BART Smiles Open-Source Model - Free Handling of Molecular Representations and SMILES Strings

Bartsmiles

Developed by gayane

BARTSmiles is a generative masked language model based on the BART architecture, specifically designed for molecular representation and SMILES string processing.

Molecular Model

Transformers

#Molecular representation generation #SMILES encoding #Chemical structure analysis

Downloads 260

Release Time : 1/4/2024

Model Overview

This model uses the BART architecture to process SMILES strings and is suitable for molecular representation, cheminformatics tasks, and drug discovery research.

Model Features

SMILES processing ability

A language model specifically designed to process the SMILES notation of chemical molecules

Generative model

A generative model based on the BART architecture, suitable for molecular representation generation tasks

Cheminformatics application

A professional model suitable for drug discovery and cheminformatics research

Model Capabilities

SMILES string processing

Molecular representation generation

Chemical structure analysis

Use Cases

Drug discovery

Molecular representation generation

Generate representations of chemical molecules for drug screening

Cheminformatics

SMILES string analysis

Analyze and process the SMILES representation of chemical molecules

🚀 BARTSmiles Adapted Repository

This repository is adapted from https://huggingface.co/chenxran/bart-smiles/tree/main, offering a way to perform feature extraction on SMILES strings.

🚀 Quick Start

The following steps and code example show how to use the model for feature extraction on SMILES strings.

from transformers import AutoTokenizer, AutoModel, SequenceFeatureExtractor
import torch
from transformers import AutoTokenizer, AutoModel

smiles = "CCC(=O)"

tokenizer = AutoTokenizer.from_pretrained("./BARTSmiles/", add_prefix_space=True)
inputs = tokenizer(smiles, return_tensors="pt", return_token_type_ids=False, add_special_tokens=True)

model = AutoModel.from_pretrained('./BARTSmiles')
model.eval()

# Use a pipeline as a high-level helper
from transformers import pipeline

extractor = pipeline("feature-extraction", model=model, tokenizer=tokenizer)
result = extractor(smiles, return_tensors=True, tokenize_kwargs={'return_token_type_ids':False})

📚 Documentation

💻 Usage Examples

Basic Usage

from transformers import AutoTokenizer, AutoModel, SequenceFeatureExtractor
import torch
from transformers import AutoTokenizer, AutoModel

smiles = "CCC(=O)"

tokenizer = AutoTokenizer.from_pretrained("./BARTSmiles/", add_prefix_space=True)
inputs = tokenizer(smiles, return_tensors="pt", return_token_type_ids=False, add_special_tokens=True)

model = AutoModel.from_pretrained('./BARTSmiles')
model.eval()

# Use a pipeline as a high-level helper
from transformers import pipeline

extractor = pipeline("feature-extraction", model=model, tokenizer=tokenizer)
result = extractor(smiles, return_tensors=True, tokenize_kwargs={'return_token_type_ids':False})

📄 Citation

If you use this work, please cite the following paper:

@article{chilingaryan2022bartsmiles,
  title={Bartsmiles: Generative masked language models for molecular representations},
  author={Chilingaryan, Gayane and Tamoyan, Hovhannes and Tevosyan, Ani and Babayan, Nelly and Khondkaryan, Lusine and Hambardzumyan, Karen and Navoyan, Zaven and Khachatrian, Hrant and Aghajanyan, Armen},
  journal={arXiv preprint arXiv:2211.16349},
  year={2022}
}

Featured Recommended AI Models

Empowering the Future, Your AI Solution Knowledge Base

English 简体中文繁體中文にほんご