├── .gitignore ├── LICENSE ├── README.md ├── bart_vocab.json ├── bart_vocab_downstream.json ├── ds_config.json ├── env-dev.yml ├── example_scripts ├── eval_forward.sh ├── fine_tune.sh ├── pre-train.sh └── predict.sh ├── molbart ├── __init__.py ├── build_tokenizer.py ├── config │ ├── build_tokenizer.yaml │ ├── fine_tune.yaml │ ├── inference_score.yaml │ ├── logger │ │ └── tensorboard.yaml │ ├── plugins │ │ └── deepspeed.yaml │ ├── predict.yaml │ ├── pretrain.yaml │ ├── round_trip_inference.yaml │ └── trainer │ │ ├── default.yaml │ │ └── inference.yaml ├── data │ ├── __init__.py │ ├── base.py │ ├── data_collection.py │ ├── datamodules.py │ ├── mol_data.py │ ├── seq2seq_data.py │ ├── util.py │ └── zinc_utils.py ├── fine_tune.py ├── inference_score.py ├── models │ ├── __init__.py │ ├── base_transformer.py │ ├── chemformer.py │ ├── transformer_models.py │ └── util.py ├── predict.py ├── pretrain.py ├── retrosynthesis │ ├── __init__.py │ ├── disconnection_aware │ │ ├── disconnection_atom_mapper.py │ │ ├── tag_converter.py │ │ └── utils.py │ ├── round_trip_inference.py │ └── round_trip_utils.py └── utils │ ├── __init__.py │ ├── base_collection.py │ ├── callbacks │ ├── __init__.py │ ├── callback_collection.py │ └── callbacks.py │ ├── data_utils.py │ ├── samplers │ ├── __init__.py │ ├── beam_search_samplers.py │ └── beam_search_utils.py │ ├── scores │ ├── __init__.py │ ├── score_collection.py │ └── scores.py │ ├── smiles_utils.py │ ├── tokenizers │ ├── __init__.py │ └── tokenizers.py │ └── trainer_utils.py ├── poetry.lock ├── pyproject.toml ├── service ├── chemformer_disconnect_service.py ├── chemformer_service.py └── service_utils.py ├── setup.py └── tests ├── __init__.py ├── conftest.py ├── data ├── example_data_backward_sampled_smiles_uspto50k.json ├── example_data_uspto.csv ├── round_trip_input_data.csv ├── round_trip_predictions_converted.json └── round_trip_predictions_raw.json ├── decoder_test.py ├── pre_train_model_test.py ├── test_atom_mapper.py ├── test_data.py ├── test_data_utils.py ├── test_decoder.py ├── test_pre_train_model.py ├── test_round_trip_utils.py ├── test_scores.py └── test_tokenizer.py /.gitignore: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MolecularAI/Chemformer/HEAD/.gitignore -------------------------------------------------------------------------------- /LICENSE: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MolecularAI/Chemformer/HEAD/LICENSE -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MolecularAI/Chemformer/HEAD/README.md -------------------------------------------------------------------------------- /bart_vocab.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MolecularAI/Chemformer/HEAD/bart_vocab.json -------------------------------------------------------------------------------- /bart_vocab_downstream.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MolecularAI/Chemformer/HEAD/bart_vocab_downstream.json -------------------------------------------------------------------------------- /ds_config.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MolecularAI/Chemformer/HEAD/ds_config.json -------------------------------------------------------------------------------- /env-dev.yml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MolecularAI/Chemformer/HEAD/env-dev.yml -------------------------------------------------------------------------------- /example_scripts/eval_forward.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MolecularAI/Chemformer/HEAD/example_scripts/eval_forward.sh -------------------------------------------------------------------------------- /example_scripts/fine_tune.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MolecularAI/Chemformer/HEAD/example_scripts/fine_tune.sh -------------------------------------------------------------------------------- /example_scripts/pre-train.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MolecularAI/Chemformer/HEAD/example_scripts/pre-train.sh -------------------------------------------------------------------------------- /example_scripts/predict.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MolecularAI/Chemformer/HEAD/example_scripts/predict.sh -------------------------------------------------------------------------------- /molbart/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /molbart/build_tokenizer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MolecularAI/Chemformer/HEAD/molbart/build_tokenizer.py -------------------------------------------------------------------------------- /molbart/config/build_tokenizer.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MolecularAI/Chemformer/HEAD/molbart/config/build_tokenizer.yaml -------------------------------------------------------------------------------- /molbart/config/fine_tune.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MolecularAI/Chemformer/HEAD/molbart/config/fine_tune.yaml -------------------------------------------------------------------------------- /molbart/config/inference_score.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MolecularAI/Chemformer/HEAD/molbart/config/inference_score.yaml -------------------------------------------------------------------------------- /molbart/config/logger/tensorboard.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MolecularAI/Chemformer/HEAD/molbart/config/logger/tensorboard.yaml -------------------------------------------------------------------------------- /molbart/config/plugins/deepspeed.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MolecularAI/Chemformer/HEAD/molbart/config/plugins/deepspeed.yaml -------------------------------------------------------------------------------- /molbart/config/predict.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MolecularAI/Chemformer/HEAD/molbart/config/predict.yaml -------------------------------------------------------------------------------- /molbart/config/pretrain.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MolecularAI/Chemformer/HEAD/molbart/config/pretrain.yaml -------------------------------------------------------------------------------- /molbart/config/round_trip_inference.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MolecularAI/Chemformer/HEAD/molbart/config/round_trip_inference.yaml -------------------------------------------------------------------------------- /molbart/config/trainer/default.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MolecularAI/Chemformer/HEAD/molbart/config/trainer/default.yaml -------------------------------------------------------------------------------- /molbart/config/trainer/inference.