Your browser doesn't support javascript.
loading
Mostrar: 20 | 50 | 100
Resultados 1 - 1 de 1
Filtrar
Mais filtros

Base de dados
Assunto principal
Ano de publicação
Tipo de documento
País de afiliação
Intervalo de ano de publicação
1.
J Chem Inf Model ; 64(10): 4286-4297, 2024 May 27.
Artigo em Inglês | MEDLINE | ID: mdl-38708520

RESUMO

C-H borylation is a high-value transformation in the synthesis of lead candidates for the pharmaceutical industry because a wide array of downstream coupling reactions is available. However, predicting its regioselectivity, especially in drug-like molecules that may contain multiple heterocycles, is not a trivial task. Using a data set of borylation reactions from Reaxys, we explored how a language model originally trained on USPTO_500_MT, a broad-scope set of patent data, can be used to predict the C-H borylation reaction product in different modes: product generation and site reactivity classification. Our fine-tuned T5Chem multitask language model can generate the correct product in 79% of cases. It can also classify the reactive aromatic C-H bonds with 95% accuracy and 88% positive predictive value, exceeding purpose-developed graph-based neural networks.


Assuntos
Hidrogênio , Hidrogênio/química , Modelos Químicos , Redes Neurais de Computação
SELEÇÃO DE REFERÊNCIAS
DETALHE DA PESQUISA