Help with ChimeraX Boltz Structure Prediction Command for Multi-Component Systems
Dear ChimeraX Team, I'm currently working with the Boltz structure prediction tool in ChimeraX GUI (ChimeraX 1.10 Release Candidate (15 June 2025) ) and would appreciate your guidance on the correct command syntax—particularly when specifying the single or multiple protein components via the ChimeraX GUI command line. I would like to run Boltz predictions with the following specific parameters: * nstruct: 5 (Default is 1) * recycles: 10 (Default is 3) * seed: 42 (Random numbers of seed (integer), Fixed seed value ensures reproducible results) * steering: true (enables or disables the steering potential) I tried running the following command in the command line, "boltz predict protein sequences "MKALTQRPLD... (your protein sequence)" nstruct 5 recycles 10 steering true" but it doesn't work. Could you please provide an example of the correct command format for: 1. A single molecular component (e.g., one protein sequence). 2. A multi-component system (e.g., protein + peptide or multiple protein chains). Additionally, if there are any special considerations or formatting requirements for specifying multiple sequences or components in the GUI , I’d be grateful for your advice. Thank you for your time and support. Best Regards, Arun Arun Gupta PhD, MRSC Sr. Post Doctoral Research Assistant Gillespie/McMichael Group Nuffield Dept. of Clinical Medicine, University of Oxford, Centre for Immuno-Oncology Old Road Campus Research Building, Roosevelt Drive, Oxford OX3 7DQ Tel: + 44 (0)1865 2612913
Hi Arun, Here is the "boltz predict" command help, which you could also see from using ChimeraX command "help boltz predict": <https://rbvi.ucsf.edu/chimerax/docs/user/commands/boltz.html#predict> The syntax is shown in the Usage line. Your command is wrong because: (1) you should not include the word "sequences" which would be replaced with the actual sequence(s) (2) there is no "nstruct" option (3) there is no "steering" option I don't know where you saw those options, maybe you are looking in some other documentation that is not for ChimeraX. So anyway you'd want something like boltz predict protein MKALTQRPLD[...rest of sequence...] recycles 10 How to specify "sequences" including multiple sequences is explained in the documentation link above. There are a few different ways so I'll let you read it there instead of repeating it all here. For a specific example, see also the following page and the video on this topic. <https://www.rbvi.ucsf.edu/chimerax/data/boltz-apr2025/boltz_help.html> <https://www.youtube.com/watch?v=377V9A_0ECc> I hope this helps, Elaine ----- Elaine C. Meng, Ph.D. UCSF Chimera(X) team Resource for Biocomputing, Visualization, and Informatics Department of Pharmaceutical Chemistry University of California, San Francisco
On Jun 20, 2025, at 2:18 AM, Arun Gupta via ChimeraX-users <chimerax-users@cgl.ucsf.edu> wrote:
Dear ChimeraX Team, I'm currently working with the Boltz structure prediction tool in ChimeraX GUI (ChimeraX 1.10 Release Candidate (15 June 2025) ) and would appreciate your guidance on the correct command syntax—particularly when specifying the single or multiple protein components via the ChimeraX GUI command line. I would like to run Boltz predictions with the following specific parameters: • nstruct: 5 (Default is 1) • recycles: 10 (Default is 3) • seed: 42 (Random numbers of seed (integer), Fixed seed value ensures reproducible results) • steering: true (enables or disables the steering potential) I tried running the following command in the command line, "boltz predict protein sequences "MKALTQRPLD... (your protein sequence)" nstruct 5 recycles 10 steering true" but it doesn't work.
Could you please provide an example of the correct command format for: • A single molecular component (e.g., one protein sequence). • A multi-component system (e.g., protein + peptide or multiple protein chains). Additionally, if there are any special considerations or formatting requirements for specifying multiple sequences or components in the GUI , I’d be grateful for your advice. Thank you for your time and support. Best Regards, Arun
Arun Gupta PhD, MRSC Sr. Post Doctoral Research Assistant Gillespie/McMichael Group Nuffield Dept. of Clinical Medicine, University of Oxford, Centre for Immuno-Oncology Old Road Campus Research Building, Roosevelt Drive, Oxford OX3 7DQ Tel: + 44 (0)1865 2612913
_______________________________________________ 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/
Oh actually I see that "help boltz predict" will still give the example page. But you can get to the command page from the User Guide command index. Regards, Elaine
On Jun 20, 2025, at 9:44 AM, Elaine Meng via ChimeraX-users <chimerax-users@cgl.ucsf.edu> wrote:
Hi Arun, Here is the "boltz predict" command help, which you could also see from using ChimeraX command "help boltz predict":
<https://rbvi.ucsf.edu/chimerax/docs/user/commands/boltz.html#predict>
The syntax is shown in the Usage line. Your command is wrong because:
(1) you should not include the word "sequences" which would be replaced with the actual sequence(s) (2) there is no "nstruct" option (3) there is no "steering" option
I don't know where you saw those options, maybe you are looking in some other documentation that is not for ChimeraX. So anyway you'd want something like
boltz predict protein MKALTQRPLD[...rest of sequence...] recycles 10
How to specify "sequences" including multiple sequences is explained in the documentation link above. There are a few different ways so I'll let you read it there instead of repeating it all here.
