Iambic Therapeutics launches AI platform to predict drug success

Share this article

Iambic Therapeutics has unveiled Enchant, an innovative AI-powered platform aimed at transforming the earliest stages of drug discovery. Enchant, a sophisticated multi-modal transformer model, is designed to predict clinical properties of new drug candidates, helping scientists assess a drug’s viability long before clinical trials begin. The platform’s predictive capabilities could lower development costs and reduce risks associated with clinical trials by filtering out less promising drug candidates early in the process.

The Enchant platform enables researchers to analyse a drug’s pharmacokinetics, understanding how a drug will interact within the human body. This approach provides insights on potential drug behaviour, allowing teams to make informed decisions on which candidates to pursue further. “Enchant represents a new frontier in AI-driven drug discovery,” says MIT Associate Professor Connor Coley. “By leveraging Enchant’s predictive capabilities, developers can accelerate the process of designing, making, and testing drug candidates, ultimately reducing the burden of traditional experimentation methods.”

The AI model, trained on a blend of preclinical and limited clinical data, uses data from multiple sources to predict key drug properties influencing clinical outcomes. Enchant is capable of integrating diverse data types generated at different research stages, addressing challenges in data variability and quality. According to Fred Manby, Chief Technology Officer at Iambic, Enchant’s predictions have already outperformed existing models in clinical outcome accuracy.

Iambic’s latest tool is poised to enhance the efficiency of drug discovery, bringing the field closer to safer, more cost-effective therapeutic development.

Related Posts
Others have also viewed

The AI boom is running into the physical economy

The extraordinary sums committed to AI infrastructure suggest an industry unconstrained by capital, but money ...

The best AI infrastructure decision is the one you can change

The infrastructure that looks optimal for an AI workload today may be the wrong place ...
Into The madverse podcast

Episode 32: Your GPUs are waiting for the network

AI performance is not decided by GPUs alone because the network now determines how effectively ...

Why the biggest challenge is not cooling AI but predicting tomorrow’s heat

The AI era has pushed data centre cooling into the spotlight, but the real challenge ...