ReactionPredictor: Prediction of Complex Chemical Reactions at the Mechanistic Level Using Machine Learning

By Matthew A. Kayala, Pierre Baldi. 2012

158 citations recorded by the source corpus.

Subfields: Catalysis, Computational Theory and Mathematics, Materials Chemistry, 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 Catalysis

1. Alán Aspuru-Guzik
2. Mark P. Waller
3. Marwin H. S. Segler

In Computational Theory and Mathematics

1. Philippe Schwaller
2. Sepp Hochreiter
3. Günter Klambauer
4. Teodoro Laino
5. Mike Preuss
6. Marwin H. S. Segler
7. Philipp Renz
8. C. Bekas

In Materials Chemistry

1. Philippe Schwaller
2. Sepp Hochreiter
3. Philipp Renz
4. Günter Klambauer
5. Teodoro Laino
6. Marwin H. S. Segler
7. Mike Preuss
8. C. Bekas

In Computational Chemistry & Drug Discovery

1. Sepp Hochreiter
2. Philippe Schwaller
3. Günter Klambauer
4. Teodoro Laino
5. C. Bekas
6. Théophile Gaudin
7. Mike Preuss
8. Philipp Renz

Citations in the corpus

• Planning chemical syntheses with deep neural networks and symbolic AI (2017, background): “[ 15–18] Given the exponential growth of chemical knowledge (it doubles roughly every 15 years), manual encoding is a hopeless endeavor.”
• Accelerating the discovery of materials for clean energy in the era of smart automation (2018, background): “The shortcomings of rule-based expert systems have provoked the idea to leverage AI approaches to reaction prediction 236 (Fig.”
• Modelling Chemical Reasoning to Predict Reactions (2016, methodology): “HTRP has been conducted with rule-based expert systems, machine-learning, formal logic and combinations thereof with force fields or semiempirical methods 6,14–27 : 17 They are appealing because they are interpretable and resemble the way undergraduate organic chemistry is taught.”
• “Found in Translation”: predicting outcomes of complex organic chemistry reactions using neural sequence-to-sequence models (2017, methodology): “A first template-free approach was introduced by Kayala et al. [22].”
• Neural Networks for the Prediction of Organic Chemistry Reactions (2016, unknown): “ReactionPredictor 31,32 is an algorithm that fi rst identi fi es potential electron sources and electron sinks in the reactant molecules based on atom and bond descriptors.”
• Detecting Cardiovascular Disease from Mammograms with Deep Learning (2017, unknown): “In recent years [23], neural networks and deep learning have been used to successfully tackle a variety of problems in engineering, ranging from computer vision [24, 25, 26, 27] to speech recognition [28], as well as in the natural sciences, in areas ranging from high energy physics [29, 30], to che”
• Modern Hopfield Networks for Few- and Zero-Shot Reaction Prediction (2021, background): “Whether a reaction has a sufficiently fast rate must also be taken into account by a reaction predictor (Kayala & Baldi, 2012), which further adds to the complexity of the problem.”