ProSST

ProSST copied to clipboard

Hi! When I try to use ProSST to predict the effect of mutations, I kept stuck in the "Quantize the structure" phase. I have tested it for nearly 4h earlier,...

ldx022

Thanks for the great work and open-sourced codebase for your model! I've been working on a project that involves fine-tuning your model, and ran into one issue. I was fine-tuning...

rcalef

SSTPredictor stopped when I use it to generate embedding for the structures from pdb file.

1

 As shown in the picture, it stopped when i use: predictor = SSTPredictor(structure_vocab_size=2048) result = predictor.predict_from_pdb('../example_data/xxx.pdb') to generate embedding for the pdb file. Some pdb files worked, but some...

XudongZhang-ny

Error in score_mutant.ipynb

4

structure_sequence_offset = [i + 3 for i in structure_sequence] TypeError: can only concatenate str (not "int") to str

MichaelAbel1

PdbQuantizer is too slow

2

It's too slow and even cannot process multiple PDBs at once. I cannot understand how the authors use this code to process the AlphaFoldDB including millions proteins for PLM training....

yourh

Discrepancy in structure quantizer outputs and request for original PDB files used in the proteingym_benchmark.zip

2

Thank you for your open-source work! Regarding the structure quantizer, I tried the example provided in the README but obtained different outputs. Below is my code and the generated output:...

yangguang8112

PdbQuantizer stuck

1

Hello everybody, i'm currently trying to use ProSST to predict the effect of mutations on different proteins in a zero-shot setting. I'm currently using the zero_shot notebook as reference, however...

j3rk0

Thank you for the work you have done. This question pertains to downstream tasks.

5

The dimension of the vector representations generated by your model is determined by the number of residues in the protein. Have you compared which method for unifying vector lengths works...

lllastronaut

Structural tokenizer (`PdbQuantizer`) is too slow at processing long proteins

9

Hi Teams, Thanks for the great work. Wondering how long it takes to process a protein of length 400 for your pre-trained `PdbQuantizer`? On my machine, somehow it's super slow....

KatarinaYuan

Thanks for your open-source model! However, when I tried the tools, I had some needs that were not met by the examples. How can I extract sequence embeddings using this...

Zmmhd