Bert Base Smiles

🚀 BERT base for SMILES

This is a bidirectional transformer pretrained on SMILES (simplified molecular - input line - entry system) strings, which can be used for various molecular - related tasks.

🚀 Quick Start

This model is a bidirectional transformer pre - trained on SMILES strings. It has two training objectives: masked language modeling and molecular - formula validity prediction.

Example of Amoxicillin

O=C([C@@H](c1ccc(cc1)O)N)N[C@@H]1C(=O)N2[C@@H]1SC([C@@H]2C(=O)O)(C)C

✨ Features

• Training Objectives:
  • Masked language modeling
  • Molecular - formula validity prediction
• Intended Uses:
  • The model is primarily aimed at being fine - tuned on the following tasks:
    • Molecule classification
    • Molecule - to - gene - expression mapping
    • Cell targeting

📦 Installation

No specific installation steps are provided in the original README.

💻 Usage Examples

Basic Usage

from transformers import BertTokenizerFast, BertModel
checkpoint = 'unikei/bert-base-smiles'
tokenizer = BertTokenizerFast.from_pretrained(checkpoint)
model = BertModel.from_pretrained(checkpoint)

example = 'O=C([C@@H](c1ccc(cc1)O)N)N[C@@H]1C(=O)N2[C@@H]1SC([C@@H]2C(=O)O)(C)C'
tokens = tokenizer(example, return_tensors='pt')
predictions = model(**tokens)

📚 Documentation

Intended Uses

This model is mainly designed to be fine - tuned for the following tasks:

• Molecule classification
• Molecule - to - gene - expression mapping
• Cell targeting

🔧 Technical Details

Two training objectives were used:

1. Masked language modeling
2. Molecular - formula validity prediction

📄 License

The model is under the bigscience - openrail - m license.

Information Table