Deli-Bright N. T. Oku
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Deli-Bright N. T. Oku has a total of 7 co-authors. Here are the top co-authors by number of shared publications:
- Ramakwala Christinah Chokwe
Department of Chemistry The Science Campus College of Science Engineering and Technology University of South Africa Roodepoort South Africa
3 shared publications Damilare D. Babatunde
Department of Chemistry, The Science Campus, College of Science Engineering and Technology, University of South Africa, Corner Christiaan de Wet Road and Pioneer Avenue Florida Park, Roodepoort 1709, South Africa
1 shared publicationGarland K. More
College of Agriculture and Environmental Sciences, CAES Laboratories, University of South Africa, PrivRate Bag X6, Johannesburg, Florida 1710, South Africa
1 shared publication- Garland Kgosi More
College of Agriculture and Environmental Sciences Laboratories, University of South Africa, Florida, Johannesburg 1710, South Africa
1 shared publication - Thandeka Hlongwa
Department of Chemistry The Science Campus College of Science Engineering and Technology University of South Africa Roodepoort South Africa
1 shared publication Yannick Nuapia
Department of Pharmacy, Turfloop Campus, School of Healthcare Science
1 shared publication
Latest Publications
- Open Access
- 20 November 2026
- Published by Wiley in ChemistrySelect
- Vol. 11 (44)
Computational Identification of Epigenetic Modulators From Artemisia afra Targeting PfHDAC1 as Potential Antimalarial Agents: In Silico and Machine Learning‐Based Virtual Screening Approach
Plasmodium falciparum ( P. falciparum ) histone deacetylase 1 (PfHDAC1) plays a critical role in the blood‐stage development of malaria parasites and represents a promising epigenetic target for antimalarial drug discovery. Despite the success of artemisinin combination therapies in reducing the global malaria burden, multidrug resistance in P. falciparum is emerging worldwide. This clearly shows the urgent need for innovative antimalarials that can target multiple stages of the parasite. In this study, we employed an integrated machine learning‐based virtual screening and molecular docking approach to identify potential epigenetic inhibitors of PfHDAC1 from Artemisia afra ( A. afra ). Multiple machine learning models were developed using different sampling strategies, feature subset sizes (10, 30, and 50 features), and hyperparameter optimization schemes. Among these, a Random Forest classifier trained using the Synthetic Minority Over‐sampling Technique with 30 selected features demonstrated strong and consistent predictive performance across the evaluated metrics. Application of the optimized model to A. afra phytochemicals identified 14 epigenetic modifiers predicted as active, all of which exhibited zero Lipinski's Rule‐of‐Five violations and fell within the model's applicability domain, supporting their selection for molecular docking and further investigation. Molecular docking further provided insights into their predicted binding interactions with PfHDAC1 and their potential for further evaluation as antimalarial candidates.
- 20 November 2026
- Published by Wiley in ChemistrySelect
- Vol. 11 (44)
Open AccessComputational Identification of Epigenetic Modulators From Artemisia afra Targeting PfHDAC1 as Potential Antimalarial Agents: In Silico and Machine Learning‐Based Virtual Screening Approach
Plasmodium falciparum ( P. falciparum ) histone deacetylase 1 (PfHDAC1) plays a critical role in the blood‐stage development of malaria parasites and represents a promising epigenetic target for antimalarial drug discovery. Despite the success of artemisinin combination therapies in reducing the global malaria burden, multidrug resistance in P. falciparum is emerging worldwide. This clearly shows the urgent need for innovative antimalarials that can target multiple stages of the parasite. In this study, we employed an integrated machine learning‐based virtual screening and molecular docking approach to identify potential epigenetic inhibitors of PfHDAC1 from Artemisia afra ( A. afra ). Multiple machine learning models were developed using different sampling strategies, feature subset sizes (10, 30, and 50 features), and hyperparameter optimization schemes. Among these, a Random Forest classifier trained using the Synthetic Minority Over‐sampling Technique with 30 selected features demonstrated strong and consistent predictive performance across the evaluated metrics. Application of the optimized model to A. afra phytochemicals identified 14 epigenetic modifiers predicted as active, all of which exhibited zero Lipinski's Rule‐of‐Five violations and fell within the model's applicability domain, supporting their selection for molecular docking and further investigation. Molecular docking further provided insights into their predicted binding interactions with PfHDAC1 and their potential for further evaluation as antimalarial candidates.
