<?xml version="1.0" encoding="utf-8"?>
<export-example>
  <doc>
    <id>4901</id>
    <completedYear>2025</completedYear>
    <publishedYear>2025</publishedYear>
    <thesisYearAccepted/>
    <language>eng</language>
    <pageFirst>3137</pageFirst>
    <pageLast>3148</pageLast>
    <pageNumber>12</pageNumber>
    <edition/>
    <issue>4</issue>
    <volume>2025</volume>
    <type>article</type>
    <publisherName>Royal Society of Chemistry</publisherName>
    <publisherPlace/>
    <creatingCorporation/>
    <contributingCorporation/>
    <belongsToBibliography>0</belongsToBibliography>
    <completedDate>2025-12-18</completedDate>
    <publishedDate>2025-09-21</publishedDate>
    <thesisDateAccepted>--</thesisDateAccepted>
    <title language="eng">MARCUS: molecular annotation and recognition for curating unravelled structures</title>
    <abstract language="eng">The exponential growth of chemical literature necessitates the development of automated tools for extracting and curating molecular information from unstructured scientific publications into open-access chemical databases. Current optical chemical structure recognition (OCSR) and named entity recognition solutions operate in isolation, which limits their scalability for comprehensive literature curation. Here we present MARCUS (Molecular Annotation and Recognition for Curating Unravelled Structures), a tool designed for natural product literature curation that integrates COCONUT-aware schema mapping, CIP-based stereochemical validation, and human-in-the-loop structure refinement. This integrated web-based platform combines automated text annotation, multi-engine OCSR, and direct submission capabilities to the COCONUT database. MARCUS employs a fine-tuned GPT-4 model to extract chemical entities and utilises a Human-in-the-loop ensemble approach integrating DECIMER, MolNexTR, and MolScribe for structure recognition. The platform aims to streamline the data extraction workflow from PDF upload to database submission, significantly reducing curation time. MARCUS bridges the gap between unstructured chemical literature and machine-actionable databases, enabling FAIR data principles and facilitating AI-driven chemical discovery. Through open-source code, accessible models, and comprehensive documentation, the web application enhances accessibility and promotes community-driven development. This approach facilitates unrestricted use and encourages the collaborative advancement of automated chemical literature curation tools.</abstract>
    <parentTitle language="eng">Digital Discovery</parentTitle>
    <identifier type="doi">10.1039/D5DD00313J</identifier>
    <identifier type="urn">urn:nbn:de:hbz:1010-opus4-49019</identifier>
    <enrichment key="opus.source">publish</enrichment>
    <enrichment key="opus.doi.autoCreate">false</enrichment>
    <enrichment key="opus.urn.autoCreate">true</enrichment>
    <licence>Creative Commons - Namensnennung</licence>
    <author>Kohulan Rajan</author>
    <author>Viktor Weißenborn</author>
    <author>Laurin Lederer</author>
    <author>Christoph Steinbeck</author>
    <author>Achim Zielesny</author>
    <collection role="open_access" number="">open_access</collection>
    <collection role="institutes" number="">Institut für biologische und chemische Informatik</collection>
    <thesisPublisher>Westfälische Hochschule Gelsenkirchen Bocholt Recklinghausen</thesisPublisher>
    <file>https://opus4.kobv.de/opus4-w-hs/files/4901/Rajan_MARCUS_2025.pdf</file>
  </doc>
  <doc>
    <id>4831</id>
    <completedYear>2025</completedYear>
    <publishedYear>2025</publishedYear>
    <thesisYearAccepted/>
    <language>eng</language>
    <pageFirst/>
    <pageLast/>
    <pageNumber/>
    <edition/>
    <issue/>
    <volume/>
    <type>preprint</type>
    <publisherName/>
    <publisherPlace/>
    <creatingCorporation/>
    <contributingCorporation/>
    <belongsToBibliography>0</belongsToBibliography>
    <completedDate>2025-07-09</completedDate>
    <publishedDate>2025-07-09</publishedDate>
    <thesisDateAccepted>--</thesisDateAccepted>
    <title language="eng">MARCUS: Molecular Annotation and Recognition for Curating Unravelled Structures</title>
    <abstract language="eng">The exponential growth of chemical literature necessitates the development of automated tools for extracting and curating molecular information from unstructured scientific publications into open-access chemical databases. Current optical chemical structure recognition (OCSR) and named entity recognition solutions operate in isolation, which limits their scalability for comprehensive literature curation. Here we present MARCUS (Molecular Annotation and Recognition for Curating Unravelled Structures), a tool to aid curators in performing literature curation in the field of natural products. This integrated web-based platform combines automated text annotation, multi-engine OCSR, and direct submission capabilities to the COCONUT database. MARCUS employs a fine-tuned GPT-4 model to extract chemical entities and utilises an ensemble approach integrating DECIMER, MolNexTR, and MolScribe for structure recognition. The platform aims to streamline the data extraction workflow from PDF upload to database submission, significantly reducing curation time. MARCUS bridges the gap between unstructured chemical literature and machine-actionable databases, enabling FAIR data principles and facilitating AI-driven chemical discovery. Through open-source code, accessible models, and comprehensive documentation, the web application enhances accessibility and promotes community-driven development. This approach facilitates unrestricted use and encourages the collaborative advancement of automated chemical literature curation tools. We dedicate MARCUS to Dr Marcus Ennis, the longest-serving curator of the ChEBI database, on the occasion of his 75th birthday.</abstract>
