Datasets, alphabets and models from paper 'Reverse Engineering Molecules from Fingerprints through Deterministic Enumeration and Generative Models.
收藏NIAID Data Ecosystem2026-05-02 收录
下载链接：
https://zenodo.org/record/14760991
下载链接
链接失效反馈官方服务：
资源简介：
Files utilized and produced within the molecule-signature project:
alphabets.zip: Alphabets of molecule signatures.
datasets.zip: Datasets from MetaNetX, eMolecules, and DrugBank used to build alphabets and train the generative models.
models.zip: PyTorch/Lightning models and SentencePiece tokenization models for decoding SMILES from ECFP.
See embedded README.md files and the publication for in depth details.
创建时间：
2025-01-31
