Data Details of RhoDesign #4
Description
Dear Team,
Thank you so much for open-sourcing this incredible project! I'm very interested in your work and I have been exploring the repository.
However, I’ve run into a few questions about the training data. As mentioned in the paper, there are “369,499 tertiary structure predictions generated by RhoFold, along with their corresponding secondary structure predictions” as part of the training data. But when I checked the data provided on Zenodo (https://zenodo.org/records/13892413), I couldn’t find this specific subset. Besides, after downloading and extracting the expanded_data-001.tar.bz2 file from Zenodo, I found a folder named filtered_data containing 316,955 entries. Are these 316,955 entries exactly the “RhoFold-generated tertiary structure predictions” mentioned in the paper? Should I be fortunate enough to receive your guidance, it would be of immense assistance to me! I would be truly grateful for your reply.
Thanks again for your work. Looking forward to your reply.
Best regards,
Aspirin