Xinyu Yuan

SVDSuperimposer._rms() is wrong?

2

### Original Code Line 116-119 in https://github.com/biopython/biopython/blob/master/Bio/SVDSuperimposer/__init__.py ``` def _rms(self, coords1, coords2): """Return rms deviations between coords1 and coords2 (PRIVATE).""" diff = coords1 - coords2 return sqrt(sum(sum(diff * diff)) /...

Implementation of softtopk_np()

1

Hi, I'm wondering if you can share some insights about the choice of Numpy instead of PyTorch for the implementation of softtopk_np() in sst.core.topk.py? Because I think that I haven't...

Extreme inefficiency for `save_to_disk` when merging datasets

1

### Describe the bug Hi, I tried to merge in total 22M sequences of data, where each sequence is of maximum length 2000. I found that merging these datasets and...

Hi, I see that you mentioned "I'll keep playing around with topk attention though, because it bothers me that softmax becomes a bottleneck for the tokens far in the future,...

How to do self-conditioning?

2

Hi, I noticed that in the paper, you mentioned that self-conditioning is quite important for RFdiffusion. Wondering if you could provide an example of implementation for us to follow? Thank...

Hi, I try to run the command in `./DNABERT_2/finetune/scripts/run_dnabert2.sh` and get the following results. However, it cannot match the reported ones in DNA-BERT2's paper. ![Screen Shot 2024-05-07 at 10 44...

Hi, Could you please release all the codes related to the evaluation experiments in the paper? The experiments in the paper seem to be very interesting, though it's a little...

Release for Raw Counts of those Downstream Datasets

1

Hi, it would be great if you can release the raw version of these datasets, along with the preprocessing scripts for these downstream datasets? Some of the released data (e.g.,...

Release of Pre-training Data Preprocess Scripts

1

Hi, If the data release for OpenGenome is still on-going, would it be possible to release the preprocess scripts for the data (no need to be exactly reproducible)?

Mismatch 3Di Sequence Inferenced from FoldSeek Command and that from mini3di repo

2

## Expected Behavior I try to transform PDB structures into 3Di sequences. For mini3di (https://github.com/althonos/mini3di/), I used ``` pdb_path = "1xso.cif" # mini3di from Bio import PDB if pdb_path.endswith(".pdb"): parser...