idiogramFISH: Shiny App. Idiograms with Marks and Karyotype Indices
Introduction
The goal of idiogramFISH functions or the shiny-app is to plot
karyotypes, plasmids and circular chr. having a set of data.frames for
chromosome data and optionally marks’ data (Roa and PC Telles, 2021). Karyotypes can
also be plotted in concentric circles.
It is possible to
calculate also chromosome and karyotype indexes (Romero-Zarco, 1986; Watanabe et al., 1999) and
classify chromosome morphology in the categories of Levan (1964), and Guerra
(1986).
Six styles of marks are available: square (and
squareLeft), dots, cM
(cMLeft), cenStyle, upArrow
(downArrow), exProtein
(inProtein) (in column style in
dfMarkColor data.frame); its legend (label) (parameter
legend) can be drawn inline or to the right
(aside) of karyotypes. Three styles of centromere are
available: rounded, triangle and
inProtein (cenFormat parameter). Chromosome
regions (column chrRegion in dfMarkPos
data.frame) for monocentrics are p (short), q
(long), cen, pcen, qcen. The last
three cannot accommodate most mark styles, but can be colored. The
region w (whole) can be used both in monocentrics and
holocentrics.
IdiogramFISH was written in R (R Core Team, 2019) and also uses crayon (Csárdi, 2017), tidyr (Wickham and Henry, 2020), plyr (Wickham, 2011) and dplyr packages (Wickham et al., 2019). Documentation was written with R-packages roxygen2 (Wickham et al., 2018), usethis (Wickham and Bryan, 2019), bookdown (Xie, 2016), knitr (Xie, 2015), pkgdown (Wickham and Hesselberth, 2019), Rmarkdown (Xie et al., 2018), rvcheck (Yu, 2019a), badger (Yu, 2019b), kableExtra (Zhu, 2019), rmdformats (Barnier, 2020) and RCurl (Temple Lang and CRAN team, 2019). For some vignette figures, packages rentrez (Winter, 2017), phytools (Revell, 2012), ggtree (Yu et al., 2018), ggplot2 (Wickham, 2016) and ggpubr (Kassambara, 2019) were used.
In addition, the shiny app runBoard() uses shiny (Chang et al.,
2021), shinydashboard (Chang and Borges Ribeiro, 2018),
rhandsontable (Owen, 2018), gtools (Warnes et al.,
2020) and rclipboard (Bihorel, 2021).
Run the Shiny app with docker
- No need to install R
- Install docker on your system
- Make sure you can run a docker example image, i.e. ubuntu, in the console (system terminal)
docker pull fercyto/idiogramfish
# Run the image
docker run -d -p 8080:8080 fercyto/idiogramfishIn your internet browser go to http://localhost:8080
# Stop the container
docker ps
docker stop {container id}Installation instructions
You can install idiogramFISH from CRAN with:
Windows users: To avoid installation of R-packages in OneDrive
.libPaths() # read library location
.libPaths("D:R/lib") # setTo do that permanently: Search (magnifier) “environment variables”
and set R_LIBS_USER to D:\R\lib (example)
Other option: something in the line of this link
Need help?
Vignettes
Online:
Launch vignettes from R for the installed version:
Citation
To cite idiogramFISH in publications, please use:
Roa F, Telles M. idiogramFISH: Shiny app. Idiograms with Marks and Karyotype Indices. doi: 10.5281/zenodo.3579417
To write citation to file:
1 Working online
Shiny App in the cloud availability:
shinyapps.io
Each chapter has a jupyter version. A jupyter notebook
seems an interactive vignette.
They are hosted in github
They can be accessed with google colab to work
online.
Chapters can be accessed locally in your jupyter-lab or
jupyter notebook
After installing jupyter, you can install the R kernel with:
install.packages("IRkernel")
IRkernel::installspec()
2 Shiny App
Attention Windows users, might require the last R version to plot correctly.
library(idiogramFISH)
runBoard()Shiny App in the cloud availability:
shinyapps.io
3 Minimal examples
Jupyter interactive version:
 Github
|
Raw |
3.1 Monocentrics
Define your plotting window size with something like
par(pin = c(10, 6)), or with svg(),
png(), etc. Add chromosome morphology according to Guerra
(1986) or
(Levan et al.,
1964)
library(idiogramFISH)
data(dfOfChrSize) # chromosome data
data(dfMarkColor) # mark general data
data(dfOfMarks2) # mark position data (inc. cen.)
