RosettaCommons / RosettaCommons/RFdiffusion
Picking more hotspots seems to be more effective for binder generation contrary to Readme
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 3.1k
- Forks
- 644
- PR merge metrics
- No merged PRs in 30d
Description
Hi,
In the Readme (https://github.com/RosettaCommons/RFdiffusion#picking-hotspots), it suggests 5-6 hotspots because "the model is expecting to have to make more contacts than you specify".
However, during my testing, I found that specifying more hotspots helped (usually more than 10), and within 15 Angstroms instead of 10. This prevents the finder from being generated in completely different location, which sometimes happens when there are not enough hot-spots specified.
Is this expected behavior? Should I be using less hotspots (3-6 as recommended) but modify the weights related to the hotspot potentials instead?
Thanks
Contributor guide
No contributing guide indexed for this repository
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
Research direction
Start with the README's “picking hotspots” section and review how its 5–6 hotspot and 10 Å guidance relates to the reported binder-generation behavior. Investigate the comparison with more than 10 hotspots, a 15 Å distance, and hotspot-potential weights; done means the expected behavior and recommended settings are clarified or corrected in the README.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python
- Domain
- bioinformatics, machine-learning
- Issue type
- Documentation
- Difficulty
- 4/5
- Estimated time
- 3-5 days
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 35/100