Isort

.github/workflows/CI_build.yml

@@ -31,8 +31,8 @@ jobs:
         run: pytest --cov --cov-report term --cov-report xml -m "not integration"
       - name: Check style against standards using prospector
         run: prospector -o grouped -o pylint:pylint-report.txt
-#      - name: Check whether import statements are used consistently
-#        run: isort --check-only --diff .
+      - name: Check whether import statements are used consistently
+        run: isort --check-only --diff .
       - name: SonarCloud Scan
         uses: sonarsource/sonarcloud-github-action@master
         env:

CHANGELOG.md

@@ -8,7 +8,8 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 ## unpublished
 ### Added
 - environment.yml and CI_build test fur building a conda env from this file
-
+### fixed
+- Allow for using uper_case additional_metadata columns
 ## 1.2.2
 ### fixed
 - Set version of matchmsextras to 0.4.0, to fix dependency issue

ms2query/__init__.py

@@ -1,14 +1,16 @@
 import os
+
+
 os.environ['TF_CPP_MIN_LOG_LEVEL'] = '3'
 # pylint: disable=wrong-import-position
 import argparse
 import logging
-from .run_ms2query import download_zenodo_files, run_complete_folder, run_ms2query_single_file
-from .ms2library import create_library_object_from_one_dir
-from .utils import SettingsRunMS2Query
 from .__version__ import __version__
-from .ms2library import MS2Library
+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())

ms2query/benchmarking/collect_test_data_results.py

@@ -4,22 +4,22 @@
 """
 
 import os
-from typing import List, Tuple, Union
-from tqdm import tqdm
 import random
-import tempfile
-from matchms import Spectrum
-from ms2query.create_new_library.calculate_tanimoto_scores import calculate_single_tanimoto_score, calculate_highest_tanimoto_score
-from ms2query.ms2library import MS2Library
 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
+from matchms.similarity.CosineGreedy import CosineGreedy
+from matchms.similarity.ModifiedCosine import ModifiedCosine
 from ms2deepscore import MS2DeepScore
 from ms2deepscore.models import SiameseModel
 from spec2vec.vector_operations import cosine_similarity_matrix
-from matchms.calculate_scores import calculate_scores
-from matchms.similarity.ModifiedCosine import ModifiedCosine
-from matchms.similarity.CosineGreedy import CosineGreedy
-
+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
 from ms2query.query_from_sqlite_database import SqliteLibrary
 from ms2query.utils import save_json_file
 

ms2query/benchmarking/create_accuracy_vs_recall_plot.py

@@ -4,11 +4,10 @@
 """
 import os
 import random
-from typing import List, Tuple, Dict
-from tqdm import tqdm
+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_json_file, load_pickled_file, save_pickled_file
 
 

ms2query/benchmarking/k_fold_cross_validation.py

@@ -6,12 +6,16 @@
 import random
 from typing import List
 from matchms import Spectrum
-from ms2query.create_new_library.split_data_for_training import split_spectra_in_random_inchikey_sets, select_spectra_per_unique_inchikey
-from ms2query.utils import load_matchms_spectrum_objects_from_file, save_pickled_file
+from ms2query.benchmarking.collect_test_data_results import (
+    generate_exact_matches_test_results, generate_test_results)
+from ms2query.clean_and_filter_spectra import \
+    clean_normalize_and_split_annotated_spectra
+from ms2query.create_new_library.split_data_for_training import (
+    select_spectra_per_unique_inchikey, split_spectra_in_random_inchikey_sets)
 from ms2query.create_new_library.train_models import train_all_models
-from ms2query.benchmarking.collect_test_data_results import generate_test_results, generate_exact_matches_test_results
-from ms2query.clean_and_filter_spectra import clean_normalize_and_split_annotated_spectra
 from ms2query.ms2library import create_library_object_from_one_dir
+from ms2query.utils import (load_matchms_spectrum_objects_from_file,
+                            save_pickled_file)
 
 
 def split_and_store_annotated_unannotated(spectrum_file_name,

ms2query/benchmarking/visualize_mass_distribution.py

@@ -1,10 +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 create_accuracy_vs_recall_plot import load_results_from_folder, \
-    calculate_means_and_standard_deviation
-from ms2query.utils import load_matchms_spectrum_objects_from_file, load_pickled_file
 from matplotlib import pyplot as plt
+from ms2query.utils import (load_matchms_spectrum_objects_from_file,
+                            load_pickled_file)
 
