Bio2token train and test datasets

This zip file contains the training and test data as described in "Bio2Token: Deep Learning Autoencoder for Biological Tokenization"arxiv: https://arxiv.org/abs/2410.19110github: https://github.com/flagshippioneering/bio2tokenWe provide pre-processed datasets in the data/ folder, including:

CATH dataset

CASP 14 and 15 datasets (testing only)

NablaDFT dataset

RNA3DB dataset

License info:The CATH dataset is a derivative of the original CATH which is licenced under the Creative Commons Attribution 4.0 International License. As such our CATH dataset derivative is licensed under the Creative Common Attribution 4.0 Licences.The CASP 14 and 15 datasets are derivatives of the original CASP 14 and 15 datasets and covered under the same MIT licence.The NablaDFT dataset is a derivative of the original NablaDFT dataset and covered under the same MIT license.The RNA3DB dataset is a derivative of the original RNA3DB dataset and covered under the same MIT license.