Hi Sohail,

  Google did not released the code for AlphaFold 3 so the only way to run it is from their web page.  They also have not provide a web service that would allow programs like ChimeraX to submit prediction jobs.  I asked a contact at Google DeepMind if they plan in the future to provide a web service or provide the code, and they said they have no plans to do so at this time.  Details here

https://www.rbvi.ucsf.edu/trac/ChimeraX/ticket/15135

Google also is not allowing researchers to run predictions with small molecule ligands except for some very common ones like ATP.  It appears Google is treating AlphaFold 3 as a commercial product so the most useful capabilities will only be accessible to the drug discovery company Google has formed called Isomorphic Labs.

  I will be making the ChimeraX display of predicted aligned error (PAE) work with AlphaFold 3 output.  Currently it is broken because AlphaFold 3 now has predicted aligned error for individual atoms of ligands, ions, glycosylation and non-standard residues while AlphaFold 2 only had values for residues of proteins.  I expect to put this fix in ChimeraX today or tomorrow and it will be in the ChimeraX daily builds and ChimeraX 1.8 release candidates.

Tom




On May 11, 2024, at 6:18 AM, Khawar Siddiqui via ChimeraX-users <chimerax-users@cgl.ucsf.edu> wrote:

Hi,
Greetings! When ChimeraX will get Alphafold 3?

Thanks and best wishes 

Dr K Sohail Siddiqui,
School of Biotechnology and Biomolecular Sciences (BABS),
Room 420, Building D26,
The University of New South Wales (UNSW),
Randwick, High Street, Sydney, Australia. NSW 2052
email: z3030204@ad.unsw.edu.au; sohailsiddiqui1995@yahoo.com
_______________________________________________
ChimeraX-users mailing list -- chimerax-users@cgl.ucsf.edu
To unsubscribe send an email to chimerax-users-leave@cgl.ucsf.edu
Archives: https://mail.cgl.ucsf.edu/mailman/archives/list/chimerax-users@cgl.ucsf.edu/