adjclust: Adjacency-Constrained Clustering of a Block-Diagonal Similarity Matrix

Implements a constrained version of hierarchical agglomerative clustering, in which each observation is associated to a position, and only adjacent clusters can be merged. Typical application fields in bioinformatics include Genome-Wide Association Studies or Hi-C data analysis, where the similarity between items is a decreasing function of their genomic distance. Taking advantage of this feature, the implemented algorithm is time and memory efficient. This algorithm is described in Ambroise et al (2019) <https://almob.biomedcentral.com/articles/10.1186/s13015-019-0157-4>.

Version: 0.6.5
Depends: R (≥ 4.0.0)
Imports: stats, graphics, grDevices, Rcpp (≥ 1.0.6), Matrix, sparseMatrixStats, methods, utils, capushe
LinkingTo: Rcpp, RcppArmadillo
Suggests: knitr, testthat, rmarkdown, rioja, HiTC, snpStats, BiocGenerics
Published: 2022-08-18
Author: Christophe Ambroise [aut], Shubham Chaturvedi [aut], Alia Dehman [aut], Pierre Neuvial [aut, cre], Guillem Rigaill [aut], Nathalie Vialaneix [aut], Gabriel Hoffman [aut]
Maintainer: Pierre Neuvial <pierre.neuvial at math.univ-toulouse.fr>
BugReports: https://github.com/pneuvial/adjclust/issues
License: GPL-3
URL: https://pneuvial.github.io/adjclust/
NeedsCompilation: yes
Language: en-US
Citation: adjclust citation info
Materials: README NEWS
CRAN checks: adjclust results

Documentation:

Reference manual: adjclust.pdf
Vignettes: Clustering of Hi-C contact maps
Implementation notes for the adjclust package
Inferring Linkage Disequilibrium blocks from genotypes

Downloads:

Package source: adjclust_0.6.5.tar.gz
Windows binaries: r-devel: adjclust_0.6.5.zip, r-release: adjclust_0.6.5.zip, r-oldrel: adjclust_0.6.5.zip
macOS binaries: r-release (arm64): adjclust_0.6.5.tgz, r-oldrel (arm64): adjclust_0.6.5.tgz, r-release (x86_64): adjclust_0.6.5.tgz, r-oldrel (x86_64): adjclust_0.6.5.tgz
Old sources: adjclust archive

Linking:

Please use the canonical form https://CRAN.R-project.org/package=adjclust to link to this page.