ColabDesign
ColabDesign copied to clipboard
Making Protein Design accessible to all via Google Colab!
When I ran the fixbb design using Afdesign on my computer, I got the following message: /home/n721/pymol/lib/python3.7/site-packages/haiku/_src/data_structures.py:37: FutureWarning: jax.tree_structure is deprecated, and will be removed in a future release. Use...
Hi, Would it be possible for AfDesign to design peptides that bind a certain structure/domain but to do so for a given length *and* within a list (fasta file) of...
Here is a working version of the "binder redesign" idea as posited on Twitter: http://github.com/avilella/utils/blob/master/af/design.ipynb I've tried it a few times and the results make me think that there is...
I tested other optimizers like adam/rmsprop/momentum from '[jax.example_libraries.optimizers'](https://github.com/google/jax/blob/36cd56824def5a6caac2cf1b837f676cfbc8dfb7/jax/example_libraries/optimizers.py). As design initiated, the whole structure predicted by AlphaFold2 became a “black hole” after 10-20 steps, then loss value changed into inf/nan...
When using `model.design_3stage()`, I observe a decrease in RMSE and at some point the error increases again with each additional iteration. I suspect the last iteration is used as design...
Do you all have any thoughts on how to specify what residues are allowed at certain positions, aka a "resfile" (in Rosetta speak), for ColabDesign? Thank you.
I would like to design a protein complex with partial hallucination. My input pdb has two chains, A and B. Chain A is the target, so the whole sequence is...
Hi, thanks for open sourcing this work! I am exploring the binder design (using the `peptide_binder_design.ipynb`) with pdb id `7BW1` with binder lengths between 6-8. What I have observed is...
This is the intermediate log of my optimization problem, where I found that the loss function is:loss=1*con+1*(1-plddt)+rmsd, However, in the readme document, it is stated that a higher value of...
Nice work! I can successfully run the Sequence Redesign and De novo Hallucination for Cyclic peptide, but I have no idea about how to do the prediction of the Cyclic...