Nature is the best source of anticancer drugs: Indexing natural products for their anticancer bioactivity

Area of Science:

• Computational chemistry
• Drug discovery
• Natural product chemistry

Background:

• Cancer poses a significant global health burden, driving the need for new anticancer therapies.
• Traditional drug discovery is time-consuming and costly, necessitating innovative approaches.
• In silico methods offer a promising solution to expedite and reduce the expense of identifying new drug candidates.

Purpose of the Study:

• To develop predictive models for identifying natural products with potential anticancer activity.
• To screen a large dataset of natural products for novel anticancer drug leads.
• To leverage computational techniques to accelerate anticancer drug discovery.

Main Methods:

• Utilized a dataset of 617 approved anticancer drugs (active domain) and 2,892 natural products (inactive domain).
• Employed the iterative stochastic elimination optimization technique to build predictive models.
• Validated model performance using the area under the curve (AUC) metric.

Main Results:

• Achieved a highly discriminative and robust predictive model with an AUC of 0.95.
• Identified twelve natural products with high scores as potential anticancer drug candidates.
• Literature search confirmed prior anticancer activity for Neoechinulin, Colchicine, and Piperolactam; others await evaluation.

Conclusions:

• In silico modeling is effective for predicting anticancer bioactivity in natural products.
• The study identified novel phytochemicals as potential leads for anticancer drug development.
• This computational approach significantly aids in prioritizing natural products for experimental validation in cancer research.