AI-Driven Discovery of Asymmetric Pauson–Khand Reactions: A New Toolbox in a Synthetic Chemist’s Treasure DOI

Neha Rani,

R. Krishna Kumar,

Shivnath Mazumder

и другие.

The Journal of Physical Chemistry A, Год журнала: 2024, Номер unknown

Опубликована: Ноя. 21, 2024

Enantioselective catalytic reactions have a significant impact on chemical synthesis, and they are important components in an experimental chemist's toolbox. However, development of asymmetric catalysts often relies the intuition experience synthetic chemist, making process both time-consuming resource-intensive. The machine-learning-assisted reaction discovery can serve as very efficient platform for obtaining high-performing time-economical manner without extensive experimentation. Herein, we report data-driven machine learning method reliably predicting enantiomeric excess (%ee) 211 Pauson-Khand (PKR 1-PKR 211) between variety 45 unique 1,6-enyne substrates 12 axially chiral biaryl ligands presence different conditions like varying CO gas pressure, temperature, solvent polarity. Four algorithms been studied: extreme gradient boosting (XGBoost), random forest (RF), light (LGBM), neural network (NN). A fivefold cross validation was applied to our k-means SMOTE-augmented data set obtain optimized hyperparameters training set, subsequently, these parameters were used test set. In case out-of-box XGBoost is found be superior among all four methods investigated. Our samples contain total 212-PKR 223) arising from three new 1,3-benzodioxole-based SEGPHOS catalysts, which never included algorithm shows impressive root mean square error (RMSE) 7.06 (±1.11) %ee. XGBoost-predicted %ee values match reasonably well with results. absolute difference XGBoost-calculated ranges 0.9 7.6 majority reactions. fluoro-substituted-SEGPHOS ligand

Язык: Английский

COBRA web application to benchmark linear regression models for catalyst optimization with few-entry datasets DOI Creative Commons
Zhen Cao, Laura Falivene, Albert Poater

и другие.

Cell Reports Physical Science, Год журнала: 2024, Номер unknown, С. 102348 - 102348

Опубликована: Дек. 1, 2024

Язык: Английский

Процитировано

4
Accelerating the Development of Sustainable Catalytic Processes through Data Science DOI
Jason M. Stevens, Jacob M. Ganley, Matthew J. Goldfogel

и другие.

Organic Process Research & Development, Год журнала: 2025, Номер unknown

Опубликована: Янв. 2, 2025

Язык: Английский

Процитировано

0
Optimizing Phosphine Ligands for Ruthenium Catalysts in Asymmetric Hydrogenation of β-Keto Esters: The Role of Water in Activity and Selectivity DOI

Chasheng He,

Guihua Luo,

Hongliang Duan

и другие.

Molecular Catalysis, Год журнала: 2025, Номер 574, С. 114877 - 114877

Опубликована: Фев. 4, 2025

Язык: Английский

Процитировано

0
NHC-Cracker: A Platform for the In Silico Engineering of N-Heterocyclic Carbenes for Diverse Chemical Applications DOI Creative Commons
Gentoku Takasao, Bholanath Maity, Sayan Dutta

и другие.

ACS Catalysis, Год журнала: 2025, Номер unknown, С. 5915 - 5927

Опубликована: Март 27, 2025

Язык: Английский

Процитировано

0
A meta-learning approach for selectivity prediction in asymmetric catalysis DOI Creative Commons
Sukriti Singh, José Miguel Hernández-Lobato

Nature Communications, Год журнала: 2025, Номер 16(1)

Опубликована: Апрель 15, 2025

Abstract Transition metal-catalyzed asymmetric reactions are of high contemporary importance in organic synthesis. Recently, machine learning (ML) has shown promise accelerating the development newer catalytic protocols. However, need for large amount experimental data can present a bottleneck implementing ML models. Here, we propose meta-learning workflow that harness literature-derived to extract shared reaction features and requires only few examples predict outcome new reactions. Prototypical networks used as method enantioselectivity hydrogenation olefins. This model consistently provides significant performance improvement over other popular methods such random forests graph neural networks. The our meta-model is analyzed with varying sizes training demonstrate its utility even limited data. A good on an out-of-sample test set further indicates general applicability approach. We believe this work will provide leap forward identifying promising early phases when minimal available.

Язык: Английский

Процитировано

0
C−S‐Selective Stille‐Coupling Enables Stereodefined Alkene Synthesis DOI Open Access

Jing Jing,

Ying Hu,

Zhenfeng Tian

и другие.

