Abstract
Objective Study the computer toxicity prediction technology and predict the carcinogenicity of rats from the chemical components of Chinese materia medica, in order to provide a new method for the safety evaluation of Chinese materia medica. Methods The Mold2 software (version 2.0.0)was used to calculate molecular descriptors of 1 532 chemical components. After preliminary screening of molecular descriptors, quantitative structure-activity relationship (QSAR)models were built up with Random Forest (RF)for screening the optimum prediction model. From the 83 kinds of toxic Chinese materia medica in Chinese Pharmacopoeia (2010 edition), 60 kinds of Chinese materia medica reported from monomer structure of chemical components carcinogenicity were under prediction. Results Totally 1 532 pieces of data were obtained. If the number of descriptors was 60, RF modeling accuracy was the highest, which was 0.69. It was predicted that 60 kinds of Chinese materia medica contained 481 carcinogenic compounds. Conclusions The QSAR model for prediction study on carcinogenicity of chemical components of Chinese mareria medica can provide the information about the experiment studies of combination of medicines. Key words: Structure-activity relationship; Chemical compositions (TCD); Carcinogenicity tests
Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
