Method for predicting enantioselectivity of chemical reaction product
An enantioselectivity, chemical reaction technology, applied in the field of chemical research, can solve the problems of time-consuming and laborious, and does not take into account the three-dimensional spatial effect of compounds, and achieves the effect of accurate and reliable results, guaranteeing integrity, and saving computing resources.
Pending Publication Date: 2021-07-23
DALIAN UNIV OF TECH +1
View PDF1 Cites 4 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
To fully consider the various characteristics of molecules, it is necessary to calculate and provide a large number of descriptors. This process is time-consuming and laborious, and these descriptors convert the information of compound molecules into two-dimensional data and pass them to the machine learning model. Real three-dimensional space effect
Method used
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment
[0031] Methods for predicting enantioselectivity of chemical reaction products, including:
[0032] 1) Collect the published experimental data of chiral phosphoric acid catalyzed N-acyl imide thiol addition reaction (Prediction of higher-selectivity catalysts by computer-driven workflow and machine learning. Science, 2019, 363, 247), a total of 975 chemical The reaction involved 39 chiral phosphoric acid catalysts and 10 reaction substrates;
[0033] 2) Carry out the molecular structure modeling of 49 compounds including substrates and catalysts, use the B3LYP / 6-31G* theoretical method in Gaussian16 software to optimize, and then calculate the molecular surface electrostatic potential (in order to predict the results more accurately, the embodiment The frontier molecular orbital levels (LUMO) of thiols were also calculated as descriptors in , and used to generate a coordinate file containing point clouds of molecular surface structures;
[0034] 3) Randomly divide 70% of the ca...
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More PUM
Login to View More Abstract
The invention provides a method for predicting enantioselectivity of a chemical reaction product, and particularly relates to a method for predicting enantioselectivity of a chemical reaction product by combining an octree convolutional neural network model and molecular surface electrostatic potential. On the basis of known molecular structures of a reaction substrate and a catalyst, the enantioselectivity of the chemical reaction product can be quickly and efficiently predicted by calculating the point cloud of each molecular structure and the surface electrostatic potential value corresponding to each point and combining the octree convolutional neural network model. According to the method, the 3D point cloud of the molecular structure and the surface electrostatic potential corresponding to the 3D point cloud are calculated, the three-dimensional effect and the electronic effect of molecules are reflected at the same time, and understanding and application are easy. The model has good prediction capability, can effectively predict the yield and enantioselectivity of organic reactions in an application domain, and has important significance for developing a new catalytic reaction for preparing chiral compounds.
Description
technical field [0001] The invention belongs to the technical field of chemical research, and relates to a method for predicting the enantioselectivity of chemical reaction products, in particular to a method for predicting the enantioselectivity of chemical reaction products based on an octree convolutional neural network model and molecular surface electrostatic potentials . Background technique [0002] Because of their special properties, chiral compounds are widely used in new fields such as medicine, optics and special materials. Therefore, how to efficiently prepare organic compound molecules of a single enantiomer is not only an important topic in the field of scientific research, but also has important application value. At present, there are three main methods to obtain chiral molecules with high optical activity: resolution of racemic compounds, synthesis from chiral sources, and asymmetric catalytic synthesis. Among them, the asymmetric catalytic synthesis meth...
Claims
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More Application Information
Patent Timeline
Login to View More Patent Type & Authority Applications(China)
IPC IPC(8): G16C20/30G16C20/70G06N3/04G06N3/08G06N20/00
CPCG16C20/30G16C20/70G06N3/08G06N20/00G06N3/045
Inventor 罗一祝雪峰温馨赵雅男王天航
Owner DALIAN UNIV OF TECH