[Chimera-users] AlphaFold Modeling

Tom Goddard goddard at sonic.net
Mon Oct 31 14:21:15 PDT 2022


Hi Raihan,

The ChimeraX AlphaFold prediction produces 5 models but it only automatically opens the best model.  All 5 models are in the ~/Downloads/ChimeraX/AlphaFold/prediction  directory after the job completes.  There is no option to run fewer models.  Running AlphaFold not through ChimeraX also produces 5 models.  This is because AlphaFold works by running 5 slightly differently trained neural networks and the best is chosen.  If you install your own AlphaFold (a somewhat difficult task, needs Linux and an Nvidia GPU and a few Tbytes of disk for databases) then you can modify the AlphaFold Python code to predict only one or a few models by choosing which of the 5 networks it should run.

	Tom

> On Oct 31, 2022, at 1:31 PM, Elaine Meng via Chimera-users <chimera-users at cgl.ucsf.edu> wrote:
> 
> Hi Raihan,
> If you are using Chimera, it does not have AlphaFold prediction.  Chimera has Modeller comparative modeling (based on template structure) with default number of models = 5, but you can change that in the "Advanced Options" on the Modeller comparative modeling tool: in that section, juist change the "Number of output models" value.
> <https://www.rbvi.ucsf.edu/chimera/docs/ContributedSoftware/multalignviewer/modeller.html#comparative>
> 
> If you are using ChimeraX, it has both Modeller Comparative Modeling, and AlphaFold prediction.  However, the Alphafold prediction only gives you one model.   If you are using ChimeraX, it is better to send your question to the address chimerax-users at cgl.ucsf.edu ... either way please be clear about which program and which tool you are using.  Thanks!
> 
> I hope this helps,
> Elaine
> -----
> Elaine C. Meng, Ph.D.                       
> UCSF Chimera(X) team
> Department of Pharmaceutical Chemistry
> University of California, San Francisco
> 
> 
> 
> 
>> On Oct 31, 2022, at 1:09 PM, S.M. RAIHAN RAHMAN via Chimera-users <chimera-users at cgl.ucsf.edu> wrote:
>> 
>> Hi!
>> Good Afternoon. I hope that you are doing well. I am facing a problem in running structure prediction of large protein sequence. Is there any way of predicting only 2 models of a given sequence in lieu of 5 models? Please let me know. Thank you.
>> 
>> Regards,
>> Raihan
> 
> 
> _______________________________________________
> Chimera-users mailing list: Chimera-users at cgl.ucsf.edu
> Manage subscription: https://www.rbvi.ucsf.edu/mailman/listinfo/chimera-users
> 




More information about the Chimera-users mailing list