untangle dendrograms

One untangle function to rule them all.

This function untangles dendrogram lists (dendlist), Using various heuristics.

untangle(dend1, ...)

# Default S3 method
untangle(dend1, ...)

untangle_labels(dend1, dend2, ...)

# S3 method for class 'dendrogram'
untangle(
  dend1,
  dend2,
  method = c("labels", "ladderize", "random", "step1side", "step2side", "stepBothSides",
    "DendSer"),
  ...
)

# S3 method for class 'dendlist'
untangle(
  dend1,
  method = c("labels", "ladderize", "random", "step1side", "step2side", "DendSer"),
  which = c(1L, 2L),
  ...
)

Arguments

dend1

a dendrogram or a dendlist object

...

passed to the relevant untangle function

dend2

A second dendrogram (to untangle against)

method

a character indicating the type of untangle heuristic to use. The options are: ("labels", "ladderize", "random", "step1side", "step2side", "stepBothSides", "DendSer")

which

an integer vector of length 2, indicating which of the trees in the dendlist object should be plotted

Value

A dendlist, with two trees after they have been untangled.

If the dendlist was originally larger than 2, it will return the original dendlist but with the relevant trees properly rotate.

Details

This function wraps all of the untangle functions, in order to make it easier to find our about (and use) them.

See also

tanglegram, untangle_random_search, untangle_step_rotate_1side, untangle_step_rotate_2side, untangle_DendSer, entanglement

Author

Tal Galili

Examples

if (FALSE) { # \dontrun{
set.seed(23235)
ss <- sample(1:150, 10)
dend1 <- iris[ss, -5] %>%
  dist() %>%
  hclust("com") %>%
  as.dendrogram()
dend2 <- iris[ss, -5] %>%
  dist() %>%
  hclust("sin") %>%
  as.dendrogram()
dend12 <- dendlist(dend1, dend2)

dend12 %>% tanglegram()

untangle(dend1, dend2, method = "random", R = 5) %>% tanglegram()

# it works, and we get something different:
set.seed(1234)
dend12 %>%
  untangle(method = "random", R = 5) %>%
  tanglegram()

set.seed(1234)
# fixes it completely:
dend12 %>%
  untangle(method = "random", R = 5) %>%
  untangle(method = "step1") %>%
  tanglegram()
# not good enough
dend12 %>%
  untangle(method = "step1") %>%
  tanglegram()
# not good enough
dend12 %>%
  untangle(method = "step2") %>%
  tanglegram()
# How we might wish to use it:
set.seed(12777)
dend12 %>%
  untangle(method = "random", R = 1) %>%
  untangle(method = "step2") %>%
  tanglegram()
} # }