College of Science and Technology

Permanent URI for this communityhttp://itsupport.cu.edu.ng:4000/handle/123456789/28738

Welcome to the community of research works in Science and Technology

Browse

Now showing 1 - 3 of 3

AN OPTIMIZED DEEP-FOREST MODEL USING A MODIFIED DIFFERENTIAL EVOLUTION OPTIMIZATION ALGORITHM: A CASE OF HOST-PATHOGEN PROTEIN-PROTEIN INTERACTION PREDICTION
(Covenant University Ota, 2025-04) EMMANUEL JERRY DAUDA; Covenant University Thesis
Deep forest is an advanced ensemble learning technique that employs forest structures within a cascade framework, leveraging deep architectures to enhance predictive performance by adaptively capturing high-level feature representations. Despite its promise, deep forest models often face critical challenges, including manual hyperparameter optimization and inefficiencies in computational time and memory usage. To address these limitations, Bayesian optimization, a prominent model-based hyperparameter optimization method, is frequently utilized, with Differential Evolution (DE) serving as the acquisition function in recent implementations. However, DE's reliance on random index selection for constructing donor vectors introduces inefficiencies, as suboptimal or redundant indices may hinder the search for optimal solutions. This study introduces an optimized deep forest algorithm that integrates a modified DE acquisition function into Bayesian optimization to improve host-pathogen protein-protein interaction (HPPPI) prediction. The modified DE approach incorporates a weighted and adaptive donor vector selection mechanism, enhancing the exploration and exploitation of hyperparameter configurations. Performance evaluations using 10-fold cross-validation on human–Plasmodium falciparum (PF) protein sequence datasets sourced from reputable databases demonstrated the model's superiority over traditional Bayesian optimization, genetic algorithms, evolutionary strategies, and conventional machine learning models. The optimized framework achieved an accuracy of 89.3%, sensitivity of 85.4%, precision of 91.6%, and Area Under the Receiver Operating Characteristic Curve (AUROC) of 89.1%, surpassing existing methods. Additionally, the model exhibited reduced computational time and memory usage. The optimized DF was deployed as a web-based pipeline, DFH3PI (Deep Forest Host-Pathogen Protein-Protein Interaction Prediction), which successfully identified three potential human–PF PPIs previously classified as non-interacting: P50250–P08319, Q8ILI6–O94813, and Q7KQL3–Q96GQ7. These findings not only present the potential of DFH3PI for advancing HPPPI prediction but also establish the optimized deep forest framework as a transformative tool in computational biology. Its ability to combine accuracy and efficiency marks a significant step forward in predictive modeling.
EVALUATION OF COST REDUCTION TECHNIQUES ON PUBLIC TERTIARY EDUCATIONAL PROJECTS IN SOUTHWESTERN NIGERIA
(Covenant University Ota, 2025-03) AKINOLA GBEMISOLA AJOKE; Covenant University Thesis
MOLECULAR DOCKING, LIGAND QUALITY AND ANTIPLASMODIAL EVALUATION OF BENZAMIDE, COUMARIN AND BENZODIAZEPINE ANALOGS
(Covenant University Ota, 2025-04) ADEBAYO GLORY PIPELOLUWA; Covenant University Thesis
Malaria chemotherapy is an essential strategy for malaria elimination but resistance has challenged existing antimalarials, including frontline artemisinin combination therapy (ACT); hence, new antimalarial drugs must be discovered and developed. This study investigated the antiplasmodial efficacy and cytotoxicity through in vitro models while also testing the antiplasmodial efficacy, and the in vivo acute toxicity of benzamide, coumarin and benzodiazepine analogss. This study also evaluated the ligand quality of the molecules and their possible Plasmodium falciparum protein targets. Three molecules, 4- amino-N-hydroxybenzamide (AHB), ethyl 2-oxo-2H-chromene-3-carboxylate (ECC), and 2,2,4-trimethyl-2-3-dihyro-1H-benzo[b][1,4] diazepine (BDZ) were screened for their in vitro antiplasmodial activities tested against P. falciparum 3D7 standard strain using the SYBR Green Dye I measuring IC50 and their cytotoxicities against MCF-7 breast cancer cells using the [3(4,5-dimethylthiazol-2-yl)-2,5-diphenyltetrazolium bromide] (MTT) assay. Their antiplasmodial efficacies were determined using Peter’s 4-day suppressive test against Plasmodium berghei in M. musculus while acute toxicities were investigated in the Mus musculus (mice). Ligand qualities were determined using ligand efficiency metrics, and molecular docking was conducted to determine the ligand interactions between ECC and the following enzymatic proteins, P. falciparum dihydroorotate dehydrogenase (PfDHOH) and P. falciparum purine nucleoside phosphorylase (PfPNP); and the molecular interaction between BDZ and PfDXR - Plasmodium falciparum 1-deoxy-D-xylulose-5-phosphate reductoisomerase, P. falciparum falcipain-2 and P. falciparum plasmepsin X (PfPMX). AHB showed no cytotoxicity against MCF-7 at (CC50) = 277.7 μM, while ECC showed inhibition with CC50= 3.930 μM, and BDZ showed no cytotoxicity CC50= 7373 μM. The in vitro antiplasmodial activity showed potency at (AHB)IC50 = 0.0020 ± 0.008 μM, (ECC) IC50= 0.0010 ± 0.002 μM, (BDZ) IC50= 0.0036 ± 0.003 μM respectively. BDZ showed the highest selectivity index at > 200,000, suggesting that it exhibited the best safety/efficacy among the three compounds. AHB displayed LD50 = >5000 mg/kg while ECC and BDZ displayed LD50 = 3162.28 mg/kg. Histopathological examinations showed non-toxicity by the three analogs on the liver and kidney of M. musculus. The percentage suppression of AHB (80.53 ± 3.26 %) at 400 mg/kg, was comparable to the standard chloroquine (81.71 ± 1.82 %) at 100 mg/kg where the mean survival time for both exceeded 30 days. ECC and BDZ showed excellent efficacies (70.98 ± 20.89 % and 83.66 ± 11.67 %) at 200 mg/kg, comparable to chloroquine 80.97 ± 5.82 %. The chemosuppression values for AHB and BDZ were significant at P value < 0.05. The ligand quality of ECC and BDZ displayed good Ligand Efficiency compared to chloroquine and artemisinin and higher enzyme affinities, and ligand efficiency dependent lipophilicity than the standard drugs. ECC and BDZ displayed good characteristics. The docking studies displayed strong hydrophobic interactions between ECC, PfDHODH, and PfPNP, suggesting good potency. BDZ’s binding with PfDXR, Pffalcipain-2, and PfPMX also displayed potency derived from hydrophobic and hydrogen interactions. Conclusively, this study showed AHB, ECC and BDZ were non-toxic to mammalian cells rodents’ liver and kidneys. These molecules exhibited good antiplasmodial inhibitory potential against both P. falciparum in vitro and P. berghei in vivo. ECC and BDZ displayed high ligand efficiency and strong molecular interactions with their protein targets. Therefore, all three analogs can be moved for further optimization in drug development.