What is it about?
Kidney stones develop when minerals and other substances accumulate and form hard deposits in the urinary tract. Finding new compounds that may help us understand and manage this condition is an important area of pharmaceutical research. Our study explored phytoconstituents—naturally occurring chemical compounds—from Bryophyllum pinnatum, a medicinal plant, using computational drug-discovery approaches. We combined machine-learning-enabled exploration with molecular docking, MM-GBSA binding-energy estimation, ADMET profiling, molecular dynamics simulations, and toxicity prediction to investigate the potential interactions of selected compounds with proteins relevant to urolithiasis.
Featured Image
Why is it important?
Computer-based drug-discovery methods can help researchers screen promising compounds before proceeding to more time-consuming laboratory experiments. Our findings highlighted several candidate compounds for further investigation, including BP1, BP3, BP8, BP10, and BP25. BP3 showed a favourable predicted docking score against carbonic anhydrase, while additional computational analyses helped assess the stability, pharmacokinetic properties, and potential toxicity of selected compounds. What are the implications? This research provides a computational starting point for investigating plant-derived compounds in urolithiasis research. However, the findings do not establish that these compounds prevent or treat kidney stones in humans. Laboratory experiments and further preclinical studies are needed to validate their biological activity, safety, and therapeutic potential. Our work illustrates how computational approaches can support the systematic exploration of medicinal plants and help prioritise candidates for future drug-discovery research.
Perspectives
This research provides a foundation for further investigation of Bryophyllum pinnatum phytoconstituents as potential candidates for urolithiasis management. Future studies should validate the computational findings through in vitro experiments, biochemical assays, and appropriate preclinical models. Further research should also investigate the mechanisms of action, dose–response relationships, pharmacokinetic properties, and safety profiles of the most promising compounds. Integrating machine learning with experimental validation may help prioritise bioactive molecules and accelerate the discovery of plant-derived therapeutic candidates. Ultimately, this approach could contribute to the development of evidence-based strategies for kidney-stone prevention and management, subject to rigorous experimental and clinical evaluation.
Ziyaul Haque Ansari
Anjuman-I-Islam's Kalsekar Technical Campus
Read the Original
This page is a summary of: Machine Learning-Enabled Exploration of Bryophyllum Pinnatum Phytoconstituents for Urolithiasis Management: Molecular Docking, MMGBSA Analysis, ADMET Profiling, MD simulations, and Toxicity Assessment, Current Pharmaceutical Design, May 2026, Bentham Science Publishers,
DOI: 10.2174/0113816128415430251208123338.
You can read the full text:
Contributors
The following have contributed to this page
