AlphaFold continues to shine

For the first time, researchers have shown that ligand docking against the protein structures predicted by AlphaFold was as effective as that against experimental structures. Structure-based protein-ligand docking is widely used in drug discovery and design. Many previous studies have shown that using AlphaFold-predicted protein structures often fails to recognize and pose ligands already known to bind to the protein. The authors of this paper argued the failure might be due to data bias from retrospective data, not AlphaFold prediction errors, because “known ligands can affect the conformations adopted by experimental structures when they are determined in complex with them, while experimental structures can influence the exploration of new ligands“. Therefore, the authors prospectively screened a large ligand library docking against two proteins where the AlphaFold models appeared before the crystal structures were released. The prospective screen yielded similar hit rates for both proteins versus docking against experimentally derived structures.

In another paper published by David Baker’s lab, AlphaFold helped design sensors that can detect endogenous Ras activity, which “should be useful for profiling Ras activities in Ras-driven cancers, their responses to drugs and mechanisms of drug resistance”.

Featured News

• BenevolentAI appoints former Bayer R&D chief as CEO

• A new $630 million venture fund bets on AI-driven healthcare and biotech

• Nature Machine Intelligence’s anniversary AI reflections

• RoboChem: an open-sourced robotic platform for photocatalysis

• COMPOSER: A deep-learning model for early prediction of sepsis that could significantly reduce the sepsis-related mortality rate

• MedSAM: Segment anything in medical images

If you find the newsletter helpful, please consider:

• 🔊 Sharing the newsletter with other people

• 👍 Upvoting on Product Hunt

• 📧 Sending any feedback, suggestions, and questions by directly replying to this email or writing reviews on Product Hunt

• 🙏 Supporting us with a cup of coffee.

Thanks, and see you next time!