Integrative machine learning and structural bioinformatics strategies for the identification of selective sterol 14A-demethylase inhibitors targeting Trypanosoma Cruzi
Abstract
ABSTRACT Background of study Chagas disease, commonly known as American trypanosomiasis is a potentially life-threatening infection caused by Trypanosoma cruzi. The current chemotherapy of chagas disease involves benznidazole and nifurtimox, however, both have several drawbacks such as intolerable side effects, resistance, and limited efficacy. These drawbacks necessitate the need to discover novel, more efficacious and safer alternatives against chagas disease. This study aims to use an integrative machine learning and structural bioinformatics strategies to discover novel small-molecule inhibitors of sterol 14α-demethylase inhibitors targeting T. cruzi (chagas disease). Methodology We retrieved 22,000 natural products from an extensive database of microbially-derived natural products, and employed a series of rigorous computational approaches, with the integration of machine learning strategy to screen these natural products. Additionally, we verified the stability of the ligand-protein complex using Molecular Dynamics (MD) simulations spanning 100 nanoseconds, guaranteeing the reliability of our results. Results and Discussion Out of the screened natural products, four novel drug candidates namely Fisheacid, Penikellide A, Ochratoxin A, and Asperlide C exhibited strong binding affinities with binding energies of −12.008 kcal/mol, −11.372 kcal/mol, −10.300 kcal/mol, and −11.444 kcal/mol respectively, surpassing the reference ligand, Ravuconazole (−8.639 kcal/mol). The pharmacokinetic profile of these drug candidates exhibited favorable drug likeness characters, and low toxicity, positioning them as promising candidates. Conclusion This study identifies four novel natural products as potent CYP 51 inhibitors, and has been proven to be energetically stable when complex with the enzyme. However, more invitro and in vivo studies are recommended to determine the therapeutic potential of these drug candidates in the treatment of Chagas disease.
Fields of Study & Subjects
Trypanosoma species research and implications
Protein Structure and Dynamics
Computational Drug Discovery Methods
Publication details
- Journal / source
- In Silico Research in Biomedicine
- Publisher
- Elsevier BV
- Volume
- 2
- Pages
- 100182–100182
- Publication date
- 1 January 2026
- Language
- EN