"""
Traceback (most recent call last):
  File "/usr/local/lib/python3.9/multiprocessing/pool.py", line 125, in worker
    result = (True, func(*args, **kwds))
  File "/usr/local/lib/python3.9/multiprocessing/pool.py", line 48, in mapstar
    return list(map(*args))
  File "/root/deeprankcore/deeprank-core/deeprankcore/query.py", line 245, in _process_one_query
    graph.write_to_hdf5(output_path)
  File "/root/deeprankcore/deeprank-core/deeprankcore/utils/graph.py", line 218, in write_to_hdf5
    node_features_group.create_dataset(
  File "/usr/local/lib/python3.9/site-packages/h5py/_hl/group.py", line 183, in create_dataset
    dsid = dataset.make_new_dset(group, shape, dtype, data, name, **kwds)
  File "/usr/local/lib/python3.9/site-packages/h5py/_hl/dataset.py", line 86, in make_new_dset
    tid = h5t.py_create(dtype, logical=1)
  File "h5py/h5t.pyx", line 1664, in h5py.h5t.py_create
  File "h5py/h5t.pyx", line 1688, in h5py.h5t.py_create
  File "h5py/h5t.pyx", line 1748, in h5py.h5t.py_create
TypeError: Object dtype dtype('O') has no native HDF5 equivalent
"""

The above exception was the direct cause of the following exception:

Traceback (most recent call last):
  File "/mnt/netcache/data/dlepikhov/propedia_ssl/script/build_propedia.py", line 44, in <module>
    h5_p = queries.process(
  File "/root/deeprankcore/deeprank-core/deeprankcore/query.py", line 329, in process
    pool.map(pool_function, self.queries)
  File "/usr/local/lib/python3.9/multiprocessing/pool.py", line 364, in map
    return self._map_async(func, iterable, mapstar, chunksize).get()
  File "/usr/local/lib/python3.9/multiprocessing/pool.py", line 771, in get
    raise self._value
TypeError: Object dtype dtype('O') has no native HDF5 equivalent

import sys
import os
sys.path.append(os.path.abspath("."))
from deeprankcore.features import torsion_angle, components, contact, exposure
from deeprankcore.query import QueryCollection, ProteinProteinInterfaceResidueQuery
from deeprankcore.dataset import GraphDataset
import pickle
import argparse
import glob

arg_parser = argparse.ArgumentParser(description="""
    Script used to build the features using deeprankcore package.
""")
arg_parser.add_argument("--h5out",
    help="Path where the HDF5 features will be saved."
)
arg_parser.add_argument("--pdb",
    help="glob string to look for pdb files used to generate features."
)
arg_parser.add_argument("--nworkers",
    help="""
    Providing this argument will set a specific number of cpus used to process the query.
    By default, all cpus are used.
    """,
    default=None,
    type=int
)
a = arg_parser.parse_args()

pdb_paths = glob.glob(a.pdb)

queries = QueryCollection()

chain_ids = [p.split("/")[-1].replace(".pdb", "").split("_")[-2:] for p in pdb_paths]
print(f"Number of cases: {len(pdb_paths)}")

for i, p in enumerate(pdb_paths):
    queries.add(ProteinProteinInterfaceResidueQuery(
        pdb_path = p,
        chain_id1 = chain_ids[i][0],
        chain_id2 = chain_ids[i][1],
    ))

h5_p = queries.process(
    a.h5out,
    cpu_count = a.nworkers,
    feature_modules = [
        components,
        torsion_angle,
        contact,
        exposure
    ]
)