Hi Kirk,

  Elaine is correct that no ligand information in Boltz predictions is sent off of your computer.  The protein sequences are sent to the public Colabfold multiple sequence alignment https://api.colabfold.com run by Martin Steinegger's lab.  I don't know if they have a privacy policy -- I suspect the delete all sequence info sent to them.

  You may also be interested in OpenFold 3 in ChimeraX daily builds (menu Tools / Structure Prediction).  It also installs and runs on your local computer and does not send ligand info, only protein sequences to the MSA server.  Boltz has ligand affinity prediction.  OpenFold 3 has an implementation of the same ligand affinity prediction but it is not yet in ChimeraX.

  You may also be interested in some tests that show ligand prediction in Boltz 2, OpenFold 3 and AlphaFold 3 half the time produces wrong ligand chemistry and chiralities.

https://www.rbvi.ucsf.edu/chimerax/data/ligchem-feb2026/badchem.html

  Tom


On Mar 4, 2026, at 4:09 PM, Elaine Meng via ChimeraX-users <chimerax-users@cgl.ucsf.edu> wrote:

Hi Kirk,
Changing subject line and sending to the recommended address for ChimeraX questions chimerax-users@cgl.ucsf.edu <mailto:chimerax-users@cgl.ucsf.edu> (just don't include anything proprietary when using it, since it has a public archive), as I'm not the expert on this topic.  Others may be able to answer your question more definitively.

However, if I had to guess I would say it doesn't send ligand info anywhere because Boltz runs on your local machine, not on Colab, as per the documentation:
<https://rbvi.ucsf.edu/chimerax/docs/user/tools/boltz.html>

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 Mar 4, 2026, at 3:22 PM, Kirk Nelson <knelson@tyra.bio> wrote:

Hello Elaine,

It is super cool that Boltz was added to ChimeraX.

Can you please confirm whether any ligand information is queried against the external database (api.colabfold.com)?

Thank you,
Kirk Nelson

   From: Elaine Meng <meng@cgl.ucsf.edu>
Date: Thursday, December 18, 2025 at 12:35 PM
To: chimerax-announce@cgl.ucsf.edu <chimerax-announce@cgl.ucsf.edu>
Subject: [chimerax-announce] UCSF ChimeraX 1.11 release

=-=-=-=-=-=-=
UCSF ChimeraX version 1.11 has been released!

This will be the last release to support Red Hat Enterprise Linux 8 and
its derivatives.

ChimeraX includes user documentation and is free for noncommercial use.
Download for Windows, Linux, and MacOS from:
https://www.rbvi.ucsf.edu/chimerax/download.html

Updates since version 1.10.1 (July 2024) include:

- 2D Labels and Arrows GUI
- Boltz 2 structure prediction of proteins, nucleic acids, and
 small-molecule ligands, with affinity prediction
- Boltz 2 batch ligand-binding predictions (many ligands to same receptor)
- General minimization (including ligands) with Minimize Structure tool
 and "minimize" command
- new ViewDock interface (replacing previous ViewDockX)
- new types of trajectory plots: H-bonds, RMSD
- save trajectory plots to image file
- Thermal Ellipsoids GUI
- "chirality" command to report stereocenter chirality
- save/restore scenes including atomic, ribbon, and volume styles and
 coloring; more to be added later

For details, please see the ChimeraX change log:
https://www.rbvi.ucsf.edu/trac/ChimeraX/wiki/ChangeLog

Enjoy!
On behalf of the team,
Elaine
-----
Elaine C. Meng, Ph.D.
UCSF Chimera(X) team
Department of Pharmaceutical Chemistry
University of California, San Francisco


_______________________________________________
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/