├── .idea ├── .gitignore ├── Lib-INVENT-dataset.iml ├── inspectionProfiles │ └── profiles_settings.xml ├── misc.xml ├── modules.xml └── vcs.xml ├── LICENSE ├── README.md ├── data_preparation ├── __init__.py ├── duplicate_finder.py ├── enums │ ├── __init__.py │ ├── dataframe_columns_enum.py │ ├── purging_enum.py │ ├── running_mode_enum.py │ └── stats_extraction_enum.py ├── file_shuffler.py ├── reaction_based_slicer.py ├── reaction_validator.py ├── reagent_validator.py ├── scaffold_memory_analysis.json ├── smiles_randomizer.py └── stats_extractor.py ├── dto ├── __init__.py ├── decoration_similarity_analyser_config.py ├── dupicate_removal_config.py ├── file_shuffling_config.py ├── general_configuration.py ├── randomization_config.py ├── reaction_slicing_config.py ├── reaction_validation_config.py ├── reagent_validation_config.py ├── scaffold_memory_analysis_config.py ├── stats_extraction_config.py └── tensorboard_extraction_config.py ├── environment.yml ├── example_configurations ├── duplicates.json ├── preprocessing.example.json ├── randomization.json ├── reaction_based_slicing.json ├── reaction_validation.json ├── reagent_validation.json ├── scaffold_memory_analysis.json ├── shuffle.json ├── supporting_files │ └── filter_conditions.json └── tensorboard_extractor.json ├── input.py ├── main_test.py ├── manager.py ├── results_analysis ├── enums │ ├── __init__.py │ └── scaffold_memory_property_enum.py ├── scaffold_memory_analyser.py └── tensorboard_logs.py ├── tests ├── __init__.py ├── compute_properties_test.py ├── fixtures │ ├── reaction_fixtures.py │ └── stats_extraction_fixtures.py ├── preprocessing_test.py ├── reaction_based_slicer_test.py ├── reaction_validation_test.py ├── reagent_validator_test.py └── smiles_randomizer_test.py ├── tutorial ├── .ipynb_checkpoints │ ├── data_preparation_demo-checkpoint.ipynb │ └── reaction_based_slicing-checkpoint.ipynb ├── README.md ├── data │ └── reaction.smirks ├── data_preparation_demo.ipynb └── reaction_based_slicing.ipynb └── utils ├── chem.py └── spark.py /.idea/.gitignore: -------------------------------------------------------------------------------- 1 | # Default ignored files 2 | /shelf/ 3 | /workspace.xml 4 | -------------------------------------------------------------------------------- /.idea/Lib-INVENT-dataset.iml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MolecularAI/Lib-INVENT-dataset/HEAD/.idea/Lib-INVENT-dataset.iml -------------------------------------------------------------------------------- /.idea/inspectionProfiles/profiles_settings.xml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MolecularAI/Lib-INVENT-dataset/HEAD/.idea/inspectionProfiles/profiles_settings.xml -------------------------------------------------------------------------------- /.idea/misc.xml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MolecularAI/Lib-INVENT-dataset/HEAD/.idea/misc.xml -------------------------------------------------------------------------------- /.idea/modules.xml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MolecularAI/Lib-INVENT-dataset/HEAD/.idea/modules.xml -------------------------------------------------------------------------------- /.idea/vcs.xml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MolecularAI/Lib-INVENT-dataset/HEAD/.idea/vcs.xml -------------------------------------------------------------------------------- /LICENSE: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MolecularAI/Lib-INVENT-dataset/HEAD/LICENSE -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MolecularAI/Lib-INVENT-dataset/HEAD/README.md -------------------------------------------------------------------------------- /data_preparation/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /data_preparation/duplicate_finder.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MolecularAI/Lib-INVENT-dataset/HEAD/data_preparation/duplicate_finder.py -------------------------------------------------------------------------------- /data_preparation/enums/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MolecularAI/Lib-INVENT-dataset/HEAD/data_preparation/enums/__init__.py -------------------------------------------------------------------------------- /data_preparation/enums/dataframe_columns_enum.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MolecularAI/Lib-INVENT-dataset/HEAD/data_preparation/enums/dataframe_columns_enum.py -------------------------------------------------------------------------------- /data_preparation/enums/purging_enum.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MolecularAI/Lib-INVENT-dataset/HEAD/data_preparation/enums/purging_enum.py -------------------------------------------------------------------------------- /data_preparation/enums/running_mode_enum.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MolecularAI/Lib-INVENT-dataset/HEAD/data_preparation/enums/running_mode_enum.py -------------------------------------------------------------------------------- /data_preparation/enums/stats_extraction_enum.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MolecularAI/Lib-INVENT-dataset/HEAD/data_preparation/enums/stats_extraction_enum.py -------------------------------------------------------------------------------- /data_preparation/file_shuffler.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MolecularAI/Lib-INVENT-dataset/HEAD/data_preparation/file_shuffler.py -------------------------------------------------------------------------------- /data_preparation/reaction_based_slicer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MolecularAI/Lib-INVENT-dataset/HEAD/data_preparation/reaction_based_slicer.py -------------------------------------------------------------------------------- /data_preparation/reaction_validator.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MolecularAI/Lib-INVENT-dataset/HEAD/data_preparation/reaction_validator.py -------------------------------------------------------------------------------- /data_preparation/reagent_validator.