- Open Access
- 28 May 2026
- Published by American Chemical Society (ACS) in Journal of Chemical Information and Modeling
- Vol. 66 (12) , 7065-7087
Chemical Profiling and Scaffold-Based Drug-Discovery Analysis of Bioactive Compounds from Ceratonia siliqua L. with Computational and Biological Validation
The scaffold concept is central in medicinal chemistry and drug design to generate, analyze, and capture the core structural frameworks that define bioactive compounds. Natural products and their underlying molecular scaffolds have long provided many of the biologically active ingredients in modern medicines and continue to inspire new therapeutic agents. However, linking these core structural frameworks to observed biological activity remains a key challenge in natural-product research. Here, this study integrates a computational-experimental approach combining scaffold-based drug analysis, chemical profiling, and computational and biological validation to identify bioactive motifs in Ceratonia siliqua L pods. A total of 253 identified compounds from the gas chromatography-mass spectrometry (GC-MS) profiling were clustered and grouped into antioxidant, antimicrobial, and cytotoxic activity sets, after which their Bemis-Murcko scaffolds were extracted using RDKit. The most common scaffolds were ranked and visualized to give a clear picture of the prevalent structural patterns throughout the data sets. Experimental assays validated the computational dominant scaffold predictions, revealing that the antioxidant activity was associated with phenolic and terpenoid scaffolds, the antimicrobial response was aligned with monoterpenoid and cyclohexane/cyclohexene-based scaffolds, and the cytotoxic trends were consistent with small heterocycles and imide-containing scaffolds. To further bridge the gap between the identified scaffolds and their corresponding biological activity, molecular docking was performed against key biological targets, including KEAP1, Staphylococcus aureus DHFR, and EGFR. The docking results demonstrated favorable binding interactions and identified key ligand-protein interactions, supporting the potential contribution of the GC-MS-identified compounds to the observed biological activities of the plant extract. These scaffold-activity relationships demonstrate that recurring structural motifs are associated with the biological effects observed in C. siliqua L., highlighting the plant as a promising source of pharmacologically relevant scaffolds for drug discovery.
- 28 May 2026
- Published by American Chemical Society (ACS) in Journal of Chemical Information and Modeling
- Vol. 66 (12) , 7065-7087
Open AccessChemical Profiling and Scaffold-Based Drug-Discovery Analysis of Bioactive Compounds from Ceratonia siliqua L. with Computational and Biological Validation
The scaffold concept is central in medicinal chemistry and drug design to generate, analyze, and capture the core structural frameworks that define bioactive compounds. Natural products and their underlying molecular scaffolds have long provided many of the biologically active ingredients in modern medicines and continue to inspire new therapeutic agents. However, linking these core structural frameworks to observed biological activity remains a key challenge in natural-product research. Here, this study integrates a computational-experimental approach combining scaffold-based drug analysis, chemical profiling, and computational and biological validation to identify bioactive motifs in Ceratonia siliqua L pods. A total of 253 identified compounds from the gas chromatography-mass spectrometry (GC-MS) profiling were clustered and grouped into antioxidant, antimicrobial, and cytotoxic activity sets, after which their Bemis-Murcko scaffolds were extracted using RDKit. The most common scaffolds were ranked and visualized to give a clear picture of the prevalent structural patterns throughout the data sets. Experimental assays validated the computational dominant scaffold predictions, revealing that the antioxidant activity was associated with phenolic and terpenoid scaffolds, the antimicrobial response was aligned with monoterpenoid and cyclohexane/cyclohexene-based scaffolds, and the cytotoxic trends were consistent with small heterocycles and imide-containing scaffolds. To further bridge the gap between the identified scaffolds and their corresponding biological activity, molecular docking was performed against key biological targets, including KEAP1, Staphylococcus aureus DHFR, and EGFR. The docking results demonstrated favorable binding interactions and identified key ligand-protein interactions, supporting the potential contribution of the GC-MS-identified compounds to the observed biological activities of the plant extract. These scaffold-activity relationships demonstrate that recurring structural motifs are associated with the biological effects observed in C. siliqua L., highlighting the plant as a promising source of pharmacologically relevant scaffolds for drug discovery.
