Single cell RNA-seq data clustering using TF-IDF based methods


Single cell transcriptomics is critical for understanding cellular heterogeneity and identification of novel cell types. Leveraging the recent advances in single cell RNA sequencing (scRNA-Seq) technology requires novel unsupervised clustering algorithms that are robust to high levels of technical and biological noise and scale to datasets of millions of cells.

University of Connecticut researchers present novel computational approaches for clustering scRNA-seq data based on the Term Frequency – Inverse Document Frequency (TF-IDF) transformation that has been successfully used in the field of text analysis.

Compared scRNA-Seq clustering methods


Empirical experimental results show that TF-IDF methods consistently outperform commonly used scRNA-Seq clustering approaches.

Moussa M, Măndoiu II. (2018) Single cell RNA-seq data clustering using TF-IDF based methods. BMC Genomics 19(Suppl 6):569. [article]

Articles You May Like

Kicking neural network automation into high gear
Materials could delay frost up to 300 times longer than existing anti-icing coatings
Statisticians’ Call To Arms: Reject Significance And Embrace Uncertainty!
When it comes to monarchs, fall migration matters
U.S. Mathematician Becomes First Woman To Win Abel Prize, ‘Math’s Nobel’

Leave a Reply

Your email address will not be published. Required fields are marked *