@unpublished{BrinkhausRajanZielesnyetal.2022, author = {Brinkhaus, Henning Otto and Rajan, Kohulan and Zielesny, Achim and Steinbeck, Christoph}, title = {RanDepict - Random Chemical Structure Depiction Generator}, series = {ChemRxiv}, journal = {ChemRxiv}, doi = {10.26434/chemrxiv-2022-t1kbb}, year = {2022}, abstract = {The development of deep learning-based optical chemical structure recognition (OCSR) systems has led to a need for datasets of chemical structure depictions. The diversity of the features in the training data is an important factor for the generation of deep learning systems that generalise well and are not overfit to a specific type of input. In the case of chemical structure depictions, these features are defined by the depiction parameters such as bond length, line thickness, label font style and many others. Here we present RanDepict, a toolkit for the creation of diverse sets of chemical structure depictions. The diversity of the image features is generated by making use of all available depiction parameters in the depiction functionalities of the CDK, RDKit, and Indigo. Furthermore, there is the option to enhance and augment the image with features such as curved arrows, chemical labels around the structure, or other kinds of distortions. Using depiction feature fingerprints, RanDepict ensures diversely picked image features. Here, the depiction and augmentation features are summarised in binary vectors and the MaxMin algorithm is used to pick diverse samples out of all valid options. By making all resources described herein publicly available, we hope to contribute to the development of deep learning-based OCSR systems.}, language = {en} } @article{BrinkhausZielesnySteinbecketal., author = {Brinkhaus, Henning Otto and Zielesny, Achim and Steinbeck, Christoph and Rajan, Kohulan}, title = {DECIMER—hand-drawn molecule images dataset}, series = {Journal of Cheminformatics}, volume = {14.2022}, journal = {Journal of Cheminformatics}, publisher = {BioMed Central}, address = {London}, issn = {1758-2946}, pages = {1 -- 5}, abstract = {The translation of images of chemical structures into machine-readable representations of the depicted molecules is known as optical chemical structure recognition (OCSR). There has been a lot of progress over the last three decades in this field, but the development of systems for the recognition of complex hand-drawn structure depictions is still at the beginning. Currently, there is no data for the systematic evaluation of OCSR methods on hand-drawn structures available. Here we present DECIMER — Hand-drawn molecule images, a standardised, openly available benchmark dataset of 5088 hand-drawn depictions of diversely picked chemical structures. Every structure depiction in the dataset is mapped to a machine-readable representation of the underlying molecule. The dataset is openly available and published under the CC-BY 4.0 licence which applies very few limitations. We hope that it will contribute to the further development of the field.}, language = {en} } @unpublished{BrinkhausZielesnySteinbecketal.2022, author = {Brinkhaus, Henning Otto and Zielesny, Achim and Steinbeck, Christoph and Rajan, Kohulan}, title = {DECIMER - Hand-drawn molecule images dataset}, year = {2022}, abstract = {The translation of images of chemical structures into machine-readable representations of the depicted molecules is known as optical chemical structure recognition (OCSR). There has been a lot of progress over the last three decades in this field, but the development of systems for the recognition of complex hand-drawn structure depictions is still at the beginning. Currently, there is no data for the systematic evaluation of OCSR methods on hand-drawn structures available. Here we present DECIMER - Hand-drawn molecule images, a standardised, openly available benchmark dataset of 5088 hand-drawn depictions of diversely picked chemical structures. Every structure depiction in the dataset is mapped to a machine-readable representation of the underlying molecule. The dataset is openly available and published under the CC-BY 4.0 licence which applies very few limitations. We hope that it will contribute to the further development of the field.}, language = {en} } @inproceedings{RajanBrinkhausZielesnyetal.2022, author = {Rajan, Kohulan and Brinkhaus, Henning Otto and Zielesny, Achim and Steinbeck, Christoph}, title = {The DECIMER (Deep lEarning for Chemical IMagE Recognition) project}, series = {17th German Conference on Cheminformatics}, booktitle = {17th German Conference on Cheminformatics}, publisher = {Gesellschaft Deutscher Chemiker}, address = {Frankfurt a.M.}, year = {2022}, language = {en} } @inproceedings{RajanBrinkhausZielesnyetal.2022, author = {Rajan, Kohulan and Brinkhaus, Henning Otto and Zielesny, Achim and Steinbeck, Christoph}, title = {The DECIMER (Deep lEarning for Chemical IMagE Recognition) project}, series = {12th International Conference on Chemical Structures}, booktitle = {12th International Conference on Chemical Structures}, year = {2022}, language = {en} } @article{BrinkhausRajanZielesnyetal., author = {Brinkhaus, Henning Otto and Rajan, Kohulan and Zielesny, Achim and Steinbeck, Christoph}, title = {RanDepict: Random chemical structure depiction generator}, series = {Journal of Cheminformatics}, volume = {14.2022}, journal = {Journal of Cheminformatics}, number = {31}, publisher = {BioMed Central}, address = {London}, issn = {1758-2946}, pages = {1 -- 7}, abstract = {The development of deep learning-based optical chemical structure recognition (OCSR) systems has led to a need for datasets of chemical structure depictions. The diversity of the features in the training data is an important factor for the generation of deep learning systems that generalise well and are not overfit to a specific type of input. In the case of chemical structure depictions, these features are defined by the depiction parameters such as bond length, line thickness, label font style and many others. Here we present RanDepict, a toolkit for the creation of diverse sets of chemical structure depictions. The diversity of the image features is generated by making use of all available depiction parameters in the depiction functionalities of the CDK, RDKit, and Indigo. Furthermore, there is the option to enhance and augment the image with features such as curved arrows, chemical labels around the structure, or other kinds of distortions. Using depiction feature fingerprints, RanDepict ensures diversely picked image features. Here, the depiction and augmentation features are summarised in binary vectors and the MaxMin algorithm is used to pick diverse samples out of all valid options. By making all resources described herein publicly available, we hope to contribute to the development of deep learning-based OCSR systems.}, language = {en} }