Artificial Intelligence Identifies Optimal Locations for Chemical Modifications in Drug Molecules

Artificial intelligence (AI) has been utilized by a team of researchers from LMU, ETH Zurich, and Roche Pharma Research and Early Development (pRED) Basel to create a method that predicts the optimal approach for synthesizing drug molecules. This innovative approach aims to reduce the number of lab experiments required and enhance the efficiency and sustainability of chemical synthesis. Published in the journal Nature Chemistry, the corresponding paper was co-authored by David Nippa, a doctoral student in Dr. David Konrad’s research group at the Faculty of Chemistry and Pharmacy at LMU and at Roche.

Active pharmaceutical ingredients typically consist of a framework to which functional groups are attached, enabling specific biological functions. Altering and adding functional groups to new positions in the framework can enhance medical effects, however, this process presents significant challenges in chemistry. The borylation reaction, for example, involves attaching a chemical group containing the element boron to a carbon atom of the framework, which can then be replaced by medically effective groups. Despite its potential, lab-controlled borylation is difficult. To address this, Nippa and Kenneth Atz trained an AI model on trustworthy scientific data and experiments from an automated lab at Roche, successfully predicting the position of borylation and providing optimal conditions for the chemical transformation.

Taking into account the three-dimensional information of the starting materials, not just their two-dimensional chemical formulas, has notably improved the accuracy of the predictions. The AI model has already been successfully used to identify positions in existing active ingredients where additional active groups can be introduced, enabling the rapid development of new and more effective variants of known drug active ingredients.

The corresponding paper, titled “Enabling late-stage drug diversification by high-throughput experimentation with geometric deep learning,” is a testament to the potential of AI in revolutionizing the pharmaceutical industry. By embracing AI’s predictive capabilities, researchers can effectively streamline the drug development process, reduce the need for extensive lab experiments, and accelerate the creation of innovative pharmaceutical solutions. This groundbreaking approach represents a significant step forward in the evolution of drug synthesis and holds promise for enhancing the efficiency and sustainability of chemical synthesis in the future.

Emily Thompson

Dr. Emily Thompson is a highly respected medical professional and seasoned health journalist, contributing her expertise to our news website. With a medical degree from Johns Hopkins University School of Medicine and over 15 years of experience in clinical practice, Dr. Thompson possesses a deep understanding of various health issues.
Back to top button

Adblock Detected

Please consider supporting us by disabling your ad blocker