    <parentTitle language="deu">ChemRxiv</parentTitle>
    <identifier type="doi">10.26434/chemrxiv-2025-9p1q1</identifier>
    <identifier type="urn">urn:nbn:de:hbz:1010-opus4-48310</identifier>
    <enrichment key="opus.source">publish</enrichment>
    <licence>© Alle Rechte vorbehalten</licence>
    <author>Achim Zielesny</author>
    <author>Viktor Weißenborn</author>
    <author>Laurin Lederer</author>
    <author>Christoph Steinbeck</author>
    <author>Kohulan Rajan</author>
    <collection role="open_access" number="">open_access</collection>
    <collection role="institutes" number="">Institut für biologische und chemische Informatik</collection>
    <thesisPublisher>Westfälische Hochschule Gelsenkirchen Bocholt Recklinghausen</thesisPublisher>
    <file>https://opus4.kobv.de/opus4-w-hs/files/4831/MARCUS_Zielesny.pdf</file>
  </doc>
  <doc>
    <id>4200</id>
    <completedYear>2023</completedYear>
    <publishedYear>2023</publishedYear>
    <thesisYearAccepted/>
    <language>eng</language>
    <pageFirst/>
    <pageLast/>
    <pageNumber>14</pageNumber>
    <edition/>
    <issue>15</issue>
    <volume>2023</volume>
    <type>article</type>
    <publisherName>Springer Nature</publisherName>
    <publisherPlace/>
    <creatingCorporation/>
    <contributingCorporation/>
    <belongsToBibliography>0</belongsToBibliography>
    <completedDate>2023-01-02</completedDate>
    <publishedDate>2023-01-02</publishedDate>
    <thesisDateAccepted>--</thesisDateAccepted>
    <title language="eng">MORTAR: a rich client application for in silico molecule fragmentation</title>
    <abstract language="eng">Developing and implementing computational algorithms for the extraction of specific substructures from molecular graphs (in silico molecule fragmentation) is an iterative process. It involves repeated sequences of implementing a rule set, applying it to relevant structural data, checking the results, and adjusting the rules. This requires a computational workflow with data import, fragmentation algorithm integration, and result visualisation. The described workflow is normally unavailable for a new algorithm and must be set up individually. This work presents an open Java rich client Graphical User Interface (GUI) application to support the development of new in silico molecule fragmentation algorithms and make them readily available upon release. The MORTAR (MOlecule fRagmenTAtion fRamework) application visualises fragmentation results of a set of molecules in various ways and provides basic analysis features. Fragmentation algorithms can be integrated and developed within MORTAR by using a specific wrapper class. In addition, fragmentation pipelines with any combination of the available fragmentation methods can be executed. Upon release, three fragmentation algorithms are already integrated: ErtlFunctionalGroupsFinder, Sugar Removal Utility, and Scaffold Generator. These algorithms, as well as all cheminformatics functionalities in MORTAR, are implemented based on the Chemistry Development Kit (CDK).</abstract>
    <parentTitle language="eng">Journal of Cheminformatics</parentTitle>
    <identifier type="doi">https://doi.org/10.1186/s13321-022-00674-9</identifier>
    <identifier type="urn">urn:nbn:de:hbz:1010-opus4-42005</identifier>
    <identifier type="issn">1758-2946</identifier>
    <licence>Creative Commons - Namensnennung</licence>
    <author>Felix Bänsch</author>
    <author>Jonas Schaub</author>
    <author>Betül Sevindik</author>
    <author>Samuel Behr</author>
    <author>Julian Zander</author>
    <author>Christoph Steinbeck</author>
    <author>Achim Zielesny</author>
    <subject>
      <language>eng</language>
      <type>uncontrolled</type>
      <value>Chemistry Development Kit</value>
    </subject>
    <subject>
      <language>eng</language>
      <type>uncontrolled</type>
      <value>CDK</value>
    </subject>
    <subject>
      <language>eng</language>
      <type>uncontrolled</type>
      <value>Molecule fragmentation</value>
    </subject>
    <subject>
      <language>eng</language>
      <type>uncontrolled</type>
      <value>In silico fragmentation</value>
    </subject>
    <subject>
      <language>eng</language>
      <type>uncontrolled</type>
      <value>Scaffolds</value>
    </subject>
    <subject>
      <language>eng</language>
      <type>uncontrolled</type>
      <value>Functional groups</value>
    </subject>
    <subject>
      <language>eng</language>
      <type>uncontrolled</type>
      <value>Glycosidic moieties</value>
    </subject>
    <subject>
      <language>eng</language>
      <type>uncontrolled</type>
      <value>Rich client</value>
    </subject>
    <subject>
      <language>eng</language>
      <type>uncontrolled</type>
      <value>Graphical user interface</value>
    </subject>
    <subject>
      <language>eng</language>
      <type>uncontrolled</type>
      <value>GUI</value>
    </subject>
    <collection role="open_access" number="">open_access</collection>
    <collection role="institutes" number="">Institut für biologische und chemische Informatik</collection>
    <thesisPublisher>Westfälische Hochschule Gelsenkirchen Bocholt Recklinghausen</thesisPublisher>
    <file>https://opus4.kobv.de/opus4-w-hs/files/4200/Baensch_MORTAR_2023.pdf</file>
  </doc>
</export-example>
