Random Forest models using RDKit descriptors from natural compounds achieve the highest accuracy and ROC-AUC for predicting neuroprotective activity, with lipophilicity, molecular weight, and polarity identified as key drivers.
In silico drug discovery: A machine learning-driven review
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
q-bio.OT 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Predictive Modelling of Natural Medicinal Compounds for Alzheimer disease Using Machine Learning and Cheminformatics
Random Forest models using RDKit descriptors from natural compounds achieve the highest accuracy and ROC-AUC for predicting neuroprotective activity, with lipophilicity, molecular weight, and polarity identified as key drivers.