there is an error whenever I put a pdb file in the custom template.

I put my sequence in query_sequence section and set num_relax as 1. I've customize the template mode as 'custom' and I put the custom sequence which is similar with my query sequence.

Everything was going well but I faced the below error.

Downloading alphafold2 weights to .: 100%|██████████| 3.47G/3.47G [00:25<00:00, 145MB/s]
2023-11-15 14:15:56,647 Unable to initialize backend 'rocm': NOT_FOUND: Could not find registered platform with name: "rocm". Available platform names are: CUDA
2023-11-15 14:15:56,649 Unable to initialize backend 'tpu': INTERNAL: Failed to open libtpu.so: libtpu.so: cannot open shared object file: No such file or directory
2023-11-15 14:16:02,334 Running on GPU
2023-11-15 14:16:02,629 Found 8 citations for tools or databases

UnicodeDecodeError Traceback (most recent call last)
in <cell line: 65>()
63
64 download_alphafold_params(model_type, Path("."))
---> 65 results = run(
66 queries=queries,
67 result_dir=result_dir,

4 frames
/usr/lib/python3.10/codecs.py in decode(self, input, final)
320 # decode input (taking the buffer into account)
321 data = self.buffer + input
--> 322 (result, consumed) = self._buffer_decode(data, self.errors, final)
323 # keep undecoded input until the next call
324 self.buffer = data[consumed:]

UnicodeDecodeError: 'utf-8' codec can't decode byte 0x94 in position 49: invalid start byte

How can I fix it?

Your Environment

Include as many relevant details about the environment you experienced the bug in.
I've just launched Alphfold2.ipynb in my MacBook Pro.

Start by reproducing the reported setup in Alphfold2.ipynb: place a custom PDB template in custom mode, set query_sequence, and use num_relax=1. Inspect the run call and traceback around the UnicodeDecodeError to determine which input is being decoded. Done means the notebook handles the reported custom-template input without this decoding failure, with an appropriate regression check.