Creation of new chemical compounds having desired properties using accumulated chemical data to construct new chemical structure for synthesis

Abstract

The present invention provides a computer implemented method of generating new chemical compounds. The method includes preparing a data-driven substructure feature vector for each of a plurality of chemical compounds for which a chemical or physical property is known. The method further includes preparing a predefined component feature vector, creating a regression model to predict a target value for the chemical or physical property, and performing a search algorithm to identify substructure features that affect the target value for the chemical or physical property. The method further includes generating a candidate structure having the target value for the chemical or physical property, and synthesizing the candidate structure.

Description

technical field [0001] The present invention relates generally to the formation of eigenvectors from a plurality of known chemical structures with known properties, and the use of eigenvectors to design new chemical structures with desired properties, and more particularly to the use of eigenvectors using regression analysis and modeling Predict target properties to design and synthesize new chemical compounds. Background technique [0002] Identifying and designing new chemical structures with specific desired properties for synthesis can be time-consuming and expensive. Researchers can spend a great deal of time and effort trying to discover new chemical compounds with a desired set of properties, but such research work can involve a lot of trial and error. In addition, researchers may be limited by the extent of their past learning and experience, such that the direction of their research efforts may include biases, and limited by incomplete knowledge of the large amount...

AI Technical Summary

Problems solved by technology

[0002] Identifying and designing new chemical structures with specific desired properties for synthesis can be time-consuming and expensive

Researchers can spend considerable time and effort trying to discover new chemical compounds with a desired set of properties, but this research effort can involve a lot of trial and error

In addition, researchers may be limited by the extent of their past learning and experience, such that the direction of their research efforts may include biases, and limited by an incomplete knowledge of the vast amount of data available on known chemical structures and their properties

Researchers using intuition to come up with promising new chemical candidates for synthesis and testing can lead researchers to take futile paths before they can gain sufficient familiarity and understanding of structure / property relationships

Images