Kohulan/DECIMER-Image_Transformer

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.

55
/ 100
Established

This tool helps chemists and researchers quickly convert images of chemical structures into a standardized text format (SMILES strings). You input an image from a scanned document, scientific literature, or even a hand-drawn sketch, and it outputs the corresponding SMILES string. This is invaluable for anyone who needs to digitize chemical information from visual sources for further analysis or database entry.

345 stars.

Use this if you need to extract chemical structure data from images or hand-drawn sketches and convert it into a machine-readable format like SMILES.

Not ideal if your primary need is to draw chemical structures from scratch or visualize existing SMILES strings.

cheminformatics chemical-structure-recognition digitization-of-chemical-data chemical-literature-analysis drug-discovery
No Package No Dependents
Maintenance 6 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 23 / 25

How are scores calculated?

Stars

345

Forks

75

Language

Python

License

MIT

Last pushed

Dec 02, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/transformers/Kohulan/DECIMER-Image_Transformer"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.