About • Installation • Powered By • License • Citation • Further Reading • Research Group
DECIMER (Deep Learning for Chemical Image Recognition)
This repository contains the code running on decimer.ai
🧪 DECIMER is a powerful tool that can:
- Perform automated chemical image segmentation
- Recognize chemical structures in scientific publications
- Convert chemical structure depictions to machine-readable formats
DECIMER is actively developed and maintained by the Steinbeck group at the Friedrich Schiller University Jena.
git clone https://github.com/OBrink/DECIMER.ai.git
sudo chmod -R 777 DECIMER.ai
cd DECIMER.ai/
mv .env.example .env
sed -i '$ d' routes/web.php # Deletes the last line "URL::forceScheme('https');"
sudo chmod -R 777 storage/
sudo chmod -R 777 bootstrap/cache/
docker-compose up --build -d- Open your browser (Chrome or Chromium-based recommended)
- Navigate to
http://localhost:80 - On first run, generate an app key when prompted
- Refresh the page
- Wait 5-10 minutes for all models to load
📘 Note: Check out the DECIMER.ai wiki for advanced setup options and customizations!
This project is licensed under the MIT License - see the LICENSE file for details.
If you use this work, please cite:
@article{rajan2023decimer,
title={DECIMER.ai - An open platform for automated optical chemical structure identification, segmentation and recognition in scientific publications},
author={Rajan, Kohulan and Brinkhaus, Henning Otto and Agea, Maria Inmaculada and Zielesny, Achim and Steinbeck, Christoph},
journal={ChemRxiv},
year={2023},
doi={10.26434/chemrxiv-2023-xhcx9}
}- DECIMER: towards deep learning for chemical image recognition
- DECIMER-Segmentation: Automated extraction of chemical structure depictions from scientific literature
- DECIMER 1.0: deep learning for chemical image recognition using transformers
- STOUT: SMILES to IUPAC names using neural machine translation
🔬 DECIMER is developed and maintained by the Steinbeck group at the Friedrich Schiller University Jena, Germany.
Made with ❤️ by the Steinbeck Group