@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} } @unpublished{BaenschDanielLanigetal.2024, author = {B{\"a}nsch, Felix and Daniel, Mirco and Lanig, Harald and Steinbeck, Christoph and Zielesny, Achim}, title = {An automated Calculation Pipeline for Differential Pair Interaction Energies with Molecular Force Fields using the Tinker Molecular Modeling Package}, doi = {10.26434/chemrxiv-2024-pkmxm}, year = {2024}, abstract = {An automated pipeline for comprehensive calculation of intermolecular interaction energies based on molecular force-fields using the Tinker molecular modelling package is presented. Starting with non-optimized chemically intuitive monomer structures, the pipeline allows the approximation of global minimum energy monomers and dimers, configuration sampling for various monomer-monomer distances, estimation of coordination numbers by molecular dynamics simulations, and the evaluation of differential pair interaction energies. The latter are used to derive Flory-Huggins parameters and isotropic particle-particle repulsions for Dissipative Particle Dynamics (DPD). The computational results for force fields MM3, MMFF94, OPLS-AA and AMOEBA09 are analyzed with Density Functional Theory (DFT) calculations and DPD simulations for a mixture of the non-ionic polyoxyethylene alkyl ether surfactant C10E4 with water to demonstrate the usefulness of the approach.}, language = {en} } @misc{Zielesny2023, author = {Zielesny, Achim}, title = {MFsim [Softwarecode, Version 2.6.0.0]}, year = {2023}, abstract = {MFsim - An open Java all-in-one rich-client simulation environment for mesoscopic simulation MFsim is an open Java all-in-one rich-client computing environment for mesoscopic simulation with Jdpd as its default simulation kernel for Molecular Fragment Dissipative Particle Dynamics (DPD). The environment integrates and supports the complete preparation-simulation-evaluation triad of a mesoscopic simulation task. Productive highlights are a SPICES molecular structure editor, a PDB-to-SPICES parser for particle-based peptide/protein representations, a support of polymer definitions, a compartment editor for complex simulation box start configurations, interactive and flexible simulation box views including analytics, simulation movie generation or animated diagrams. As an open project, MFsim enables customized extensions for different fields of research. MFsim uses several open libraries (see MFSimVersionHistory.txt for details and references below) and is published as open source under the GNU General Public License version 3 (see LICENSE). MFsim has been described in the scientific literature and used for DPD studies.}, 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} }