 
 def split_results_mass(list_of_test_spectra: List[List[Spectrum]],

ms2query/benchmarking/visualize_tanimoto_score_distribution.py

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

ms2query/clean_and_filter_spectra.py

@@ -1,12 +1,13 @@
 from typing import List, Tuple
 import matchms.filtering as msfilters
-from tqdm import tqdm
 from matchms import Spectrum
-from matchms.metadata_utils import is_valid_inchi, is_valid_inchikey, is_valid_smiles
-from matchms.typing import SpectrumType
 from matchms.logging_functions import set_matchms_logger_level
+from matchms.metadata_utils import (is_valid_inchi, is_valid_inchikey,
+                                    is_valid_smiles)
+from matchms.typing import SpectrumType
 from matchmsextras.pubchem_lookup import pubchem_metadata_lookup
 from spec2vec import SpectrumDocument
+from tqdm import tqdm
 
 
 def clean_metadata(spectrum: Spectrum) -> Spectrum:

ms2query/create_new_library/add_classifire_classifications.py

@@ -2,7 +2,6 @@
 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

@@ -4,12 +4,11 @@
 """
 from collections import Counter
 from typing import List
-
+import numpy as np
 import pandas as pd
 from matchms import Spectrum
-import numpy as np
-
-from matchms.similarity.vector_similarity_functions import jaccard_similarity_matrix, jaccard_index
+from matchms.similarity.vector_similarity_functions import (
+    jaccard_index, jaccard_similarity_matrix)
 from rdkit import Chem
 from tqdm import tqdm
 

ms2query/create_new_library/create_sqlite_database.py

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

@@ -15,9 +15,11 @@
 from ms2deepscore.models import load_model as load_ms2ds_model
 from spec2vec.vector_operations import calc_vector
 from tqdm import tqdm
-from ms2query.create_new_library.create_sqlite_database import make_sqlfile_wrapper
 from ms2query.clean_and_filter_spectra import create_spectrum_documents
-from ms2query.create_new_library.add_classifire_classifications import select_compound_classes, convert_to_dataframe
+from ms2query.create_new_library.add_classifire_classifications import (
+    convert_to_dataframe, select_compound_classes)
+from ms2query.create_new_library.create_sqlite_database import \
+    make_sqlfile_wrapper
 
 
 class LibraryFilesCreator:

ms2query/create_new_library/split_data_for_training.py

@@ -3,9 +3,9 @@
 new models
 """
 
-from typing import List, Dict
-from matchms import Spectrum
 import random
+from typing import Dict, List
+from matchms import Spectrum
 
 
 def select_unique_inchikeys(spectra: List[Spectrum]) -> List[str]:

ms2query/create_new_library/train_models.py

@@ -5,11 +5,15 @@
 
 import os
 from spec2vec.model_building import train_new_word2vec_model
-from ms2query.create_new_library.train_ms2deepscore import train_ms2deepscore_wrapper
-from ms2query.create_new_library.train_ms2query_model import train_ms2query_model, convert_to_onnx_model
-from ms2query.create_new_library.library_files_creator import LibraryFilesCreator
+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.train_ms2deepscore import \
+    train_ms2deepscore_wrapper
+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 ms2query.clean_and_filter_spectra import create_spectrum_documents, clean_normalize_and_split_annotated_spectra
 
 
 class SettingsTrainingModels:

ms2query/create_new_library/train_ms2deepscore.py

@@ -4,19 +4,21 @@
 """
 
 import os
-from typing import List, Dict, Optional
+from typing import Dict, List, Optional
 import numpy as np
 import tensorflow as tf
-from matplotlib import pyplot as plt
 from matchms import Spectrum
+from matplotlib import pyplot as plt
 from ms2deepscore import SpectrumBinner
 from ms2deepscore.data_generators import DataGeneratorAllInchikeys
 from ms2deepscore.models import SiameseModel
 from tensorflow.keras.callbacks import (  # pylint: disable=import-error
     EarlyStopping, ModelCheckpoint)
 from tensorflow.keras.optimizers import Adam  # pylint: disable=import-error
-from ms2query.create_new_library.split_data_for_training import split_spectra_on_inchikeys
-from ms2query.create_new_library.calculate_tanimoto_scores import calculate_tanimoto_scores_unique_inchikey
+from ms2query.create_new_library.calculate_tanimoto_scores import \
+    calculate_tanimoto_scores_unique_inchikey
+from ms2query.create_new_library.split_data_for_training import \
+    split_spectra_on_inchikeys
 
 
 def train_ms2ds_model(training_spectra,

ms2query/create_new_library/train_ms2query_model.py

@@ -6,18 +6,21 @@
 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 tqdm import tqdm
-from matchms import Spectrum
 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
+from ms2query.create_new_library.library_files_creator import \
+    LibraryFilesCreator
+from ms2query.create_new_library.split_data_for_training import (
+    split_spectra_on_inchikeys, split_training_and_validation_spectra)
 from ms2query.query_from_sqlite_database import SqliteLibrary
-from ms2query.create_new_library.library_files_creator import LibraryFilesCreator
-from ms2query.create_new_library.split_data_for_training import split_spectra_on_inchikeys, split_training_and_validation_spectra
-from ms2query.create_new_library.calculate_tanimoto_scores import calculate_tanimoto_scores_from_smiles
-from ms2query.utils import save_pickled_file, return_non_existing_file_name
+from ms2query.utils import return_non_existing_file_name, save_pickled_file
 
