decimer
DECIMER Image Transformer is a deep-learning-based tool designed for automated recognition of chemical structure images. Leveraging transformer architectures, the model converts chemical images into SMILES strings, enabling the digitization of chemical data from scanned documents, literature, and patents.
Science Score: 77.0%
This score indicates how likely this project is to be science-related based on various indicators:
-
✓CITATION.cff file
Found CITATION.cff file -
✓codemeta.json file
Found codemeta.json file -
✓.zenodo.json file
Found .zenodo.json file -
✓DOI references
Found 3 DOI reference(s) in README -
✓Academic publication links
Links to: zenodo.org -
✓Committers with academic emails
1 of 12 committers (8.3%) from academic institutions -
○Institutional organization owner
-
○JOSS paper metadata
-
○Scientific vocabulary similarity
Low similarity (15.4%) to scientific vocabulary
Keywords
chemical-image-recognition
decimer
deep-learning
image-data-mining
python
tensorflow
tpu
transformers
Keywords from Contributors
cheminformatics
chemistry
rdkit
chemical-structure
decimer-segmentation
segmented-images
segmented-structure-depictions
chemistry-development-kit
microservices-architecture
openbabel
Last synced: 6 months ago
·
JSON representation
·
Repository
DECIMER Image Transformer is a deep-learning-based tool designed for automated recognition of chemical structure images. Leveraging transformer architectures, the model converts chemical images into SMILES strings, enabling the digitization of chemical data from scanned documents, literature, and patents.
Basic Info
Statistics
- Stars: 276
- Watchers: 7
- Forks: 71
- Open Issues: 4
- Releases: 14
Topics
chemical-image-recognition
decimer
deep-learning
image-data-mining
python
tensorflow
tpu
transformers
Created over 5 years ago
· Last pushed 10 months ago
Metadata Files
Readme
Changelog
License
Code of conduct
Citation
README.md
# 🧪 DECIMER Image Transformer 🖼️
### Deep Learning for Chemical Image Recognition using Efficient-Net V2 + Transformer
📚 Table of Contents
- Abstract
- Method and Model Changes
- Installation
- Usage
- Hand-drawn Model
- Citation
- Acknowledgements
- Author
- Project Website
- Research Group
🔬 Abstract
The DECIMER 2.2 project tackles the OCSR (Optical Chemical Structure Recognition) challenge using cutting-edge computational intelligence methods. Our goal? To provide an automated, open-source software solution for chemical image recognition.
We've supercharged DECIMER with Google's TPU (Tensor Processing Unit) to handle datasets of over 1 million images with lightning speed!
🧠 Method and Model Changes
🖼️ Image Feature ExtractionNow utilizing EfficientNet-V2 for superior image analysis |
🔮 SMILES PredictionEmploying a state-of-the-art transformer model |
🚀 Training Enhancements
- TFRecord Files: Lightning-fast data reading
- Google Cloud Buckets: Efficient cloud storage solution
- TensorFlow Data Pipeline: Optimized data loading
- TPU Strategy: Harnessing the power of Google's TPUs
💻 Installation
```bash
Create a conda wonderland
conda create --name DECIMER python=3.10.0 -y conda activate DECIMER
Equip yourself with DECIMER
pip install decimer ```
🎮 Usage
```python from DECIMER import predict_SMILES
Unleash the power of DECIMER
imagepath = "path/to/your/chemical/masterpiece.jpg" SMILES = predictSMILES(image_path) print(f"🎉 Decoded SMILES: {SMILES}") ```
✍️ DECIMER - Hand-drawn Model
🌟 **New Feature Alert!** 🌟
Our latest model brings the magic of AI to hand-drawn chemical structures!
[](https://doi.org/10.5281/zenodo.10781330)
📜 Citation
If DECIMER helps your research, please cite:
1. Rajan K, et al. "DECIMER.ai - An open platform for automated optical chemical structure identification, segmentation and recognition in scientific publications." *Nat. Commun.* 14, 5045 (2023).
2. Rajan, K., et al. "DECIMER 1.0: deep learning for chemical image recognition using transformers." *J Cheminform* 13, 61 (2021).
3. Rajan, K., et al. "Advancements in hand-drawn chemical structure recognition through an enhanced DECIMER architecture," *J Cheminform* 16, 78 (2024).
🙏 Acknowledgements
- A big thank you to Charles Tapley Hoyt for his invaluable contributions!
- Powered by Google's TPU Research Cloud (TRC)
👨🔬 Author: Kohulan
🌐 Project Website
Experience DECIMER in action at decimer.ai, brilliantly implemented by Otto Brinkhaus!
