基于范数指数构效关系预测单端孢霉烯真菌毒素毒性

Structure-activity Relationship for Predicting the Toxicity of Trichothecene Mycotoxins Based on Norm Indexes

依据本课题组前期提出的范数指数描述符,建立了一个预测单端孢霉烯真菌毒素(trichothecene mycotoxins)毒性的QSAR模型,并对35个毒素物质的毒性进行了计算.留一交叉验证和Y随机验证表明这个新计算模型预测结果可靠、稳定(R^2为0.944,2,Q^2为0.878,9);同时,该模型的应用域验证结果表明此模型有可能在大范围上推广运用.模型统计结果和相关验证结果都表明基于范数指数建立的QSAR模型可以成功应用于预测单端孢霉烯真菌毒素毒性.

Based on the norm indexes descriptor proposed earlier in this project,a model for predicting the toxicity of 35,trichothecene mycotoxins was developed.The model was validated by leave-one-out validation and Y-randomization test with satisfactory results(R2 of 0.944,2,Q2 of 0.878,9),which further demonstrated that this model is reliable and stable.Besides,the applicability domain of this model was validated by using the leverage approach and the results suggested a potentially large scale of further utilization.The statistical values and validation test results demonstrated that our proposed norm indexes-based model could be successfully applied to predicting the toxicity of trichothecene mycotoxins.