Neural-Symbolic Machine Learning for Retrosynthesis and Reaction Prediction.

By Marwin H. S. Segler, Mark P. Waller. 2017

512 citations recorded by the source corpus.

Subfields: Computational Theory and Mathematics, Materials Chemistry, Molecular Biology, 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 Theory and Mathematics

In Materials Chemistry

In Molecular Biology

In Computational Chemistry & Drug Discovery

Citations in the corpus

Planning chemical syntheses with deep neural networks and symbolic AI (2017, methodology): “[24] This allows to mimic the expert’s intuitive decision-making.”
Molecular Transformer: A Model for Uncertainty-Calibrated Chemical Reaction Prediction (2018, methodology): “Recent machine learning approaches employ template libraries that are automatically extracted from datasets of reactions [20, 21].”
The rise of deep learning in drug discovery. (2018, methodology): “Segler et al. [76] used 3.5 million reactions as the training set for DNN.”
Unsupervised Attention-Guided Atom-Mapping (2020, methodology): “This match is called atom-mapping and is crucial for numerous tasks like template-based reaction prediction (Coley et al., 2017; Segler & Waller, 2017) and retrosynthesis planning methods (Segler et al., 2018; Thakkar et al., 2020; Fortunato et al., 2020), reaction graph neural network algorithms…”
Modern Hopfield Networks for Few- and Zero-Shot Reaction Prediction (2021, methodology): “004 * DNN (Segler & Waller, 2017) 0 .”
DEEPre: sequence-based enzyme EC number prediction by deep learning (2017, background): “The use of reaction fingerprints, for instance, could be one viable solution for this (Segler and Waller, 2017).”
Emerging materials intelligence ecosystems propelled by machine learning (2020, methodology): “Other approaches rely on classification models (NNs) for this selection task 214 .”
Machine learning for molecular and materials science (2018, methodology): “…of ANNs with other learning techniques such as Boltzmann machines, are showing particular promise for predicting chemical synthesis routes by combining rules-based expert systems with neural networks that rank the candidates, 36 or rank the likelihood of a predicted product by applying the rules.”
Machine Learning Methods in Drug Discovery (2020, methodology): “In a groundbreaking study conducted by Segler and Waller [84], an MCTS method using three NNs alongside 12.4 million transformation rules, retrieved through AI-based data mining, from all the available chemical synthesis literature at the time to generate a sensible workﬂow for CASP.”
Predicting Organic Reaction Outcomes with Weisfeiler-Lehman Network (2017, methodology): “In Segler and Waller [14], molecules are represented based on their Morgan fingerprints, while Coley et al. [3] represents reactions by the features of atoms and bonds in the reaction center.”