% Generated by roxygen2: do not edit by hand
% Please edit documentation in R/HiC2Tree.R
\name{HiC2Tree}
\alias{HiC2Tree}
\title{Convert Hi-C to trees}
\usage{
HiC2Tree(files, format, binsize = NULL, index = NULL, chromosomes, replicates)
}
\arguments{
\item{files}{A character vector containing the file paths of the input data.}

\item{format}{A character vector indicating the format of the input data:
"tabular", "cooler", "juicer", or "HiC-Pro".}

\item{binsize}{An integer indicating the bin size of the Hi-C matrix.}

\item{index}{A character indicating the path of the index for the input data.
Required (and used) only with the "HiC-Pro" format.}

\item{chromosomes}{A vector containing the chromosomes to be included in the
analysis.}

\item{replicates}{An integer indicating the number of replicates to be used
in \code{treediff}.}
}
\value{
A list containing:
\item{trees}{ A list of all trees.}
\item{metadata}{ A data frame containing the following columns: names (name
of each tree), chromosome, cluster, and file.}
\item{index}{ A data table containing the correspondence of each bin in the
genome.}
\item{testRes}{ A list of treediff results for each cluster.}
}
\description{
This function converts Hi-C data into trees, using 
\link[adjclust]{adjClust}. It takes as input a file path vector, the format 
of the input data, the bin size of the Hi-C array, the chromosomes to be 
included in the analysis, and the number of replicates. It returns a list 
containing all trees, metadata, index and treediff results.
}
\examples{
replicates <- 1:3
cond <- c("90", "110")
all_begins <- interaction(expand.grid(replicates, cond), sep = "-")
all_begins <- as.character(all_begins)

# single chromosome
nb_chr <- 1
chromosomes <- 1:nb_chr
all_mat_chr <- lapply(chromosomes, function(chr) {
  all_mat <- lapply(all_begins, function(ab) {
    mat_file <- paste0("Rep", ab, "-chr", chr, "_200000.bed")
  })
  all_mat <- unlist(all_mat)
})
index <- system.file("extdata", "index.200000.longest18chr.abs.bed",
                     package = "treediff")
format <- rep("HiC-Pro", length(replicates) * length(cond) * nb_chr)
binsize <- 200000
files <- system.file("extdata", unlist(all_mat_chr), package = "treediff")
replicates <- c(3, 3)
HiC2Tree(files, format, binsize, index, chromosomes, replicates)

\dontrun{
# two chromosomes
nb_chr <- 2
chromosomes <- 1:nb_chr
all_mat_chr <- lapply(chromosomes, function(chr) {
  all_mat <- lapply(all_begins, function(ab) {
    mat_file <- paste0("Rep", ab, "-chr", chr, "_200000.bed")
  })
  all_mat <- unlist(all_mat)
})
files <- system.file("extdata", unlist(all_mat_chr), package = "treediff")
format <- rep("HiC-Pro", length(replicates) * length(cond) * nb_chr)
replicates <- c(3, 3)
HiC2Tree(files, format, binsize, index, chromosomes, replicates)
}

}
\references{
Christophe Ambroise, Alia Dehman, Pierre Neuvial, Guillem Rigaill, and 
Nathalie Vialaneix (2019) Adjacency-constrained hierarchical clustering of a
band similarity matrix with application to genomics. \emph{Algorithms for 
Molecular Biology}, \strong{14}(22), 363–389.
}