Research Square
In recent years, it has been seen that artificial intelligence (AI) starts to bring revolutionary changes to chemical synthesis. However, the lack of suitable ways of representing chemical reactions and the scarceness of reaction data has limited the wider application of AI to reaction prediction. Here, we introduce a novel reaction representation, GraphRXN, for reaction prediction. It utilizes a universal graph-based neural network framework to encode chemical reactions by directly taking two-dimension reaction structures as inputs. The GraphRXN model was evaluated by three publically available chemical reaction datasets and gave on-par or superior results compared with other baseline models. To further evaluate the effectiveness of GraphRXN, wet-lab experiments were carried out for the purpose of generating reaction data. GraphRXN model was then built on high-throughput experimentation data and a decent accuracy (R2 of 0.713) was obtained on our in-house data validation. This highlights that the GraphRXN model can be deployed in an integrated workflow which combines robotics and AI technologies for forward reaction prediction.
For details:
GraphRXN: A Novel Representation for Reaction Prediction
Baiqing Li, Shimin Su, Chan Zhu, Jie Lin, Xinyue Hu, Lebin Su, Zhunzhun Yu, Kuangbiao Liao, Hongming Chen
Guangzhou Laboratory
Research Square
https://doi.org/10.21203/rs.3.rs-1665893/v1
For more information about Chemspeed solutions:
FLEX ISYNTH for Library Synthesis Small Scale
FLEX ISYNTH Library Synthesis with online NMR
ISYNTH with Integrated Online Offline NMR
Contact us to learn more about this exciting article:
https://www.chemspeed.com/contact-us/