Human developmental toxicity prediction method based on action mode

Abstract

The invention discloses a human developmental toxicity prediction method based on an action mode, and belongs to the field of human developmental toxicity virtual screening and activity prediction of chemicals. The method comprises the following steps: constructing a compound activity data set, selecting a harmful outcome path based on a human developmental toxicity action mode, and collecting research events and activity data thereof on a signal path of the harmful outcome path; constructing a first prediction model based on the data set; training by using a naive Bayesian algorithm to obtain a second prediction model by using a plurality of compounds with in-vivo experimental data and a prediction result obtained by predicting the compounds with the in-vivo experimental data by using the first prediction model; and inputting a to-be-detected compound into the first prediction model for qualitative prediction, and inputting a qualitative prediction result into the second prediction model to complete the prediction of the human developmental toxicity of the chemical. The method provided by the invention can be used for high-throughput screening of potential action mode-based human developmental toxic chemicals.

Description

technical field [0001] The present invention relates to the field of virtual screening and activity prediction of human developmental toxicity of chemicals, more specifically, a method for prediction of human developmental toxicity based on mode of action. Background technique [0002] A large number of animal experiments and epidemiological studies have found that most environmental small molecule compounds can interfere with nuclear receptor-mediated nucleic acid translation and expression, thereby affecting the growth and development of human individuals, which is called developmental toxicity (Developmental Toxicity). In particular, several official and non-official organizations, including the U.S. Environmental Protection Agency (U.S.EPA) and the European Chemicals Agency (ECHA), have found that many environmentally relevant pollutants can potentially affect harmful outcome pathways (Adverse Outcome Pathway, AOP) and lead to abnormal development of human reproductive o...

AI Technical Summary

Problems solved by technology

[0006] Technical problem: The purpose of the present invention is to overcome the deficiency in the prior art that the high-throughput prediction of human developmental toxicity based on the mode of action cannot be effectively performed, and to provide a method for predicting human developmental toxicity based on the mode of action

Images