A method of building a predictive model

Abstract

The invention discloses a method for predicting the water-phase reaction rate constant of organic matter and a sulfuric acid free radical in a water phase through quantitative structure activity relationship. Based on a compound structure, a molecular descriptor with a structural feature is calculated, and by the adoption of a multiple linear regression method, a QSAR model of an organic compound kso4- is constructed. Establishment of the model strictly confirms to the constructing and using guideline of the QSAR model from organization for economic cooperation and development, the constructed model has a definite application field, contains 197 kinds of organic compounds of different structures, and contains compounds containing carbon-carbon double bonds, carbon-carbon triple bonds, a hydroxyl group, phenolic hydroxyl, a carbonyl group, an aldehyde group, a carboxy group, an ester group, an amide group, nitro, an amino group, a cyano-group, an ether bond, a disulfide bond, fluorine, chlorine, bromine, iodine, arsenium and other radical groups. The mode has good fitting capacity, robustness and predicting capacity, can rapidly and accurately predict the kso4- value of the organic compound, and reference is provided for application of an advanced oxidation process based on a sulfuric acid free radical.

Description

technical field [0001] The invention relates to a method for predicting the reaction rate constant of organic matter and sulfuric acid free radicals in an aqueous phase by establishing a quantitative structure-activity relationship model (QSAR), and belongs to the technical field of ecological risk assessment testing strategies. Background technique [0002] Advanced Oxidation Processes (AOPs) is a commonly used process in water pollution control, and has a good development prospect in removing trace pollutants contained in water bodies. The principle is to stimulate the production of active species such as hydroxyl radicals and sulfuric acid radicals, and then attack various pollutants in the water body and degrade them into CO 2 , water and mineral salts, so as to achieve the removal of toxic substances in the water. According to the different activation methods of free radicals, advanced oxidation technologies are divided into: photochemical oxidation, electrochemical ox...

AI Technical Summary

Problems solved by technology

The literature "RSCAdv.2016,110: 108448-108457" used PaDEL descriptors to establish and predict the same 85 kinds of organic molecules based on two machine learning methods: single decision tree and gradient boosting decision tree. Numerical QSAR model, although the model parameters reported in the literature are good, but it lacks a clear calculation formula and the algorithm is not transparent, which greatly limits the application of the model

The literature "Water Res.2017,116:106-115" established two predictions of 113 organic molecules based on the group contribution method Numerical QSAR model, the model can determine the value of each descriptor and calculate the reaction rate constant only by the molecular structure formula, but the disadvantage is that the external verification ability of the model is not ideal (external verification coefficient R 2 ext Only 0.42-0.62, i.e. poor predictive power)

[0007] In summary, reactions based on sulfuric acid radicals have good prospects for development in advanced oxidation technologies, but currently The lack of numerical values ​​is still very serious, which limits the development potential of this technology, and the experimental determination of this parameter is time-consuming and laborious, and it is difficult to carry out in large quantities. equal advantage model

Images