Cargando…
Improving Few- and Zero-Shot Reaction Template Prediction Using Modern Hopfield Networks
[Image: see text] Finding synthesis routes for molecules of interest is essential in the discovery of new drugs and materials. To find such routes, computer-assisted synthesis planning (CASP) methods are employed, which rely on a single-step model of chemical reactivity. In this study, we introduce...
Autores principales: | Seidl, Philipp, Renz, Philipp, Dyubankova, Natalia, Neves, Paulo, Verhoeven, Jonas, Wegner, Jörg K., Segler, Marwin, Hochreiter, Sepp, Klambauer, Günter |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
American Chemical Society
2022
|
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9092346/ https://www.ncbi.nlm.nih.gov/pubmed/35034452 http://dx.doi.org/10.1021/acs.jcim.1c01065 |
Ejemplares similares
-
DEXUS: identifying differential expression in RNA-Seq studies with unknown conditions
por: Klambauer, Günter, et al.
Publicado: (2013) -
Modern Hopfield Networks for graph embedding
por: Liang, Yuchen, et al.
Publicado: (2022) -
CLOOME: contrastive learning unlocks bioimaging databases for queries with chemical structures
por: Sanchez-Fernandez, Ana, et al.
Publicado: (2023) -
Flight of the PEGASUS? Comparing Transformers on Few-Shot and Zero-Shot Multi-document Abstractive Summarization
por: Goodwin, Travis R., et al.
Publicado: (2020) -
Large-scale comparison of machine learning methods for drug target prediction on ChEMBL
por: Mayr, Andreas, et al.
Publicado: (2018)