Data-science driven autonomous process optimization

Christensen, Melodie; Yunker, Lars P. E.; Adedeji, Folarin; Häse, Florian; Roch, Loı̈c M.; Gensch, Tobias; Gomes, Gabriel; Zepel, Tara; Sigman, Matthew S.; Aspuru‐Guzik, Alán; Hein, Jason E.

doi:10.26434/chemrxiv.13146404.v2

Cited by 8 publications

(5 citation statements)

References 1 publication

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To generate machine-readable inputs, we need to quantify physicochemical properties of candidate molecules, which is also called chemical descriptors. Although there are some researches on feature extraction using unsupervised learning [24][25][26][27] , the mainstream feature extraction method is still using DFT to calculate the relevant properties or use software libraries such as RDKIT 28 to generate feature matrices which is like molecular ngerprints. Considering the molecular ngerprint is encoded using a one-hot encoding scheme, it can't re ect more modest changes compared to the continuous variables calculated by DFT 29,30 .…”

Section: Resultsmentioning

confidence: 99%

Highly accurate prediction of reaction performance and enantioselectivity with a uniform machine learning protocol

Sun

Zhu

You

et al. 2021

Preprint

View full text Add to dashboard Cite

Synthetic reactions, especially asymmetric reactions are key components of modern chemistry. Chemists have put enormous experimental effort into recognizing various molecule patterns to enable efficient synthesis and asymmetric catalysis. Recent application of machine learning algorithms and chemoinformatics in this field demonstrated their huge potential in facilitating this process by accurate prediction. However, existing methods are relatively limited to specific designed data set, and only implement single prediction of reaction performance or reaction enantioselectivity, rendering their general use in broader scenarios challenging. Here we provide a uniform machine learning protocol that can predict both reaction performance and enantioselectivity with high accuracy. Reconstruction of molecular chemical space derived from more comprehensive three-dimensional atomic and molecular descriptors allow for training of our neural network-based model over four representative datasets. This uniform machine learning protocol was validated with outperformance of accuracy than other methods over all four cases (C-C, C-N, C-S cross coupling reactions and asymmetric hydrogenation) in the prediction of both reaction performance and enantioselectivity. It was also successfully applied to the out-of-set and sparse set prediction, leveraging its possible wide application in accelerating synthesis improve and molecular architects.

show abstract

Section: Resultsmentioning

confidence: 99%

Highly accurate prediction of reaction performance and enantioselectivity with a uniform machine learning protocol

Sun

Zhu

You

et al. 2021

Preprint

View full text Add to dashboard Cite

show abstract

“…This mindset enables the identification of subtle trends within the data, even when a particular result may be unexpected from a chemical intuition standpoint, which can guide further screening, hypothesis development, and future optimization campaigns. The expansion and distribution of databases of physical organic features will help to increase the accessibility of the data science workflow to chemists in a variety of fields. , It should be noted that the incorporation of data science principles to project design goes hand-in-hand with modern advances in automation that streamline the data collection process. , …”

Section: Discussionmentioning

confidence: 99%

Data Science Meets Physical Organic Chemistry

et al. 2021

View full text Add to dashboard Cite

Metrics & MoreArticle Recommendations CONSPECTUS: At the heart of synthetic chemistry is the holy grail of predictable catalyst design. In particular, researchers involved in reaction development in asymmetric catalysis have pursued a variety of strategies toward this goal. This is driven by both the pragmatic need to achieve high selectivities and the inability to readily identify why a certain catalyst is effective for a given reaction.While empiricism and intuition have dominated the field of asymmetric catalysis since its inception, enantioselectivity offers a mechanistically rich platform to interrogate catalyst-structure response patterns that explain the performance of a particular catalyst or substrate.In the early stages of an asymmetric reaction development campaign, the overarching mechanism of the reaction, catalyst speciation, the turnover limiting step, and many other details are unknown or posited based on related reactions. Considering the unclear details leading to a successful reaction, initial enantioselectivity data are often used to intuitively guide the ultimate direction of optimization. However, if the conditions of the Curtin−Hammett principle are satisfied, then measured enantioselectivity can be directly connected to the ensemble of diastereomeric transition states (TSs) that lead to the enantiomeric products, and the associated free energy difference between competing TSs (ΔΔG ⧧ = −RT ln[(S)/(R)], where (S) and (R) represent the concentrations of the enantiomeric products). We, and others, speculated that this important piece of information can be leveraged to guide reaction optimization in a quantitative way.Although traditional linear free energy relationships (LFERs), such as Hammett plots, have been used to illuminate important mechanistic features, we sought to develop data science derived tools to expand the power of LFERs in order to describe complex reactions frequently encountered in modern asymmetric catalysis. Specifically, we investigated whether enantioselectivity data from a reaction can be quantitatively connected to the attributes of reaction components, such as catalyst and substrate structural features, to harness data for asymmetric catalyst design.In this context, we developed a workflow to relate computationally derived features of reaction components to enantioselectivity using data science tools. The mathematical representation of molecules can incorporate many aspects of a transformation, such as molecular features from substrate, product, catalyst, and proposed transition states. Statistical models relating these features to reaction outputs can be used for various tasks, such as performance prediction of untested molecules. Perhaps most importantly, statistical models can guide the generation of mechanistic hypotheses that are embedded within complex patterns of reaction continued...

show abstract

“…The kraken tool may enable informed catalyst design based on organophosphorus ligands, facilitate the optimization of reaction process parameters, inspire new ligand choices and promote the synthesis of new organophosphorus compounds. The database and tools reported herein are currently being applied to enhance reaction optimization 47 and mechanistic workflows. 48 The open-source nature of our codes, as well as the open database, is designed to be extended by others and we welcome further contributions by the community.…”

Section: Discussionmentioning

confidence: 99%

A Comprehensive Discovery Platform for Organophosphorus Ligands for Catalysis

Gensch¹,

Gomes

Friederich³

et al. 2021

Preprint

Self Cite

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 <i>kraken</i>, 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 <i>kraken</i> 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

Data-science driven autonomous process optimization

Cited by 8 publications

References 1 publication

Highly accurate prediction of reaction performance and enantioselectivity with a uniform machine learning protocol

Highly accurate prediction of reaction performance and enantioselectivity with a uniform machine learning protocol

Data Science Meets Physical Organic Chemistry

A Comprehensive Discovery Platform for Organophosphorus Ligands for Catalysis

Contact Info

Product

Resources

About