Angewandte Chemie International Edition, Год журнала: 2024, Номер unknown

Опубликована: Июль 30, 2024

Abstract A palladium‐catalyzed highly C−S‐selective Stille cross‐coupling between aryl thianthrenium salts and tri‐ or tetrasubstituted alkenyl stannanes is described. Herein, critical challenges including site‐ chemoselectivity control are well addressed through C−H thianthrenation C−S alkenylation, thereby providing an expedient access to stereodefined alkenes in a stereoretentive fashion. Indeed, the Stille‐alkenylation of poly( pseudo )halogenated arenes displays privileged capability differentiate over C−I, C−Br, C−Cl bonds, as oxygen‐based triflates (C−OTf), tosylates (C−OTs), carbamates sulfamates under mild reaction conditions. Sequential multiple cross‐couplings via selective C−X functionalization should be widely applicable for increasing functional molecular complexity. Modular installation stereospecific alkene motifs into pharmaceuticals illustrated synthetic application present protocol drug discovery.

Язык: Английский

Процитировано

0
C−S‐Selective Stille‐Coupling Enables Stereodefined Alkene Synthesis DOI

Jing Jing,

Ying Hu,

Zhenfeng Tian

и другие.

Angewandte Chemie, Год журнала: 2024, Номер 136(43)

Опубликована: Июль 30, 2024

Abstract In dieser Arbeit wird eine Palladium‐katalysierte, hochselektive C−S‐Stille‐Kreuzkupplung zwischen Arylthianthreniumsalzen und tri‐ oder tetrasubstituierten Alkenylstannanen präsentiert. Dabei werden Herausforderungen wie die Kontrolle der Positions‐ Chemoselektivität durch C−H‐Thianthrenierung C−S‐Alkenylierung erfolgreich gelöst, wodurch ein nützlicher Zugang zu stereodefinierten Alkenen stereoretentiv ermöglicht wird. Die Palladium‐katalysierte Stille‐Alkenylierung von poly(pseudo)halogenierten Arenen zeigt privilegierte Fähigkeit, C−S‐ über C−I‐, C−Br‐ C−Cl‐Bindungen sowie Triflate (C−OTf), Tosylate (C−OTs), Carbamate Sulfamate unter milden Reaktionsbedingungen differenzieren. Sequenzielle mehrfache Kreuzkupplungen selektive C−X‐Funktionalisierung sollten bei zunehmender funktioneller Molekülkomplexität breit einsetzbar sein. Der modulare Einbau stereospezifischen Alken‐Motiven in Pharmazeutika veranschaulicht synthetische Anwendung Arzneimittelforschung.

Процитировано

0
AI-Driven Discovery of Asymmetric Pauson–Khand Reactions: A New Toolbox in a Synthetic Chemist’s Treasure DOI

Neha Rani,

R. Krishna Kumar,

Shivnath Mazumder

и другие.

The Journal of Physical Chemistry A, Год журнала: 2024, Номер unknown

Опубликована: Ноя. 21, 2024

Enantioselective catalytic reactions have a significant impact on chemical synthesis, and they are important components in an experimental chemist's toolbox. However, development of asymmetric catalysts often relies the intuition experience synthetic chemist, making process both time-consuming resource-intensive. The machine-learning-assisted reaction discovery can serve as very efficient platform for obtaining high-performing time-economical manner without extensive experimentation. Herein, we report data-driven machine learning method reliably predicting enantiomeric excess (%ee) 211 Pauson-Khand (PKR 1-PKR 211) between variety 45 unique 1,6-enyne substrates 12 axially chiral biaryl ligands presence different conditions like varying CO gas pressure, temperature, solvent polarity. Four algorithms been studied: extreme gradient boosting (XGBoost), random forest (RF), light (LGBM), neural network (NN). A fivefold cross validation was applied to our k-means SMOTE-augmented data set obtain optimized hyperparameters training set, subsequently, these parameters were used test set. In case out-of-box XGBoost is found be superior among all four methods investigated. Our samples contain total 212-PKR 223) arising from three new 1,3-benzodioxole-based SEGPHOS catalysts, which never included algorithm shows impressive root mean square error (RMSE) 7.06 (±1.11) %ee. XGBoost-predicted %ee values match reasonably well with results. absolute difference XGBoost-calculated ranges 0.9 7.6 majority reactions. fluoro-substituted-SEGPHOS ligand

Язык: Английский

Процитировано

0