Baseline Code: Translation between Molecules and Natural Language

Baseline training code for "Translation between Molecules and Natural Language".

Installation

Installation instructions will be uploaded soon.

Training Commands

Command	Purpose
python main_RNN_smiles2caption.py --output_file RNN_caption2smiles.txt --mol_replace	Run the RNN baseline for molecule captioning.
python main_transformer_smiles2caption.py --output_file transformer_caption2smiles.txt --mol_replace	Run the Transformer baseline for molecule captioning.
python main_RNN_smiles2caption.py --output_file RNN_smiles2caption.txt --mol_replace	Run the RNN baseline for text-based molecule generation.
python main_transformer_smiles2caption.py --output_file transformer_smiles2caption.txt --mol_replace	Run the Transformer baseline for text-based molecule generation.

Citation

If you found our work useful, please cite:

@article{edwards2022translation,
  title={Translation between Molecules and Natural Language},
  author={Edwards, Carl and Lai, Tuan and Ros, Kevin and Honke, Garrett and Ji, Heng},
  journal={arXiv preprint arXiv:2204.11817},
  year={2022}
}

References

https://pytorch.org/tutorials/intermediate/seq2seq_translation_tutorial.html https://pytorch.org/tutorials/beginner/chatbot_tutorial.html https://pytorch.org/tutorials/beginner/translation_transformer.html