deepmodeling / Uni-Mol

Official Repository for the Uni-Mol Series Methods
MIT License
723 stars 126 forks source link

demo.sh doesn't make pkl file #256

Open min0210 opened 3 months ago

min0210 commented 3 months ago

sh demo.sh Namespace(model_dir='checkpoint_best.pt', input_protein='../example_data/protein.pdb', input_ligand='../example_data/ligand.sdf', input_batch_file='input_batch.csv', input_docking_grid='../example_data/docking_grid.json', output_ligand_name='ligand_predict', output_ligand_dir='predict_sdf', mode='single', batch_size=4, nthreads=8, conf_size=10, cluster=True, use_current_ligand_conf=False, steric_clash_fix=True) Start preprocessing data... Number of ligands: 1 1it [00:01, 1.89s/it] Total num: 1, Success: 1, Failed: 0 Done! Error: mkl-service + Intel(R) MKL: MKL_THREADING_LAYER=INTEL is incompatible with libgomp.so.1 library. Try to import numpy first or set the threading layer accordingly. Set MKL_SERVICE_FORCE_INTEL to force it. Traceback (most recent call last): File "/home/sangmin/apps/docking/Uni-Mol/unimol_docking_v2/interface/demo.py", line 189, in main_cli() File "/home/sangmin/apps/docking/Uni-Mol/unimol_docking_v2/interface/demo.py", line 185, in main_cli main(args) File "/home/sangmin/apps/docking/Uni-Mol/unimol_docking_v2/interface/demo.py", line 24, in main output_ligand) = clf.predict_sdf( ^^^^^^^^^^^^^^^^ File "/home/sangmin/apps/docking/Uni-Mol/unimol_docking_v2/interface/predictor/unimol_predictor.py", line 82, in predict_sdf output_sdf = self.postprocess(output_pkl, ^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/home/sangmin/apps/docking/Uni-Mol/unimol_docking_v2/interface/predictor/unimol_predictor.py", line 66, in postprocess mol_list, smi_list, coords_predict_list, holo_coords_list, holo_center_coords_list, prmsd_score_list = postprocessor.postprocess_data_pre(output_pkl, output_lmdb) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/home/sangmin/apps/docking/Uni-Mol/unimol_docking_v2/interface/predictor/processor.py", line 331, in postprocess_data_pre predict = pd.read_pickle(predict_file) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/home/sangmin/anaconda3/envs/PLBA/lib/python3.11/site-packages/pandas/io/pickle.py", line 189, in read_pickle with get_handle( ^^^^^^^^^^^ File "/home/sangmin/anaconda3/envs/PLBA/lib/python3.11/site-packages/pandas/io/common.py", line 872, in get_handle handle = open(handle, ioargs.mode) ^^^^^^^^^^^^^^^^^^^^^^^^^ FileNotFoundError: [Errno 2] No such file or directory: '/home/sangmin/apps/docking/Uni-Mol/unimol_docking_v2/interface/predict_sdf/ligand_predict.pkl'

how to solve this problem?

ZhouGengmo commented 3 months ago

Error: mkl-service + Intel(R) MKL: MKL_THREADING_LAYER=INTEL is incompatible with libgomp.so.1 library. Try to import numpy first or set the threading layer accordingly. Set MKL_SERVICE_FORCE_INTEL to force it.

It seems to be caused by this error, which is related to Intel MKL and OpenMP library conflict. You can import numpy before any other libraries that might use OpenMP.

