logo
ResearchBunny Logo
DECIMER.ai: an open platform for automated optical chemical structure identification, segmentation and recognition in scientific publications

Chemistry

DECIMER.ai: an open platform for automated optical chemical structure identification, segmentation and recognition in scientific publications

K. Rajan, H. O. Brinkhaus, et al.

Discover DECIMER.ai, an innovative open-source platform that automates the extraction and interpretation of chemical structures from scientific literature! Developed by Kohulan Rajan, Henning Otto Brinkhaus, M. Isabel Agea, Achim Zielesny, and Christoph Steinbeck, this powerful tool leverages advanced segmentation and classification technologies for superior chemical structure recognition. Explore its impressive capabilities and publicly available resources!

00:00
00:00
Playback language: English
Abstract
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
Listen, Learn & Level Up
Over 10,000 hours of research content in 25+ fields, available in 12+ languages.
No more digging through PDFs, just hit play and absorb the world's latest research in your language, on your time.
listen to research audio papers with researchbunny