# column Mbp not for plotting purposes
dfOfChrSize$Mbp <- (dfOfChrSize$shortArmSize + dfOfChrSize$longArmSize) * 100
svg("dfOfChrSize.svg", width = 10, height = 6)
# png("dfOfChrSize.png", width = 500, height = 400)
plotIdiograms(dfChrSize = dfOfChrSize, # data.frame of chr. size
dfMarkColor = dfMarkColor, # d.f of mark style <- Optional
dfMarkPos = dfOfMarks2, # d.f of mark positions (includes cen. marks)
karHeight = 5, # kar. height
chrWidth = 1.2, # chr. width
chrSpacing = 1, # space among chr.
morpho = "Guerra", # chr. morpho. classif. (Guerra, Levan, both, "" ) ver. >= 1.12 only
chrIndex = "CI", # cen. pos. (CI, AR, both, "" ) ver. >= 1.12 only
chrSize = TRUE, # add chr. sizes under chr.
chrSizeMbp = TRUE, # add Mbp sizes under chr. (see above)
rulerPos = 0, # position of ruler
ruler.tck = -0.01, # size and orientation of ruler ticks
rulerNumberSize = .8 # font size of rulers
, xPosRulerTitle = 3 # pos of ruler title
, legendWidth = 1 # width of legend items
, fixCenBorder = TRUE # use chrColor as border color of cen. or cen. marks
, distTextChr = 1.2 # chr. text separation
, xlimLeftMod = 0 # xlim left param.
, xlimRightMod = 3 # xlim right param.
, ylimBotMod = 0 # modify ylim bottom argument
, ylimTopMod = 0 # modify ylim top argument
)
dev.off() # close svg()Let’s explore the data.frames for monocentrics:
If only one species, column OTU is optional
dfOfChrSize| chrName | shortArmSize | longArmSize | Mbp |
|---|---|---|---|
| 1 | 3 | 4 | 700 |
| 2 | 4 | 5 | 900 |
| 3 | 2 | 3 | 500 |
| X | 1 | 2 | 300 |
dfMarkColor| markName | markColor | style |
|---|---|---|
| 5S | red | dots |
| 45S | chartreuse3 | square |
| DAPI | blue | square |
| CMA | darkgoldenrod1 | square |
p, q and w marks can have empty columns
markDistCen and markSize since v. 1.9.1 to
plot whole arms (p, q) and whole chr.
w.
# mark position data (inc. cen.)
dfOfMarks2| chrName | markName | chrRegion | markSize | markDistCen |
|---|---|---|---|---|
| 1 | 5S | p | 1 | 0.5 |
| 1 | 45S | q | 1 | 0.5 |
| X | 45S | p | NA | NA |
| 3 | DAPI | q | 1 | 1.0 |
| 1 | DAPI | cen | NA | NA |
| X | CMA | cen | NA | NA |
3.2 Holocentrics
library(idiogramFISH)
# load some package data.frames - optional
data(dfChrSizeHolo, dfMarkColor, dfMarkPosHolo)
# column Mbp not for plotting purposes
dfChrSizeHolo$Mbp <- dfChrSizeHolo$chrSize * 100
# svg("testing.svg",width = 14, height = 8 )
par(mar = c(0, 0, 0, 0), omi = rep(0, 4))
plotIdiograms(dfChrSize = dfChrSizeHolo, # data.frame of chr. size
dfMarkColor = dfMarkColor, # df of mark style
dfMarkPos = dfMarkPosHolo, # df of mark positions
addOTUName = FALSE, # do not add OTU names
distTextChr = 1, # chr. name distance to chr.
chrSize = TRUE, # show chr. size under chr.
chrSizeMbp = TRUE, # show chr. size in Mbp under chr. requires Mbp column
rulerPos = -0.1, # position of ruler
rulerNumberPos = .9 # position of numbers of rulers
, xPosRulerTitle = 3 # pos. of ruler title (units)
, xlimLeftMod = 2 # modify xlim left argument of plot
, ylimBotMod = .2 # modify ylim bottom argument of plot
, legendHeight = .5 # height of legend labels
, legendWidth = 1.2 # width of legend labels
, xModifier = 20 # separ. among chromatids
)
Let’s explore the data.frames for holocentrics:
- chromosome data, if only 1 species, column OTU is optional
dfChrSizeHolo| chrName | chrSize | Mbp |
|---|---|---|
| 1 | 3 | 300 |
| 2 | 4 | 400 |
| 3 | 2 | 200 |
| 4 | 5 | 500 |
- mark general data
dfMarkColor| markName | markColor | style |
|---|---|---|
| 5S | red | dots |
| 45S | chartreuse3 | square |
| DAPI | blue | square |
| CMA | darkgoldenrod1 | square |
- mark position data, if only 1 species, column OTU is optional (mandatory if in d.f of Chr. Size)