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MolecularAI/Lib-INVENT-dataset/HEAD/data_preparation/reagent_validator.py -------------------------------------------------------------------------------- /data_preparation/scaffold_memory_analysis.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MolecularAI/Lib-INVENT-dataset/HEAD/data_preparation/scaffold_memory_analysis.json -------------------------------------------------------------------------------- /data_preparation/smiles_randomizer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MolecularAI/Lib-INVENT-dataset/HEAD/data_preparation/smiles_randomizer.py -------------------------------------------------------------------------------- /data_preparation/stats_extractor.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MolecularAI/Lib-INVENT-dataset/HEAD/data_preparation/stats_extractor.py -------------------------------------------------------------------------------- /dto/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MolecularAI/Lib-INVENT-dataset/HEAD/dto/__init__.py -------------------------------------------------------------------------------- /dto/decoration_similarity_analyser_config.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MolecularAI/Lib-INVENT-dataset/HEAD/dto/decoration_similarity_analyser_config.py -------------------------------------------------------------------------------- /dto/dupicate_removal_config.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MolecularAI/Lib-INVENT-dataset/HEAD/dto/dupicate_removal_config.py -------------------------------------------------------------------------------- /dto/file_shuffling_config.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MolecularAI/Lib-INVENT-dataset/HEAD/dto/file_shuffling_config.py -------------------------------------------------------------------------------- /dto/general_configuration.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MolecularAI/Lib-INVENT-dataset/HEAD/dto/general_configuration.py -------------------------------------------------------------------------------- /dto/randomization_config.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MolecularAI/Lib-INVENT-dataset/HEAD/dto/randomization_config.py -------------------------------------------------------------------------------- /dto/reaction_slicing_config.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MolecularAI/Lib-INVENT-dataset/HEAD/dto/reaction_slicing_config.py -------------------------------------------------------------------------------- /dto/reaction_validation_config.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MolecularAI/Lib-INVENT-dataset/HEAD/dto/reaction_validation_config.py -------------------------------------------------------------------------------- /dto/reagent_validation_config.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MolecularAI/Lib-INVENT-dataset/HEAD/dto/reagent_validation_config.py -------------------------------------------------------------------------------- /dto/scaffold_memory_analysis_config.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MolecularAI/Lib-INVENT-dataset/HEAD/dto/scaffold_memory_analysis_config.py -------------------------------------------------------------------------------- /dto/stats_extraction_config.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MolecularAI/Lib-INVENT-dataset/HEAD/dto/stats_extraction_config.py -------------------------------------------------------------------------------- /dto/tensorboard_extraction_config.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MolecularAI/Lib-INVENT-dataset/HEAD/dto/tensorboard_extraction_config.py -------------------------------------------------------------------------------- /environment.yml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MolecularAI/Lib-INVENT-dataset/HEAD/environment.yml -------------------------------------------------------------------------------- /example_configurations/duplicates.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MolecularAI/Lib-INVENT-dataset/HEAD/example_configurations/duplicates.json -------------------------------------------------------------------------------- /example_configurations/preprocessing.example.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MolecularAI/Lib-INVENT-dataset/HEAD/example_configurations/preprocessing.example.json -------------------------------------------------------------------------------- /example_configurations/randomization.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MolecularAI/Lib-INVENT-dataset/HEAD/example_configurations/randomization.json -------------------------------------------------------------------------------- /example_configurations/reaction_based_slicing.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MolecularAI/Lib-INVENT-dataset/HEAD/example_configurations/reaction_based_slicing.json -------------------------------------------------------------------------------- /example_configurations/reaction_validation.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MolecularAI/Lib-INVENT-dataset/HEAD/example_configurations/reaction_validation.json -------------------------------------------------------------------------------- /example_configurations/reagent_validation.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MolecularAI/Lib-INVENT-dataset/HEAD/example_configurations/reagent_validation.json -------------------------------------------------------------------------------- /example_configurations/scaffold_memory_analysis.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MolecularAI/Lib-INVENT-dataset/HEAD/example_configurations/scaffold_memory_analysis.json -------------------------------------------------------------------------------- /example_configurations/shuffle.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MolecularAI/Lib-INVENT-dataset/HEAD/example_configurations/shuffle.json -------------------------------------------------------------------------------- /example_configurations/supporting_files/filter_conditions.