Update yml file

environment.yml

@@ -12,7 +12,7 @@ dependencies:
   - pyarrow=12.0.1
   - tensorflow=2.12.1
   - scikit-learn=1.3.2
-  - ms2deepscore=0.5.0
+  - ms2deepscore=2.0.0
   - pandas=2.0.3
   - matplotlib=3.7.3
   - skl2onnx=1.16.0

ms2query/__init__.py

@@ -1,18 +1,17 @@
 import os
 
-
 os.environ['TF_CPP_MIN_LOG_LEVEL'] = '3'
 # pylint: disable=wrong-import-position
 import argparse
 import logging
+
 from .__version__ import __version__
 from .ms2library import MS2Library, create_library_object_from_one_dir
 from .results_table import ResultsTable
 from .run_ms2query import (download_zenodo_files, run_complete_folder,
                            run_ms2query_single_file)
 from .utils import SettingsRunMS2Query
 
-
 logging.getLogger(__name__).addHandler(logging.NullHandler())
 
 __author__ = "Netherlands eScience Center"

ms2query/benchmarking/collect_test_data_results.py

@@ -8,6 +8,7 @@
 import sqlite3
 import tempfile
 from typing import List, Tuple, Union
+
 import pandas as pd
 from matchms import Spectrum
 from matchms.calculate_scores import calculate_scores
@@ -16,6 +17,7 @@
 from ms2deepscore.models import SiameseSpectralModel, compute_embedding_array
 from spec2vec.vector_operations import cosine_similarity_matrix
 from tqdm import tqdm
+
 from ms2query.create_new_library.calculate_tanimoto_scores import (
     calculate_highest_tanimoto_score, calculate_single_tanimoto_score)
 from ms2query.ms2library import MS2Library

ms2query/benchmarking/create_accuracy_vs_recall_plot.py

@@ -5,9 +5,11 @@
 import os
 import random
 from typing import Dict, List, Tuple
+
 import numpy as np
 from matplotlib import pyplot as plt
 from tqdm import tqdm
+
 from ms2query.utils import (load_df_from_parquet_file, load_json_file,
                             save_df_as_parquet_file)
 

ms2query/benchmarking/k_fold_cross_validation.py

@@ -5,8 +5,10 @@
 import os
 import random
 from typing import List
+
 from matchms import Spectrum
 from matchms.exporting.save_as_mgf import save_as_mgf
+
 from ms2query.benchmarking.collect_test_data_results import (
     generate_exact_matches_test_results, generate_test_results)
 from ms2query.clean_and_filter_spectra import \

ms2query/benchmarking/visualize_mass_distribution.py

@@ -1,9 +1,11 @@
 import os
 from typing import Dict, List, Tuple
+
 from create_accuracy_vs_recall_plot import (
     calculate_means_and_standard_deviation, load_results_from_folder)
 from matchms import Spectrum
 from matplotlib import pyplot as plt
+
 from ms2query.utils import (load_df_from_parquet_file,
                             load_matchms_spectrum_objects_from_file)
 

ms2query/benchmarking/visualize_tanimoto_score_distribution.py

@@ -1,4 +1,5 @@
 from typing import Dict, List, Tuple
+
 import numpy as np
 from matplotlib import pyplot as plt
 

ms2query/clean_and_filter_spectra.py

@@ -1,4 +1,5 @@
 from typing import List, Optional, Tuple
+
 import matchms.filtering as msfilters
 from matchms.filtering.filter_utils.smile_inchi_inchikey_conversions import (
     is_valid_inchi, is_valid_inchikey, is_valid_smiles)

ms2query/create_new_library/add_classifire_classifications.py

@@ -2,6 +2,7 @@
 import urllib
 from http.client import InvalidURL
 from typing import List, Optional
+
 import pandas as pd
 from tqdm import tqdm
 

ms2query/create_new_library/calculate_tanimoto_scores.py

@@ -4,6 +4,7 @@
 """
 from collections import Counter
 from typing import List
+
 import numpy as np
 import pandas as pd
 from matchms import Spectrum

ms2query/create_new_library/create_sqlite_database.py

@@ -5,9 +5,11 @@
 
 import sqlite3
 from typing import Dict, List
+
 import pandas as pd
 from matchms import Spectrum
 from tqdm import tqdm
+
 from ms2query.create_new_library.calculate_tanimoto_scores import \
     calculate_highest_tanimoto_score
 from ms2query.utils import return_non_existing_file_name

