martinez-zacharya / trill Goto Github PK

Hi! Looking to play around with trill on colab- the link to the notebook with install instructions from the online documentation appears to have the wrong permissions or not be functional- I can not access it.

https://colab.research.google.com/drive/1mx16cDAEgCYtflKm80mE8L_ZEk7Upxxe#scrollTo=AunNpGWa8tGn

Thanks!

Running any trill command in an environment with the latest biopython release (1.82) throws the following error:

Traceback (most recent call last):
  File "/home/arjuna/micromamba/envs/trill/bin/trill", line 5, in <module>
    from trill.trill_main import cli
  File "/home/arjuna/micromamba/envs/trill/lib/python3.10/site-packages/trill/trill_main.py", line 32, in <module>
    from trill.utils.dock_utils import perform_docking, fixer_of_pdbs, write_docking_results_to_file
  File "/home/arjuna/micromamba/envs/trill/lib/python3.10/site-packages/trill/utils/dock_utils.py", line 15, in <module>
    from biobb_vs.utils.box import box
  File "/home/arjuna/micromamba/envs/trill/lib/python3.10/site-packages/biobb_vs/utils/box.py", line 11, in <module>
    from biobb_vs.utils.common import check_input_path, check_output_path, get_box_coordinates
  File "/home/arjuna/micromamba/envs/trill/lib/python3.10/site-packages/biobb_vs/utils/common.py", line 15, in <module>
    from Bio.Data.SCOPData import protein_letters_3to1 as prot_one_letter
ModuleNotFoundError: No module named 'Bio.Data.SCOPData'

It appears that (doc link) Bio.Data.SCOPData was removed from biopython beginning with version 1.82. A workaround is to downgrade biopython (e.g. by pip install biopython==1.81) after completing all other setup instructions, but this should probably be addressed as a dependency.

running 'embed' got me this:
Traceback (most recent call last): File "/usr/local/bin/trill", line 8, in <module> sys.exit(cli()) File "/usr/local/lib/python3.8/dist-packages/trill/trill_main.py", line 394, in cli main(args) File "/usr/local/lib/python3.8/dist-packages/trill/trill_main.py", line 273, in main model = ESM(eval(model_import_name), float(args.lr), args.LEGGO) AttributeError: 'Namespace' object has no attribute 'lr'

Running the command to generate sequences produces the following:

File "/usr/local/bin/trill", line 8, in <module>
   sys.exit(cli())
 File "/usr/local/lib/python3.8/dist-packages/trill/trill_main.py", line 387, in cli
   main(args)
 File "/usr/local/lib/python3.8/dist-packages/trill/trill_main.py", line 340, in main
   generated_output = model.generate(seed_seq=args.seed_seq, max_length=int(args.max_length), do_sample = args.do_sample, top_k=int(args.top_k), repetition_penalty=float(args.repetition_penalty), num_return_sequences=int(args.num_return_sequences))
TypeError: generate() got an unexpected keyword argument 'seed_seq'

Hello. Thank you for putting together this great resource. Are there any plans in place for integrating the ProGen model within this repository in the near future?

Reference: https://www.nature.com/articles/s41587-022-01618-2

after finetuning protgpt2 and trying to generate, I get the following:
Global seed set to 123 Traceback (most recent call last): File "/usr/local/bin/trill", line 8, in <module> sys.exit(cli()) File "/usr/local/lib/python3.8/dist-packages/trill/trill_main.py", line 385, in cli main(args) File "/usr/local/lib/python3.8/dist-packages/trill/trill_main.py", line 264, in main model = model.load_from_checkpoint(args.preTrained_model, strict = False) File "/usr/local/lib/python3.8/dist-packages/pytorch_lightning/core/saving.py", line 139, in load_from_checkpoint return _load_from_checkpoint( File "/usr/local/lib/python3.8/dist-packages/pytorch_lightning/core/saving.py", line 188, in _load_from_checkpoint return _load_state(cls, checkpoint, strict=strict, **kwargs) File "/usr/local/lib/python3.8/dist-packages/pytorch_lightning/core/saving.py", line 234, in _load_state obj = cls(**_cls_kwargs) TypeError: __init__() missing 1 required positional argument: 'lr'