Bilingual

AI helps Stanford scientists discover natural Ozempic without usual side effects
a day ago
- Stanford researchers used AI to discover a natural molecule, BRP, that suppresses appetite and reduces weight like Ozempic but without common side effects such as nausea, constipation, and muscle loss.
- BRP acts specifically in the hypothalamus, offering a more targeted approach to appetite control compared to semaglutide, which affects multiple tissues.
- The AI algorithm Peptide Predictor screened human genes to identify 373 prohormones and 2,683 possible peptides, leading to the discovery of BRP, a 12-amino-acid peptide that strongly activates neuronal cells.
- In animal studies, BRP reduced food intake by up to 50% and promoted fat loss without significant side effects; treated mice showed improved glucose and insulin tolerance.
- The research was published in Nature, and the senior author has co-founded a company planning human clinical trials.
The Isomorphic Labs Drug Design Engine unlocks a new frontier beyond AlphaFold
12 days ago
- IsoDDE significantly outperforms AlphaFold 3 in protein-ligand structure prediction, more than doubling accuracy on challenging benchmarks.
- The model predicts small molecule binding affinities with higher accuracy than physics-based methods like FEP, while being much faster and cheaper.
- IsoDDE can accurately identify novel binding pockets on proteins using only amino acid sequences, even for cryptic or allosteric sites.
- It shows exceptional performance in antibody-antigen interface modeling, especially for the variable CDR-H3 loop, enabling de novo antibody design.
- The system generalizes well to unseen biomolecular systems, handling complex events like induced fits and cryptic pocket opening.
- IsoDDE provides scalable, unified computational drug design, bridging structure prediction and real-world drug discovery applications.
Anthropic wants to develop its own drugs
a month ago
- Anthropic announces Claude Science, an AI workbench for scientists, aiming to accelerate scientific discovery and healthcare interventions.
- Anthropic plans to develop its own drugs, focusing on treatments for neglected diseases, which is a direct move into drug development by a frontier AI company.
- Experts note AI's broad application in drug discovery across all stages, but highlight challenges such as data gaps, the necessity of real-world experiments, and the long timeline for drug approval.
- Despite AI's potential to speed up research and suggest new drug ideas, no AI-designed drug has yet reached the market, with clinical trials and safety testing remaining slow and resource-intensive.
- Anthropic is actively hiring biologists and building wet labs, indicating commitment to its drug development ambitions, though specifics on targets and partnerships remain undisclosed.

Hasty Briefsbeta

ai drug discovery

AI helps Stanford scientists discover natural Ozempic without usual side effects

The Isomorphic Labs Drug Design Engine unlocks a new frontier beyond AlphaFold

Anthropic wants to develop its own drugs