NisargRhino/SmileBERTa

This model is a lightweight model pre-trained on SELFIES (Self-Referencing Embedded Strings) representations of molecules. It is trained on 2.7M unique and valid molecules taken from COCONUTDB and ChemBL34, with 7.3M total generated masked examples.

Deep learning for chemistry and materials science remains a novel field with lots of potiential. However, the popularity of transfer learning based methods in areas such as NLP and computer vision have not yet been effectively developed in computational chemistry + machine learning.

Question Answering Model for the PathoTHREAT Project

🤗 Blog | 📄 Paper | 💻 Code | 🌐 FineMed | 🩺 DoctoBERT

This is a ReactionT5 pre-trained to predict the products of reactions. You can use the demo here.

Target-Conditioned Molecular Ideation Model for Drug Discovery Research