• Corpus ID: 84186721

A Generative Model For Electron Paths

@article{Bradshaw2019AGM,
  title={A Generative Model For Electron Paths},
  author={John Bradshaw and Matt J. Kusner and Brooks Paige and Marwin H. S. Segler and Jos{\'e} Miguel Hern{\'a}ndez-Lobato},
  journal={arXiv: Chemical Physics},
  year={2019}
}
Chemical reactions can be described as the stepwise redistribution of electrons in molecules. [...] Key MethodWe design a method to extract approximate reaction paths from any dataset of atom-mapped reaction SMILES strings. Our model achieves excellent performance on an important subset of the USPTO reaction dataset, comparing favorably to the strongest baselines. Furthermore, we show that our model recovers a basic knowledge of chemistry without being explicitly trained to do so.Expand
Non-Autoregressive Electron Redistribution Modeling for Reaction Prediction
TLDR
This work formulate a reaction as an arbitrary electron flow and predict it with a novel multipointer decoding network and achieves at least 27 times inference speedup over the state-of-the-art methods.
Molecule Edit Graph Attention Network: Modeling Chemical Reactions as Sequences of Graph Edits
TLDR
It is argued that representing the reaction as a sequence of edits enables MEGAN to efficiently explore the space of plausible chemical reactions, maintaining the flexibility of modeling the reaction in an end-to-end fashion and achieving state-of-the-art accuracy in standard benchmarks.
Extraction of organic chemistry grammar from unsupervised learning of chemical reactions
TLDR
This work demonstrates that Transformer Neural Networks learn atom-mapping information between products and reactants without supervision or human labeling, and provides the missing link between data-driven and rule-based approaches for numerous chemical reaction tasks.
Molecular Transformer: A Model for Uncertainty-Calibrated Chemical Reaction Prediction
TLDR
This work shows that a multihead attention Molecular Transformer model outperforms all algorithms in the literature, achieving a top-1 accuracy above 90% on a common benchmark data set and is able to handle inputs without a reactant–reagent split and including stereochemistry, which makes the method universally applicable.
Learning Graph Models for Template-Free Retrosynthesis
TLDR
A graph-based approach that capitalizes on the idea that the graph topology of precursor molecules is largely unaltered during the reaction, greatly simplifying the underlying architecture and improving its ability to generalize.
A Model to Search for Synthesizable Molecules
TLDR
This work proposes a new molecule generation model that can generate diverse, valid and unique molecules due to the useful inductive biases of modeling reactions, and allows chemists to interrogate not only the properties of the generated molecules but also the feasibility of the synthesis routes.
Retrosynthesis Prediction with Conditional Graph Logic Network
TLDR
The Conditional Graph Logic Network is proposed, a conditional graphical model built upon graph neural networks that learns when rules from reaction templates should be applied, implicitly considering whether the resulting reaction would be both chemically feasible and strategic.
Permutation invariant graph-to-sequence model for template-free retrosynthesis and reaction prediction
TLDR
A novel Graph2SMILES model is described that combines the power of Transformer models for text generation with the permutation invariance of molecular graph encoders that mitigates the need for input data augmentation.
Self-Improved Retrosynthetic Planning
TLDR
This work proposes an endto-end framework for directly training the DNNs towards generating reaction pathways with the desirable properties based on a self-improving procedure that trains the model to imitate successful trajectories found by itself.
Barking up the right tree: an approach to search over molecule synthesis DAGs
TLDR
This work proposes a deep generative model that better represents the real world process, by directly outputting molecule synthesis DAGs, and argues that this provides sensible inductive biases, ensuring that the model searches over the same chemical space that chemists would also have access to, as well as interpretability.
...
1
2
3
...

References

SHOWING 1-10 OF 36 REFERENCES
Predicting Organic Reaction Outcomes with Weisfeiler-Lehman Network
TLDR
This paper proposes a template-free approach to efficiently explore the space of product molecules by first pinpointing the reaction center -- the set of nodes and edges where graph edits occur, and demonstrates that the model accuracy rivals the performance of domain experts.
A Machine Learning Approach to Predict Chemical Reactions
TLDR
This work uses an existing rule-based expert system to derive a dataset and trains an ensemble of ranking models on pairs of interacting orbitals to learn a relative productivity function over single mechanistic reactions in a given system, allowing multi-step reaction prediction.
Deep learning for chemical reaction prediction
TLDR
An alternative approach to predicting electron sources and sinks using recurrent neural networks, specifically long short-term memory (LSTM) architectures, operating directly on SMILES strings is discussed, which has shown promising preliminary results.
Learning to Predict Chemical Reactions
TLDR
This work describes single mechanistic reactions as interactions between coarse approximations of molecular orbitals (MOs) and use topological and physicochemical attributes as descriptors and proposes a new approach to reaction prediction utilizing elements from each pole.
ReactionPredictor: Prediction of Complex Chemical Reactions at the Mechanistic Level Using Machine Learning
TLDR
A machine learning approach to reaction prediction that models elementary, mechanistic reactions as interactions between approximate molecular orbitals (MOs) and makes decisions about which of the polar, pericyclic, or radical reaction type ranking models to use can be made with >99% accuracy.
Automated discovery of chemically reasonable elementary reaction steps
TLDR
A systematic approach is proposed for locating reaction paths that bypasses the required human effort and expands the reactive search space, all while maintaining low computational cost.
Neural Message Passing for Quantum Chemistry
TLDR
Using MPNNs, state of the art results on an important molecular property prediction benchmark are demonstrated and it is believed future work should focus on datasets with larger molecules or more accurate ground truth labels.
Synergies Between Quantum Mechanics and Machine Learning in Reaction Prediction
TLDR
The proposed ML approach identifies electron sources and sinks among reactants and then ranks all source-sink pairs, addressing a bottleneck of QM calculations by providing a prioritized list of mechanistic reaction steps.
Context-Driven Exploration of Complex Chemical Reaction Networks.
  • G. Simm, M. Reiher
  • Chemistry, Medicine
    Journal of chemical theory and computation
  • 2017
TLDR
A computational protocol is presented that constructs reaction networks in a fully automated fashion steered in an intuitive, graph-based fashion through a single graphical user interface to study different pathways of sugar formation and to rationalize its autocatalytic nature.
Heuristics-Guided Exploration of Reaction Mechanisms.
TLDR
A computational protocol is presented that constructs chemical reaction networks in a parallelized and automated manner and applies it to the Schrock dinitrogen-fixation catalyst to study alternative pathways of catalytic ammonia production.
...
1
2
3
4
...