search

TencentAI4S / tfold

open source code for Tencent tFold
Other
68 stars 9 forks source link

"seqmb_model_enabled" error on running example. #2

Closed tsjain closed 9 months ago

tsjain commented 9 months ago

I installed tFold and the sequence database as per the instructions, and downloaded the trained model weights.

On trying to run the following example: python projects/tfold_ag/predict.py --pid_fpath=examples/prot_ids.abag.txt --fas_dpath=examples/fasta.files --msa_fpath=examples/msa.files/8df5_R.a3m --pdb_dpath=examples/pdb.files.abag

I get the following error:

`KeyError: 'seqemb_mode_enabled'

During handling of the above exception, another exception occurred:

Traceback (most recent call last): File "/home/ubuntu/miniforge3/envs/tfold/lib/python3.8/site-packages/ml_collections/config_dict/config_dict.py", line 827, in getattr return self[attribute] File "/home/ubuntu/miniforge3/envs/tfold/lib/python3.8/site-packages/ml_collections/config_dict/config_dict.py", line 909, in getitem raise KeyError(self._generate_did_you_mean_message(key, str(e))) KeyError: "'seqemb_mode_enabled'"

During handling of the above exception, another exception occurred:

Traceback (most recent call last): File "projects/tfold_ag/predict.py", line 81, in main() File "projects/tfold_ag/predict.py", line 73, in main predict(args.pid_fpath, args.fas_dpath, File "projects/tfold_ag/predict.py", line 62, in predict predictor = AgPredictor( File "/home/ubuntu/tFold/tfold/deploy/ag_predictor.py", line 32, in init self.psp_featurizer = PspFeaturizer.restore(psp_path) File "/home/ubuntu/tFold/tfold/deploy/psp_featurizer.py", line 52, in restore model = cls(config).eval() File "/home/ubuntu/tFold/tfold/deploy/psp_featurizer.py", line 39, in init self.model = AlphaFold(self.config) File "/home/ubuntu/tFold/openfold/openfold/model/model.py", line 84, in init self.seqemb_mode = config.globals.seqemb_mode_enabled File "/home/ubuntu/miniforge3/envs/tfold/lib/python3.8/site-packages/ml_collections/config_dict/config_dict.py", line 829, in getattr raise AttributeError(e) AttributeError: "'seqemb_mode_enabled'"`

tsjain commented 9 months ago

Issue was solved by installing openfold v1, instead of latest release

Cloud-Rambler commented 9 months ago

Thanks for your attention, we have modified the installation in conda step to avoid such problems.