This website requires JavaScript.

Higher order organizational features can distinguish protein interaction networks of disease classes: a case study of neoplasms and neurological diseases

Vikram SinghVikram Singh
Dec 2022
摘要
Neoplasms (NPs) and neurological diseases and disorders (NDDs) are amongstthe major classes of diseases underlying deaths of a disproportionate number ofpeople worldwide. To determine if there exist some distinctive features in thelocal wiring patterns of protein interactions emerging at the onset of adisease belonging to either of these two classes, we examined 112 and 175protein interaction networks belonging to NPs and NDDs, respectively. Orbitusage profiles (OUPs) for each of these networks were enumerated byinvestigating the networks' local topology. 56 non-redundant OUPs (nrOUPs) werederived and used as network features for classification between these twodisease classes. Four machine learning classifiers, namely, k-nearest neighbour(KNN), support vector machine (SVM), deep neural network (DNN), random forest(RF) were trained on these data. DNN obtained the greatest average AUPRC(0.988) among these classifiers. DNNs developed on node2vec and the proposednrOUPs embeddings were compared using 5-fold cross validation on the basis ofaverage values of the six of performance measures, viz., AUPRC, Accuracy,Sensitivity, Specificity, Precision and MCC. It was found that nrOUPs basedclassifier performed better in all of these six performance measures.
展开全部
图表提取

暂无人提供速读十问回答

论文十问由沈向洋博士提出,鼓励大家带着这十个问题去阅读论文,用有用的信息构建认知模型。写出自己的十问回答,还有机会在当前页面展示哦。

Q1论文试图解决什么问题?
Q2这是否是一个新的问题?
Q3这篇文章要验证一个什么科学假设?
0
被引用
笔记
问答