Machine Learning Classifiers for Endometriosis Using Transcriptomics and Methylomics Data [Transcriptomics]

We experimented how well various supervised machine learning methods such as decision tree, partial least squares discriminant analysis (PLSDA), support vector machine and random forest perform in classifying endometriosis from the control samples trained on both transcriptomics and methylomics data. The assessment was done from two different perspectives for improving classification performances: (a) implication of three different normalization techniques, and (b) implication of differential analysis using the generalized linear model (GLM). We concluded that an appropriate machine learning diagnostic pipeline for endometriosis should use TMM normalization for transcriptomics data, and quantile or voom normalization for methylomics data, GLM for feature space reduction and classification performance maximization. Total 38 RNA-seq samples were analyzed where 22 were control and 16 were disease samples Please note that the GSE134052 records represent the methylomics data.

本研究探究了多种监督式机器学习方法在基于转录组学与甲基化组学数据训练的模型中，区分子宫内膜异位症样本与对照样本的分类性能，所涉方法包括决策树、偏最小二乘判别分析（PLSDA）、支持向量机及随机森林。本研究从两个不同维度展开评估以优化分类性能：其一为三种不同归一化技术的应用效果，其二为基于广义线性模型（GLM）的差异分析的应用价值。研究结论表明，适用于子宫内膜异位症的机器学习诊断流程，应针对转录组学数据采用TMM归一化，针对甲基化组学数据采用分位数归一化或voom归一化，并通过GLM实现特征空间降维与分类性能最大化。本次研究共分析38例RNA测序样本，其中对照样本22例，疾病样本16例。请注意，GSE134052数据集对应本次研究的甲基化组学数据。