Issues Encountered During Feature Generation

[hkhkhove]

Hi,

I've encountered a couple of issues while generating features:

It seems that the batch_save_msa_feat.py script is not compatible with the latest ColabFold 1.5.5. Could you please specify which version of ColabFold your batch_save_msa_feat.py script is compatible with?

It appears that there is no script in the repository to generate the distmap.

To address these issues, I modified the ColabFold 1.5.5 batch.py script to extract the MSA first row features, and I wrote a script to extract the distmap based on the provided distmap example. However, the AUC obtained with my modified code on the DNA_test_129 dataset is 0.9386, which is lower than the 0.9428 AUC obtained with your provided features. I suspect there might be an issue with my modifications.

Could you please provide some guidance on these issues?

Thank you!

[rahmatullah-roche]

Distance maps can be created using any publicly available scripts such as this one or you can create your own script. The input is the protein structure (PDB format), and the output is the corresponding distance map (distmap).

To save the msa_first_row features, the ['representations']['msa_first_row'] representation should be extracted and saved. Since we used an earlier version of ColabFold (1.2.0) in our work, this could explain the difference in AUC between the provided features and those generated using your modifications with ColabFold 1.5.5.