On the use of real-world datasets for reaction yield prediction.
Chem Sci
; 14(19): 4997-5005, 2023 May 17.
Article
en En
| MEDLINE
| ID: mdl-37206399
ABSTRACT
The lack of publicly available, large, and unbiased datasets is a key bottleneck for the application of machine learning (ML) methods in synthetic chemistry. Data from electronic laboratory notebooks (ELNs) could provide less biased, large datasets, but no such datasets have been made publicly available. The first real-world dataset from the ELNs of a large pharmaceutical company is disclosed and its relationship to high-throughput experimentation (HTE) datasets is described. For chemical yield predictions, a key task in chemical synthesis, an attributed graph neural network (AGNN) performs as well as or better than the best previous models on two HTE datasets for the Suzuki-Miyaura and Buchwald-Hartwig reactions. However, training the AGNN on an ELN dataset does not lead to a predictive model. The implications of using ELN data for training ML-based models are discussed in the context of yield predictions.
Texto completo:
1
Colección:
01-internacional
Banco de datos:
MEDLINE
Tipo de estudio:
Prognostic_studies
/
Risk_factors_studies
Idioma:
En
Revista:
Chem Sci
Año:
2023
Tipo del documento:
Article