D-SCRIPT
D-SCRIPT copied to clipboard
samsledje
A structure-aware interpretable deep learning model for sequence-based prediction of protein-protein interactions
Current behavior ([here](https://github.com/samsledje/D-SCRIPT/blob/0955991a27180c9ff4f4e8cd2804d77337aa72f1/dscript/utils.py#L72)) by default uses `n_jobs=-1` to load sequence embeddings in parallel. As a result, any other computation running on the same machine slows down drastically. This should be...
Could you please suggest a method to compare the contact map to an AlphaFold prediction? If I understand correctly, the default TT3D output contact map is a matrix of length(protein1)*length(protein2)...
https://github.com/samsledje/D-SCRIPT/blob/5cefd93122fc9f2b9b4e176a0fa74fca719919dd/dscript/models/interaction.py#L112C72-L112C72 When the size of the sequence is > 2000. The parameter used from broadcasting downstream causes multiplication errors. These errors are silenced in the try except block in `commands/predict.py`....
in train.py: print(f"# Loading embeddings", file=output) tensors = {} all_proteins = set(train_n0).union(set(train_n1)).union(set(test_n0)).union(set(test_n1)) for prot_name in tqdm(all_proteins): **tensors[prot_name] = torch.from_numpy(h5fi[prot_name][:, :])** Can it be modified with pytorch dataloader?
A single process splits candidate interactions to the number of allocated GPUs, and all are able to access the same loaded embeddings in memory - currently can't run more than...
I tried to run `dscript extract-3di` on [.pdb files that include three polypeptide chains](https://github.com/samsledje/D-SCRIPT/files/15346658/atp1a3_pdb.tar.gz), but [the fasta output](https://github.com/samsledje/D-SCRIPT/files/15346715/dscript_extract_output_3di.fasta.gz) only includes one sequence per file. When comparing the length of the...
Hello, How is PPI inference performed with this package? Best, Logan
Thanks for your wonderfull software. I'm fresh in protein-protein interaction analysis. And I have run all the scripts in the dscript/tests/test_commands.py. However, I still didn't know how to create the...