min0210 commented 2 months ago

Traceback (most recent call last): File "/home/sangmin/apps/docking/Uni-Mol/unimol_docking_v2/unimol/infer.py", line 117, in cli_main() File "/home/sangmin/apps/docking/Uni-Mol/unimol_docking_v2/unimol/infer.py", line 113, in cli_main distributed_utils.call_main(args, main) File "/home/sangmin/anaconda3/envs/PLBA/lib/python3.11/site-packages/unicore/distributed/utils.py", line 189, in call_main main(args, **kwargs) File "/home/sangmin/apps/docking/Uni-Mol/unimol_docking_v2/unimol/infer.py", line 94, in main for i, sample in enumerate(progress): File "/home/sangmin/anaconda3/envs/PLBA/lib/python3.11/site-packages/unicore/logging/progress_bar.py", line 219, in iter for i, obj in enumerate(self.iterable, start=self.n): File "/home/sangmin/anaconda3/envs/PLBA/lib/python3.11/site-packages/unicore/data/iterators.py", line 60, in iter for x in self.iterable: File "/home/sangmin/anaconda3/envs/PLBA/lib/python3.11/site-packages/unicore/data/iterators.py", line 551, in next raise item File "/home/sangmin/anaconda3/envs/PLBA/lib/python3.11/site-packages/unicore/data/iterators.py", line 482, in run for item in self._source: File "/home/sangmin/anaconda3/envs/PLBA/lib/python3.11/site-packages/torch/utils/data/dataloader.py", line 633, in next data = self._next_data() ^^^^^^^^^^^^^^^^^ File "/home/sangmin/anaconda3/envs/PLBA/lib/python3.11/site-packages/torch/utils/data/dataloader.py", line 1345, in _next_data return self._process_data(data) ^^^^^^^^^^^^^^^^^^^^^^^^ File "/home/sangmin/anaconda3/envs/PLBA/lib/python3.11/site-packages/torch/utils/data/dataloader.py", line 1371, in _process_data data.reraise() File "/home/sangmin/anaconda3/envs/PLBA/lib/python3.11/site-packages/torch/_utils.py", line 644, in reraise raise exception IndexError: Caught IndexError in DataLoader worker process 0. Original Traceback (most recent call last): File "/home/sangmin/anaconda3/envs/PLBA/lib/python3.11/site-packages/torch/utils/data/_utils/worker.py", line 308, in _worker_loop data = fetcher.fetch(index) ^^^^^^^^^^^^^^^^^^^^ File "/home/sangmin/anaconda3/envs/PLBA/lib/python3.11/site-packages/torch/utils/data/_utils/fetch.py", line 51, in fetch data = [self.dataset[idx] for idx in possibly_batched_index] ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/home/sangmin/anaconda3/envs/PLBA/lib/python3.11/site-packages/torch/utils/data/_utils/fetch.py", line 51, in data = [self.dataset[idx] for idx in possibly_batched_index]


  File "/home/sangmin/anaconda3/envs/PLBA/lib/python3.11/site-packages/unicore/data/nested_dictionary_dataset.py", line 69, in __getitem__
    return OrderedDict((k, ds[index]) for k, ds in self.defn.items())
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/sangmin/anaconda3/envs/PLBA/lib/python3.11/site-packages/unicore/data/nested_dictionary_dataset.py", line 69, in <genexpr>
    return OrderedDict((k, ds[index]) for k, ds in self.defn.items())
                           ~~^^^^^^^
  File "/home/sangmin/anaconda3/envs/PLBA/lib/python3.11/site-packages/unicore/data/base_wrapper_dataset.py", line 18, in __getitem__
    return self.dataset[index]
           ~~~~~~~~~~~~^^^^^^^
  File "/home/sangmin/anaconda3/envs/PLBA/lib/python3.11/site-packages/unicore/data/append_token_dataset.py", line 21, in __getitem__
    item = self.dataset[idx]
           ~~~~~~~~~~~~^^^^^
  File "/home/sangmin/anaconda3/envs/PLBA/lib/python3.11/site-packages/unicore/data/prepend_token_dataset.py", line 22, in __getitem__
    item = self.dataset[idx]
           ~~~~~~~~~~~~^^^^^
  File "/home/sangmin/anaconda3/envs/PLBA/lib/python3.11/site-packages/unicore/data/tokenize_dataset.py", line 26, in __getitem__
    raw_data = self.dataset[index]
               ~~~~~~~~~~~~^^^^^^^
  File "/home/sangmin/apps/docking/Uni-Mol/unimol_docking_v2/unimol/data/key_dataset.py", line 19, in __getitem__
    return self.dataset[idx][self.key]
           ~~~~~~~~~~~~^^^^^
  File "/home/sangmin/apps/docking/Uni-Mol/unimol_docking_v2/unimol/data/realign_ligand_dataset.py", line 39, in __getitem__
    return self.__cached_item__(index, self.epoch)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/sangmin/apps/docking/Uni-Mol/unimol_docking_v2/unimol/data/realign_ligand_dataset.py", line 28, in __cached_item__
    dd = self.dataset[index].copy()
         ~~~~~~~~~~~~^^^^^^^
  File "/home/sangmin/apps/docking/Uni-Mol/unimol_docking_v2/unimol/data/remove_hydrogen_dataset.py", line 61, in __getitem__
    return self.__cached_item__(index, self.epoch)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/sangmin/apps/docking/Uni-Mol/unimol_docking_v2/unimol/data/remove_hydrogen_dataset.py", line 34, in __cached_item__
    dd = self.dataset[index].copy()
         ~~~~~~~~~~~~^^^^^^^
  File "/home/sangmin/apps/docking/Uni-Mol/unimol_docking_v2/unimol/data/cropping_dataset.py", line 67, in __getitem__
    return self.__cached_item__(index, self.epoch)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/sangmin/apps/docking/Uni-Mol/unimol_docking_v2/unimol/data/cropping_dataset.py", line 32, in __cached_item__
    dd = self.dataset[index].copy()
         ~~~~~~~~~~~~^^^^^^^
  File "/home/sangmin/apps/docking/Uni-Mol/unimol_docking_v2/unimol/data/remove_hydrogen_dataset.py", line 61, in __getitem__
    return self.__cached_item__(index, self.epoch)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/sangmin/apps/docking/Uni-Mol/unimol_docking_v2/unimol/data/remove_hydrogen_dataset.py", line 34, in __cached_item__
    dd = self.dataset[index].copy()
         ~~~~~~~~~~~~^^^^^^^
  File "/home/sangmin/apps/docking/Uni-Mol/unimol_docking_v2/unimol/data/tta_dataset.py", line 77, in __getitem__
    return self.__cached_item__(index, self.epoch)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/sangmin/apps/docking/Uni-Mol/unimol_docking_v2/unimol/data/tta_dataset.py", line 46, in __cached_item__
    coordinates = np.array(self.dataset[smi_idx][self.coordinates][coord_idx])
                           ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~^^^^^^^^^^^
IndexError: list index out of range