- Open Access
- 19 November 2025
- Published by American Chemical Society (ACS) in ACS Omega
- Vol. 10 (47) , 57365-57384
Harnessing Machine Learning for the Virtual Screening of Natural Compounds as Both EGFR and HER2 Inhibitors in Colorectal Cancer: A Novel Therapeutic Approach
Colorectal cancer (CRC) is a type of cancer that affects the colon and rectum, with overexpression of epidermal growth factor receptor (EGFR) and human epidermal growth factor receptor 2 (HER2) observed in up to 85% of colorectal cancer cases. Although CRC treatment has progressed with the introduction of targeted drugs, current approaches have primarily focused on a single blockage of EGFR or HER2 to combat colon cancer. However, monotherapies that target either the EGFR or HER2 receptor frequently have low efficacy due to mutations in downstream effectors such as Kirsten Rat Sarcoma 2 Viral Oncogene Homologue (KRAS) and the activation of compensatory signaling pathways that support tumor survival and proliferation. Hence, the discovery and development of a therapy with the capability to combat CRC by simultaneously inhibiting both EGFR and HER2 remain avenues for further exploration. This study introduces a novel machine learning (ML)-based stacking ensemble framework for rapidly and accurately identifying dual EGFR and HER2 inhibitors using SMILES notation. A benchmark data set comprising active and inactive compounds against EGFR and HER2 was curated from the ChEMBL database. Based on this data set, 40 baseline models were developed and optimized using a comprehensive set of well-known molecular descriptors and ML algorithms (Figure 1). These models generated probabilistic features integrated via a logistic regression model as a final estimate to construct the final stacking ensemble model. The model was applied to bioactive compounds identified through LC-MS/MS profiling of Ceratonia siliqua extract as well as to a subset of natural products from the LOTUS database for virtual screening. The cytotoxic potential of Ceratonia siliqua was experimentally validated using the MTT assay against HCT116 colorectal cancer cells and noncancerous Vero cells, where the extract exhibited an IC50 value of 13.32 ± 1.09 μg/mL against HCT116 cells, indicating its significant anticancer potential. Additionally, molecular docking and in silico ADMET studies were conducted on the top three compounds from both the LOTUS database and the predicted candidate from the LC-MS/MS data set identified by the stacking model, alongside four FDA-approved anticancer drugs for comparative analysis. Among these, LTS0131923 demonstrated the highest binding affinity against HER2 (PDB ID: 7MN5), with a binding energy of −11.2 kcal/mol and an inhibition constant of 0.00626 μM, outperforming Tucatinib, a standard CRC treatment. This study reveals the potential of ML-driven approaches to accelerate the discovery of dual-target inhibitors for CRC therapy and highlights Ceratonia siliqua L. as a promising source of bioactive compounds for cancer treatment.
- 19 November 2025
- Published by American Chemical Society (ACS) in ACS Omega
- Vol. 10 (47) , 57365-57384
Open AccessHarnessing Machine Learning for the Virtual Screening of Natural Compounds as Both EGFR and HER2 Inhibitors in Colorectal Cancer: A Novel Therapeutic Approach
Colorectal cancer (CRC) is a type of cancer that affects the colon and rectum, with overexpression of epidermal growth factor receptor (EGFR) and human epidermal growth factor receptor 2 (HER2) observed in up to 85% of colorectal cancer cases. Although CRC treatment has progressed with the introduction of targeted drugs, current approaches have primarily focused on a single blockage of EGFR or HER2 to combat colon cancer. However, monotherapies that target either the EGFR or HER2 receptor frequently have low efficacy due to mutations in downstream effectors such as Kirsten Rat Sarcoma 2 Viral Oncogene Homologue (KRAS) and the activation of compensatory signaling pathways that support tumor survival and proliferation. Hence, the discovery and development of a therapy with the capability to combat CRC by simultaneously inhibiting both EGFR and HER2 remain avenues for further exploration. This study introduces a novel machine learning (ML)-based stacking ensemble framework for rapidly and accurately identifying dual EGFR and HER2 inhibitors using SMILES notation. A benchmark data set comprising active and inactive compounds against EGFR and HER2 was curated from the ChEMBL database. Based on this data set, 40 baseline models were developed and optimized using a comprehensive set of well-known molecular descriptors and ML algorithms (Figure 1). These models generated probabilistic features integrated via a logistic regression model as a final estimate to construct the final stacking ensemble model. The model was applied to bioactive compounds identified through LC-MS/MS profiling of Ceratonia siliqua extract as well as to a subset of natural products from the LOTUS database for virtual screening. The cytotoxic potential of Ceratonia siliqua was experimentally validated using the MTT assay against HCT116 colorectal cancer cells and noncancerous Vero cells, where the extract exhibited an IC50 value of 13.32 ± 1.09 μg/mL against HCT116 cells, indicating its significant anticancer potential. Additionally, molecular docking and in silico ADMET studies were conducted on the top three compounds from both the LOTUS database and the predicted candidate from the LC-MS/MS data set identified by the stacking model, alongside four FDA-approved anticancer drugs for comparative analysis. Among these, LTS0131923 demonstrated the highest binding affinity against HER2 (PDB ID: 7MN5), with a binding energy of −11.2 kcal/mol and an inhibition constant of 0.00626 μM, outperforming Tucatinib, a standard CRC treatment. This study reveals the potential of ML-driven approaches to accelerate the discovery of dual-target inhibitors for CRC therapy and highlights Ceratonia siliqua L. as a promising source of bioactive compounds for cancer treatment.