Iambic Therapeutics Launches 'Enchant' AI Model To Accelerate The Discovery Of New Medicines

Fred Manby, founder and Chief Technology Officer of Iambic (photo: x @SciBaskerville ·).

JAKARTA Biotechnology company Iambic Therapeutics announced a breakthrough in artificial intelligence (AI) technology by launching a new model called "Enchant." This technology is claimed to be able to accelerate and reduce drug development costs.

Enchant offers more accurate prediction capabilities from the early stages of development, a move that can simplify the process of creating new drugs. This step further strengthens Iambic's position in the industry, especially with investment support from tech giant Nvidia.

The Enchant model is trained using a large amount of preclinical data, namely laboratory test results conducted before the drug is tested on humans. Different from other AI models, Enchant is designed to predict how drugs will interact with the human body in the early stages.

In a report published by Iambic, Enchant was able to reach an accuracy level of 0.74, higher than the previous model which only reached an accuracy of 0.58. This result has been verified by matching the results of Enchant's prediction with real-world data.

According to Fred Manby, co-founder and Chief Technology Officer Iambic, the use of Enchant can halve the costs required in drug development, particularly with the ability to predict the possibility of drug success in the early stages.

"The cost of bringing a product to market is often cited at around US$2 billion (Rp31.4 trillion), and much of that cost is due to the high failure rate at the end," said Manby. "If you can increase 10% at every stage of clinical development, then the cost can be reduced by half because this savings is cumulative."

Pharmacokinetic Challenges With AI

Frances Arnold, the Nobelist of Kimia in 2018 who is also a member of the Iambic council, stated that the Enchant model represents great progress in the use of AI for drug discovery. He compared Enchant with AlphaFold, a Google DeepMind-made program that won the Nobel Chemical award for the prediction capabilities of the 3D molecular bond structure.

AlphaFold predicts the 3D structure of how molecules are related to protein targets, but the structure alone is not enough. The success of drug candidates is determined by the nature of pharmacokinetics, efficacy, and toxicity. Enchants overcome these important challenges," said Arnold.

Armed with Enchants, Iambic hopes to provide a more efficient solution and reduce the dependence of the pharmaceutical industry on the long and expensive trial process. The model is also expected to help scientists and researchers around the world to bring essential medicines to market more quickly.