English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Like many scientific fields, new chemistry literature has grown at astaggering pace, with thousands of papers released every month. A large portionof chemistry literature focuses on new molecules and reactions betweenmolecules. Most vital information is conveyed through 2-D images of molecules,representing the underlying molecules or reactions described. In order toensure reproducible and machine-readable molecule representations, text-basedmolecule descriptors like SMILES and SELFIES were created. These text-basedmolecule representations provide molecule generation but are unfortunatelyrarely present in published literature. In the absence of molecule descriptors,the generation of molecule descriptors from the 2-D images present in theliterature is necessary to understand chemistry literature at scale. Successfulmethods such as Optical Structure Recognition Application (OSRA), andChemSchematicResolver are able to extract the locations of molecules structuresin chemistry papers and infer molecular descriptions and reactions. Whileeffective, existing systems expect chemists to correct outputs, making themunsuitable for unsupervised large-scale data mining. Leveraging the taskformulation of image captioning introduced by DECIMER, we introduce IMG2SMI, amodel which leverages Deep Residual Networks for image feature extraction andan encoder-decoder Transformer layers for molecule description generation.Unlike previous Neural Network-based systems, IMG2SMI builds around the task ofmolecule description generation, which enables IMG2SMI to outperform OSRA-basedsystems by 163% in molecule similarity prediction as measured by the molecularMACCS Fingerprint Tanimoto Similarity. Additionally, to facilitate furtherresearch on this task, we release a new molecule prediction dataset. including81 million molecules for molecule description generation

IMG2SMI: Translating Molecular Structure Images to Simplified Molecular-input Line-entry System