Is it time for artificial intelligence to predict the function of natural products based on 2D-structure

Area of Science:

• Metabolomics
• Cheminformatics
• Artificial Intelligence

Background:

• Predicting the function of naturally occurring compounds based solely on their 2D chemical structure remains an unsolved problem in chemistry.
• Identifying the biological roles of all known metabolites is a significant challenge in the field.

Purpose of the Study:

• To explore the potential of Artificial Intelligence (AI) in predicting the function of metabolites.
• To develop a method for the rationale interrogation of chemical structures to determine metabolite function.

Main Methods:

• Utilizing Artificial Intelligence algorithms for the analysis of chemical structures.
• Applying computational methods to interrogate metabolite data.

Main Results:

• Demonstrated the feasibility of using AI to predict metabolite function from 2D structures.
• Provided a novel approach to address a grand challenge in chemistry.

Conclusions:

• Artificial Intelligence presents a promising avenue for deciphering the functional roles of natural compounds.
• This AI-driven approach can accelerate the identification of metabolite functions, advancing metabolomics and drug discovery.