Comparative Analysis of Supervised Cell Type Detection in Single-Cell RNA-seq Data

Vasighizaker, Akram; Hora, Sheena; Trivedi, Yash; Rueda, Luis

doi:10.1007/978-3-031-07802-6_28

Cited by 1 publication

(2 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The idea behind gene selection in cell type identification is motivated by the fact that cell types are often distinguished by only a few essential genes known as biomarkers. The effectiveness of three general-purpose feature selection methods was explored in cell-type classification problems in [ 16 ], including Analysis of Variance (ANOVA) F-value, Chi-squared, and information gain. The findings show that information gain yields the best biomarkers among all other models.…”

Section: Methodsmentioning

confidence: 99%

“…XGBoost is well-suited to large datasets by performing in parallel. Moreover, in our recent comparative study, it has been shown that the support vector machine (SVM), with the help of information gain (IG), as a feature selection method, outperformed the other approaches [ 16 ]. The study was performed on nine different experiments composed of three different state-of-the-art popular classifiers combined with three general-purpose feature selection methods.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Cell Type Annotation Model Selection: General-Purpose vs. Pattern-Aware Feature Gene Selection in Single-Cell RNA-Seq Data

Vasighizaker

Trivedi

Rueda

2023

Genes

View full text Add to dashboard Cite

With the advances in high-throughput sequencing technology, an increasing amount of research in revealing heterogeneity among cells has been widely performed. Differences between individual cells’ functionality are determined based on the differences in the gene expression profiles. Although the observations indicate a great performance of clustering methods, manual annotation of the clusters of cells is a challenge yet to be addressed more scalable and faster. On the other hand, due to the lack of enough labelled datasets, just a few supervised techniques have been used in cell type identification, and they obtained more robust results compared to clustering methods. A recent study showed that a complementary step of feature selection helped support vector machine (SVM) to outperform other classifiers in different scenarios. In this article, we compare and evaluate the performance of two state-of-the-art supervised methods, XGBoost and SVM, with information gain as a feature selection method. The results of the experiments on three standard scRNA-seq datasets indicate that XGBoost automatically annotates cell types in a simpler and more scalable framework. Additionally, it sheds light on the potential use of boosting tree approaches combined with deep neural networks to capture underlying information of single-cell RNA-Seq data more effectively. It can be used to identify marker genes and other applications in biological studies.

show abstract

Section: Methodsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%