A novel approach to generate robust classification models to predict developmental toxicity from imbalanced datasets

Computational models to predict the developmental toxicity of compounds are built on imbalanced datasets wherein the toxicants outnumber the non-toxicants. Consequently, the results are biased towards the majority class (toxicants). To overcome this problem and to obtain sensitive but also accurate classifiers, we followed an integrated approach wherein (i) Synthetic Minority Over Sampling (SMOTE) is used for re-sampling, (ii) genetic algorithm (GA) is used for variable selection and (iii) support vector machines (SVM) is used for model development. The best model, M3, has (i) sensitivity (SE) = 85.54% and specificity (SP) = 85.62% in leave-one-out validation, (ii) classification accuracy of the training set = 99.67%, (iii) classification accuracy of the test set = 92.59%; and (iv) sensitivity = 92.68, specificity = 92.31 on the test set. Consensus prediction based on models M3–M5 improved these percentages by 5% over M3. From the analysis of results we infer that data imbalance in toxicity studies can be effectively addressed by the application of re-sampling techniques.     

A Novel Method for Colorectal Cancer Screening Based on Circulating Tumor Cells and Machine Learning

Colorectal cancer is one of the most common types of cancer, and it can have a high mortality rate if left untreated or undiagnosed. The fact that CRC becomes symptomatic at advanced stages highlights the importance of early screening. The reference screening method for CRC is colonoscopy, an invasive, time-consuming procedure that requires sedation or anesthesia and is recommended from a certain age and above. The aim of this study was to build a machine learning classifier that can distinguish cancer from non-cancer samples. For this, circulating tumor cells were enumerated using flow cytometry. Their numbers were used as a training set for building an optimized SVM classifier that was subsequently used on a blind set. The SVM classifier’s accuracy on the blind samples was found to be 90.0%, sensitivity was 80.0%, specificity was 100.0%, precision was 100.0% and AUC was 0.98. Finally, in order to test the generalizability of our method, we also compared the performances of different classifiers developed by various machine learning models, using over-sampling datasets generated by the SMOTE algorithm. The results showed that SVM achieved the best performances according to the validation accuracy metric. Overall, our results demonstrate that CTCs enumerated by flow cytometry can provide significant information, which can be used in machine learning algorithms to successfully discriminate between healthy and colorectal cancer patients. The clinical significance of this method could be the development of a simple, fast, non-invasive cancer screening tool based on blood CTC enumeration by flow cytometry and machine learning algorithms.     

基于守恒高阶模型和支持向量机的多车道车辆换道模型

针对高速公路车辆换道问题, 提出一个多车道车辆换道模型。利用支持向量机(SVM)在多维特征下二分类问题的优势, 将SVM和Lagrange坐标下的高阶守恒模型(CHO)结合, 通过全离散跟车模型生成原始数据, 采用SMOTE(Synthetic Minority Oversampling Technique)算法对数据进行预处理, 采用双指标评估度SVM进行训练, 建立多车道车辆换道仿真模型。仿真结果表明: 基于支持向量机和CHO模型的换道模型, 驾驶车能够就当前的驾驶环境, 准确地作出决策, 有效地模拟高速公路上真实的多车道驾驶情况。