Dropclust: Efficient clustering of ultra-large scRNA-seq data

Authors

Debajyoti Sinha, Indian Statistical Institute, Kolkata
Akhilesh Kumar, Indian Institute of Science Education and Research Bhopal
Himanshu Kumar, Indian Institute of Science Education and Research Bhopal
Sanghamitra Bandyopadhyay, Indian Statistical Institute, Kolkata
Debarka Sengupta, Indraprastha Institute of Information Technology, Delhi

Article Type

Research Article

Publication Title

Nucleic Acids Research

Abstract

Droplet based single cell transcriptomics has recently enabled parallel screening of tens of thousands of single cells. Clustering methods that scale for such high dimensional data without compromising accuracy are scarce. We exploit Locality Sensitive Hashing, an approximate nearest neighbour search technique to develop a de novo clustering algorithm for large-scale single cell data. On a number of real datasets, dropClust outperformed the existing best practice methods in terms of execution time, clustering accuracy and detectability of minor cell sub-types.

DOI

10.1093/nar/gky007

Publication Date

4-6-2018

Comments

All Open Access, Gold, Green

Recommended Citation

Sinha, Debajyoti; Kumar, Akhilesh; Kumar, Himanshu; Bandyopadhyay, Sanghamitra; and Sengupta, Debarka, "Dropclust: Efficient clustering of ultra-large scRNA-seq data" (2018). Journal Articles. 1414.
https://digitalcommons.isical.ac.in/journal-articles/1414