martinez-zacharya / trill Goto Github PK
View Code? Open in Web Editor NEWSandbox for Deep-Learning based Computational Protein Design
License: MIT License
Sandbox for Deep-Learning based Computational Protein Design
License: MIT License
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'
A declarative, efficient, and flexible JavaScript library for building user interfaces.
๐ Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
An Open Source Machine Learning Framework for Everyone
The Web framework for perfectionists with deadlines.
A PHP framework for web artisans
Bring data to life with SVG, Canvas and HTML. ๐๐๐
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
Some thing interesting about web. New door for the world.
A server is a program made to process requests and deliver data to clients.
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Some thing interesting about visualization, use data art
Some thing interesting about game, make everyone happy.
We are working to build community through open source technology. NB: members must have two-factor auth.
Open source projects and samples from Microsoft.
Google โค๏ธ Open Source for everyone.
Alibaba Open Source for everyone
Data-Driven Documents codes.
China tencent open source team.