How to use the DECIMER web app?
Just upload a pdf document or one or multiple images that contain chemical structure depictions above. If a pdf document is uploaded, DECIMER Segmentation is used to detect and segment all chemical structure depictions. The detected or uploaded chemical structure depictions are processed using the powerful OCSR engine of DECIMER V2. The chemical structure depictions and the corresponding SMILES representation are presented above. You can edit the structures according to your needs in the Ketcher chemical structure editor windows before downloading the segmented images and the correponding mol files. Additionally, the IUPAC names of the chemical structures can be resolved using STOUT V2.
If our toolkit helped your work, please cite our publications.
- DECIMER: towards deep learning for chemical image recognition Rajan, K., Zielesny, A., Steinbeck, C. J Cheminform, 12, 65 (2020).
- DECIMER-Segmentation: Automated extraction of chemical structure depictions from scientific literature Rajan, K., Brinkhaus, H.O., Sorokina, M. et al. J Cheminform, 13, 20 (2021).
- DECIMER 1.0: deep learning for chemical image recognition using transformers Rajan, K., Zielesny, A., Steinbeck, C. J Cheminform, 13, 61 (2021).
- STOUT: SMILES to IUPAC names using neural machine translation Rajan, K., Zielesny, A., Steinbeck, C. J Cheminform, 13, 34 (2021).