Method for screening molecular descriptors of compounds and determining value ranges of molecular descriptors

The invention relates to the technical field of molecular compound data screening and mining, in particular to a method for screening compound molecular descriptors and determining the value range of the compound molecular descriptors, which comprises the following steps of: S1, screening the first 20 molecular descriptors which have the most obvious influence on biological activity by using a Pearson's correlation coefficient method and a maximum information coefficient method; s2, using a random forest regression model to construct a quantitative prediction model of the compound on the ERalpha biological activity; s3, respectively constructing classification prediction models of Caco-2, CYP3A4, hERG, HOB and MN of the compounds; and S4, analyzing and processing the data by using a statistical principle, screening the data through digital characteristics in combination with the model, obtaining a rough value range, and performing verification. According to the present invention, the compound can provide good