Refine
Document Type
- Article (15)
- Preprint (7)
- Conference Proceeding (5)
- Doctoral Thesis (1)
Language
- English (28)
Is part of the Bibliography
- no (28)
Keywords
- Deep Learning (3)
- OCSR (3)
- Transformer (3)
- Artificial Intelligence (2)
- DECIMER (2)
- Deep learning (2)
- OCSR, Optical Chemical Structure Recognition (2)
- AI (1)
- CDK (1)
- Chemical image depiction (1)
Institute
Advancements in hand-drawn chemical structure recognition through an enhanced DECIMER architecture
(2024)
Accurate recognition of hand-drawn chemical structures is crucial for digitising hand-written chemical information in traditional laboratory notebooks or facilitating stylus-based structure entry on tablets or smartphones. However, the inherent variability in hand-drawn structures poses challenges for existing Optical Chemical Structure Recognition (OCSR) software. To address this, we present an enhanced Deep lEarning for Chemical ImagE Recognition (DECIMER) architecture that leverages a combination of Convolutional Neural Networks (CNNs) and Transformers to improve the recognition of hand-drawn chemical structures. The model incorporates an EfficientNetV2 CNN encoder that extracts features from hand-drawn images, followed by a Transformer decoder that converts the extracted features into Simplified Molecular Input Line Entry System (SMILES) strings. Our models were trained using synthetic hand-drawn images generated by RanDepict, a tool for depicting chemical structures with different style elements. A benchmark was performed using a real-world dataset of hand-drawn chemical structures to evaluate the model's performance. The results indicate that our improved DECIMER architecture exhibits a significantly enhanced recognition accuracy compared to other approaches.
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.
Advancements in Hand-Drawn Chemical Structure Recognition through an Enhanced DECIMER Architecture
(2024)
Accurate recognition of hand-drawn chemical structures is crucial for digitising hand-written chemical information found in traditional laboratory notebooks or for facilitating stylus-based structure entry on tablets or smartphones. However, the inherent variability in hand-drawn structures poses challenges for existing Optical Chemical Structure Recognition (OCSR) software. To address this, we present an enhanced Deep lEarning for Chemical ImagE Recognition (DECIMER) architecture that leverages a combination of Convolutional Neural Networks (CNNs) and Transformers to improve the recognition of hand-drawn chemical structures. The model incorporates an EfficientNetV2 CNN encoder that extracts features from hand-drawn images, followed by a Transformer decoder that converts the extracted features into Simplified Molecular Input Line Entry System (SMILES) strings. Our models were trained using synthetic hand-drawn images generated by RanDepict, a tool for depicting chemical structures with different style elements. To evaluate the model's performance, a benchmark was performed using a real-world dataset of hand-drawn chemical structures. The results indicate that our improved DECIMER architecture exhibits a significantly enhanced recognition accuracy compared to other approaches.
Naming chemical compounds systematically is a complex task governed by a set of rules established by the International Union of Pure and Applied Chemistry (IUPAC). These rules are universal and widely accepted by chemists worldwide, but their complexity makes it challenging for individuals to consistently apply them accurately. A translation method can be employed to address this challenge. Accurate translation of chemical compounds from SMILES notation into their corresponding IUPAC names is crucial, as it can significantly streamline the laborious process of naming chemical structures. Here, we present STOUT (SMILES-TO-IUPAC-name translator) V2.0, which addresses this challenge by introducing a transformer-based model that translates string representations of chemical structures into IUPAC names. Trained on a dataset of nearly 1 billion SMILES strings and their corresponding IUPAC names, STOUT V2.0 demonstrates exceptional accuracy in generating IUPAC names, even for complex chemical structures. The model's ability to capture intricate patterns and relationships within chemical structures enables it to generate precise and standardised IUPAC names. Deterministic algorithms for systematically naming chemical structures have been available for many years. Also, this work has only been possible through an academic license for OpenEye’s Lexichem software.
The number of publications describing chemical structures has increased steadily over the last decades. However, the majority of published chemical information is currently not available in machine-readable form in public databases. It remains a challenge to automate the process of information extraction in a way that requires less manual intervention - especially the mining of chemical structure depictions. As an open-source platform that leverages recent advancements in deep learning, computer vision, and natural language processing, DECIMER.ai (Deep lEarning for Chemical IMagE Recognition) strives to automatically segment, classify, and translate chemical structure depictions from the printed literature. The segmentation and classification tools are the only openly available packages of their kind, and the optical chemical structure recognition (OCSR) core application yields outstanding performance on all benchmark datasets. The source code, the trained models and the datasets developed in this work have been published under permissive licences. An instance of the DECIMER web application is available at https://decimer.ai.
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.
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.
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.

