JHJohn E. Herr

John E. Herr

*This is an algorithmically generated author record based on publicly available information.

John E. Herr has a total of 10 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Graph Neural Networks for Predicting Chemical Reaction Performance

    by Mandana Saebi, Bozhao Nan, John Herr, Jessica Wahlers, Olaf Wiest, Nitesh Chawla

    Chemical reactions are a complex process, as they involve interaction between several molecular compounds. As a result, predicting the success of a reaction is a non-trivial task, which often requires running several experiments in the lab. This process is is expensive, time consuming, and inefficient. As a result, in recent years, researchers have explored the use of machine learning algorithms to predict reaction success. These methods mainly rely on chemical properties of the molecules involved in the reactions. Despite their promising success, none of existing methods explored the use of structural properties of molecules in predicting reaction success. In this work, we develop an Attributed Graph Neural Network model that integrates both structural properties as well as chemical properties of molecules for predicting reaction success. Our model shows remarkable performance on two hand-crafted datasets obtained from high-throughput experiments, as well as one real-world dataset.


  • Open Access

    Graph Neural Networks for Predicting Chemical Reaction Performance

    by Mandana Saebi, Bozhao Nan, John Herr, Jessica Wahlers, Olaf Wiest, Nitesh Chawla

    Chemical reactions are a complex process, as they involve interaction between several molecular compounds. As a result, predicting the success of a reaction is a non-trivial task, which often requires running several experiments in the lab. This process is is expensive, time consuming, and inefficient. As a result, in recent years, researchers have explored the use of machine learning algorithms to predict reaction success. These methods mainly rely on chemical properties of the molecules involved in the reactions. Despite their promising success, none of existing methods explored the use of structural properties of molecules in predicting reaction success. In this work, we develop an Attributed Graph Neural Network model that integrates both structural properties as well as chemical properties of molecules for predicting reaction success. Our model shows remarkable performance on two hand-crafted datasets obtained from high-throughput experiments, as well as one real-world dataset.

  • Compressing physics with an autoencoder: Creating an atomic species representation to improve machine learning models in the chemical sciences

    by John E. Herr, Kevin Koh, Kun Yao, John Parkhill

    We define a vector quantity which corresponds to atomic species identity by compressing a set of physical properties with an autoencoder. This vector, referred to here as the elemental modes, provides many advantages in downstream machine learning tasks. Using the elemental modes directly as the feature vector, we trained a neural network to predict formation energies of elpasolites with improved accuracy over previous works on the same task. Combining the elemental modes with geometric features used in high-dimensional neural network potentials (HD-NNPs) solves many problems of scaling and efficiency in the development of such neural network potentials. Whereas similar models in the past have been limited to typically four atomic species (H, C, N, and O), our implementation does not scale in cost by adding more atomic species and allows us to train an HD-NNP model which treats molecules containing H, C, N, O, F, P, S, Cl, Se, Br, and I. Finally, we establish that our implementation allows us to define feature vectors for alchemical intermediate states in the HD-NNP model, which opens up new possibilities for performing alchemical free energy calculations on systems where bond breaking/forming is important.


  • Metadynamics for training neural network model chemistries: A competitive assessment

    by John E. Herr, Kun Yao, Ryker McIntyre, David W. Toth, John Parkhill

    Neural network model chemistries (NNMCs) promise to facilitate the accurate exploration of chemical space and simulation of large reactive systems. One important path to improving these models is to add layers of physical detail, especially long-range forces. At short range, however, these models are data driven and data limited. Little is systematically known about how data should be sampled, and “test data” chosen randomly from some sampling techniques can provide poor information about generality. If the sampling method is narrow, “test error” can appear encouragingly tiny while the model fails catastrophically elsewhere. In this manuscript, we competitively evaluate two common sampling methods: molecular dynamics (MD), normal-mode sampling, and one uncommon alternative, Metadynamics (MetaMD), for preparing training geometries. We show that MD is an inefficient sampling method in the sense that additional samples do not improve generality. We also show that MetaMD is easily implemented in any NNMC software package with cost that scales linearly with the number of atoms in a sample molecule. MetaMD is a black-box way to ensure samples always reach out to new regions of chemical space, while remaining relevant to chemistry near kbT. It is a cheap tool to address the issue of generalization.


  • The many-body expansion combined with neural networks

    by Kun Yao, John E. Herr, John Parkhill

    Fragmentation methods such as the many-body expansion (MBE) are a common strategy to model large systems by partitioning energies into a hierarchy of decreasingly significant contributions. The number of calculations required for chemical accuracy is still prohibitively expensive for the ab initio MBE to compete with force field approximations for applications beyond single-point energies. Alongside the MBE, empirical models of ab initio potential energy surfaces have improved, especially non-linear models based on neural networks (NNs) which can reproduce ab initio potential energy surfaces rapidly and accurately. Although they are fast, NNs suffer from their own curse of dimensionality; they must be trained on a representative sample of chemical space. In this paper we examine the synergy of the MBE and NN’s and explore their complementarity. The MBE offers a systematic way to treat systems of arbitrary size while reducing the scaling problem of large systems. NN’s reduce, by a factor in excess of 106, the computational overhead of the MBE and reproduce the accuracy of ab initio calculations without specialized force fields. We show that for a small molecule extended system like methanol, accuracy can be achieved with drastically different chemical embeddings. To assess this we test a new chemical embedding which can be inverted to predict molecules with desired properties. We also provide our open-source code for the neural network many-body expansion, Tensormol.