Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

code error running colabfold_batch with custom templates #271

Open
bioinfcib opened this issue Oct 30, 2024 · 4 comments
Open

code error running colabfold_batch with custom templates #271

bioinfcib opened this issue Oct 30, 2024 · 4 comments

Comments

@bioinfcib
Copy link

Hi,
First of all, I'd like to thank you for making freely available your software development.

The following command line:
colabfold_batch --templates --amber --num-relax 1 target.fasta --custom-template-path ./my_template results_dir

ends with the next error code lines:
Traceback (most recent call last):
File "/home/mario/Colabfold/localcolabfold/colabfold-conda/bin/colabfold_batch", line 8, in
sys.exit(main())
File "/home/mario/Colabfold/localcolabfold/colabfold-conda/lib/python3.10/site-packages/colabfold/batch.py", line 2046, in main
run(
File "/home/mario/Colabfold/localcolabfold/colabfold-conda/lib/python3.10/site-packages/colabfold/batch.py", line 1562, in run
model_runner_and_params = load_models_and_params(
File "/home/mario/Colabfold/localcolabfold/colabfold-conda/lib/python3.10/site-packages/colabfold/alphafold/models.py", line 161, in load_models_and_params
params = get_model_haiku_params(
File "/home/mario/Colabfold/localcolabfold/colabfold-conda/lib/python3.10/site-packages/colabfold/alphafold/models.py", line 41, in get_model_haiku_params
return utils.flat_params_to_haiku(params, fuse=use_fuse, to_jnp=to_jnp)
File "/home/mario/Colabfold/localcolabfold/colabfold-conda/lib/python3.10/site-packages/alphafold/model/utils.py", line 102, in flat_params_to_haiku
P[scope][name] = jnp.array(array) if to_jnp else array
File "/home/mario/Colabfold/localcolabfold/colabfold-conda/lib/python3.10/site-packages/jax/_src/numpy/lax_numpy.py", line 2608, in array
out_array: Array = lax_internal._convert_element_type(
File "/home/mario/Colabfold/localcolabfold/colabfold-conda/lib/python3.10/site-packages/jax/_src/lax/lax.py", line 559, in _convert_element_type
return convert_element_type_p.bind(operand, new_dtype=new_dtype,
File "/home/mario/Colabfold/localcolabfold/colabfold-conda/lib/python3.10/site-packages/jax/_src/core.py", line 387, in bind
return self.bind_with_trace(find_top_trace(args), args, params)
File "/home/mario/Colabfold/localcolabfold/colabfold-conda/lib/python3.10/site-packages/jax/_src/core.py", line 391, in bind_with_trace
out = trace.process_primitive(self, map(trace.full_raise, args), params)
File "/home/mario/Colabfold/localcolabfold/colabfold-conda/lib/python3.10/site-packages/jax/_src/core.py", line 879, in process_primitive
return primitive.impl(*tracers, **params)
File "/home/mario/Colabfold/localcolabfold/colabfold-conda/lib/python3.10/site-packages/jax/_src/dispatch.py", line 86, in apply_primitive
outs = fun(*args)
ValueError: std::bad_cast

Alternatively, using as input an a3m alignment file, some other error lines are shown:
Traceback (most recent call last):
File "/home/mario/Colabfold/localcolabfold/colabfold-conda/lib/python3.10/site-packages/colabfold/batch.py", line 1496, in run
= generate_input_feature(query_seqs_unique, query_seqs_cardinality, unpaired_msa, paired_msa,
File "/home/mario/Colabfold/localcolabfold/colabfold-conda/lib/python3.10/site-packages/colabfold/batch.py", line 1022, in generate_input_feature
feature_dict = build_monomer_feature(
File "/home/mario/Colabfold/localcolabfold/colabfold-conda/lib/python3.10/site-packages/colabfold/batch.py", line 875, in build_monomer_feature
**pipeline.make_sequence_features(
File "/home/mario/Colabfold/localcolabfold/colabfold-conda/lib/python3.10/site-packages/alphafold/data/pipeline.py", line 40, in make_sequence_features
features['aatype'] = residue_constants.sequence_to_onehot(
File "/home/mario/Colabfold/localcolabfold/colabfold-conda/lib/python3.10/site-packages/alphafold/common/residue_constants.py", line 580, in sequence_to_onehot
raise ValueError(f'Invalid character in the sequence: {aa_type}')
ValueError: Invalid character in the sequence: -

Please, some advice to fix the issue will be welcome. Thank you very much in advance.

@YoshitakaMo
Copy link
Owner

raise ValueError(f'Invalid character in the sequence: {aa_type}')
ValueError: Invalid character in the sequence: -

It says that your input sequence target.fasta may contain an invalid character -. Please check your file first.

@bioinfcib
Copy link
Author

raise ValueError(f'Invalid character in the sequence: {aa_type}')
ValueError: Invalid character in the sequence: -

It says that your input sequence target.fasta may contain an invalid character -. Please check your file first.

Thank you for your prompt reply. As I was said, that error is coming from an a3m align file as input, knowing that file format contains '-' character for deletions.

Additonally, what about the code error I was reporting firtstcoming from using as input a fasta file (with no '-' at all, of course)?

Thank you so much in advance for your replies.

@YoshitakaMo
Copy link
Owner

YoshitakaMo commented Oct 31, 2024

Ah, I missed there were two questions in your first comment. Sorry.
But,

File "/home/mario/Colabfold/localcolabfold/colabfold-conda/lib/python3.10/site-packages/jax/_src/dispatch.py", line 86, in apply_primitive
outs = fun(*args)
ValueError: std::bad_cast

I have never encountered such an issue in localcolabfold. I have no idea about what caused this. Please check whether your input fasta is correct or the issue occurs with other fasta files.

@bioinfcib
Copy link
Author

Ah, I missed there were two questions in your first comment. Sorry. But,

File "/home/mario/Colabfold/localcolabfold/colabfold-conda/lib/python3.10/site-packages/jax/_src/dispatch.py", line 86, in apply_primitive
outs = fun(*args)
ValueError: std::bad_cast

I have never encountered such an issue in localcolabfold. I have no idea about what caused this. Please check whether your input fasta is correct or the issue occurs with other fasta files.

Unfortunately, the same error occurs with whatever fasta files as input.

Regarding the issue with the a3m file as input, any ideas that could help us to fix it? If you think that checking files I'm using could help, please don't hesitate to say me. I'll be glad to send them you. Thank you very much.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

2 participants