A review of optical chemical structure recognition tools
Ontology highlight
ABSTRACT:
SUBMITTER: Rajan K
PROVIDER: S-EPMC7541205 | biostudies-literature | 2020 Jan
REPOSITORIES: biostudies-literature
Similar Datasets
Project description: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 .
| S-EPMC10439916 | biostudies-literature
Project description:Molecular structures are commonly depicted in 2D printed forms in scientific documents such as journal papers and patents. However, these 2D depictions are not machine readable. Due to a backlog of decades and an increasing amount of printed literatures, there is a high demand for translating printed depictions into machine-readable formats, which is known as Optical Chemical Structure Recognition (OCSR). Most OCSR systems developed over the last three decades use a rule-based approach, which vectorizes the depiction based on the interpretation of vectors and nodes as bonds and atoms. Here, we present a practical software called MolMiner, which is primarily built using deep neural networks originally developed for semantic segmentation and object detection to recognize atom and bond elements from documents. These recognized elements can be easily connected as a molecular graph with a distance-based construction algorithm. MolMiner gave state-of-the-art performance on four benchmark data sets and a self-collected external data set from scientific papers. As MolMiner performed similarly well in real-world OCSR tasks with a user-friendly interface, it is a useful and valuable tool for daily applications. The free download links of Mac and Windows versions are available at https://github.com/iipharma/pharmamind-molminer.
| S-EPMC9710516 | biostudies-literature
Project description:A magnetic resonance light scattering (RLS) sensor based on the molecularly imprinted polymer (MIP) technique was developed for specific recognition of trace quantities of hepatitis A virus (HAV). Through a surface imprinting technique, the virus-magnetic-MIPs (virus-MMIPs) were prepared as the specific identification element, which was based on the effective synthesis of biomimetic polydopamine (PDA) inspired by mussels on the surface of Fe3O4 magnetic nanoparticles. The preparation process of the virus-magnetic-MIPs was simple and rapid under an applied magnetic field. The surface of the magnetic-MIP captured viruses through specific recognition in water, which caused changes to the particle size and shape, and subsequently resulted in changes in the intensity of the RLS. The sensor was applied to determine the amount of HAV in the linear concentration range of 0.02-1.40 nmol L-1, with a low detection limit of 6.2 pmol L-1, and it was successfully applied for the immediate detection of added HAV from a 2000-fold dilution of human serum. More importantly, the proposed strategy addressed the difficulty of virus-MIP detection in the elution process and it is rapid, easy, sensitive, and eco-friendly.
| S-EPMC9086391 | biostudies-literature
Project description:The rapid increase in the flow rate of published digital information in all disciplines has resulted in a pressing need for techniques that can simplify the use of this information. The chemistry literature is very rich with information about chemical entities. Extracting molecules and their related properties and activities from the scientific literature to "text mine" these extracted data and determine contextual relationships helps research scientists, particularly those in drug development. One of the most important challenges in chemical text mining is the recognition of chemical entities mentioned in the texts. In this review, the authors briefly introduce the fundamental concepts of chemical literature mining, the textual contents of chemical documents, and the methods of naming chemicals in documents. We sketch out dictionary-based, rule-based and machine learning, as well as hybrid chemical named entity recognition approaches with their applied solutions. We end with an outlook on the pros and cons of these approaches and the types of chemical entities extracted.
| S-EPMC4022577 | biostudies-literature
Project description:Descriptor generation methods using latent representations of encoder-decoder (ED) models with SMILES as input are useful because of the continuity of descriptor and restorability to the structure. However, it is not clear how the structure is recognized in the learning progress of ED models. In this work, we created ED models of various learning progress and investigated the relationship between structural information and learning progress. We showed that compound substructures were learned early in ED models by monitoring the accuracy of downstream tasks and input-output substructure similarity using substructure-based descriptors, which suggests that existing evaluation methods based on the accuracy of downstream tasks may not be sensitive enough to evaluate the performance of ED models with SMILES as descriptor generation methods. On the other hand, we showed that structure restoration was time-consuming, and in particular, insufficient learning led to the estimation of a larger structure than the actual one. It can be inferred that determining the endpoint of the structure is a difficult task for the model. To our knowledge, this is the first study to link the learning progress of SMILES by ED model to chemical structures for a wide range of chemicals.
| S-EPMC10100163 | biostudies-literature
Project description:Protein aggregation into highly ordered, regularly repeated cross-β sheet structures called amyloid fibrils is closely associated to human disorders such as neurodegenerative diseases including Alzheimer's and Parkinson's diseases, or systemic diseases like type II diabetes. Yet, in some cases, such as the HET-s prion, amyloids have biological functions. High-resolution structures of amyloids fibrils from cryo-electron microscopy have very recently highlighted their ultrastructural organization and polymorphisms. However, the molecular mechanisms and the role of co-factors (posttranslational modifications, non-proteinaceous components and other proteins) acting on the fibril formation are still poorly understood. Whether amyloid fibrils play a toxic or protective role in the pathogenesis of neurodegenerative diseases remains to be elucidated. Furthermore, such aberrant protein-protein interactions challenge the search of small-molecule drugs or immunotherapy approaches targeting amyloid formation. In this review, we describe how chemical biology tools contribute to new insights on the mode of action of amyloidogenic proteins and peptides, defining their structural signature and aggregation pathways by capturing their molecular details and conformational heterogeneity. Challenging the imagination of scientists, this constantly expanding field provides crucial tools to unravel mechanistic detail of amyloid formation such as semisynthetic proteins and small-molecule sensors of conformational changes and/or aggregation. Protein engineering methods and bioorthogonal chemistry for the introduction of protein chemical modifications are additional fruitful strategies to tackle the challenge of understanding amyloid formation.
