In silico toxicity prediction by support vector machine and SMILES representation-based string kernel
作者单位：Research center of modernization of traditional Chinese medicinesCentral South UniversityChangsha 410083P.R.China School of Mathematical Sciences and Computing TechnologyCentral South UniversityChangsha 410083P.R.China
会议名称：《第十一届全国计算（机）化学学术会议》
会议日期：2011年
学科分类：12[管理学] 1201[管理学-管理科学与工程(可授管理学、工学学位)] 07[理学] 081104[工学-模式识别与智能系统] 08[工学] 0703[理学-化学] 0835[工学-软件工程] 0811[工学-控制科学与工程] 0812[工学-计算机科学与技术（可授工学、理学学位）]
关 键 词：toxicity prediction structure-toxicity relationship(STR) support vector machine(SVM) simplified molecular input line entry specification(SMILES) string kernel
摘 要：正There is a great need to assess the harmful effects or toxicities of chemicals to which man is *** the present paper,the simplified molecular input line entry specification（SMILES） representation-based string kernel,together with the state-of-the-art support vector machine（SVM） algorithm,were developed to classify the toxicity of chemicals from Distributed Structure-Searchable Toxicity（DSSTox） database *** this method,the molecular structure can be directly encoded by a series of SMILES substrings that represent the presence of some chemical elements and different kinds of chemical bonds（double,triple,and stereochemistry）.Thus, SMILES string kernel can accurately and directly measure the similarities of molecules by a series of local information hidden in the *** model validation approaches,five-fold cross-validation and independent validation set,were used for assessing the predictive capability of our developed models（see Figure 1）.The results obtained indicate that SVM based on SMILES string kernel can be regarded as a very promising and alternative modeling approach for potential toxicity prediction of *** datasets can be downloaded from the website: http://***/p/data-share/.