Executive Summary:
Researchers at The Ohio State University have developed an AI framework called G2Retro that can generate chemical reactions for any given molecule, which could accelerate the drug development process. The framework uses deep neural networks to generate possible reactant structures that could be used to synthesize molecules. The study showed that G2Retro was able to cover an enormous range of possible chemical reactions and accurately discern which reactions might work best to create a given drug molecule. The AI framework could enable the pharmaceutical industry to manufacture stronger drugs at a quicker pace.
Key Insights:
1. G2Retro can generate hundreds of new reaction predictions in only a few minutes, which is much faster than current manual-planning methods.
2. The AI framework can supply multiple different synthesis routes and options, as well as a way to rank different options for each molecule.
3. G2Retro was able to correctly generate the same patented synthesis routes for four newly released drugs already in circulation and provided alternative synthesis routes that are also feasible and synthetically useful.
Business Impact:
The pharmaceutical industry is a highly competitive and lucrative market, and the development of new drugs is a time-consuming and expensive process. The use of AI frameworks like G2Retro could significantly accelerate the drug development process, saving researchers time and money. The generative power of G2Retro could provide drug candidates that may have much better properties than any molecules that exist in nature, enabling the industry to manufacture stronger drugs at a quicker pace. However, it is important to note that the medicines G2Retro or any generative AI creates still need to be validated through animal models and human trials.
—
Read the full article:
https://www.sciencedaily.com/releases/2023/05/230530174302.htm