Discovery of novel chemical reactions by deep generative recurrent neural network
Open Access
- 4 February 2021
- journal article
- research article
- Published by Springer Science and Business Media LLC in Scientific Reports
- Vol. 11 (1), 1-15
- https://doi.org/10.1038/s41598-021-81889-y
Abstract
The “creativity” of Artificial Intelligence (AI) in terms of generating de novo molecular structures opened a novel paradigm in compound design, weaknesses (stability & feasibility issues of such structures) notwithstanding. Here we show that “creative” AI may be as successfully taught to enumerate novel chemical reactions that are stoichiometrically coherent. Furthermore, when coupled to reaction space cartography, de novo reaction design may be focused on the desired reaction class. A sequence-to-sequence autoencoder with bidirectional Long Short-Term Memory layers was trained on on-purpose developed “SMILES/CGR” strings, encoding reactions of the USPTO database. The autoencoder latent space was visualized on a generative topographic map. Novel latent space points were sampled around a map area populated by Suzuki reactions and decoded to corresponding reactions. These can be critically analyzed by the expert, cleaned of irrelevant functional groups and eventually experimentally attempted, herewith enlarging the synthetic purpose of popular synthetic pathways.Keywords
Other Versions
This publication has 75 references indexed in Scilit:
- Palladium-Catalyzed Cross-Coupling Reaction of Arylboronic Acids with Chloroformate or Carbamoyl ChlorideSynlett, 2004
- Computer-aided design of new organic transformations: exposition of the ARGENT-1 programJournal of Physical Organic Chemistry, 2003
- SYMBEQ Program and Its Application in Computer-Assisted Reaction DesignJournal of Chemical Information and Computer Sciences, 1994
- Reaction Planning: Computer-Aided Discovery of a Novel Elimination ReactionScience, 1992
- IGOR2: a PC-program for generating new reactions and molecular structuresTetrahedron Computer Methodology, 1989
- Reaction planning: Computer-aided reaction designTetrahedron Computer Methodology, 1988
- A formalism for the classification and design of organic reactions. II. The classes of (+ −)n + and (− +)n − reactionsRecueil des Travaux Chimiques des Pays-Bas, 1979
- A formalism for the classification and design of organic reactions. I. The class of (− +)nreactionsRecueil des Travaux Chimiques des Pays-Bas, 1979
- A formalism for the classification and design of organic reactions III. The class of (+ ‐ )nC reactionsRecueil des Travaux Chimiques des Pays-Bas, 1979
- The Variety of Thermal Pericyclic ReactionsAngewandte Chemie-International Edition, 1974