@article{Wolff_Backofen_Gruning-Robus_and_effic-2021,
author = {Wolff, Joachim and Backofen, Rolf and Grüning, Björn},
title = {Robust and efficient single-cell {Hi}-{C} clustering with 
         approximate k-nearest neighbor graphs},
journal = {Bioinformatics},
year = {2021},
doi = {10.1093/bioinformatics/btab394},
volume = {37},
user = {backofen},
pmid = {34021764},
pages = {4006-4013},
number = {22},
issn = {1367-4803},
abstract = {MOTIVATION: Hi-C technology provides insights into the 3D 
            organization of the chromatin, and the single-cell Hi-C 
            method enables researchers to gain knowledge about the 
            chromatin state in individual cell levels. Single-cell Hi-C 
            interaction matrices are high dimensional and very sparse. 
            To cluster thousands of single-cell Hi-C interaction 
            matrices, they are flattened and compiled into one matrix. 
            Depending on the resolution, this matrix can have a few 
            million or even billions of features; therefore, 
            computations can be memory intensive. We present a 
            single-cell Hi-C clustering approach using an approximate 
            nearest neighbors method based on locality-sensitive hashing 
            to reduce the dimensions and the computational resources. 
            RESULTS: The presented method can process a 10 kb 
            single-cell Hi-C dataset with 2600 cells and needs 40 GB of 
            memory, while competitive approaches are not computable even 
            with 1 TB of memory. It can be shown that the 
            differentiation of the cells by their chromatin folding 
            properties and, therefore, the quality of the clustering of 
            single-cell Hi-C data is advantageous compared to 
            competitive algorithms. AVAILABILITY AND IMPLEMENTATION: The 
            presented clustering algorithm is part of the scHiCExplorer, 
            is available on Github 
            https://github.com/joachimwolff/scHiCExplorer, and as a 
            conda package via the bioconda channel. The approximate 
            nearest neighbors implementation is available via 
            https://github.com/joachimwolff/sparse-neighbors-search and 
            as a conda package via the bioconda channel. SUPPLEMENTARY 
            INFORMATION: Supplementary data are available at 
            Bioinformatics online.}
}