Identification of CXCR4 inhibitory activity in natural compounds using cheminformatics-guided machine learning...

Area of Science:

• Neuroscience
• Computational Chemistry
• Pharmacology

Background:

• Neurodegenerative disorders like Alzheimer's and Parkinson's involve progressive neuron damage, with current treatments only managing symptoms.
• Previous research identified upregulation of CXC motif chemokine receptor 4 (CXCR4) in Alzheimer's disease (AD) and Parkinson's disease (PD) patients.

Purpose of the Study:

• To identify natural compounds with potential CXCR4 inhibitory activity using cheminformatics-guided machine learning.
• To aid in the drug discovery process for neurodegenerative disorders, particularly AD and PD.
• To leverage AI and ML for identifying novel therapeutic leads.

Main Methods:

• Utilized machine learning models trained on compounds with known CXCR4 activity from the Binding Database.
• Analyzed physicochemical attributes of natural compounds from the COCONUT Database.
• Employed cheminformatics and machine learning algorithms to predict CXCR4 inhibitory activity.

Main Results:

• The study successfully developed a machine learning model for predicting CXCR4 inhibitory activity of natural compounds.
• Identified potential natural compounds for further investigation as therapeutic agents against neurodegenerative diseases.
• Demonstrated the efficacy of AI/ML in accelerating drug discovery for complex diseases.

Conclusions:

• AI and ML are powerful tools for identifying potential drug candidates for neurodegenerative disorders.
• Natural compounds show promise for modulating CXCR4 and offer biocompatible therapeutic options.
• Interdisciplinary collaboration is crucial for advancing drug discovery pipelines.