What is it about?

Millions of people suffer from opioid use disorder, and current treatments often fall short. We used an AI platform to analyze brain tissue from people who had been dependent on opioids, identifying the molecular changes caused by addiction. The AI then predicted which targets a new drug should hit, and helped design two candidate compounds. The most promising one, GATC-1021, targets serotonin receptors in the brain and dramatically reduces fentanyl intake in rats, without causing side effects or hallucinogenic responses, even after repeated doses.

Featured Image

Why is it important?

Our findings show that AI-guided drug discovery, when anchored in real human brain data, can generate effective therapeutic candidates faster than traditional approaches. GATC-1021 not only reduced drug-seeking behavior but also triggered changes in the brain linked to learning and cellular plasticity, suggesting it may help the brain adjust back to normal signaling following drug-induced alterations, not just suppress addiction. This work provides a strong foundation for moving forward to clinical trials and offers hope for the millions of people for whom existing treatments are not enough.

Perspectives

"This study feels like winning a Connect Four game: we combined AI, gene expression, brain structure, behavior, and toxicity, all lined up at once. That is a big win in drug discovery. And the fact that it started from the brains of people who actually suffered from this disease makes it mean even more." Valeria Lallai, University of California, Irvine

Christie Fowler
University of California Irvine

Read the Original

This page is a summary of: AI-derived therapeutic development of a serotonin receptor–targeting drug for the treatment of opioid use disorder, Proceedings of the National Academy of Sciences, April 2026, Proceedings of the National Academy of Sciences,
DOI: 10.1073/pnas.2516807123.
You can read the full text:

Read

Contributors

The following have contributed to this page