Selecting Classification Methods for Small Samples of Next-Generation Sequencing Data

Abstract

Next-generation sequencing has emerged as an essential technology for the quantitative analysis of gene expression. In medical research, RNA sequencing (RNA-seq) data are commonly used to identify which type of disease a patient has. Because of the discrete nature of RNA-seq data, the existing statistical methods that have been developed for microarray data cannot be directly applied to RNA-seq data. Existing statistical methods usually model RNA-seq data by a discrete distribution, such as the Poisson, the negative binomial, or the mixture distribution with a point mass at zero and a Poisson distribution to further allow for data with an excess of zeros. Consequently, analytic tools corresponding to the above three discrete distributions have been developed: Poisson linear discriminant analysis (PLDA), negative binomial linear discriminant analysis (NBLDA), and zero-inflated Poisson logistic discriminant analysis (ZIPLDA). However, it is unclear what the real distributions would be for these classifications when applied to a new and real dataset. Considering that count datasets are frequently characterized by excess zeros and overdispersion, this paper extends the existing distribution to a mixture distribution with a point mass at zero and a negative binomial distribution and proposes a zero-inflated negative binomial logistic discriminant analysis (ZINBLDA) for classification. More importantly, we compare the above four classification methods from the perspective of model parameters, as an understanding of parameters is necessary for selecting the optimal method for RNA-seq data. Furthermore, we determine that the above four methods could transform into each other in some cases. Using simulation studies, we compare and evaluate the performance of these classification methods in a wide range of settings, and we also present a decision tree model created to help us select the optimal classifier for a new RNA-seq dataset. The results of the two real datasets coincide with the theory and simulation analysis results. The methods used in this work are implemented in the open-scource R scripts, with a source code freely available at https://github.com/FocusPaka/ZINBLDA.

Classification of RNA-Sequencing Data Via Poisson and Negative Binomial Linear Discriminant Analyses: A Methodological Study

“…The current body of literature suggests the utilization of zero-inflated mixture distributions for the classification analysis of RNA-Seq data. Two recent techniques in this regard are the zero-inflated Poisson logistic discriminant analysis, introduced by Zhou et al, and the zero-inflated negative binomial logistic discriminant analysis, proposed by Zhu et al 26,27 Although the zero-inflated classifiers were not employed in our study, it is worth considering the comparison of NBLDA and PLDA with zero-inflated models.…”

Machine Learning-Aided Microdroplets Breakup Characteristic Prediction in Flow-Focusing Microdevices by Incorporating Variations of Cross-Flow Tilt Angles

“…The LDA classification technique has been previously described in detail. 38 The MLP classification method is the most widely used variant of ANN. The MLP technique's ability to solve nonlinear problems is the main advantage of this technique over linear techniques.…”

“…Then, accuracy calculation is done by comparing the results with the known objective matrix. The LDA classification technique has been previously described in detail . The MLP classification method is the most widely used variant of ANN.…”