 
 class DataCollectorForTraining():

ms2query/ms2library.py

@@ -1,22 +1,23 @@
 import os.path
-from typing import Dict, List, Set, Tuple, Union, Optional, Iterator
+from typing import Dict, Iterator, List, Optional, Set, Tuple, Union
 import numpy as np
 import pandas as pd
 from gensim.models import Word2Vec
 from matchms.Spectrum import Spectrum
 from ms2deepscore import MS2DeepScore
 from ms2deepscore.models import load_model as load_ms2ds_model
+from onnxruntime import InferenceSession
 from spec2vec.vector_operations import calc_vector, cosine_similarity_matrix
 from tqdm import tqdm
-from onnxruntime import InferenceSession
-from ms2query.query_from_sqlite_database import SqliteLibrary
-from ms2query.results_table import ResultsTable
 from ms2query.clean_and_filter_spectra import (clean_metadata,
                                                create_spectrum_documents,
                                                normalize_and_filter_peaks)
-from ms2query.utils import (column_names_for_output, load_ms2query_model,
-                            load_pickled_file, SettingsRunMS2Query, predict_onnx_model,
-                            select_files_in_directory, return_non_existing_file_name)
+from ms2query.query_from_sqlite_database import SqliteLibrary
+from ms2query.results_table import ResultsTable
+from ms2query.utils import (SettingsRunMS2Query, column_names_for_output,
+                            load_ms2query_model, load_pickled_file,
+                            predict_onnx_model, return_non_existing_file_name,
+                            select_files_in_directory)
 
 
 class MS2Library:

ms2query/query_from_sqlite_database.py

@@ -6,7 +6,6 @@
 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

@@ -3,7 +3,7 @@
 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)
+from ms2query.utils import column_names_for_output
 
 
 class ResultsTable:

ms2query/run_ms2query.py

@@ -3,7 +3,9 @@
 from typing import Union
 from urllib.request import urlopen, urlretrieve
 from ms2query.ms2library import MS2Library
-from ms2query.utils import load_matchms_spectrum_objects_from_file, SettingsRunMS2Query, return_non_existing_file_name
+from ms2query.utils import (SettingsRunMS2Query,
+                            load_matchms_spectrum_objects_from_file,
+                            return_non_existing_file_name)
 
 
 def zenodo_dois(ionisation_mode):

ms2query/utils.py

@@ -1,11 +1,11 @@
+import json
 import os
 import sys
-import json
-from typing import List, Union, Tuple, Optional
+from typing import List, Optional, Tuple, Union
 import numpy as np
 from matchms import importing
-from spec2vec.Spec2Vec import Spectrum
 from onnxruntime import InferenceSession
+from spec2vec.Spec2Vec import Spectrum
 
 
 if sys.version_info < (3, 8):

tests/conftest.py

@@ -3,7 +3,7 @@
 import pytest
 from matchms import Spectrum
 from matchms.importing.load_from_mgf import load_from_mgf
-from ms2query.ms2library import (MS2Library)
+from ms2query.ms2library import MS2Library
 from ms2query.query_from_sqlite_database import SqliteLibrary
 
 

tests/test_add_classifier_annotations.py

@@ -1,7 +1,8 @@
 import numpy as np
-from matchms import Spectrum
 import pytest
-from ms2query.create_new_library.add_classifire_classifications import select_compound_classes
+from matchms import Spectrum
+from ms2query.create_new_library.add_classifire_classifications import \
+    select_compound_classes
 
 
 @pytest.fixture

tests/test_calculate_tanimoto_scores.py

@@ -1,11 +1,12 @@
 import os
-
 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 calculate_tanimoto_scores_unique_inchikey, \
-    calculate_highest_tanimoto_score
-from ms2query.utils import load_matchms_spectrum_objects_from_file, load_pickled_file
+from ms2query.clean_and_filter_spectra import \
+    normalize_and_filter_peaks_multiple_spectra
+from ms2query.create_new_library.calculate_tanimoto_scores import (
+    calculate_highest_tanimoto_score,
+    calculate_tanimoto_scores_unique_inchikey)
+from ms2query.utils import (load_matchms_spectrum_objects_from_file,
+                            load_pickled_file)
 
 
 def test_calculate_tanimoto_scores_unique_inchikey(path_to_general_test_files, hundred_test_spectra):