Error while running trRosetta2

[anu-bioinfo]

Hi, I get this error while running the pipeline script. No PDB model is generated. Could you please help me out with this ?

Traceback (most recent call last): File "./get_embeddings.py", line 25, in model = ProteinBertModel.from_pretrained('bert-base') File "/mnt/NewHDD/anaconda3/envs/casp14-baker/lib/python3.6/site-packages/tape/models/modeling_utils.py", line 470, in from_pretrained **kwargs File "/mnt/NewHDD/anaconda3/envs/casp14-baker/lib/python3.6/site-packages/tape/models/modeling_utils.py", line 172, in from_pretrained config = cls.from_json_file(resolved_config_file) File "/mnt/NewHDD/anaconda3/envs/casp14-baker/lib/python3.6/site-packages/tape/models/modeling_utils.py", line 202, in from_json_file return cls.from_dict(json.loads(text)) File "/mnt/NewHDD/anaconda3/envs/casp14-baker/lib/python3.6/json/init.py", line 354, in loads return _default_decoder.decode(s) File "/mnt/NewHDD/anaconda3/envs/casp14-baker/lib/python3.6/json/decoder.py", line 339, in decode obj, end = self.raw_decode(s, idx=_w(s, 0).end()) File "/mnt/NewHDD/anaconda3/envs/casp14-baker/lib/python3.6/json/decoder.py", line 357, in raw_decode raise JSONDecodeError("Expecting value", s, err.value) from None json.decoder.JSONDecodeError: Expecting value: line 1 column 1 (char 0)

Best,

Anupam

[colinwprice]

I am having the same issues, I noticed the last update was around the same time this was posted. This seems like it's a part of the tape repo which hasn't changed recently. I've followed the install/demo example instructions from scratch a few times and it's always here where I get stuck.

[anu-bioinfo]

@colinwprice I too could not fix this. Now, I am running RoseTTaFold instead. Runs smoothly.

[Arielbs]

To fix this issue go to ./tape/get_embeddings.py Add to line 4: ProteinBertConfig from tape import ProteinBertModel, TAPETokenizer, ProteinBertConfig

Than comment out line ~26: #model = ProteinBertModel.from_pretrained('bert-base') and add instead: config = ProteinBertConfig() model = ProteinBertModel(config)

[GayatriNavle]

To fix this issue go to ./tape/get_embeddings.py Add to line 4: ProteinBertConfig from tape import ProteinBertModel, TAPETokenizer, ProteinBertConfig

Than comment out line ~26: #model = ProteinBertModel.from_pretrained('bert-base') and add instead: config = ProteinBertConfig() model = ProteinBertModel(config)

Hi i tried this but i am still getting the same error can you suggest me an alternate

[KhodezaBegum]

I don't get this error anymore, but there is no model saved in example/T1078/model/