The Marburg virus (MARV), responsible for severe hemorrhagic fevers with mortality rates as high as 90%, remains a significant public health threat. This study employs machine learning to identify inhibitors targeting the MARV Gene 4 Small ORF protein, crucial for the virus's replication and immune evasion. The Gene 4 Small ORF protein is pivotal in taking over the host's cellular mechanisms, facilitating unchecked viral replication and significant immune system disruption. Effective targeting of this protein holds promise for mitigating the viral lifecycle and entry, potentially curbing the severity of the disease outbreaks. A dataset from PubChem, including 301,745 compounds, was utilized to train models like Random Forest (RF), Gradient Boosting Machines (GBM), CatBoost (CB), AdaBoost (AB), and Logistic Regression (LR). The activity outcomes were classified with integers active as 1 and inactive as 0, followed by molecular descriptor generation using RDKit and PaDEL. The models were trained on an 80:20 split and validated on a novel dataset to ensure robustness, with performance metrics such as accuracy and AUC-ROC guiding evaluation. Morgan fingerprints outperformed PubChem fingerprints, achieving higher accuracy (76%), precision (80%), and ROC-AUC (84%). Among the machine learning models evaluated, RF and GBM were the best performers, with RF achieving the highest specificity (83%) and ROC-AUC (0.84). Validation on new datasets further confirmed the effectiveness of these models, with RF and GBM demonstrating strong predictive reliability for identifying potential inhibitors of the Marburg virus. A Web Application known as MARVpred was developed to predict the activity of compounds with anti-MARV properties from the ChEMBL database. MARVpred is freely accessible online (https://igmr.org/software/marvpred). This study signifies a critical step forward in the computational prediction of viral inhibitors, offering a valuable tool for accelerating the development of Marburg virus therapeutics.
Background: Human African trypanosomiasis (HAT) is a fatal vector-borne disease caused by Trypanosoma brucei. Although HAT incidence has declined, meeting WHO's elimination targets remain difficult, particularly due to limited diagnostic sensitivity for low-parasite load-infections. Arboviruses such as dengue (DENV 1-4), chikungunya (CHIKV), and yellow fever (YFV) virus, present with nonspecific febrile symptoms similar to HAT and are underdiagnosed in Sub-Saharan Africa. Due to this overlap in symptoms and a suspected geographical overlap of vectors and pathogens in the Democratic Republic of the Congo (DRC) the pathogens were combined in a multiplex-PCR panel. Sample-to-result platforms (S2R) can reduce hands-on time and infrastructure requirements, making them ideal for peripheral laboratories. We developed a multiplex real-time RT-PCR assay on the ARIES® platform, for simultaneous detection of HAT, DENV, CHIKV and YFV, showing how automated, closed-cartridge PCR can simplify testing.
Methods: A technical validation and retrospective sample testing (n = 242) were performed at the Institute of Tropical Medicine (ITM). Field validation took place in the DRC with retrospective samples from a CHIKV outbreak (n = 121) in Institut National pour la Recherche Biomédicale (INRB) Kinshasa and 52 prospective whole blood samples from acute febrile patients in Centre de Recherche en Santé de Kimpese (CRSK) in Kimpese.
Results: The assay showed a slight loss of sensitivity, evidenced in the technical validation, and the non-detection of some T.b.gambiense and retrospective arboviral samples at ITM with low pathogen loads. CHIKV samples tested in Kinshasa showed a sensitivity of 89.4%. Although all samples tested in Kimpese were negative for the pathogens, it demonstrated how just a few days of training and the simplified workflows of a S2R-platform can enable robust diagnostics under challenging conditions.
Conclusion: Ensuring rapid, sensitive molecular diagnostics in resource-limited settings is critical for eliminating HAT and strengthening surveillance of emerging arboviruses. Despite the recent discontinuation of ARIES®, our findings confirm the feasibility and reliability of detecting diverse pathogens with minimal laboratory resources. The assay aligns with WHO and FIND target-product profiles, highlighting its relevance for neglected diseases in low-resource settings. These results emphasize the ongoing need for open, flexible S2R platforms to support disease surveillance and outbreak preparedness.
Clinical trial: Clinicaltrials.gov NCT04760678, registered on February 17th, 2021.
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：