【作者】 芦静； 郑明月； 王雍； 沈倩诚； 罗小民； 蒋华良； 陈凯先；

【机构】 中国科学院上海药物研究所新药研究国家重点实验室,药物发现与设计中心；

【摘要】 <正>Skin sensitization is an important toxic endpoint to be taken into account in the risk assessment of chemicals.In this paper,SAR(structure-activity relationships) analysis was performed on the skin sensitization potential of 320 compounds with local lymph node assay(LLNA) data.Structural fragments were extracted by GASTON(GrAph/Sequence/Tree extractiON) based on ’quickstart principle’ from the training set.8 fragments of which the accuracy Q is significantly higher than 0.73(p<0.1) were retained to make up an indicator descriptor fragment.The fragment descriptor and 8 other physicochemical descriptors closely related to the endpoint,were calculated to construct the recursive partitioning tree(RP tree) for classification.The balanced accuracy of the training set and test set in the leave-one-out model were 0.846 and 0.800,respectively.The results highlight that fragment-based RP tree is a preferable method for identifying skin sensitizers.Moreover,the selected fragments provide useful structural information for exploring sensitization mechanisms, and RP tree creates a graphic tree to identify the most important properties of skin sensitization. They can provide some instruction for designing of drugs with lower sensitizability.更多还原

【Abstract】 Skin sensitization is an important toxic endpoint to be taken into account in the risk assessment of chemicals.In this paper,SAR(structure-activity relationships) analysis was performed on the skin sensitization potential of 320 compounds with local lymph node assay(LLNA) data.Structural fragments were extracted by GASTON(GrAph/Sequence/Tree extractiON) based on ’quickstart principle’ from the training set.8 fragments of which the accuracy Q is significantly higher than 0.73(p<0.1) were retained to make up an indicator descriptor fragment.The fragment descriptor and 8 other physicochemical descriptors closely related to the endpoint,were calculated to construct the recursive partitioning tree(RP tree) for classification.The balanced accuracy of the training set and test set in the leave-one-out model were 0.846 and 0.800,respectively.The results highlight that fragment-based RP tree is a preferable method for identifying skin sensitizers.Moreover,the selected fragments provide useful structural information for exploring sensitization mechanisms, and RP tree creates a graphic tree to identify the most important properties of skin sensitization. They can provide some instruction for designing of drugs with lower sensitizability.更多还原