search

instadeepai / protein-structure-tokenizer

Official implementation of "Learning the language of protein structures"
Apache License 2.0
6 stars 0 forks source link

run tokenize_pdb.py error #2

Open wtyang908 opened 3 weeks ago

wtyang908 commented 3 weeks ago

when I run tokenize_pdb.py, I met this Traceback (most recent call last): File "/app/scripts/tokenize_pdb.py", line 108, in main( File "/app/scripts/tokenize_pdb.py", line 64, in main runner.tokenize( File "/app/scripts/inference_runner.py", line 261, in tokenize graphs = [ File "/app/scripts/inference_runner.py", line 262, in make_graph_from_pdb( File "/app/scripts/inference_runner.py", line 64, in make_graph_from_pdb protein_graph = preprocess_sample( File "/app/structure_tokenizer/data/preprocessing.py", line 180, in preprocess_sample ) = compute_nearest_neighbors_graph( File "/app/structure_tokenizer/utils/protein_utils.py", line 373, in compute_nearest_neighbors_graph means_of_atom_coordinates = np.stack( File "<__array_function__ internals>", line 200, in stack File "/opt/conda/envs/structure-tokenizer/lib/python3.10/site-packages/numpy/core/shape_base.py", line 460, in stack raise ValueError('need at least one array to stack') ValueError: need at least one array to stack I want to know why this is happening and how I can fix it

JeremieDona commented 5 days ago

Could you provide more details on how you use the tokenize_pdb.py ?