sokrypton / sokrypton/ColabFold
AlphaFold2_advanced notebook
Nobody has claimed this yet.
- Dominant language
- Jupyter Notebook
- Stars
- 2.9k
- Forks
- 747
- PR merge metrics
- No merged PRs in 30d
Description
Hi sokrypton,
First, many thanks for the notebooks...
I was using intensively the AlphaFold2_advanced notebook, and I am very sad that it is not working anymore.
What is missing for me on the new main notebook is :
- the homooligomer "1:2" --> because it is more user friendly that copy/paste sequences, especially to quickly check is the sequence length is >1.400 for example.
- Trim sequence --> really useful (use the full length sequence for the MSA but not to generate the model) and convenient with the graphic representation before and after trim !
- The extra output, especially the distogram plot, to see coevolution between proteins: If I am correct, the coevolution is a very useful information by itself, and because the AlphaFOLD model could be wrong, but not the coevolution, it is a robust result. So sometime I used the AlphaFold2_advanced notebook just to have the coevolution information rather than structural models.
So, my question is: it is doable to simply update the AlphaFold2_advanced notebook to use it again? Or to integrate in the AlphaFold2_mmseqs2 notebook the functions mentioned above?
Best,
Kevin
Contributor guide
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 by comparing the AlphaFold2_advanced notebook with the AlphaFold2_mmseqs2 notebook, focusing on homooligomer input, sequence trimming, and extra outputs such as the distogram plot. Confirm which requested capabilities are still present and define completion as restoring or integrating the requested functions in a usable notebook.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- jupyter-notebook
- Domain
- bioinformatics, machine-learning
- Issue type
- Feature
- Difficulty
- 5/5
- Estimated time
- Over a week
- Activity status
- Stale
- Clarity
- Mostly clear
- Newbie friendliness
- 25/100