For a specific example, see also the following page and the video on this topic. <https://www.rbvi.ucsf.edu/chimerax/data/boltz-apr2025/boltz_help.html> <https://www.youtube.com/watch?v=377V9A_0ECc>
I hope this helps, Elaine ----- Elaine C. Meng, Ph.D. UCSF Chimera(X) team Resource for Biocomputing, Visualization, and Informatics Department of Pharmaceutical Chemistry University of California, San Francisco
On Jun 20, 2025, at 2:18 AM, Arun Gupta via ChimeraX-users <chimerax-users@cgl.ucsf.edu> wrote:
Dear ChimeraX Team, I'm currently working with the Boltz structure prediction tool in ChimeraX GUI (ChimeraX 1.10 Release Candidate (15 June 2025) ) and would appreciate your guidance on the correct command syntax—particularly when specifying the single or multiple protein components via the ChimeraX GUI command line. I would like to run Boltz predictions with the following specific parameters: • nstruct: 5 (Default is 1) • recycles: 10 (Default is 3) • seed: 42 (Random numbers of seed (integer), Fixed seed value ensures reproducible results) • steering: true (enables or disables the steering potential) I tried running the following command in the command line, "boltz predict protein sequences "MKALTQRPLD... (your protein sequence)" nstruct 5 recycles 10 steering true" but it doesn't work.
Could you please provide an example of the correct command format for: • A single molecular component (e.g., one protein sequence). • A multi-component system (e.g., protein + peptide or multiple protein chains). Additionally, if there are any special considerations or formatting requirements for specifying multiple sequences or components in the GUI , I’d be grateful for your advice. Thank you for your time and support. Best Regards, Arun
Arun Gupta PhD, MRSC Sr. Post Doctoral Research Assistant Gillespie/McMichael Group Nuffield Dept. of Clinical Medicine, University of Oxford, Centre for Immuno-Oncology Old Road Campus Research Building, Roosevelt Drive, Oxford OX3 7DQ Tel: + 44 (0)1865 2612913
_______________________________________________ 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/
_______________________________________________ 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/
Hi Arun, The ChimeraX boltz predict documentation shows to specify the number of structures you use the "samples" option (that is what Boltz itself calls separate structures). Here is the most up to date documentation https://www.rbvi.ucsf.edu/chimerax/data/boltz-apr2025/boltz_help.html#comman... The ChimeraX User Guide also describes the command but is slightly out of date (e.g. no steering option) because the Boltz feature has been changing every week. https://www.cgl.ucsf.edu/chimerax//docs/user/commands/boltz.html So an example command would be boltz predict protein MKALTQRPLD... protein LTQRPLDLTQRPLD... recycles 10 samples 5 steering true seed 42 name my_dimer Tom
On Jun 20, 2025, at 12:44 PM, Elaine Meng via ChimeraX-users <chimerax-users@cgl.ucsf.edu> wrote:
Hi Arun, Here is the "boltz predict" command help, which you could also see from using ChimeraX command "help boltz predict":
<https://rbvi.ucsf.edu/chimerax/docs/user/commands/boltz.html#predict>
The syntax is shown in the Usage line. Your command is wrong because:
(1) you should not include the word "sequences" which would be replaced with the actual sequence(s) (2) there is no "nstruct" option (3) there is no "steering" option
I don't know where you saw those options, maybe you are looking in some other documentation that is not for ChimeraX. So anyway you'd want something like
boltz predict protein MKALTQRPLD[...rest of sequence...] recycles 10
How to specify "sequences" including multiple sequences is explained in the documentation link above. There are a few different ways so I'll let you read it there instead of repeating it all here.
For a specific example, see also the following page and the video on this topic. <https://www.rbvi.ucsf.edu/chimerax/data/boltz-apr2025/boltz_help.html> <https://www.youtube.com/watch?v=377V9A_0ECc>
I hope this helps, Elaine ----- Elaine C. Meng, Ph.D. UCSF Chimera(X) team Resource for Biocomputing, Visualization, and Informatics Department of Pharmaceutical Chemistry University of California, San Francisco
On Jun 20, 2025, at 2:18 AM, Arun Gupta via ChimeraX-users <chimerax-users@cgl.ucsf.edu> wrote:
Dear ChimeraX Team, I'm currently working with the Boltz structure prediction tool in ChimeraX GUI (ChimeraX 1.10 Release Candidate (15 June 2025) ) and would appreciate your guidance on the correct command syntax—particularly when specifying the single or multiple protein components via the ChimeraX GUI command line. I would like to run Boltz predictions with the following specific parameters: • nstruct: 5 (Default is 1) • recycles: 10 (Default is 3) • seed: 42 (Random numbers of seed (integer), Fixed seed value ensures reproducible results) • steering: true (enables or disables the steering potential) I tried running the following command in the command line, "boltz predict protein sequences "MKALTQRPLD... (your protein sequence)" nstruct 5 recycles 10 steering true" but it doesn't work.
Could you please provide an example of the correct command format for: • A single molecular component (e.g., one protein sequence). • A multi-component system (e.g., protein + peptide or multiple protein chains). Additionally, if there are any special considerations or formatting requirements for specifying multiple sequences or components in the GUI , I’d be grateful for your advice. Thank you for your time and support. Best Regards, Arun
Arun Gupta PhD, MRSC Sr. Post Doctoral Research Assistant Gillespie/McMichael Group Nuffield Dept. of Clinical Medicine, University of Oxford, Centre for Immuno-Oncology Old Road Campus Research Building, Roosevelt Drive, Oxford OX3 7DQ Tel: + 44 (0)1865 2612913
_______________________________________________ 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/
_______________________________________________ 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/
participants (3)
-
Arun Gupta -
Elaine Meng -
Tom Goddard