead to rapid development and rollout of new diagnostic platforms, treatments, and vaccines. Several advances in new TB diagnostics, new treatments and vaccine development are underpinned by basic science research. CONCLUSIONS Blue Skies research is required to pave the way for a personalized medicine approach for management of TB and other Respiratory Tract Infections and preventing long-term functional disability. Transfer of skills and resources by wealthier nations is required to empower researchers in LMICs countries to engage in and lead Blue Skies research.
Collapse
Affiliation(s)
- Francine Ntoumi
- Fondation Congolaise pour la Recherche Médicale (FCRM), Brazzaville, Republic of Congo; Institute for Tropical Medicine, University of Tübingen, Germany.
| | - Eskild Petersen
- European Society for Clinical Microbiology and Infectious Diseases, Emerging Infections Task Force, ESCMID, Basel, Switzerland; Institute for Clinical Medicine, Aarhus University, Denmark; European Travel Medicine Network, Méditerranée Infection Foundation, Marseille, France.
| | - Peter Mwaba
- Lusaka Apex Medical University, Faculty of Medicine: Zambia National Public Health Institute; UNZA-UCLMS Research and Training Project, Lusaka, Zambia.
| | - Eleni Aklillu
- Division of Clinical Pharmacology, Department of Laboratory Medicine, Karolinska Institutet, Karolinska University Hospital-Huddinge, Stockholm, Sweden.
| | - Sayoki Mfinanga
- Muhimbili Medical Research Centre National Institute for Medical Research, Dar es Salaam, Tanzania.
| | - Dorothy Yeboah-Manu
- Noguchi Memorial Institute for Medical Research, University of Ghana, Legon, Ghana.
| | - Markus Maeurer
- ImmunoSurgery Unit, Champalimaud Centre for the Unknown, Lisbon, Portugal; Medizinische Klinik, Johannes Gutenberg University Mainz, Germany.
| | - Alimuddin Zumla
- Division of Infection and Immunity, Center for Clinical Microbiology, University College London, and NIHR Biomedical Research Centre, UCL Hospitals NHS Foundation Trust, London, United Kingdom.
| |
Collapse
|