🏫 Research Group
### 📊 Project Analytics
Owner
- Name: Kohulan Rajan
- Login: Kohulan
- Kind: user
- Location: Jena,Germany
- Company: Friedrich-Schiller-University
- Website: https://kohulanr.com
- Twitter: KohulanRajan
- Repositories: 12
- Profile: https://github.com/Kohulan
PostDoc @Steinbeck-Lab Currently based at Friedrich-Schiller-University, Jena
Citation (CITATION.cff)
cff-version: 1.2.0
message: "If you use this software, please cite it as below."
authors:
- family-names: "Rajan"
given-names: "Kohulan"
orcid: "https://orcid.org/0000-0003-1066-7792"
- family-names: "Zielesny"
given-names: "Achim"
orcid: "https://orcid.org/0000-0003-0722-4229"
- family-names: "Steinbeck"
given-names: "Christoph"
orcid: "https://orcid.org/0000-0001-6966-0814"
title: "DECIMER-V2"
version: 2.2.0
doi: 10.5281/zenodo.7655952
date-released: 2022.05.18
url: "https://github.com/Kohulan/DECIMER-Image_Transformer-2"
license: MIT
GitHub Events
Total
- Create event: 1
- Release event: 1
- Issues event: 11
- Watch event: 72
- Issue comment event: 19
- Push event: 4
- Pull request event: 7
- Fork event: 20
Last Year
- Create event: 1
- Release event: 1
- Issues event: 11
- Watch event: 72
- Issue comment event: 19
- Push event: 4
- Pull request event: 7
- Fork event: 20
Committers
Last synced: 9 months ago
Top Committers
| Name | Commits | |
|---|---|---|
| Kohulan Rajan | k****n@u****e | 213 |
| OBrink | b****s@g****m | 19 |
| Charles Tapley Hoyt | c****t@g****m | 9 |
| Dr. Aleksei Krasnov | a****v@o****m | 6 |
| Eisuke Kawashima | e****m | 3 |
| github-actions[bot] | 4****] | 2 |
| Joao Damas CHST | j****s@s****m | 2 |
| Tobias Bernhard | t****d@b****m | 1 |
| NishaSharma14 | s****4@g****m | 1 |
| Mathias Winkel | m****l@m****m | 1 |
| BinaryBlaze | 6****1 | 1 |
| Andrew White | w****w@g****m | 1 |
Committer Domains (Top 20 + Academic)
Issues and Pull Requests
Last synced: 9 months ago
All Time
- Total issues: 58
- Total pull requests: 56
- Average time to close issues: 27 days
- Average time to close pull requests: 9 days
- Total issue authors: 40
- Total pull request authors: 13
- Average comments per issue: 3.02
- Average comments per pull request: 0.48
- Merged pull requests: 52
- Bot issues: 0
- Bot pull requests: 2
Past Year
- Issues: 7
- Pull requests: 8
- Average time to close issues: 7 days
- Average time to close pull requests: 25 days
- Issue authors: 6
- Pull request authors: 3
- Average comments per issue: 2.57
- Average comments per pull request: 0.5
- Merged pull requests: 6
- Bot issues: 0
- Bot pull requests: 0
Top Authors
Issue Authors
- cthoyt (10)
- OBrink (3)
- pythonnewbie3 (3)
- LaurinL0801 (2)
- mapengsen (2)
- DocMinus (2)
- TAEUKHAM (1)
- yangxiaofei77 (1)
- CurtisColwell (1)
- atef199 (1)
- NaphJohn (1)
- nbosc (1)
- Tim4ik77 (1)
- sunys-pki (1)
- qbKhanh (1)
Pull Request Authors
- Kohulan (42)
- alexey-krasnov (10)
- OBrink (5)
- cthoyt (4)
- e-kwsm (4)
- dasmy (2)
- j3mdamas (2)
- atef199 (2)
- NishaSharma14 (1)
- github-actions[bot] (1)
- tobbber (1)
- sg-s (1)
- ghost (1)
- whitead (1)
Top Labels
Issue Labels
question (14)
bug (7)
enhancement (7)
wontfix (5)
documentation (4)
good first issue (2)
invalid (2)
performance (2)
More information needed (1)
stale (1)
Pull Request Labels
autorelease: tagged (5)
bug (4)
autorelease: pending (4)
enhancement (3)
Packages
- Total packages: 1
-
Total downloads:
- pypi 2,379 last-month
- Total dependent packages: 0
- Total dependent repositories: 1
- Total versions: 19
- Total maintainers: 1
pypi.org: decimer
DECIMER 2.6.0: Deep Learning for Chemical Image Recognition using Efficient-Net V2 + Transformer
- Homepage: https://github.com/Kohulan/DECIMER-Image_Transformer
- Documentation: https://decimer.readthedocs.io/
- License: MIT
-
Latest release: 2.7.1
published over 1 year ago
Rankings
Stargazers count: 6.2%
Forks count: 6.8%
Dependent packages count: 10.0%
Average: 12.2%
Downloads: 16.2%
Dependent repos count: 21.8%
Maintainers (1)
Last synced:
6 months ago
Dependencies
docs/requirements.txt
pypi
- efficientnet *
- nbsphinx *
- numpy >=1.19
- opencv-python *
- pystow *
- sphinx-autodoc-typehints *
- sphinx_rtd_theme *
- tensorflow >=2.6.3
setup.py
pypi
- efficientnet *
- opencv-python *
- pystow *
- tensorflow >=2.6.3
.github/workflows/pypi_release.yml
actions
- actions/checkout master composite
- actions/setup-python v3 composite
- pypa/gh-action-pypi-publish release/v1 composite
.github/workflows/test-release.yml
actions
- actions/checkout v2 composite
- actions/setup-python v1 composite
- google-github-actions/release-please-action v3 composite
requirements.txt
pypi
- efficientnet *
- opencv-python *
- pillow-heif *
- pre-commit *
- pystow *
- tensorflow >=2.8.0