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MolecularAI/Chemformer/HEAD/molbart/config/trainer/inference.yaml -------------------------------------------------------------------------------- /molbart/data/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MolecularAI/Chemformer/HEAD/molbart/data/__init__.py -------------------------------------------------------------------------------- /molbart/data/base.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MolecularAI/Chemformer/HEAD/molbart/data/base.py -------------------------------------------------------------------------------- /molbart/data/data_collection.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MolecularAI/Chemformer/HEAD/molbart/data/data_collection.py -------------------------------------------------------------------------------- /molbart/data/datamodules.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MolecularAI/Chemformer/HEAD/molbart/data/datamodules.py -------------------------------------------------------------------------------- /molbart/data/mol_data.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MolecularAI/Chemformer/HEAD/molbart/data/mol_data.py -------------------------------------------------------------------------------- /molbart/data/seq2seq_data.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MolecularAI/Chemformer/HEAD/molbart/data/seq2seq_data.py -------------------------------------------------------------------------------- /molbart/data/util.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MolecularAI/Chemformer/HEAD/molbart/data/util.py -------------------------------------------------------------------------------- /molbart/data/zinc_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MolecularAI/Chemformer/HEAD/molbart/data/zinc_utils.py -------------------------------------------------------------------------------- /molbart/fine_tune.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MolecularAI/Chemformer/HEAD/molbart/fine_tune.py -------------------------------------------------------------------------------- /molbart/inference_score.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MolecularAI/Chemformer/HEAD/molbart/inference_score.py -------------------------------------------------------------------------------- /molbart/models/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MolecularAI/Chemformer/HEAD/molbart/models/__init__.py -------------------------------------------------------------------------------- /molbart/models/base_transformer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MolecularAI/Chemformer/HEAD/molbart/models/base_transformer.py -------------------------------------------------------------------------------- /molbart/models/chemformer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MolecularAI/Chemformer/HEAD/molbart/models/chemformer.py -------------------------------------------------------------------------------- /molbart/models/transformer_models.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MolecularAI/Chemformer/HEAD/molbart/models/transformer_models.py -------------------------------------------------------------------------------- /molbart/models/util.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MolecularAI/Chemformer/HEAD/molbart/models/util.py -------------------------------------------------------------------------------- /molbart/predict.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MolecularAI/Chemformer/HEAD/molbart/predict.py -------------------------------------------------------------------------------- /molbart/pretrain.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MolecularAI/Chemformer/HEAD/molbart/pretrain.py -------------------------------------------------------------------------------- /molbart/retrosynthesis/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /molbart/retrosynthesis/disconnection_aware/disconnection_atom_mapper.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MolecularAI/Chemformer/HEAD/molbart/retrosynthesis/disconnection_aware/disconnection_atom_mapper.py -------------------------------------------------------------------------------- /molbart/retrosynthesis/disconnection_aware/tag_converter.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MolecularAI/Chemformer/HEAD/molbart/retrosynthesis/disconnection_aware/tag_converter.py -------------------------------------------------------------------------------- /molbart/retrosynthesis/disconnection_aware/utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MolecularAI/Chemformer/HEAD/molbart/retrosynthesis/disconnection_aware/utils.py -------------------------------------------------------------------------------- /molbart/retrosynthesis/round_trip_inference.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MolecularAI/Chemformer/HEAD/molbart/retrosynthesis/round_trip_inference.py -------------------------------------------------------------------------------- /molbart/retrosynthesis/round_trip_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MolecularAI/Chemformer/HEAD/molbart/retrosynthesis/round_trip_utils.py -------------------------------------------------------------------------------- /molbart/utils/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /molbart/utils/base_collection.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MolecularAI/Chemformer/HEAD/molbart/utils/base_collection.py -------------------------------------------------------------------------------- /molbart/utils/callbacks/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MolecularAI/Chemformer/HEAD/molbart/utils/callbacks/__init__.py -------------------------------------------------------------------------------- /molbart/utils/callbacks/callback_collection.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MolecularAI/Chemformer/HEAD/molbart/utils/callbacks/callback_collection.py -------------------------------------------------------------------------------- /molbart/utils/callbacks/callbacks.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MolecularAI/Chemformer/HEAD/molbart/utils/callbacks/callbacks.py -------------------------------------------------------------------------------- /molbart/utils/data_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MolecularAI/Chemformer/HEAD/molbart/utils/data_utils.py -------------------------------------------------------------------------------- /molbart/utils/samplers/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MolecularAI/Chemformer/HEAD/molbart/utils/samplers/__init__.py -------------------------------------------------------------------------------- /molbart/utils/samplers/beam_search_samplers.