ms2query/create_new_library/library_files_creator.py

@@ -6,6 +6,7 @@
 import os
 from pathlib import Path
 from typing import List, Union
+
 import matchms.filtering as msfilters
 import numpy as np
 import pandas as pd
@@ -15,6 +16,7 @@
 from ms2deepscore.models.SiameseSpectralModel import compute_embedding_array
 from spec2vec.vector_operations import calc_vector
 from tqdm import tqdm
+
 from ms2query.clean_and_filter_spectra import create_spectrum_documents
 from ms2query.create_new_library.add_classifire_classifications import (
     convert_to_dataframe, select_compound_classes)

ms2query/create_new_library/split_data_for_training.py

@@ -5,6 +5,7 @@
 
 import random
 from typing import Dict, List
+
 from matchms import Spectrum
 
 

ms2query/create_new_library/train_models.py

@@ -6,16 +6,18 @@
 import os
 
 from ms2deepscore import SettingsMS2Deepscore
+from ms2deepscore.train_new_model.train_ms2deepscore import train_ms2ds_model
 from spec2vec.model_building import train_new_word2vec_model
+
 from ms2query.clean_and_filter_spectra import (
     clean_normalize_and_split_annotated_spectra, create_spectrum_documents)
 from ms2query.create_new_library.library_files_creator import \
     LibraryFilesCreator
-from ms2query.create_new_library.split_data_for_training import split_spectra_on_inchikeys
+from ms2query.create_new_library.split_data_for_training import \
+    split_spectra_on_inchikeys
 from ms2query.create_new_library.train_ms2query_model import (
     convert_to_onnx_model, train_ms2query_model)
 from ms2query.utils import load_matchms_spectrum_objects_from_file
-from ms2deepscore.train_new_model.train_ms2deepscore import train_ms2ds_model
 
 
 class SettingsTrainingModels:

ms2query/create_new_library/train_ms2query_model.py

@@ -5,13 +5,15 @@
 
 import os
 from typing import List
+
 import pandas as pd
 from matchms import Spectrum
 from onnxconverter_common import FloatTensorType
 from skl2onnx import convert_sklearn
 from sklearn.ensemble import RandomForestRegressor
 from sklearn.metrics import mean_squared_error
 from tqdm import tqdm
+
 from ms2query import MS2Library
 from ms2query.create_new_library.calculate_tanimoto_scores import \
     calculate_tanimoto_scores_from_smiles

ms2query/old_query_from_sqlite_functions.py

@@ -3,10 +3,12 @@
 import os
 import sqlite3
 from typing import Dict, List
+
 import numpy as np
 import pandas as pd
 from matchms.Spectrum import Spectrum
 from tqdm import tqdm
+
 from ms2query.utils import load_pickled_file
 
 

ms2query/query_from_sqlite_database.py

@@ -6,7 +6,9 @@
 import os.path
 import sqlite3
 from typing import Dict, List, Tuple
+
 import pandas as pd
+
 from ms2query.utils import column_names_for_output
 
 

ms2query/results_table.py

@@ -1,7 +1,9 @@
 from typing import Tuple, Union
+
 import numpy as np
 import pandas as pd
 from matchms.Spectrum import Spectrum
+
 from ms2query.query_from_sqlite_database import SqliteLibrary
 from ms2query.utils import column_names_for_output
 

ms2query/run_ms2query.py

@@ -2,6 +2,7 @@
 import os
 from typing import Union
 from urllib.request import urlopen, urlretrieve
+
 from ms2query.ms2library import MS2Library
 from ms2query.utils import (SettingsRunMS2Query,
                             load_matchms_spectrum_objects_from_file,

ms2query/utils.py

@@ -1,6 +1,7 @@
 import json
 import os
 from typing import List, Optional, Tuple, Union
+
 import numpy as np
 import pandas as pd
 from matchms import importing

notebooks/GNPS_15_12_2021/benchmarking/benchmark_speed_ms2query.py

@@ -6,10 +6,10 @@
 
 import os
 import time
+
 from ms2query.ms2library import MS2Library
 from ms2query.run_ms2query import run_complete_folder
 
-
 start_time = time.time()
 
 path_root = os.path.dirname(os.getcwd())

notebooks/GNPS_15_12_2021/data_processing_and_training_models/5_train_ms2deepscore_model.py

@@ -1,5 +1,6 @@
 import os
 import pickle
+
 import numpy as np
 import tensorflow as tf
 from ms2deepscore import SpectrumBinner
@@ -9,7 +10,6 @@
     EarlyStopping, ModelCheckpoint)
 from tensorflow.keras.optimizers import Adam  # pylint: disable=import-error
 
-
 path_data = "C:\\HSD\\OneDrive - Hochschule Düsseldorf\\Data\\ms2query"
 
 outfile = os.path.join(path_data, "GNPS_15_12_2021_pos_train.pickle")

notebooks/GNPS_15_12_2021/data_processing_and_training_models/6_train_spec2vec_model.py

