Abstract

Clustering unleashes the power of scRNA-seq through identification of appropriate cell groups. Most existing clustering methods applied on or developed for scRNA-seq data require user inputs. A few also require rigorous external preprocessing. In this paper, we propose an effective clustering method, which integrates required preprocessing steps for data cleaning, followed by robust cell group identification method from scRNA-seq data. The method is completely free of user input, although it requires threshold setting. We compare our method with 14 recent clustering methods on 12 real-world scRNA-seq datasets in terms of internal cluster evaluation matrices, and running time. Our method outperforms most other methods. Sensitivity and robustness analyses of the proposed method are also carried out extensively to understand the effect of the thresholds, followed by benchmarking. Our method is available as an R package at https://sites.google.com/view/hussinchowdhury/software for download.

Full Text
Published version (Free)

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call