Matches in SemOpenAlex for { <https://semopenalex.org/work/W4206029367> ?p ?o ?g. }
- W4206029367 abstract "Abstract The rise of deep learning in various scientific and technology areas promotes the development of AI‐based tools for information retrieval. Optical recognition of organic structures is a key part of the automated extraction of chemical information. However, this is a challenging task because there is a large variety of representation styles. In this research, we present a Transformer‐based artificial neural network to convert images of organic structures to molecular structures. To train the model, we created a comprehensive data generator that stochastically simulates various drawing styles, functional groups, functional group placeholders (R‐groups), and visual contamination. We demonstrate that the Transformer‐based architecture can gather chemical insights from our generator with almost absolute confidence. That means that, with Transformer, one can fully concentrate on data simulation to build a good recognition model. A web demo of our optical recognition engine is available online at Syntelly platform, and the code for dataset generation is available on GitHub." @default.
- W4206029367 created "2022-01-25" @default.
- W4206029367 creator A5013131492 @default.
- W4206029367 creator A5014755535 @default.
- W4206029367 creator A5070076249 @default.
- W4206029367 creator A5083374905 @default.
- W4206029367 date "2022-01-01" @default.
- W4206029367 modified "2023-10-10" @default.
- W4206029367 title "Image2SMILES: Transformer‐Based Molecular Optical Recognition Engine**" @default.
- W4206029367 cites W1966456689 @default.
- W4206029367 cites W2021662118 @default.
- W4206029367 cites W2051554764 @default.
- W4206029367 cites W2111044246 @default.
- W4206029367 cites W2160592517 @default.
- W4206029367 cites W2518838044 @default.
- W4206029367 cites W2521093415 @default.
- W4206029367 cites W2524233233 @default.
- W4206029367 cites W2526273046 @default.
- W4206029367 cites W2793253687 @default.
- W4206029367 cites W2796108585 @default.
- W4206029367 cites W2913076747 @default.
- W4206029367 cites W2963734039 @default.
- W4206029367 cites W2967551275 @default.
- W4206029367 cites W2981644170 @default.
- W4206029367 cites W2982924835 @default.
- W4206029367 cites W2988348266 @default.
- W4206029367 cites W2988685436 @default.
- W4206029367 cites W2990104906 @default.
- W4206029367 cites W2992546470 @default.
- W4206029367 cites W3004733013 @default.
- W4206029367 cites W3007750971 @default.
- W4206029367 cites W3009466077 @default.
- W4206029367 cites W3030978062 @default.
- W4206029367 cites W3034849970 @default.
- W4206029367 cites W3045928028 @default.
- W4206029367 cites W3083046170 @default.
- W4206029367 cites W3088999551 @default.
- W4206029367 cites W3091262316 @default.
- W4206029367 cites W3092396754 @default.
- W4206029367 cites W3096614986 @default.
- W4206029367 cites W3097598035 @default.
- W4206029367 cites W3099559071 @default.
- W4206029367 cites W3103092523 @default.
- W4206029367 cites W3138074128 @default.
- W4206029367 cites W3159789740 @default.
- W4206029367 cites W3186326839 @default.
- W4206029367 cites W3195801735 @default.
- W4206029367 cites W3203895579 @default.
- W4206029367 doi "https://doi.org/10.1002/cmtd.202100069" @default.
- W4206029367 hasPublicationYear "2022" @default.
- W4206029367 type Work @default.
- W4206029367 citedByCount "11" @default.
- W4206029367 countsByYear W42060293672022 @default.
- W4206029367 countsByYear W42060293672023 @default.
- W4206029367 crossrefType "journal-article" @default.
- W4206029367 hasAuthorship W4206029367A5013131492 @default.
- W4206029367 hasAuthorship W4206029367A5014755535 @default.
- W4206029367 hasAuthorship W4206029367A5070076249 @default.
- W4206029367 hasAuthorship W4206029367A5083374905 @default.
- W4206029367 hasConcept C108583219 @default.
- W4206029367 hasConcept C116409475 @default.
- W4206029367 hasConcept C119599485 @default.
- W4206029367 hasConcept C119857082 @default.
- W4206029367 hasConcept C123657996 @default.
- W4206029367 hasConcept C127413603 @default.
- W4206029367 hasConcept C142362112 @default.
- W4206029367 hasConcept C153180895 @default.
- W4206029367 hasConcept C153349607 @default.
- W4206029367 hasConcept C154945302 @default.
- W4206029367 hasConcept C165801399 @default.
- W4206029367 hasConcept C41008148 @default.
- W4206029367 hasConcept C50644808 @default.
- W4206029367 hasConcept C66322947 @default.
- W4206029367 hasConceptScore W4206029367C108583219 @default.
- W4206029367 hasConceptScore W4206029367C116409475 @default.
- W4206029367 hasConceptScore W4206029367C119599485 @default.
- W4206029367 hasConceptScore W4206029367C119857082 @default.
- W4206029367 hasConceptScore W4206029367C123657996 @default.
- W4206029367 hasConceptScore W4206029367C127413603 @default.
- W4206029367 hasConceptScore W4206029367C142362112 @default.
- W4206029367 hasConceptScore W4206029367C153180895 @default.
- W4206029367 hasConceptScore W4206029367C153349607 @default.
- W4206029367 hasConceptScore W4206029367C154945302 @default.
- W4206029367 hasConceptScore W4206029367C165801399 @default.
- W4206029367 hasConceptScore W4206029367C41008148 @default.
- W4206029367 hasConceptScore W4206029367C50644808 @default.
- W4206029367 hasConceptScore W4206029367C66322947 @default.
- W4206029367 hasIssue "1" @default.
- W4206029367 hasLocation W42060293671 @default.
- W4206029367 hasOpenAccess W4206029367 @default.
- W4206029367 hasPrimaryLocation W42060293671 @default.
- W4206029367 hasRelatedWork W2588198209 @default.
- W4206029367 hasRelatedWork W2611989081 @default.
- W4206029367 hasRelatedWork W2731899572 @default.
- W4206029367 hasRelatedWork W3215138031 @default.
- W4206029367 hasRelatedWork W4230611425 @default.
- W4206029367 hasRelatedWork W4294635752 @default.
- W4206029367 hasRelatedWork W4304166257 @default.
- W4206029367 hasRelatedWork W4327774331 @default.
- W4206029367 hasRelatedWork W4375867731 @default.