AI in pharmaceuticals: Tech accelerates active drug ingredients development

Getting your Trinity Audio player ready...

Amid the rapid pace of innovation in generative artificial intelligence (AI), pharmaceutical research involving AI is recording groundbreaking innovations for the development of new drugs.

Researchers at ETH Zurich have tested an AI model capable of identifying and producing active pharmaceutical ingredients—an essential process in developing new drugs. Per the report, the AI model demonstrated proficiency in spotting the appropriate areas for developing active ingredients while streamlining existing processes.

Traditionally, the process involves a tedious approach of “trial-and-error,” which researchers say is often “littered with dead ends.” However, researchers submit that the successes recorded by the AI model can significantly reduce the time spent in the lab attempting to develop new active pharmaceutical ingredients while minimizing the chances of errors.

The AI model identifies the most plausible method for synthesis and can deduce the probability of success. Kenneth Atz, a researcher at ETH Zurich, said the model relies on borylation to activate hydrocarbon scaffolds to speed up the process but highlighted some challenges associated with this method, including difficulty in controlling reactions.

“Although borylation has great potential, the reaction is difficult to control in the lab,” said Atz. “That’s why our comprehensive search of the worldwide literature only turned up just over 1,700 scientific papers on the subject.”

The AI model was trained using 38 papers vetted by researchers as meeting the minimum requirements. The research team supplemented the 1,380 borylation reactions described in 38 papers with an additional 1,000 reactions obtained from Roche’s medicinal chemistry research department.

When fed with 3D information, the AI model recorded impressive results, with the research team members eyeing novel use cases in pharmaceutical research.

“It is very exciting to work at the interface of academic AI research and laboratory automation,” said Atz. “This innovative project is another outstanding example of collaboration between academia and industry and demonstrates the enormous potential of public-private partnerships for Switzerland,” Gisbert Schneider, Professor at the Institute of Pharmaceutical Sciences at ETH Zurich, added.

AI and medical research forge ahead

Researchers have been leaning on AI for impressive medical advances in recent months, underscored by Google’s (NASDAQ: GOOGL) partnership with iCAD for an AI-based cancer detection tool.

NVIDIA (NASDAQ: NVDA) took things up a notch with the introduction of GenSLMs, an AI model capable of identifying COVID-19 variants and classifying genome sequences.

“The AI’s ability to predict the kinds of gene mutations present in recent COVID strains—despite having only seen the Alpha and Beta variants during training—is a strong validation of its capabilities,” said GenSLMs lead researcher.

As emerging technologies find new use cases in health, critics are raising awareness of the risks to patient privacy, copyrights, and misuse by bad actors.

In order for artificial intelligence (AI) to work right within the law and thrive in the face of growing challenges, it needs to integrate an enterprise blockchain system that ensures data input quality and ownership—allowing it to keep data safe while also guaranteeing the immutability of data. Check out CoinGeek’s coverage on this emerging tech to learn more why Enterprise blockchain will be the backbone of AI.

Watch: AI truly is not generative, it’s synthetic