Matches in SemOpenAlex for { <https://semopenalex.org/work/W3181403764> ?p ?o ?g. }
- W3181403764 endingPage "3284" @default.
- W3181403764 startingPage "3273" @default.
- W3181403764 abstract "The central challenge in automated synthesis planning is to be able to generate and predict outcomes of a diverse set of chemical reactions. In particular, in many cases, the most likely synthesis pathway cannot be applied due to additional constraints, which requires proposing alternative chemical reactions. With this in mind, we present Molecule Edit Graph Attention Network (MEGAN), an end-to-end encoder–decoder neural model. MEGAN is inspired by models that express a chemical reaction as a sequence of graph edits, akin to the arrow pushing formalism. We extend this model to retrosynthesis prediction (predicting substrates given the product of a chemical reaction) and scale it up to large data sets. We argue that representing the reaction as a sequence of edits enables MEGAN to efficiently explore the space of plausible chemical reactions, maintaining the flexibility of modeling the reaction in an end-to-end fashion and achieving state-of-the-art accuracy in standard benchmarks. Code and trained models are made available online at https://github.com/molecule-one/megan." @default.
- W3181403764 created "2021-07-19" @default.
- W3181403764 creator A5002193139 @default.
- W3181403764 creator A5005328526 @default.
- W3181403764 creator A5024552077 @default.
- W3181403764 creator A5032381726 @default.
- W3181403764 creator A5040654786 @default.
- W3181403764 creator A5044654291 @default.
- W3181403764 creator A5074000331 @default.
- W3181403764 creator A5087173640 @default.
- W3181403764 date "2021-07-12" @default.
- W3181403764 modified "2023-10-02" @default.
- W3181403764 title "Molecule Edit Graph Attention Network: Modeling Chemical Reactions as Sequences of Graph Edits" @default.
- W3181403764 cites W1975147762 @default.
- W3181403764 cites W1997974358 @default.
- W3181403764 cites W2014731568 @default.
- W3181403764 cites W2027611895 @default.
- W3181403764 cites W2046747992 @default.
- W3181403764 cites W2328708083 @default.
- W3181403764 cites W2538573120 @default.
- W3181403764 cites W2551217916 @default.
- W3181403764 cites W2558057290 @default.
- W3181403764 cites W2578240541 @default.
- W3181403764 cites W2580919858 @default.
- W3181403764 cites W2606363443 @default.
- W3181403764 cites W2610148085 @default.
- W3181403764 cites W2621742623 @default.
- W3181403764 cites W2747592475 @default.
- W3181403764 cites W2769423117 @default.
- W3181403764 cites W2769756736 @default.
- W3181403764 cites W2789366878 @default.
- W3181403764 cites W2789913372 @default.
- W3181403764 cites W2799620402 @default.
- W3181403764 cites W2806816322 @default.
- W3181403764 cites W2910734083 @default.
- W3181403764 cites W2950377709 @default.
- W3181403764 cites W2962814079 @default.
- W3181403764 cites W2963396480 @default.
- W3181403764 cites W2963684875 @default.
- W3181403764 cites W2970764640 @default.
- W3181403764 cites W2972608805 @default.
- W3181403764 cites W2979588939 @default.
- W3181403764 cites W2985694911 @default.
- W3181403764 cites W2991279511 @default.
- W3181403764 cites W2994678679 @default.
- W3181403764 cites W3009202547 @default.
- W3181403764 cites W3010145447 @default.
- W3181403764 cites W3014154196 @default.
- W3181403764 cites W3014689923 @default.
- W3181403764 cites W3036578548 @default.
- W3181403764 cites W3043969542 @default.
- W3181403764 cites W3087655841 @default.
- W3181403764 cites W3088999551 @default.
- W3181403764 cites W3094771832 @default.
- W3181403764 cites W3098269892 @default.
- W3181403764 cites W3100545487 @default.
- W3181403764 cites W3100751385 @default.
- W3181403764 cites W3102693939 @default.
- W3181403764 cites W3103092523 @default.
- W3181403764 cites W3114339437 @default.
- W3181403764 cites W3116434238 @default.
- W3181403764 cites W3117879109 @default.
- W3181403764 cites W3123775255 @default.
- W3181403764 cites W3135130381 @default.
- W3181403764 cites W3154275519 @default.
- W3181403764 cites W4231645939 @default.
- W3181403764 cites W4232909485 @default.
- W3181403764 cites W4233035680 @default.
- W3181403764 cites W4285670373 @default.
- W3181403764 doi "https://doi.org/10.1021/acs.jcim.1c00537" @default.
- W3181403764 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/34251814" @default.
- W3181403764 hasPublicationYear "2021" @default.
- W3181403764 type Work @default.
- W3181403764 sameAs 3181403764 @default.
- W3181403764 citedByCount "36" @default.
- W3181403764 countsByYear W31814037642021 @default.
- W3181403764 countsByYear W31814037642022 @default.
- W3181403764 countsByYear W31814037642023 @default.
- W3181403764 crossrefType "journal-article" @default.
- W3181403764 hasAuthorship W3181403764A5002193139 @default.
- W3181403764 hasAuthorship W3181403764A5005328526 @default.
- W3181403764 hasAuthorship W3181403764A5024552077 @default.
- W3181403764 hasAuthorship W3181403764A5032381726 @default.
- W3181403764 hasAuthorship W3181403764A5040654786 @default.
- W3181403764 hasAuthorship W3181403764A5044654291 @default.
- W3181403764 hasAuthorship W3181403764A5074000331 @default.
- W3181403764 hasAuthorship W3181403764A5087173640 @default.
- W3181403764 hasBestOaLocation W31814037642 @default.
- W3181403764 hasConcept C111919701 @default.
- W3181403764 hasConcept C118505674 @default.
- W3181403764 hasConcept C132525143 @default.
- W3181403764 hasConcept C142362112 @default.
- W3181403764 hasConcept C153349607 @default.
- W3181403764 hasConcept C154945302 @default.
- W3181403764 hasConcept C178790620 @default.
- W3181403764 hasConcept C185592680 @default.
- W3181403764 hasConcept C35753019 @default.
- W3181403764 hasConcept C41008148 @default.