@@ -1,10 +1,12 @@
 import os
+
 from matchms.filtering import (add_losses, add_precursor_mz, default_filters,
                                normalize_intensities,
                                reduce_to_number_of_peaks,
                                require_minimum_number_of_peaks, select_by_mz)
 from spec2vec import SpectrumDocument
 from spec2vec.model_building import train_new_word2vec_model
+
 from ms2query.utils import load_pickled_file
 
 

notebooks/GNPS_15_12_2021/data_processing_and_training_models/negative_mode/5_neg_train_ms2deepscore_model.py

@@ -1,5 +1,6 @@
 import os
 import pickle
+
 import numpy as np
 import tensorflow as tf
 from ms2deepscore import SpectrumBinner
@@ -9,7 +10,6 @@
     EarlyStopping, ModelCheckpoint)
 from tensorflow.keras.optimizers import Adam  # pylint: disable=import-error
 
-
 path_root = os.path.dirname(os.getcwd())
 
 path_data = os.path.join(path_root, "../../../data/libraries_and_models/gnps_15_12_2021/in_between_files")

notebooks/GNPS_15_12_2021/data_processing_and_training_models/negative_mode/6_neg_train_spec2vec_model.py

@@ -1,10 +1,12 @@
 import os
+
 from matchms.filtering import (add_losses, add_precursor_mz, default_filters,
                                normalize_intensities,
                                reduce_to_number_of_peaks,
                                require_minimum_number_of_peaks, select_by_mz)
 from spec2vec import SpectrumDocument
 from spec2vec.model_building import train_new_word2vec_model
+
 from ms2query.utils import load_pickled_file
 
 

setup.py

@@ -1,7 +1,7 @@
 #!/usr/bin/env python
 import os
-from setuptools import find_packages, setup
 
+from setuptools import find_packages, setup
 
 here = os.path.abspath(os.path.dirname(__file__))
 

tests/conftest.py

@@ -1,9 +1,11 @@
 import os
+
 import numpy as np
 import pandas as pd
 import pytest
 from matchms import Spectrum
 from matchms.importing.load_from_mgf import load_from_mgf
+
 from ms2query.ms2library import MS2Library
 from ms2query.query_from_sqlite_database import SqliteLibrary
 from ms2query.utils import load_df_from_parquet_file

tests/test_add_classifier_annotations.py

@@ -1,6 +1,7 @@
 import numpy as np
 import pytest
 from matchms import Spectrum
+
 from ms2query.create_new_library.add_classifire_classifications import \
     select_compound_classes
 

tests/test_calculate_tanimoto_scores.py

@@ -1,4 +1,5 @@
 import pandas as pd
+
 from ms2query.clean_and_filter_spectra import \
     normalize_and_filter_peaks_multiple_spectra
 from ms2query.create_new_library.calculate_tanimoto_scores import (

tests/test_clean_and_filter_spectra.py

@@ -1,6 +1,7 @@
 import numpy as np
 from matchms import Spectrum
 from spec2vec import SpectrumDocument
+
 from ms2query.clean_and_filter_spectra import (
     clean_normalize_and_split_annotated_spectra, create_spectrum_documents,
     harmonize_annotation, normalize_and_filter_peaks,

tests/test_collect_test_data_results.py

@@ -1,8 +1,10 @@
 import os
+
 import numpy as np
 import pandas as pd
 import pytest
 from matchms import Spectrum
+
 from ms2query.benchmarking.collect_test_data_results import (
     create_optimal_results, create_random_results, generate_test_results,
     generate_test_results_ms2query, get_all_ms2ds_scores,

tests/test_library_files_creator.py

@@ -1,6 +1,8 @@
 import os
+
 import pandas as pd
 import pytest
+
 from ms2query.clean_and_filter_spectra import normalize_and_filter_peaks
 from ms2query.create_new_library.library_files_creator import \
     LibraryFilesCreator

tests/test_ms2library.py

@@ -1,10 +1,12 @@
 import math
 import os
+
 import numpy as np
 import pandas as pd
+from tests.test_utils import check_expected_headers
+
 from ms2query.ms2library import MS2Library, create_library_object_from_one_dir
 from ms2query.utils import SettingsRunMS2Query, column_names_for_output
-from tests.test_utils import check_expected_headers
 
 
 def test_get_all_ms2ds_scores(ms2library, test_spectra):

tests/test_results_table.py

@@ -2,6 +2,7 @@
 import pandas as pd
 import pytest
 from matchms import Spectrum
+
 from ms2query import ResultsTable