Yesterday Google DeepMind released the new version of AlphaFold

AlphaFold 3 creates capabilities for drug design with predictions for molecules commonly used in drugs, such as ligands and antibodies, that bind to proteins to change how they interact in human health and disease.

AlphaFold 3 achieves unprecedented accuracy in predicting drug-like interactions, including the binding of proteins with ligands and antibodies with their target proteins. AlphaFold 3 is 50% more accurate than the best traditional methods on the PoseBusters benchmark without needing the input of any structural information, making AlphaFold 3 the first AI system to surpass physics-based tools for biomolecular structure prediction. The ability to predict antibody-protein binding is critical to understanding aspects of the human immune response and the design of new antibodies — a growing class of therapeutics.

And the new AlphaFold Server is online for everyone

---

And the new AlphaFold Server is online for everyone

There is a lot of "excitement" about this new Alphafold (a lot of researchers are commenting on socials), but there is some issues:
- public server permits only 10 simulations/day.
- they not published the source code.

---

'cause the high use of the alphafold portal, the team are doubling daily job limit to 20.
And they say they will release the source code (for academic use) within 6 months.

---

......some issues:
- they not published the source code.

Over 200 scientists wrote a mail to Nature about closed code of AlphaFold3 (even to reviewers of the article - violating their own policy!!)
Nature answered

---