Cell Type Annotation of scRNA-seq Data Using Machine Learning Approaches

Single-cell RNA sequencing (scRNA-seq) enables high-resolution characterization of cellular heterogeneity,offering unprecedented insights into complex biological systems. A key step in translating these data intobiological knowledge is accurate cell-type annotation, which defines the unique transcriptomic profiles ofindividual cells. However, manual annotation is often impractical in large-scale single-cell studies due to itsreliance on expert knowledge, time-intensive nature, and inherent subjectivity. Machine learning-basedannotation provides a powerful alternative, allowing the automated extraction of meaningful biologicalinsights from scRNA-seq data. This study provides a comparative evaluation of supervised machine learningmethods for cell-type annotation in scRNA-seq data. We assessed the performance of widely used algorithmsacross multiple datasets representing diverse tissue types, sample sizes, and cellular compositions. Ourresults show that the k-Nearest Neighbors (kNN) and Random Forest (RF) classifiers achieved the mostbalanced trade-off between accuracy and sensitivity. These findings underscore the potential of automatedscRNA-seq analysis to enhance the accuracy, reproducibility, and efficiency of cell-type annotation in largescale single-cell studies.