DECIMER-Segmentation: Automated extraction of chemical structure depictions from scientific literature
Abstract Chemistry looks back at many decades of publications on chemical compounds, their structures and properties, in scientific articles. Liberating this knowledge (semi-)automatically and making it available to the world in open-access databases is a current challenge. Apart from mining textual...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
BMC
2021-03-01
|
| Series: | Journal of Cheminformatics |
| Subjects: | |
| Online Access: | https://doi.org/10.1186/s13321-021-00496-1 |
| _version_ | 1818649065970204672 |
|---|---|
| author | Kohulan Rajan Henning Otto Brinkhaus Maria Sorokina Achim Zielesny Christoph Steinbeck |
| author_facet | Kohulan Rajan Henning Otto Brinkhaus Maria Sorokina Achim Zielesny Christoph Steinbeck |
| author_sort | Kohulan Rajan |
| collection | DOAJ |
| description | Abstract Chemistry looks back at many decades of publications on chemical compounds, their structures and properties, in scientific articles. Liberating this knowledge (semi-)automatically and making it available to the world in open-access databases is a current challenge. Apart from mining textual information, Optical Chemical Structure Recognition (OCSR), the translation of an image of a chemical structure into a machine-readable representation, is part of this workflow. As the OCSR process requires an image containing a chemical structure, there is a need for a publicly available tool that automatically recognizes and segments chemical structure depictions from scientific publications. This is especially important for older documents which are only available as scanned pages. Here, we present DECIMER (Deep lEarning for Chemical IMagE Recognition) Segmentation, the first open-source, deep learning-based tool for automated recognition and segmentation of chemical structures from the scientific literature. The workflow is divided into two main stages. During the detection step, a deep learning model recognizes chemical structure depictions and creates masks which define their positions on the input page. Subsequently, potentially incomplete masks are expanded in a post-processing workflow. The performance of DECIMER Segmentation has been manually evaluated on three sets of publications from different publishers. The approach operates on bitmap images of journal pages to be applicable also to older articles before the introduction of vector images in PDFs. By making the source code and the trained model publicly available, we hope to contribute to the development of comprehensive chemical data extraction workflows. In order to facilitate access to DECIMER Segmentation, we also developed a web application. The web application, available at https://decimer.ai , lets the user upload a pdf file and retrieve the segmented structure depictions. |
| first_indexed | 2024-12-17T01:28:24Z |
| format | Article |
| id | doaj.art-19f62439eb544a07b3b5faebf5ea6bf7 |
| institution | Directory Open Access Journal |
| issn | 1758-2946 |
| language | English |
| last_indexed | 2024-12-17T01:28:24Z |
| publishDate | 2021-03-01 |
| publisher | BMC |
| record_format | Article |
| series | Journal of Cheminformatics |
| spelling | doaj.art-19f62439eb544a07b3b5faebf5ea6bf72022-12-21T22:08:38ZengBMCJournal of Cheminformatics1758-29462021-03-011311910.1186/s13321-021-00496-1DECIMER-Segmentation: Automated extraction of chemical structure depictions from scientific literatureKohulan Rajan0Henning Otto Brinkhaus1Maria Sorokina2Achim Zielesny3Christoph Steinbeck4Institute for Inorganic and Analytical Chemistry, Friedrich-Schiller-University JenaInstitute for Inorganic and Analytical Chemistry, Friedrich-Schiller-University JenaInstitute for Inorganic and Analytical Chemistry, Friedrich-Schiller-University JenaInstitute for Bioinformatics and Chemoinformatics, Westphalian University of Applied SciencesInstitute for Inorganic and Analytical Chemistry, Friedrich-Schiller-University JenaAbstract Chemistry looks back at many decades of publications on chemical compounds, their structures and properties, in scientific articles. Liberating this knowledge (semi-)automatically and making it available to the world in open-access databases is a current challenge. Apart from mining textual information, Optical Chemical Structure Recognition (OCSR), the translation of an image of a chemical structure into a machine-readable representation, is part of this workflow. As the OCSR process requires an image containing a chemical structure, there is a need for a publicly available tool that automatically recognizes and segments chemical structure depictions from scientific publications. This is especially important for older documents which are only available as scanned pages. Here, we present DECIMER (Deep lEarning for Chemical IMagE Recognition) Segmentation, the first open-source, deep learning-based tool for automated recognition and segmentation of chemical structures from the scientific literature. The workflow is divided into two main stages. During the detection step, a deep learning model recognizes chemical structure depictions and creates masks which define their positions on the input page. Subsequently, potentially incomplete masks are expanded in a post-processing workflow. The performance of DECIMER Segmentation has been manually evaluated on three sets of publications from different publishers. The approach operates on bitmap images of journal pages to be applicable also to older articles before the introduction of vector images in PDFs. By making the source code and the trained model publicly available, we hope to contribute to the development of comprehensive chemical data extraction workflows. In order to facilitate access to DECIMER Segmentation, we also developed a web application. The web application, available at https://decimer.ai , lets the user upload a pdf file and retrieve the segmented structure depictions.https://doi.org/10.1186/s13321-021-00496-1Deep learningImage SegmentationOptical Chemical Structure RecognitionNeural NetworksChemical data extraction |
| spellingShingle | Kohulan Rajan Henning Otto Brinkhaus Maria Sorokina Achim Zielesny Christoph Steinbeck DECIMER-Segmentation: Automated extraction of chemical structure depictions from scientific literature Journal of Cheminformatics Deep learning Image Segmentation Optical Chemical Structure Recognition Neural Networks Chemical data extraction |
| title | DECIMER-Segmentation: Automated extraction of chemical structure depictions from scientific literature |
| title_full | DECIMER-Segmentation: Automated extraction of chemical structure depictions from scientific literature |
| title_fullStr | DECIMER-Segmentation: Automated extraction of chemical structure depictions from scientific literature |
| title_full_unstemmed | DECIMER-Segmentation: Automated extraction of chemical structure depictions from scientific literature |
| title_short | DECIMER-Segmentation: Automated extraction of chemical structure depictions from scientific literature |
| title_sort | decimer segmentation automated extraction of chemical structure depictions from scientific literature |
| topic | Deep learning Image Segmentation Optical Chemical Structure Recognition Neural Networks Chemical data extraction |
| url | https://doi.org/10.1186/s13321-021-00496-1 |
| work_keys_str_mv | AT kohulanrajan decimersegmentationautomatedextractionofchemicalstructuredepictionsfromscientificliterature AT henningottobrinkhaus decimersegmentationautomatedextractionofchemicalstructuredepictionsfromscientificliterature AT mariasorokina decimersegmentationautomatedextractionofchemicalstructuredepictionsfromscientificliterature AT achimzielesny decimersegmentationautomatedextractionofchemicalstructuredepictionsfromscientificliterature AT christophsteinbeck decimersegmentationautomatedextractionofchemicalstructuredepictionsfromscientificliterature |