Catalyst design in asymmetric reaction development has traditionally been driven by empiricism, wherein experimentalists attempt to qualitatively recognize structural patterns to improve selectivity. Machine learning algorithms and chemoinformatics can potentially accelerate this process by recognizing otherwise inscrutable patterns in large datasets. Herein we report a computationally guided workflow for chiral catalyst selection using chemoinformatics at every stage of development. Robust molecular descriptors that are agnostic to the catalyst scaffold allow for selection of a universal training set on the basis of steric and electronic properties. This set can be used to train machine learning methods to make highly accurate predictive models over a broad range of selectivity space. Using support vector machines and deep feed-forward neural networks, we demonstrate accurate predictive modeling in the chiral phosphoric acid-catalyzed thiol addition to N-acylimines.

A quality prediction method, a preparation method and a system of high resistance gallium oxide based on deep learning and Czochralski method. The quality prediction method includes the steps of obtaining preparation data of high resistance gallium oxide single crystal prepared by Czochralski method. The preparation data includes a seed crystal data, an environmental data, and a control data. The environmental data includes doping element concentration and doping element type; preprocessing the preparation data to obtain a preprocessed preparation data; preparing the preprocessed data is input to a trained neural network model, and a predicted quality data corresponding to the high resistance gallium oxide single crystal is obtained through the trained neural network model, and the predicted quality data includes a predicted resistivity.

A high resistance gallium oxide quality prediction method based on deep learning and an edge-defined film-fed crystal growth method, a preparation method and a system; the quality prediction method includes the following steps: obtaining preparation data of a high resistance gallium oxide single crystal prepared by the edge-defined film-fed crystal growth method, the preparation data including seed crystal data, environment data and control data, and the control data including doping element concentration and doping element type; preprocessing the preparation data to obtain preprocessed preparation data; inputting the preprocessing preparation data into a trained neural network model, acquiring the predicted quality data corresponding to the high resistance gallium oxide single crystal through the trained neural network model, the predicted quality data including predicted resistivity.

A conductive gallium oxide quality prediction method based on deep learning and an edge-defined film-fed crystal growth method, a preparation method and a system; the quality prediction method includes the following steps: obtaining preparation data of a conductive gallium oxide single crystal prepared by the edge-defined film-fed crystal growth method, the preparation data including seed crystal data, environment data and control data, and the control data including doping element concentration and doping element type; preprocessing the preparation data to obtain preprocessed preparation data; inputting the preprocessing preparation data into a trained neural network model, acquiring the predicted quality data corresponding to the conductive gallium oxide single crystal through the trained neural network model, the predicted quality data including predicted carrier concentration.

A quality prediction method, a preparation method and a system of conductive gallium oxide based on deep learning and Czochralski method. The quality prediction method includes the steps of obtaining preparation data of conductive gallium oxide single crystal prepared by Czochralski method. The preparation data includes a seed crystal data, an environmental data, and a control data. The environmental data includes doping element concentration and doping element type; preprocessing the preparation data to obtain a preprocessed preparation data; preparing the preprocessed data is input to a trained neural network model, and a predicted quality data corresponding to the conductive gallium oxide single crystal is obtained through the trained neural network model, and the predicted quality data includes a predicted carrier concentration.

A method and a system for the real-time optimization of a molecular-level device, and a storage medium are described. The method includes: inputting molecular composition of petroleum processing feedstocks into a pre-trained product prediction model to obtain a predicted molecular composition of corresponding predicted products and a predicted molecular content of each single molecule; determining whether the predicted product meets a preset standard for a target product; if the predicted product does not meet any preset standard for a target product, adjusting an operation parameter in the product prediction model, to re-obtain the predicted molecular composition and the predicted molecular content, until the preset standard is met. By means of the present disclosure, molecular-level integral simulation and real-time optimization of the molecular-level device from the feedstocks to the product processing process are achieved, and the precision and production efficiency are improved.

An optimization method and system for a whole process of molecular-level oil refinery processing and a storage medium are described. According to an embodiment, for mixed products obtained by prediction from simulation of a molecular-level crude oil processing process, when physical properties of any mixed product do not meet any preset standard, or when a target parameter of the mixed products does not meet a preset condition, the proportion of different fractions entering respective petroleum processing device, an operating parameter in a product prediction model, and a mixing rule for mixing predicted products are adjusted, and the mixed products are re-obtained, until the product properties meet any preset standard and the target parameter meets the preset condition. Final predicted products are predicted by adjusting the proportion of fractions for secondary processing, and the production efficiency is improved by means of the simulation optimization of a production process.

Disclosed are systems and methods for generating candidate recipes for batch testing battery recipes in robotics laboratory equipment. In one embodiment, the candidate recipes in a batch, share the maximum number of chemicals in common, while as a batch, they utilize a minimum number of chemicals. The candidate recipes are identified by constructing a graph where an initial selection of recipes are placed at each node. The graph yields the candidate recipes in the batch.

Disclosed are systems and methods for generating candidate recipes for batch testing battery recipes in robotics laboratory equipment. In one embodiment, the candidate recipes in a batch, share the maximum number of chemicals in common, while as a batch, they utilize a minimum number of chemicals. The candidate recipes are identified by constructing a graph where an initial selection of recipes are placed at each node. The graph yields the candidate recipes in the batch.

The embodiments disclose a method including planning a combining sequence of the atoms and compounds with carbon atoms to achieve sequentially predetermined covalent and ion bonding molecular structures, using magnetic fields of force to align atoms and molecules to uniformly orient the atoms and molecules polar alignments when sequentially combining with the carbon atoms, confirming the final carbon combined compound molecular structure conforms to the planned sequential molecular structure using an apparatus, and creating a beverage using the final carbon combined compound molecules to fortify the beverage nutritional content including fulvic acid.