Universal descriptors of quasi transition states for small-data-driven asymmetric catalysis prediction in machine learning model DOI Creative Commons
Guan-Ming Chen,

Zi-Hao Ye,

Zhiming Li

и другие.

Cell Reports Physical Science, Год журнала: 2024, Номер 5(7), С. 102043 - 102043

Опубликована: Июнь 12, 2024

In enantioselectivity prediction models, the demand for numerous descriptors and extensive datasets poses a substantial challenge. Descriptor selection, fraught with uncertainty, compounds issue, while amassing requisite data remains daunting task. The introduction of derived from quasi transition states offers promising avenue to alleviate this burden. However, challenge descriptor selection persists. Here, we report small-data-driven model based on universal descriptors. Key differentiating properties between diastereomeric states, encompassing single-point energies, frontier orbital Cartesian forces, charges core atoms, are proposed as model's efficacy is validated through its application asymmetric aldol Negishi reactions, utilizing 3 experimental variables, merely less than 9 descriptors, fewer 150 training samples. Moreover, method presented using forces rectify discrepancies true states. This strategy circumvents tedious large-scale exploration screening, offering an efficient choice prediction.

Язык: Английский

Machine learning accelerated design of magnesium alloys with high strength and high ductility DOI

Guosong Zhu,

Xiaoming Du,

Dandan Sun

и другие.

Materials Today Communications, Год журнала: 2025, Номер unknown, С. 111894 - 111894

Опубликована: Фев. 1, 2025

Язык: Английский

Процитировано

1
Photocatalyzed Azidofunctionalization of Alkenes via Radical‐Polar Crossover DOI Open Access
Pierre Palamini, Alexandre A. Schoepfer, Jérôme Waser

и другие.

Angewandte Chemie International Edition, Год журнала: 2025, Номер unknown

Опубликована: Янв. 2, 2025

The azidofunctionalization of alkenes under mild conditions using commercially available starting materials and easily accessible reagents is reported based on a radical-polar crossover strategy. A broad range alkenes, including vinyl arenes, enamides, enol ethers, sulfides, dehydroamino esters, were regioselectively functionalized with an azide nucleophiles such as azoles, carboxylic acids, alcohols, phosphoric oximes, phenols. method led to more efficient synthesis 1,2-azidofunctionalized pharmaceutical intermediates when compared previous approaches, resulting in both reduction step count increase overall yield. scope limitations these transformations further investigated through standard unbiased selection 15 substrate combinations out 1,175,658 possible clustering technique.

Язык: Английский

Процитировано

0
Photocatalyzed Azidofunctionalization of Alkenes via Radical‐Polar Crossover DOI Open Access
Pierre Palamini, Alexandre A. Schoepfer, Jérôme Waser

и другие.

Angewandte Chemie, Год журнала: 2025, Номер unknown

Опубликована: Янв. 2, 2025

Abstract The azidofunctionalization of alkenes under mild conditions using commercially available starting materials and easily accessible reagents is reported based on a radical‐polar crossover strategy. A broad range alkenes, including vinyl arenes, enamides, enol ethers, sulfides, dehydroamino esters, were regioselectively functionalized with an azide nucleophiles such as azoles, carboxylic acids, alcohols, phosphoric oximes, phenols. method led to more efficient synthesis 1,2‐azidofunctionalized pharmaceutical intermediates when compared previous approaches, resulting in both reduction step count increase overall yield. scope limitations these transformations further investigated through standard unbiased selection 15 substrate combinations out 1,175,658 possible clustering technique.

Язык: Английский

Процитировано

0
Enhancing solar radiation forecasting accuracy with a hybrid SA-Bi-LSTM-Bi-GRU model DOI

Girijapati Sharma,

Subhash Chandra,

Arvind Yadav

и другие.

Earth Science Informatics, Год журнала: 2025, Номер 18(3)

Опубликована: Фев. 19, 2025

Язык: Английский

Процитировано

0
Prediction of the Infrared Absorbance Intensities and Frequencies of Hydrocarbons: A Message Passing Neural Network Approach DOI
Maliheh Shaban Tameh, Veaceslav Coropceanu, Thomas A. R. Purcell

и другие.

The Journal of Physical Chemistry A, Год журнала: 2024, Номер 128(44), С. 9695 - 9706

Опубликована: Окт. 28, 2024

Accurately and efficiently predicting the infrared (IR) spectra of a molecule can provide insights into structure–properties relationships molecular species, which has led to proliferation machine learning tools designed for this purpose. However, earlier studies have focused primarily on obtaining normalized IR spectra, limits their potential comprehensive analysis behavior in range. For instance, fully understand predict optical properties, such as transparency characteristics, it is necessary molar absorptivity instead. Here, we propose graph-based communicative message passing neural network algorithm that both peak positions absolute intensities corresponding density functional theory calculated absorptivities domain. By modifying existing spectral loss functions, show our method able with DFT-accuracy level series hydrocarbons containing up ten carbon atoms apply model set larger molecules. We also compare predicted those generated by direct network. The results suggest algorithms demonstrate similar predictive capabilities hydrocarbons, indicating either could be effectively used future research prediction systems.

Язык: Английский

Процитировано

1
Universal descriptors of quasi transition states for small-data-driven asymmetric catalysis prediction in machine learning model DOI Creative Commons
Guan-Ming Chen,

Zi-Hao Ye,

Zhiming Li

и другие.

Cell Reports Physical Science, Год журнала: 2024, Номер 5(7), С. 102043 - 102043

Опубликована: Июнь 12, 2024

In enantioselectivity prediction models, the demand for numerous descriptors and extensive datasets poses a substantial challenge. Descriptor selection, fraught with uncertainty, compounds issue, while amassing requisite data remains daunting task. The introduction of derived from quasi transition states offers promising avenue to alleviate this burden. However, challenge descriptor selection persists. Here, we report small-data-driven model based on universal descriptors. Key differentiating properties between diastereomeric states, encompassing single-point energies, frontier orbital Cartesian forces, charges core atoms, are proposed as model's efficacy is validated through its application asymmetric aldol Negishi reactions, utilizing 3 experimental variables, merely less than 9 descriptors, fewer 150 training samples. Moreover, method presented using forces rectify discrepancies true states. This strategy circumvents tedious large-scale exploration screening, offering an efficient choice prediction.

Язык: Английский

Процитировано

0