-
Notifications
You must be signed in to change notification settings - Fork 226
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Hydra-Powered YAML Configuration and Enhanced File Support in HelixFold3 #321
Conversation
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Thank you for your interest in our work and for the new features you've provided! Before we review your PR, we kindly ask that you split the implemented features into different PRs based on their categories. This will ensure that each PR contains minimal changes, making it easier for us to track code modifications. Once again, thank you for your contribution!
@Fairly Sure! The biggest problem to me however, is splitting those commits into several PRs simutanously would create huge load of conflict solving issues. Any solutions for this? Or can I just create a single PR each time for you to revise and merge? That may take long but would be simplest. |
Creating a single PR each time is fine. Please split these commits based on functionality; for example, changes related to configuration files (Hydra & OmegaConf) can be placed in one PR, while support for covalent bond inputs can be in another. Bug fixes can be distributed across different PRs, so there's no need to be particularly concerned about keeping them organised. Hope these work isn't too much of a burden for you~ |
@Fairly Great! I have reordered these commits and did some stashings to reduce the total number of commits that you guys need to revise. I will create 3 PRs in total, with each contains 4-6 commits. The full branch can be found here. Now, here's the PR roadmap:
|
Added
helixfold
run command for performing inference.Changed
CONFIG_DIFFS
.ml_collections.ConfigDict
withDictConfig
for better integration.Fixed
ref_atom_name_chars
and problematic atoms that caused errors.None-value
inTemplateAtomMaskAllZerosError
to prevent incorrect warning triggers.Removed
requirements.txt
in favor of direct pip installation dependencies.run_infer.sh
script as functionality is now integrated into the main command interface.