YH-Zhu

How to get the reported performance

1

I have some trouble evaluating the performance. Take experiments about image classification as an example, 1) Does the reported uniformity stand for the mean of uniformity computed per preference ray,...

Downloading AlphaFoldDB

3

Hello, After I manually downloaded the data, I found that md5 is inconsistent with that provided by the code. So the code will re-download the data again. What should I...

Hello! I have one question about the input features 'residue' of pockets. The 'residue' is constructed with chain id and residue number from pdb file. However, I could not find...

Question about the input feature of pockets

2

Hi, I have two questions about the input features of pockets. 1) For 'side', I think it means whether the atom is in the side chain. So, I do not...

How to fine-tune in the PDBbind

2

Hi, It's a very interesting model. Would you mind providing the code for preprocessing the data of PDBbind and fine-tuning?

Hi, thank you for providing this code! in L185-186 (pcd_potts.py), - logp_real = (model(x).squeeze() * weights).mean() - logp_fake = model(x_fake).squeeze().mean() 1. Why reweighting is only applied to x 2. Should...

about decoding topk_masking

1

Hi Thanks for your excellent work. I have a question about the rate schedule for topk_masking. As described in the appendix, "To ensure that the degree of noise decreases as...

Question about the time encoding

1

Hi, I have a question about the time encoding. As DiffPreT is trained like a diffusion model, does the backbone network GearNet explicitly encode the time step?

Code for computing the metrics

2

Hi Thanks for your excellent work! I have some trouble in computing the metrics. I don't know how to get the inputs for [get_batch_descriptors](https://github.com/prescient-design/walk-jump/blob/1f9a6a5068904a6fe7474d79dfa41b7a7b589ba2/src/walkjump/metrics/_get_batch_descriptors.py#L47). Could you please provide a script...