| S-EPMC9133342 | biostudies-literature
Project description:Intercellular signaling dynamics critically influence the functional roles that the signals can play. Small lipids are synthesized and released from neurons, acting as intercellular signals in regulating neurotransmitter release, modulating ion channels on target cells, and modifying synaptic plasticity. The repertoire of biological effects of lipids such as endocannabinoids (eCBs) is rapidly expanding, yet lipid signaling dynamics have not been studied. The eCB system constitutes a powerful tool for bioassaying the dynamics of lipid signaling. The eCBs are synthesized in, and released from, postsynaptic somatodendritic domains that are readily accessible to whole-cell patch electrodes. The dramatic effects of these lipid signals are detected electrophysiologically as CB1-dependent alterations in conventional synaptic transmission, which therefore serve as a sensitive reporter of eCB actions. We used electrophysiological recording, photolytic release of caged glutamate and a newly developed caged AEA (anandamide), together with rapid [Ca2+]i measurements, to investigate the dynamics of retrograde eCB signaling between CA1 pyramidal cells and GABAergic synapses in rat hippocampus in vitro. We show that, at 22 degrees C, eCB synthesis and release must occur within 75-190 ms after the initiating stimulus, almost an order of magnitude faster than previously thought. At 37 degrees C, the time could be < 50 ms. Activation of CB1 and downstream processes constitute a significant fraction of the total delay and are identified as major rate-limiting steps in retrograde signaling. Our findings imply that lipid messenger dynamics are comparable with those of metabotropic neurotransmitters and can modulate neuronal interactions on a similarly fast time scale.
| S-EPMC6725697 | biostudies-literature
Project description:K(+) channels are revered for their universal action of suppressing electrical activity in nerve and muscle, as well as regulating salt and water transport in epithelial tissues involved in metabolism and digestion. These multisubunit membrane-embedded proteins carry out their physiological chore, selectively allowing the passage of potassium across the membrane, in response to changes in membrane voltage and ligand concentration. Elucidating the diverse gating properties of K(+) channels is of great biological interest since their molecular motions provide insight into how these structurally similar proteins function in a wide variety of tissues. Armed with patch clamps, chart recorders, and now high-resolution structures, electrophysiologists have been dipping into the top tray of the chemist's tool box: synthesizing cysteine-modifying agents and organic cations and grinding up insects, spiders, and other vermin to isolate natural products to poke, probe, and prod K(+) channels. Recently, there has been further cross-fertilization between chemists and K(+) channelologists, resulting in greater accessibility to more elaborate synthetic methodologies and screening approaches. In this review, we catalogue the evolution of chemical tools and approaches that have been utilized to elucidate the mechanistic underpinnings of K(+) channel biology.
| S-EPMC2629505 | biostudies-literature
Project description:Moving toward species-relevant chemical safety assessments and away from animal testing requires access to reliable data to develop and build confidence in new approaches. The Integrated Chemical Environment (ICE) provides tools and curated data centered around chemical safety assessment. This article describes updates to ICE, including improved accessibility and interpretability of in vitro data via mechanistic target mapping and enhanced interactive tools for in vitro to in vivo extrapolation (IVIVE). Mapping of in vitro assay targets to toxicity endpoints of regulatory importance uses literature-based mode-of-action information and controlled terminology from existing knowledge organization systems to support data interoperability with external resources. The most recent ICE update includes Tox21 high-throughput screening data curated using analytical chemistry data and assay-specific parameters to eliminate potential artifacts or unreliable activity. Also included are physicochemical/ADME parameters for over 800,000 chemicals predicted by quantitative structure-activity relationship models. These parameters are used by the new ICE IVIVE tool in combination with the U.S. Environmental Protection Agency's httk R package to estimate in vivo exposures corresponding to in vitro bioactivity concentrations from stored or user-defined assay data. These new ICE features allow users to explore the applications of an expanded data space and facilitate building confidence in non-animal approaches.
| S-EPMC7393692 | biostudies-literature
Project description:Unique features of Light-Oxygen-Voltage (LOV) proteins like relatively small size (~12-19 kDa), inherent modularity, highly-tunable photocycle and oxygen-independent fluorescence have lately been exploited for the generation of optical tools. Structures of LOV domains reported so far contain a flavin chromophore per protein molecule. Here we report two new findings on the short LOV protein W619_1-LOV from Pseudomonas putida. First, the apo-state crystal structure of W619_1-LOV at 2.5 Å resolution reveals conformational rearrangements in the secondary structure elements lining the chromophore pocket including elongation of the Fα helix, shortening of the Eα-Fα loop and partial unfolding of the Eα helix. Second, the apo W619_1-LOV protein binds both natural and structurally modified flavin chromophores. Remarkably different photophysical and photochemical properties of W619_1-LOV bound to 7-methyl-8-chloro-riboflavin (8-Cl-RF) and lumichrome imply application of these variants as novel optical tools as they offer advantages such as no adduct state formation, and a broader choice of wavelengths for in vitro studies.
| S-EPMC5314338 | biostudies-literature