BERT base for SMILES This is bidirectional transformer pretrained on SMILES (simplified molecular input line entry system) strings. Example: Amoxicillin Two training objectives were used: 1. masked language modeling 2. molecular formula validity prediction Intended uses This model is primarily aimed at being fine tuned on the following tasks: molecule classification molecule to gene expression mapping cell targeting How to use in your code Research Jouary et al. (2025) Bridging scales between chemical space and behavioral phenotype: A cross modal mapping between behavior and molecular structure, derived using the unikei/bert base smiles model, effectively distinguished between distinct neurotransmitter classes, such as dopaminergic/serotonergic ligands, purines, and metabotropic glutamate ligands.
We use cookies for essential functionality and analytics. You can accept or reject analytics cookies.Cookie policy