@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} } @inproceedings{RajanZielesnySteinbeck2024, author = {Rajan, Kohulan and Zielesny, Achim and Steinbeck, Christoph}, title = {Also in Chemistry, Deep Learning Models Love Really Big Data}, series = {Beilstein Bozen Symposium 2024 - AI in Chemistry and Biology: Evolution or Revolution?, R{\"u}desheim, Germany}, booktitle = {Beilstein Bozen Symposium 2024 - AI in Chemistry and Biology: Evolution or Revolution?, R{\"u}desheim, Germany}, year = {2024}, abstract = {Inspired by the super-human performance of deep learning models in playing the game of Go after being presented with virtually unlimited training data, we looked into areas in chemistry where similar situations could be achieved. Encountering large amounts of training data in chemistry is still rare, so we turned to two areas where realistic training data can be fabricated in large quantities, namely a) the recognition of machine-readable structures from images of chemical diagrams and b) the conversion of IUPAC(-like) names into structures and vice versa. In this talk, we outline the challenges, technical implementation and results of this study. Optical Chemical Structure Recognition (OCSR): Vast amounts of chemical information remain hidden in the primary literature and have yet to be curated into open-access databases. To automate the process of extracting chemical structures from scientific papers, we developed the DECIMER.ai project. This open-source platform provides an integrated solution for identifying, segmenting, and recognising chemical structure depictions in scientific literature. DECIMER.ai comprises three main components: DECIMER-Segmentation, which utilises a Mask-RCNN model to detect and segment images of chemical structure depictions; DECIMER-Image Classifier EfficientNet-based classification model identifies which images contain chemical structures and DECIMER-Image Transformer which acts as an OCSR engine which combines an encoder-decoder model to convert the segmented chemical structure images into machine-readable formats, like the SMILES string. DECIMER.ai is data-driven, relying solely on the training data to make accurate predictions without hand-coded rules or assumptions. The latest model was trained with 127 million structures and 483 million depictions (4 different per structure) on Google TPU-V4 VMs Name to Structure Conversion: The conversion of structures to IUPAC(-like) or systematic names has been solved algorithmically or rule-based in satisfying ways. This fact, on the other side, provided us with an opportunity to generate a name-structure training pair at a very large scale to train a proof-of-concept transformer network and evaluate its performance. In this work, the largest model was trained using almost one billion SMILES strings. The Lexichem software utility from OpenEye was employed to generate the IUPAC names used in the training process. STOUT V2 was trained on Google TPU-V4 VMs. The model's accuracy was validated through one-to-one string matching, BLEU scores, and Tanimoto similarity calculations. To further verify the model's reliability, every IUPAC name generated by STOUT V2 was analysed for accuracy and retranslated using OPSIN, a widely used open-source software for converting IUPAC names to SMILES. This additional validation step confirmed the high fidelity of STOUT V2's translations.}, language = {en} } @article{RajanZielesnySteinbeck2021, author = {Rajan, Kohulan and Zielesny, Achim and Steinbeck, Christoph}, title = {DECIMER 1.0: deep learning for chemical image recognition using transformers}, series = {Journal of Cheminformatics}, volume = {13}, journal = {Journal of Cheminformatics}, issn = {1758-2946}, doi = {10.1186/s13321-021-00538-8}, pages = {Artikelnr. 61}, year = {2021}, language = {en} } @unpublished{RajanSteinbeckZielesny2021, author = {Rajan, Kohulan and Steinbeck, Christoph and Zielesny, Achim}, title = {Performance of chemical structure string representations for chemical image recognition using transformers}, doi = {10.33774/chemrxiv-2021-7c9wf-v2}, pages = {19}, year = {2021}, language = {en} } @inproceedings{RajanZielesnySteinbeck2024, author = {Rajan, Kohulan and Zielesny, Achim and Steinbeck, Christoph}, title = {The DECIMER.ai Project}, series = {Workshop Computer Vision for Science (CV4Science) at the IEEE / CVF Computer Vision and Pattern Recognition Conference (CVPR), June 17, 2024, Seattle, USA}, booktitle = {Workshop Computer Vision for Science (CV4Science) at the IEEE / CVF Computer