cluster_position: Build Hierarchical Tree based on Position

Description Usage Arguments Details Value References See Also Examples

Description

Build a hierarchical tree based on the position of the variables.

Usage

1
2
cluster_position(position, block = NULL, sort.parallel = TRUE,
  parallel = c("no", "multicore", "snow"), ncpus = 1L, cl = NULL)

Arguments

position

a data frame with two columns specifying the variable names and the corresponding position or a list of data frames for multiple data sets. The first column is required to contain the variable names and to be of type character. The second column is required to contain the position and to be of type numeric.

block

a data frame or matrix specifying the second level of the hierarchical tree. The first column is required to contain the variable names and to be of type character. The second column is required to contain the group assignment and to be a vector of type character or numeric. If not supplied, the second level is built based on the data.

sort.parallel

a logical indicating whether the values are sorted with respect to the size of the block. This can reduce the run time for parallel computation.

parallel

type of parallel computation to be used. See the 'Details' section.

ncpus

number of processes to be run in parallel.

cl

an optional parallel or snow cluster used if parallel = "snow". If not supplied, a cluster on the local machine is created.

Details

The hierarchical tree is built based on recursive binary partitioning of consecutive variables w.r.t. their position. The partitioning consists of splitting a given node / cluster into two children of about equal size based on the positions of the variables. If a node contains an odd number of variables, then the variable in the middle w.r.t. position is assigned to the cluster containing the closest neighbouring variable. Hence, clusters at a given depth of the binary hierarchical tree contain about the same number of variables.

If the argument block is supplied, i.e. the second level of the hierarchical tree is given, the function can be run in parallel across the different blocks by specifying the arguments parallel and ncpus. There is an optional argument cl if parallel = "snow". There are three possibilities to set the argument parallel: parallel = "no" for serial evaluation (default), parallel = "multicore" for parallel evaluation using forking, and parallel = "snow" for parallel evaluation using a parallel socket cluster. It is recommended to select RNGkind("L'Ecuyer-CMRG") and set a seed to ensure that the parallel computing of the package hierinf is reproducible. This way each processor gets a different substream of the pseudo random number generator stream which makes the results reproducible if the arguments (as sort.parallel and ncpus) remain unchanged. See the vignette or the reference for more details.

Value

The returned value is an object of class "hierD", consisting of two elements, the argument "block" and the hierarchical tree "res.tree".

The element "block" defines the second level of the hierarchical tree if supplied.

The element "res.tree" contains a dendrogram for each of the blocks defined in the argument block. If the argument block is NULL (i.e. not supplied), the element contains only one dendrogram.

References

Renaux, C. et al. (2018), Hierarchical inference for genome-wide association studies: a view on methodology with software. (arXiv:1805.02988)

See Also

cluster_var and test_hierarchy.

Examples

 1
 2
 3
 4
 5
 6
 7
 8
 9
10
# The column names of the data frames position and block are optional.
position <- data.frame("var.name" = paste0("Var", 1:500),
                       "position" = seq(from = 1, to = 1000, by = 2),
                       stringsAsFactors = FALSE)
dendr1 <- cluster_position(position = position)

block <- data.frame("var.name" = paste0("Var", 1:500),
                    "block" = rep(c(1, 2), each = 250),
                    stringsAsFactors = FALSE)
dendr2 <- cluster_position(position = position, block = block)

crbasel/hierinf documentation built on May 24, 2019, 7:14 a.m.