BonDNet: a graph neural network for the prediction of bond dissociation energies for charged molecules

Wen, Mingjian; Blau, Samuel M.; Spotte-Smith, Evan Walter Clark; Dwaraknath, Shyam; Persson, Kristin A.

doi:10.1039/d0sc05251e

“…1 The success of such data-driven approaches relies on the availability of powerful molecular representations [2][3][4] that can be used in a wide range of machine learning (ML) methods. [5][6][7][8][9][10] Organophosphorous (III) ligands are amongst the most widely-used ligands in homogeneous catalysis. In this study, we establish a comprehensive workflow to study these ubiquitous compounds that can be further extended to other ligand classes.…”

Section: Introductionmentioning

confidence: 99%

A Comprehensive Discovery Platform for Organophosphorus Ligands for Catalysis

Gensch¹,

Gomes

²

,

Friederich³

et al. 2021

Preprint

View full text Add to dashboard Cite

The design of molecular catalysts typically involves reconciling multiple conflicting property requirements, largely relying on human intuition and local structural searches. However, the vast number of potential catalysts requires pruning of the candidate space by efficient property prediction with quantitative structure-property relationships. Data-driven workflows embedded in a library of potential catalysts can be used to build predictive models for catalyst performance and serve as a blueprint for novel catalyst designs. Herein we introduce kraken, a discovery platform covering monodentate organophosphorus(III) ligands providing comprehensive physicochemical descriptors based on representative conformer ensembles. Using quantum-mechanical methods, we calculated descriptors for 1,558 ligands, including commercially available examples, and trained machine learning models to predict properties of over 300,000 new ligands. We demonstrate the application of kraken to systematically explore the property space of organophosphorus ligands and how existing datasets in catalysis can be used to accelerate ligand selection during reaction optimization.

show abstract

“…1 The success of such data-driven approaches relies on the availability of powerful molecular representations [2][3][4] that can be used in a wide range of machine learning (ML) methods. [5][6][7][8][9][10] Organophosphorous (III) ligands are amongst the most widely-used ligands in homogeneous catalysis. In this study, we establish a comprehensive workflow to study these ubiquitous compounds that can be further extended to other ligand classes.…”

Section: Introductionmentioning

confidence: 99%

A Comprehensive Discovery Platform for Organophosphorus Ligands for Catalysis

Gensch¹,

Gomes

²

,

Friederich³

et al. 2021

Preprint

View full text Add to dashboard Cite

The design of molecular catalysts typically involves reconciling multiple conflicting property requirements, largely relying on human intuition and local structural searches. However, the vast number of potential catalysts requires pruning of the candidate space by efficient property prediction with quantitative structure-property relationships. Data-driven workflows embedded in a library of potential catalysts can be used to build predictive models for catalyst performance and serve as a blueprint for novel catalyst designs. Herein we introduce kraken, a discovery platform covering monodentate organophosphorus(III) ligands providing comprehensive physicochemical descriptors based on representative conformer ensembles. Using quantum-mechanical methods, we calculated descriptors for 1,558 ligands, including commercially available examples, and trained machine learning models to predict properties of over 300,000 new ligands. We demonstrate the application of kraken to systematically explore the property space of organophosphorus ligands and how existing datasets in catalysis can be used to accelerate ligand selection during reaction optimization.

show abstract

“…Machine learning methods, especially deep learning, have significantly expanded a chemist's toolbox, enabling the construction of quantitatively predictive models directly from data without explicitly designing rule-based models using chemical insights and intuitions. They have recently been successfully applied to address challenging chemical reaction problems, ranging from the prediction of reaction and activation energies [1][2][3][4][5] , reaction products 6,7 , and reaction conditions 8,9 , as well as designing synthesis a routes 10,11 to name a few. A key ingredient underlying these successes is that modern machine learning methods excel in extracting the patterns in data from sufficient, labelled training examples 12 .…”

Section: Introductionmentioning

confidence: 99%

“…A key ingredient underlying these successes is that modern machine learning methods excel in extracting the patterns in data from sufficient, labelled training examples 12 . It has been shown that the performance of these chemical machine learning models can be systematically improved with the increase of training examples 1,13 . Despite various recent efforts to generate large labelled reaction datasets that are suitable for modern machine learning 3,[14][15][16] , they are typically sparse and still small considering the size of the chemical reaction space 17 .…”

Section: Introductionmentioning

confidence: 99%

“…Wei et al 40 developed the first learnable graph neural network (GNN) reaction fingerprints based on GNN molecule descriptors 41,42 . The GNN reaction fingerprints are flexible to adapt themselves to unseen reactions and have achieved satisfying results in a number of applications, such as the prediction of reaction energy and activation energy 1,3 . However, as many other modern machine learning methods, they need a large number of labelled reactions to train.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Improving machine learning performance on small chemical reaction data with unsupervised contrastive pretraining

Wen

¹

,

Blau

²

,

Xie

³

et al. 2021

Preprint

Self Cite

View full text Add to dashboard Cite

Machine learning (ML) methods have great potential to transform chemical discovery by accelerating the exploration of chemical space and drawing scientific insights from data. However, modern chemical reaction ML models, such as those based on graph neural networks (GNNs), must be trained on a large amount of labelled data in order to avoid overfitting the data and thus possessing low accuracy and transferability. In this work, we propose a strategy to leverage unlabelled data to learn accurate ML models for small labelled chemical reaction data. We focus on an old and prominent problem—classifying reactions into distinct families—and build a GNN model for this task. We first pretrain the model on unlabelled reaction data using unsupervised contrastive learning and then fine-tune it on a small number of labelled reactions. The contrastive pretraining learns by making the representations of two augmented versions of a reaction similar to each other but distinct from other reactions. We propose chemically consistent reaction augmentation methods that protect the reaction center and find they are the key for the model to extract relevant information from unlabelled data to aid the reaction classification task. The transfer learned model outperforms a supervised model trained from scratch by a large margin. Further, it consistently performs better than models based on traditional rule-driven reaction fingerprints, which have long been the default choice for small datasets. In addition to reaction classification, the learned GNN-based reaction fingerprints can also be used to navigate the chemical reaction space, which we demonstrate by querying for similar reactions. The strategy can be readily applied to other predictive reaction problems to uncover the power of unlabelled data for learning better models with a limited supply of labels.

show abstract

BonDNet: a graph neural network for the prediction of bond dissociation energies for charged molecules

Abstract: Prediction of bond dissociation energies for charged molecules with a graph neural network enabled by global molecular features and reaction difference features between products and reactants.

Cited by 54 publications

References 60 publications

A Comprehensive Discovery Platform for Organophosphorus Ligands for Catalysis

A Comprehensive Discovery Platform for Organophosphorus Ligands for Catalysis

A Comprehensive Discovery Platform for Organophosphorus Ligands for Catalysis

Improving machine learning performance on small chemical reaction data with unsupervised contrastive pretraining

Contact Info

Product

Resources

About