Reactive Intermediate

Reactive intermediates are short-lived, highly reactive species crucial in chemical reactions, particularly in catalysis and synthesis. Current research focuses on improving the prediction and manipulation of these intermediates, employing machine learning models like convolutional neural networks and generative pre-trained transformers to enhance efficiency and accuracy in areas such as drug discovery and materials science. These advancements aim to optimize computational workflows, reduce wasted resources, and ultimately accelerate the design and development of new molecules and catalysts. The ability to accurately predict and control reactive intermediates holds significant promise for various fields, including drug discovery and materials science.

Papers

March 14, 2024

Leap: molecular synthesisability scoring with intermediates
Antonia Calvi, Théophile Gaudin, Dominik Miketa, Dominique Sydow, Liam Wilbraham
Leap Forward Molecular Generative Reactive Intermediate

April 1, 2022

Better Intermediates Improve CTC Inference
Tatsuya Komatsu, Yusuke Fujita, Jaesong Lee, Lukas Lee, Shinji Watanabe, Yusuke Kida
CTC Based Reactive Intermediate

March 2, 2022

Machine learning models predict calculation outcomes with the transferability necessary for computational catalysis
Chenru Duan, Aditya Nandy, Husain Adamji, Yuriy Roman-Leshkov, Heather J. Kulik
Machine Learning Model Task Transferability Multiple Outcome Electronic Structure Catalyst Design Reactive Intermediate

Reactive Intermediate

Papers

Leap: molecular synthesisability scoring with intermediates

Better Intermediates Improve CTC Inference

Machine learning models predict calculation outcomes with the transferability necessary for computational catalysis