Autonomous process optimization involves the human intervention-free exploration of a range process parameters to improve responses such as product yield and selectivity. Utilizing off-the-shelf components, we develop a closed-loop system for carrying out parallel autonomous process optimization experiments in batch. Upon implementation of our system in the optimization of a stereoselective Suzuki-Miyaura coupling, we find that the definition of a set of meaningful, broad, and unbiased process parameters is the most critical aspect of successful optimization. Importantly, we discern that phosphine ligand, a categorical parameter, is vital to determination of the reaction outcome. To date, categorical parameter selection has relied on chemical intuition, potentially introducing bias into the experimental design. In seeking a systematic method for selecting a diverse set of phosphine ligands, we develop a strategy that leverages computed molecular feature clustering. The resulting optimization uncovers conditions to selectively access the desired product isomer in high yield. An automated closed-loop system optimizes a stereoselective Suzuki-Miyaura reaction using a machine learning algorithm that incorporates unbiased and categorical process parameters.

/pdf/data-science-driven-autonomous-process-optimization-2e3zr5bqer.pdf

Data-science driven autonomous process optimization

Chemists often use statistical analysis of reaction data with molecular descriptors to identify structure-reactivity relationships, which can enable prediction and mechanistic understanding. In thi...

Univariate classification of phosphine ligation state and reactivity in cross-coupling catalysis.

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 1558 ligands, including commercially available examples, and trained machine learning models to predict properties of over 300000 new ligands. We demonstrate the application of kraken to systematically explore the property space of organophosphorus ligands and how existing data sets in catalysis can be used to accelerate ligand selection during reaction optimization. 

A Comprehensive Discovery Platform for Organophosphorus Ligands for Catalysis

Ni/photoredox catalysis has emerged as a powerful platform for C(sp2)–C(sp3) bond formation. In principle, these reactions enable access to the same product scaffolds, but it can be hard to discern which method to employ because non-standardized sets of aryl bromides are used in scope evaluation. Herein we report a Ni/photoredox-catalyzed alkylation of aryl halides where benzaldehyde di(alkyl) acetals serve as alcohol-derived radical sources. We describe the integration of data science techniques, including DFT featurization, dimensionality reduction, and hierarchical clustering, to delineate a diverse and succinct collection of aryl bromides that is representative of the chemical space of the substrate class. By superimposing the scope examples from published Ni/photoredox methods on this chemical space, we identify areas of sparse coverage and high/low yields, enabling comparisons between prior art and this method. We demonstrate that the systematically-selected scope of aryl bromides can be used to quantify population-wide reactivity trends with supervised ML.

/pdf/using-data-science-to-guide-aryl-bromide-substrate-scope-1fp1jtn79g.pdf

Using Data Science to Guide Aryl Bromide Substrate Scope Analysis in a Ni/Photoredox-Catalyzed Cross-Coupling with Acetals as Alcohol-Derived Radical Sources

ConspectusAt 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 responses. Overall, merging traditional physical organic experiments with statistical modeling techniques creates a feedback loop that enables both evaluation of multiple mechanistic hypotheses and future catalyst design. In this Account, we highlight the evolution and application of this approach in the context of a collaborative program based on chiral phosphoric acid catalysts (CPAs) in asymmetric catalysis.

Data Science Meets Physical Organic Chemistry.

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.

/pdf/a-comprehensive-discovery-platform-for-organophosphorus-4sljn0ywbh.pdf

Organic chemistry is replete with complex relationships: for example, how a reactant's structure relates to the resulting product formed; how reaction conditions relate to yield; how a catalyst's structure relates to enantioselectivity. Questions like these are at the foundation of understanding reactivity and developing novel and improved reactions. An approach to probing these questions that is both longstanding and contemporary is data-driven modeling. Here, we provide a synopsis of the history of data-driven modeling in organic chemistry and the terms used to describe these endeavors. We include a timeline of the steps that led to its current state. The case studies included highlight how, as a community, we have advanced physical organic chemistry tools with the aid of computers and data to augment the intuition of expert chemists and to facilitate the prediction of structure-activity and structure-property relationships.

The Evolution of Data-Driven Modeling in Organic Chemistry.

In reaction discovery, the search space of discrete reaction parameters such as catalyst structure is often not explored systematical-ly. We have developed a tool set to aid the search of optimal catalysts in the context of phosphine ligands. A virtual library, kra-ken, that is representative of the monodentate P(III)-ligand chemical space was utilized as the basis to represent the discrete lig-ands as continuous variables. Using dimensionality reduction and clustering techniques, we suggested a Phosphine Optimization Screening Set (PHOSS) of 32 commercially available ligands that samples this chemical space completely and evenly. We present the application of this screening set in the identification of active catalyst for various cross-coupling reactions and how well-distributed sampling of the chemical space facilitates identification of active catalysts. Furthermore, we demonstrate how proximi-ty in ligand space can be a useful guide to further explore ligands when very few active catalysts are known.

Design and Application of a Screening Set for Monophosphine Lig-ands in Metal Catalysis

Statistical analysis of reaction data with molecular descriptors can enable chemists to identify reactivity cliffs that result from a mechanistic dependence on a specific structural feature. In this study, we develop a broadly applicable and quantitative classification workflow that identifies reactivity cliffs in eleven Ni- and Pd-catalyzed cross-coupling datasets employing monodentate phosphine ligands. A unique ligand steric descriptor, %Vbur (min), is found to divide these datasets into active and inactive regions at a similar threshold value. Organometallic studies demonstrate that this threshold corresponds to the binary outcome of bisligated versus monoligated metal and that %Vbur (min) is a physically meaningful and predictive representation of ligand structure in catalysis. Taken together, we expect that this strategy will be of broad value in mechanistic investigation of structure-reactivity relationships, while providing a means to rationally partition datasets for data-driven modeling.

/pdf/linking-mechanistic-analysis-of-catalytic-reactivity-cliffs-2474be721r.pdf

Tobias Gensch

Papers

A Comprehensive Discovery Platform for Organophosphorus Ligands for Catalysis

The Evolution of Data-Driven Modeling in Organic Chemistry.

Design and Application of a Screening Set for Monophosphine Lig-ands in Metal Catalysis

Linking Mechanistic Analysis of Catalytic Reactivity Cliffs to Ligand Classification