Vision and Pattern Recognition Conference (CVPR), June 17, 2024, Seattle, USA}, year = {2024}, abstract = {Over the past few decades, the number of publications describing chemical structures and their metadata has increased significantly. Chemists have published the majority of this information as bitmap images along with other important information as human-readable text in printed literature and have never been retained and preserved in publicly available databases as machine-readable formats. Manually extracting such data from printed literature is error-prone, time-consuming, and tedious. The recognition and translation of images of chemical structures from printed literature into machine-readable format is known as Optical Chemical Structure Recognition (OCSR). In recent years, deep-learning-based OCSR tools have become increasingly popular. While many of these tools claim to be highly accurate, they are either unavailable to the public or proprietary. Meanwhile, the available open-source tools are significantly time-consuming to set up. Furthermore, none of these offers an end-to-end workflow capable of detecting chemical structures, segmenting them, classifying them, and translating them into machine-readable formats. To address this issue, we present the DECIMER.ai project, an open-source platform that provides an integrated solution for identifying, segmenting, and recognizing chemical structure depictions within the scientific literature. DECIMER.ai comprises three main components: DECIMER-Segmentation, which utilizes a Mask-RCNN model to detect and segment images of chemical structure depictions; DECIMER-Image Classifier EfficientNet-based classification model identifies which images contain chemical structures and DECIMER-Image Transformer which acts as an OCSR engine which combines an encoder-decoder model to convert the segmented chemical structure images into machine-readable formats, like the SMILES string. A key strength of DECIMER.ai is that its algorithms are data-driven, relying solely on the training data to make accurate predictions without any hand-coded rules or assumptions. By offering this comprehensive, open-source, and transparent pipeline, DECIMER.ai enables automated extraction and representation of chemical data from unstructured publications, facilitating applications in chemoinformatics and drug discovery.}, language = {en} } @inproceedings{ZielesnyRajanSteinbeck2025, author = {Zielesny, Achim and Rajan, Kohulan and Steinbeck, Christoph}, title = {Comparative Analysis of Chemical Structure String Representations for Neural Machine Translation}, series = {Artificial Neural Networks and Machine Learning. ICANN 2025 International Workshops and Special sessions : 34th International Conference on Artificial Neural Networks, Kaunas, Lithuania, September 9-12, 2025, Proceedings, Part V. Lecture Notes in Computer Science (LNCS), vol 16072}, volume = {2025}, booktitle = {Artificial Neural Networks and Machine Learning. ICANN 2025 International Workshops and Special sessions : 34th International Conference on Artificial Neural Networks, Kaunas, Lithuania, September 9-12, 2025, Proceedings, Part V. Lecture Notes in Computer Science (LNCS), vol 16072}, publisher = {Springer}, doi = {10.1007/978-3-032-04552-2_2}, pages = {8 -- 16}, year = {2025}, abstract = {In this work, we present a comparative analysis of SMILES, DeepSMILES, and SELFIES string representations for chemical struc-tures in neural machine translation tasks in cheminformatics. Using transformer-based models, we systematically evaluated their effective-ness in translating between these representations and the correspond-ing linguistic IUPAC nomenclature. The experimental results demon-strate comparable performance for all three string representations, with SMILES achieving a marginally higher accuracy (99.30\% with stereo-chemical information, 99.21\% without) compared to its alternatives. In scaling experiments with 1, 10, and 50 million compounds, the perfor-mance differences remained small, though the performance gap narrowed with larger datasets. These findings suggest that researchers can con-fidently continue using SMILES for neural machine translation tasks with transformers, which benefits from their extensive support in exist-ing chemical libraries, tools, and databases, rather than adopting newer representations. This work has a significant impact on developing more efficient chemical language models in drug discovery, material science, and chemical database curation.}, language = {en} }