We found a match
Your institution may have rights to this item. Sign in to continue.
- Title
Machine Learning-Based Approach to Identify Inhibitors of Sterol-14-Alpha Demethylase: A Study on Chagas Disease.
- Authors
Saliu, Jamiyu A
- Abstract
Objectives: Chagas Disease, caused by the parasite Trypanosoma cruzi, remains a significant public health concern, particularly in Latin America. The current standard treatment for Chagas Disease, benznidazole, is associated with various side effects, necessitating the search for alternative therapeutic options. In this study, we aimed to identify potential therapeutics for Chagas Disease through a comprehensive computational analysis. Methods: A library of compounds derived from Cananga odorata was screened using a combination of pharmacophore modeling, structure-based screening, and quantitative structure-activity relationship (QSAR) analysis. The pharmacophore model facilitated the efficient screening of the compound library, while the structure-based screening identified hit compounds with promising inhibitory potential against the target enzyme, sterol-14-alpha demethylase. Results: The QSAR model predicted the bioactivity of the hit compounds, revealing one compound to exhibit superior activity compared to benznidazole. Evaluation of the physicochemical, pharmacokinetic, toxicity, and medicinal chemistry properties of the hit compounds indicated their drug-like characteristics, oral bioavailability, ease of synthesis, and reduced toxicity profiles. Conclusion: Overall, our findings present a promising avenue for the discovery of novel therapeutics for Chagas Disease. The identified hit compounds possess favorable drug-like properties and demonstrate potent inhibitory effects against the target enzyme. Further in vitro and in vivo studies are warranted to validate their efficacy and safety profiles.
- Subjects
CHAGAS' disease; CHEMICAL libraries; QSAR models; PUBLIC health; PHARMACEUTICAL chemistry
- Publication
Bioinformatics & Biology Insights, 2024, p1
- ISSN
1177-9322
- Publication type
Article
- DOI
10.1177/11779322241262635