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MolecularAI/Lib-INVENT-dataset/HEAD/example_configurations/supporting_files/filter_conditions.json -------------------------------------------------------------------------------- /example_configurations/tensorboard_extractor.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MolecularAI/Lib-INVENT-dataset/HEAD/example_configurations/tensorboard_extractor.json -------------------------------------------------------------------------------- /input.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MolecularAI/Lib-INVENT-dataset/HEAD/input.py -------------------------------------------------------------------------------- /main_test.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MolecularAI/Lib-INVENT-dataset/HEAD/main_test.py -------------------------------------------------------------------------------- /manager.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MolecularAI/Lib-INVENT-dataset/HEAD/manager.py -------------------------------------------------------------------------------- /results_analysis/enums/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MolecularAI/Lib-INVENT-dataset/HEAD/results_analysis/enums/__init__.py -------------------------------------------------------------------------------- /results_analysis/enums/scaffold_memory_property_enum.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MolecularAI/Lib-INVENT-dataset/HEAD/results_analysis/enums/scaffold_memory_property_enum.py -------------------------------------------------------------------------------- /results_analysis/scaffold_memory_analyser.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MolecularAI/Lib-INVENT-dataset/HEAD/results_analysis/scaffold_memory_analyser.py -------------------------------------------------------------------------------- /results_analysis/tensorboard_logs.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MolecularAI/Lib-INVENT-dataset/HEAD/results_analysis/tensorboard_logs.py -------------------------------------------------------------------------------- /tests/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MolecularAI/Lib-INVENT-dataset/HEAD/tests/__init__.py -------------------------------------------------------------------------------- /tests/compute_properties_test.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MolecularAI/Lib-INVENT-dataset/HEAD/tests/compute_properties_test.py -------------------------------------------------------------------------------- /tests/fixtures/reaction_fixtures.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MolecularAI/Lib-INVENT-dataset/HEAD/tests/fixtures/reaction_fixtures.py -------------------------------------------------------------------------------- /tests/fixtures/stats_extraction_fixtures.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MolecularAI/Lib-INVENT-dataset/HEAD/tests/fixtures/stats_extraction_fixtures.py -------------------------------------------------------------------------------- /tests/preprocessing_test.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MolecularAI/Lib-INVENT-dataset/HEAD/tests/preprocessing_test.py -------------------------------------------------------------------------------- /tests/reaction_based_slicer_test.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MolecularAI/Lib-INVENT-dataset/HEAD/tests/reaction_based_slicer_test.py -------------------------------------------------------------------------------- /tests/reaction_validation_test.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MolecularAI/Lib-INVENT-dataset/HEAD/tests/reaction_validation_test.py -------------------------------------------------------------------------------- /tests/reagent_validator_test.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MolecularAI/Lib-INVENT-dataset/HEAD/tests/reagent_validator_test.py -------------------------------------------------------------------------------- /tests/smiles_randomizer_test.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MolecularAI/Lib-INVENT-dataset/HEAD/tests/smiles_randomizer_test.py -------------------------------------------------------------------------------- /tutorial/.ipynb_checkpoints/data_preparation_demo-checkpoint.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MolecularAI/Lib-INVENT-dataset/HEAD/tutorial/.ipynb_checkpoints/data_preparation_demo-checkpoint.ipynb -------------------------------------------------------------------------------- /tutorial/.ipynb_checkpoints/reaction_based_slicing-checkpoint.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MolecularAI/Lib-INVENT-dataset/HEAD/tutorial/.ipynb_checkpoints/reaction_based_slicing-checkpoint.ipynb -------------------------------------------------------------------------------- /tutorial/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MolecularAI/Lib-INVENT-dataset/HEAD/tutorial/README.md -------------------------------------------------------------------------------- /tutorial/data/reaction.smirks: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MolecularAI/Lib-INVENT-dataset/HEAD/tutorial/data/reaction.smirks -------------------------------------------------------------------------------- /tutorial/data_preparation_demo.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MolecularAI/Lib-INVENT-dataset/HEAD/tutorial/data_preparation_demo.ipynb -------------------------------------------------------------------------------- /tutorial/reaction_based_slicing.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MolecularAI/Lib-INVENT-dataset/HEAD/tutorial/reaction_based_slicing.ipynb -------------------------------------------------------------------------------- /utils/chem.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MolecularAI/Lib-INVENT-dataset/HEAD/utils/chem.py -------------------------------------------------------------------------------- /utils/spark.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MolecularAI/Lib-INVENT-dataset/HEAD/utils/spark.py --------------------------------------------------------------------------------