Total num: 3889, Success: 3889, Failed: 0
Done!
/home/sangmin/project/classification/dataset/DUDE/comt/unidock/result/batch_data.pkl /home/sangmin/project/classification/dataset/DUDE/comt/unidock/result/batch_data.lmdb
Traceback (most recent call last):
  File "/home/sangmin/apps/docking/Uni-Mol/unimol_docking_v2/interface/demo.py", line 192, in <module>
    main_cli()
  File "/home/sangmin/apps/docking/Uni-Mol/unimol_docking_v2/interface/demo.py", line 188, in main_cli
    main(args)
  File "/home/sangmin/apps/docking/Uni-Mol/unimol_docking_v2/interface/demo.py", line 53, in main
    output_ligand) = clf.predict_sdf(
                     ^^^^^^^^^^^^^^^^
  File "/home/sangmin/apps/docking/Uni-Mol/unimol_docking_v2/interface/predictor/unimol_predictor.py", line 83, in predict_sdf
    output_sdf = self.postprocess(output_pkl, 
                 ^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/sangmin/apps/docking/Uni-Mol/unimol_docking_v2/interface/predictor/unimol_predictor.py", line 66, in postprocess
    mol_list, smi_list, coords_predict_list, holo_coords_list, holo_center_coords_list, prmsd_score_list = postprocessor.postprocess_data_pre(output_pkl, output_lmdb)
                                                                                                           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/sangmin/apps/docking/Uni-Mol/unimol_docking_v2/interface/predictor/processor.py", line 331, in postprocess_data_pre
    predict = pd.read_pickle(predict_file)
              ^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/sangmin/anaconda3/envs/PLBA/lib/python3.11/site-packages/pandas/io/pickle.py", line 185, in read_pickle
    with get_handle(
         ^^^^^^^^^^^
  File "/home/sangmin/anaconda3/envs/PLBA/lib/python3.11/site-packages/pandas/io/common.py", line 882, in get_handle
    handle = open(handle, ioargs.mode)
             ^^^^^^^^^^^^^^^^^^^^^^^^^
FileNotFoundError: [Errno 2] No such file or directory: '/home/sangmin/project/classification/dataset/DUDE/comt/unidock/result/batch_data.pkl'
@ZhouGengmo 

Hi, ZhouGengmo.
I fixed the crash issue with the feedback you gave me. But still no pkl file is created. How do I fix this. 
Thanks for your response.