Cargando…
Unbiasing Retrosynthesis Language Models with Disconnection Prompts
[Image: see text] Data-driven approaches to retrosynthesis are limited in user interaction, diversity of their predictions, and recommendation of unintuitive disconnection strategies. Herein, we extend the notions of prompt-based inference in natural language processing to the task of chemical langu...
Autores principales: | Thakkar, Amol, Vaucher, Alain C., Byekwaso, Andrea, Schwaller, Philippe, Toniato, Alessandra, Laino, Teodoro |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
American Chemical Society
2023
|
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10390024/ https://www.ncbi.nlm.nih.gov/pubmed/37529205 http://dx.doi.org/10.1021/acscentsci.3c00372 |
Ejemplares similares
-
Enhancing diversity in language based models for single-step retrosynthesis
por: Toniato, Alessandra, et al.
Publicado: (2023) -
Quantum chemical data generation as fill-in for reliability enhancement of machine-learning reaction and retrosynthesis planning
por: Toniato, Alessandra, et al.
Publicado: (2023) -
Fast Customization
of Chemical Language Models to
Out-of-Distribution Data Sets
por: Toniato, Alessandra, et al.
Publicado: (2023) -
Designing catalysts with deep generative models and computational data. A case study for Suzuki cross coupling reactions
por: Schilter, Oliver, et al.
Publicado: (2023) -
Automated extraction of chemical synthesis actions from experimental procedures
por: Vaucher, Alain C., et al.
Publicado: (2020)