ChemGPT-4.7M Open Source Molecular Modeling Model - Empowering Chemical Research with a Large-Scale Dataset

Chemgpt 4.7M

Developed by ncfrey

ChemGPT is a generative molecular modeling Transformer model based on the GPT-Neo architecture, pretrained on the PubChem10M dataset.

Molecular Model

Transformers

#Molecular Generation #Chemical Pretraining #SELFIES Encoding

Downloads 652

Release Time : 5/11/2022

Model Overview

ChemGPT is a Transformer model for generative molecular modeling, primarily used for molecular generation and investigating the mechanisms of pretraining and fine-tuning on downstream datasets.

Model Features

Generative Molecular Modeling

Capable of generating chemical molecular structures, supporting SMILES and SELFIES formats.

Based on PubChem Dataset

Pretrained on the PubChem10M dataset, which includes extensive chemical molecular information.

Investigating Pretraining and Fine-Tuning Mechanisms

Primarily designed to investigate the impact mechanisms of pretraining and fine-tuning on downstream datasets.

Model Capabilities

Chemical Molecular Generation

Molecular Structure Prediction

Chemical Model Research

Use Cases

Chemical Research

New Molecule Generation

Generate new chemical molecular structures for drug discovery and material design.

Molecular Property Prediction

Predict physicochemical properties of molecules through fine-tuning the model.

Education

Chemistry Teaching Aid

Used in chemistry education to demonstrate molecular structures and generate examples.

🚀 ChemGPT 4.7M

ChemGPT is a generative molecular modeling transformers model based on the GPT - Neo model, offering solutions for chemical research.

🚀 Quick Start

You can use this model directly from the 🤗/transformers library.

✨ Features

ChemGPT is a transformers model for generative molecular modeling, which was pretrained on the PubChem10M dataset.

📦 Installation

No installation steps were provided in the original document, so this section is skipped.

💻 Usage Examples

No code examples were provided in the original document, so this section is skipped.

📚 Documentation

Intended uses & limitations

How to use

You can use this model directly from the 🤗/transformers library.

Limitations and bias

This model was trained on a subset of molecules from PubChem. You can use this model to generate molecules, but it is mostly intended to be used for investigations of the effects of pre - training and fine - tuning on downstream datasets.

Training data

PubChem10M, a dataset of SMILES strings from PubChem, available via DeepChem.

Training procedure

Preprocessing

SMILES strings were converted to SELFIES using version 1.0.4 of the SELFIES library.

Pretraining

See code in the LitMatter repository.

BibTeX entry and citation info

@article{frey_soklaski_axelrod_samsi_gomez-bombarelli_coley_gadepally_2022, 
place={Cambridge}, title={Neural Scaling of Deep Chemical Models}, 
DOI={10.26434/chemrxiv-2022-3s512}, journal={ChemRxiv}, publisher={Cambridge Open Engage}, 
author={Frey, Nathan and Soklaski, Ryan and Axelrod, Simon and Samsi, Siddharth and Gomez-Bombarelli, Rafael and Coley, Connor and Gadepally, Vijay}, 
year={2022}} This content is a preprint and has not been peer-reviewed.

Frey, Nathan, Ryan Soklaski, Simon Axelrod, Siddharth Samsi, Rafael Gomez-Bombarelli, Connor Coley, and Vijay Gadepally. 
"Neural Scaling of Deep Chemical Models." ChemRxiv (2022). Print. This content is a preprint and has not been peer-reviewed.

🔧 Technical Details

The model is based on the GPT - Neo model and was introduced in the paper Neural Scaling of Deep Chemical Models. It is a transformers model for generative molecular modeling, pretrained on the PubChem10M dataset. During preprocessing, SMILES strings were converted to SELFIES using version 1.0.4 of the SELFIES library.

📄 License

No license information was provided in the original document, so this section is skipped.

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