EHreact: Extended Hasse Diagrams for the Extraction and Scoring of Enzymatic Reaction Templates

Heid, Esther; Goldman, Samuel; Sankaranarayanan, Karthik; Coley, Connor W.; Flamm, Christoph; Green, William

doi:10.1021/acs.jcim.1c00921

Cited by 10 publications

(14 citation statements)

References 59 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Still, the supergroups and decision trees are often manually defined for each reaction type, which is tedious and error-prone. Thus, there has been interest in automating tree construction , to facilitate the incorporation of new training reactions, but the process is still cumbersome.…”

Section: Introductionmentioning

confidence: 99%

Fast Predictions of Reaction Barrier Heights: Toward Coupled-Cluster Accuracy

2022

Self Cite

View full text Add to dashboard Cite

Quantitative estimates of reaction barriers are essential for developing kinetic mechanisms and predicting reaction outcomes. However, the lack of experimental data and the steep scaling of accurate quantum calculations often hinder the ability to obtain reliable kinetic values. Here, we train a directed message passing neural network on nearly 24,000 diverse gas-phase reactions calculated at CCSD(T)-F12a/cc-pVDZ-F12//ωB97X-D3/def2-TZVP. Our model uses 75% fewer parameters than previous studies, an improved reaction representation, and proper data splits to accurately estimate performance on unseen reactions. Using information from only the reactant and product, our model quickly predicts barrier heights with a testing MAE of 2.6 kcal mol–1 relative to the coupled-cluster data, making it more accurate than a good density functional theory calculation. Furthermore, our results show that future modeling efforts to estimate reaction properties would significantly benefit from fine-tuning calibration using a transfer learning technique. We anticipate this model will accelerate and improve kinetic predictions for small molecule chemistry.

show abstract

Section: Introductionmentioning

confidence: 99%

Fast Predictions of Reaction Barrier Heights: Toward Coupled-Cluster Accuracy

2022

Self Cite

View full text Add to dashboard Cite

show abstract

“…Presentation of data in this way can give scientists a simple way to understand the types of molecules which might be accepted by an enzyme. RetroBioCat-DB provides a substrate summary view which uses a Hasse diagram as reported by Heid et al to automatically group substrates into a hierarchical structure for analysis . The substrate summary view shows core structures with R groups and the number of examples these represent, with an ability to select cores for further exploration (Figure B).…”

Section: Resultsmentioning

confidence: 99%

“…The substrate summary tool is created using a modified version of EHReact . Seed molecules are predefined for each reaction and used to create a Hasse diagram given a set of unique molecules for a reaction.…”

Section: Methodsmentioning

confidence: 99%

RetroBioCat Database: A Platform for Collaborative Curation and Automated Meta-Analysis of Biocatalysis Data

Finnigan,

Lubberink,

Hepworth

et al. 2023

ACS Catal.

View full text Add to dashboard Cite

Despite the increasing use of biocatalysis for organic synthesis, there are currently no databases that adequately capture synthetic biotransformations. The lack of a biocatalysis database prevents accelerating biocatalyst characterization efforts from being leveraged to quickly identify candidate enzymes for reactions or cascades, slowing their development. The RetroBioCat Database (available at retrobiocat.com) addresses this gap by capturing information on synthetic biotransformations and providing an analysis platform that allows biocatalysis data to be searched and explored through a range of highly interactive data visualization tools. This database makes it simple to explore available enzymes, their substrate scopes, and how characterized enzymes are related to each other and the wider sequence space. Data entry is facilitated through an openly accessible curation platform, featuring automated tools to accelerate the process. The RetroBioCat Database democratizes biocatalysis knowledge and has the potential to accelerate biocatalytic reaction development, making it a valuable resource for the community.

show abstract

“…There are many ways of estimating thermochemical and kinetic parameters. By far, the most common way of estimating thermochemical parameters is the Benson-type group additivity method. , Implementations of this method are used in THERM and Genesys. , Graph convolutional neural network methods are beginning to emerge as an alternative. − Kinetics estimators typically rely on either the use of rate rules assigning specific rates to reactions matching specific templates or reaction group additivity. − Recent machine learning approaches using hierarchical decision trees have been found to be effective for predicting rate coefficients and reactivity. , …”

Section: Introductionmentioning

confidence: 99%

RMG Database for Chemical Property Prediction

Johnson

Dong

Dana

et al. 2022

J. Chem. Inf. Model.

View full text Add to dashboard Cite

The Reaction Mechanism Generator (RMG) database for chemical property prediction is presented. The RMG database consists of curated datasets and estimators for accurately predicting the parameters necessary for constructing a wide variety of chemical kinetic mechanisms. These datasets and estimators are mostly published and enable prediction of thermodynamics, kinetics, solvation effects, and transport properties. For thermochemistry prediction, the RMG database contains 45 libraries of thermochemical parameters with a combination of 4564 entries and a group additivity scheme with 9 types of corrections including radical, polycyclic, and surface absorption corrections with 1580 total curated groups and parameters for a graph convolutional neural network trained using transfer learning from a set of >130 000 DFT calculations to 10 000 high-quality values. Correction schemes for solvent−solute effects, important for thermochemistry in the liquid phase, are available. They include tabulated values for 195 pure solvents and 152 common solutes and a group additivity scheme for predicting the properties of arbitrary solutes. For kinetics estimation, the database contains 92 libraries of kinetic parameters containing a combined 21 000 reactions and contains rate rule schemes for 87 reaction classes trained on 8655 curated training reactions. Additional libraries and estimators are available for transport properties. All of this information is easily accessible through the graphical user interface at https://rmg.mit.edu. Bulk or on-the-fly use can be facilitated by interfacing directly with the RMG Python package which can be installed from Anaconda. The RMG database provides kineticists with easy access to estimates of the many parameters they need to model and analyze kinetic systems. This helps to speed up and facilitate kinetic analysis by enabling easy hypothesis testing on pathways, by providing parameters for model construction, and by providing checks on kinetic parameters from other sources.

show abstract

EHreact: Extended Hasse Diagrams for the Extraction and Scoring of Enzymatic Reaction Templates

Cited by 10 publications

References 59 publications

Fast Predictions of Reaction Barrier Heights: Toward Coupled-Cluster Accuracy

Fast Predictions of Reaction Barrier Heights: Toward Coupled-Cluster Accuracy

RetroBioCat Database: A Platform for Collaborative Curation and Automated Meta-Analysis of Biocatalysis Data

RMG Database for Chemical Property Prediction

Contact Info

Product

Resources

About