Evaluating the Performance of the Generalized Linear Model (glm) R Package Using Single-Cell RNA-Sequencing Data

Abstract

The glm R package is commonly used for generalized linear modeling. In this paper, we evaluate the ability of the glm package to predict binomial outcomes using logistic regression. We use single-cell RNA-sequencing datasets, after a series of normalization, to fit data into glm models repeatedly using 10-fold cross-validation over 100 iterations. Our evaluation criteria are glm’s Precision, Recall, F1-Score, Area Under the Curve (AUC), and Runtime. Scores for each evaluation category are collected, and their medians are calculated. Our findings show that glm has fluctuating Precision and F1-Scores. In terms of Recall, glm has shown more stable performance, while in the AUC category, glm shows remarkable performance. Also, the Runtime of glm is consistent. Our findings also show that there are no correlations between the size of fitted data and glm’s Precision, Recall, F1-Score, and AUC, except for Runtime.