adjclust: Adjacency-Constrained Clustering of a Block-Diagonal Similarity Matrix (R package, available on CRAN)

Pierre Neuvial (1) , Christophe Ambroise (2) , Shubham Chaturvedi (3) , Alia Dehman (4) , Michel Koskas (2) , Guillem Rigaill (5) , Nathalie Vialaneix (6)

1 IMT - Institut de Mathématiques de Toulouse UMR5219
2 MIA-Paris - Mathématiques et Informatique Appliquées
3 Google Summer of Code
4 Hyphen-stat
5 IPS2 (UMR_9213 / UMR_1403) - Institut des Sciences des Plantes de Paris-Saclay
6 MIAT INRA - Unité de Mathématiques et Informatique Appliquées de Toulouse

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 Chapter 4 of Alia Dehman (2015) .

Mots clés: constrained hierarchical clustering; Hi-C; SNP

Domaines: Mathématiques [math]; Informatique [cs]; Sciences du Vivant [q-bio]; Biologie végétale

Pierre Neuvial, Christophe Ambroise, Shubham Chaturvedi, Alia Dehman, Michel Koskas, et al.. adjclust: Adjacency-Constrained Clustering of a Block-Diagonal Similarity Matrix (R package, available on CRAN). 2017. ⟨hal-02791370⟩