Modelling Chemical Reasoning to Predict and Invent Reactions Marwin
By H. S. Segler, Mark P. Waller. 2016
Subfields: Computational Chemistry & Drug Discovery
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Computational Chemistry & Drug Discovery
- Marwin H. S. Segler
- Mark P. Waller
- Philippe Schwaller
- Teodoro Laino
- Mike Preuss
- C. Bekas
- Théophile Gaudin
- Christoph Steinbeck
Citations in the corpus
- Planning chemical syntheses with deep neural networks and symbolic AI (2017, background): “[41, 42] Here, we make the assumption that the reactants can only react in the reported way.”
- Prediction of Organic Reaction Outcomes Using Machine Learning (2017, unknown): “11 In one validation, the recorded product is found in the list of candidate products (with a median size of 3, mean 5.3) 67.5% of the time using a knowledge-base of eight million reactions.”
- “Found in Translation”: predicting outcomes of complex organic chemistry reactions using neural sequence-to-sequence models (2017, methodology): “One major advancement by Segler and Waller [5] and Coley et al. [6] was to consider alternative products as negative examples.”
- The Chemistry Development Kit (CDK) v2.0: atom typing, depiction, molecular formulas, and substructure searching (2017, background): “The CDK has also played a role in a number of chemical studies, such as finding the maximally bridging rings in chemical structures [32], prediction of organic reactions [33], and bioactivities of compounds [34].”