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MolecularAI/Chemformer/HEAD/molbart/utils/samplers/beam_search_samplers.py -------------------------------------------------------------------------------- /molbart/utils/samplers/beam_search_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MolecularAI/Chemformer/HEAD/molbart/utils/samplers/beam_search_utils.py -------------------------------------------------------------------------------- /molbart/utils/scores/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MolecularAI/Chemformer/HEAD/molbart/utils/scores/__init__.py -------------------------------------------------------------------------------- /molbart/utils/scores/score_collection.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MolecularAI/Chemformer/HEAD/molbart/utils/scores/score_collection.py -------------------------------------------------------------------------------- /molbart/utils/scores/scores.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MolecularAI/Chemformer/HEAD/molbart/utils/scores/scores.py -------------------------------------------------------------------------------- /molbart/utils/smiles_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MolecularAI/Chemformer/HEAD/molbart/utils/smiles_utils.py -------------------------------------------------------------------------------- /molbart/utils/tokenizers/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MolecularAI/Chemformer/HEAD/molbart/utils/tokenizers/__init__.py -------------------------------------------------------------------------------- /molbart/utils/tokenizers/tokenizers.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MolecularAI/Chemformer/HEAD/molbart/utils/tokenizers/tokenizers.py -------------------------------------------------------------------------------- /molbart/utils/trainer_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MolecularAI/Chemformer/HEAD/molbart/utils/trainer_utils.py -------------------------------------------------------------------------------- /poetry.lock: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MolecularAI/Chemformer/HEAD/poetry.lock -------------------------------------------------------------------------------- /pyproject.toml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MolecularAI/Chemformer/HEAD/pyproject.toml -------------------------------------------------------------------------------- /service/chemformer_disconnect_service.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MolecularAI/Chemformer/HEAD/service/chemformer_disconnect_service.py -------------------------------------------------------------------------------- /service/chemformer_service.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MolecularAI/Chemformer/HEAD/service/chemformer_service.py -------------------------------------------------------------------------------- /service/service_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MolecularAI/Chemformer/HEAD/service/service_utils.py -------------------------------------------------------------------------------- /setup.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MolecularAI/Chemformer/HEAD/setup.py -------------------------------------------------------------------------------- /tests/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /tests/conftest.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MolecularAI/Chemformer/HEAD/tests/conftest.py -------------------------------------------------------------------------------- /tests/data/example_data_backward_sampled_smiles_uspto50k.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MolecularAI/Chemformer/HEAD/tests/data/example_data_backward_sampled_smiles_uspto50k.json -------------------------------------------------------------------------------- /tests/data/example_data_uspto.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MolecularAI/Chemformer/HEAD/tests/data/example_data_uspto.csv -------------------------------------------------------------------------------- /tests/data/round_trip_input_data.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MolecularAI/Chemformer/HEAD/tests/data/round_trip_input_data.csv -------------------------------------------------------------------------------- /tests/data/round_trip_predictions_converted.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MolecularAI/Chemformer/HEAD/tests/data/round_trip_predictions_converted.json -------------------------------------------------------------------------------- /tests/data/round_trip_predictions_raw.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MolecularAI/Chemformer/HEAD/tests/data/round_trip_predictions_raw.json -------------------------------------------------------------------------------- /tests/decoder_test.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MolecularAI/Chemformer/HEAD/tests/decoder_test.py -------------------------------------------------------------------------------- /tests/pre_train_model_test.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MolecularAI/Chemformer/HEAD/tests/pre_train_model_test.py -------------------------------------------------------------------------------- /tests/test_atom_mapper.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MolecularAI/Chemformer/HEAD/tests/test_atom_mapper.py -------------------------------------------------------------------------------- /tests/test_data.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MolecularAI/Chemformer/HEAD/tests/test_data.py -------------------------------------------------------------------------------- /tests/test_data_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MolecularAI/Chemformer/HEAD/tests/test_data_utils.py -------------------------------------------------------------------------------- /tests/test_decoder.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MolecularAI/Chemformer/HEAD/tests/test_decoder.py -------------------------------------------------------------------------------- /tests/test_pre_train_model.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MolecularAI/Chemformer/HEAD/tests/test_pre_train_model.py -------------------------------------------------------------------------------- /tests/test_round_trip_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MolecularAI/Chemformer/HEAD/tests/test_round_trip_utils.py -------------------------------------------------------------------------------- /tests/test_scores.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MolecularAI/Chemformer/HEAD/tests/test_scores.py -------------------------------------------------------------------------------- /tests/test_tokenizer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MolecularAI/Chemformer/HEAD/tests/test_tokenizer.py --------------------------------------------------------------------------------