The paper introduces DECIMER.ai, an open-source platform for automated extraction and interpretation of chemical structures from scientific literature. It combines three key components: DECIMER Segmentation (for detecting and segmenting chemical structures), DECIMER Image Classifier (for identifying images containing chemical structures), and DECIMER Image Transformer (for converting depictions into machine-readable SMILES format). The platform's OCSR (Optical Chemical Structure Recognition) engine shows superior performance on benchmark datasets. All source code, trained models, and datasets are publicly available under permissive licenses.
Publisher
Nature Communications
Published On
Aug 19, 2023
Authors
Kohulan Rajan, Henning Otto Brinkhaus, M. Isabel Agea, Achim Zielesny, Christoph Steinbeck
Tags
chemical structures
automated extraction
scientific literature
open-source platform
machine-readable
Optical Chemical Structure Recognition
DECIMER
Related Publications
Explore these studies to deepen your understanding of the subject.