dfMarkPosHolo| chrName | markName | markPos | markSize |
|---|---|---|---|
| 3 | 5S | 1.0 | 0.5 |
| 3 | DAPI | 1.5 | 0.5 |
| 1 | 45S | 2.0 | 0.5 |
| 2 | DAPI | 2.0 | 0.5 |
| 4 | CMA | 2.0 | 0.5 |
| 4 | 5S | 0.5 | 0.5 |
3.3 Plotting both mono. and holo.
Merge data.frames with plyr (Wickham, 2011)
# chromosome data, if only 1 species, column OTU is optional
require(plyr)
dfOfChrSize$OTU <- "Species mono"
dfChrSizeHolo$OTU <- "Species holo"
monoholoCS <- plyr::rbind.fill(dfOfChrSize, dfChrSizeHolo)
dfOfMarks2$OTU <- "Species mono"
dfOfMarks2[which(dfOfMarks2$markName == "5S"), ]$markSize <- .7
dfMarkPosHolo$OTU <- "Species holo"
monoholoMarks <- plyr::rbind.fill(dfOfMarks2, dfMarkPosHolo)Plot
library(idiogramFISH)
# svg("testing.svg",width = 14, height = 10 )
png("monoholoCS.png", width = 700, height = 600)
par(mar = rep(0, 4))
plotIdiograms(dfChrSize = monoholoCS, # data.frame of chr. size
dfMarkColor = dfMarkColor, # df of mark style
dfMarkPos = monoholoMarks, # df of mark positions, includes cen. marks
chrSize = TRUE, # show chr. size under chr.
squareness = 4, # vertices squareness
addOTUName = TRUE, # add OTU names
OTUTextSize = .7, # font size of OTU
distTextChr = .5, # separ. among chr. and text and among chr. name and indices
karHeiSpace = 4, # karyotype height inc. spacing
karIndexPos = .2, # move karyotype index
legendHeight = 1, # height of legend labels
legendWidth = 1, # width of legend labels
fixCenBorder = TRUE, # use chrColor as border color of cen. or cen. marks
rulerPos = 0, # position of ruler
ruler.tck = -0.02, # size and orientation of ruler ticks
rulerNumberPos = .9, # position of numbers of rulers
xPosRulerTitle = 3.5, # ruler title (units) position
xlimLeftMod = 1, # modify xlim left argument of plot
xlimRightMod = 3, # modify xlim right argument of plot
ylimBotMod = 0.2 # modify ylim bottom argument of plot
, chromatids = FALSE # do not show separ. chromatids
# ,useOneDot = TRUE
# ,circularPlot = TRUE # circularPlot
# ,shrinkFactor = .9 # percentage 1 = 100% of circle with chr.
# ,circleCenter = 3 # X coordinate of circleCenter (affects legend pos.)
# ,chrLabelSpacing = .9 # chr. names spacing
# ,OTUsrt = 0 # angle for OTU name (or number)
# ,OTUplacing = "number" # Use number and legend instead of name
# ,OTULabelSpacerx = -0.6 # modify position of OTU label, when OTUplacing = "number" or "simple"
# ,OTUlegendHeight = 1.5 # space among OTU names when in legend - OTUplacing
# ,separFactor = 0.75 # alter separ. of kar.
)
dev.off() # close png
4 Plotting chromosomes
Jupyter interactive version:|
Github
|
Raw |
This guide shows how to plot idiograms of measured karyotypes and optionally marks.
4.1 Load package
Visit the Introduction for installation instructions
library(idiogramFISH) 4.2 Plot monocentrics
Initially you have to put chromosome data in data.frames.
Main three data.frames:
- One for chr. sizes (parameter
dfChrSize) - One for marks’ positions (parameter
dfMarkPos) - One (optional) for mark style (parameter
dfMarkColor)
For a way to start with only one data.frame of chr. size and marks’ pos., see Chapter 8.
data.frame of chr. size
# Example data.frame to write in R, use: (column OTU is optional if only 1 OTU)
mydfChrSize <- read.table(text =
" OTU chrName shortArmSize longArmSize
\"Species one\" 1 1.5 2.0
\"Species one\" 2 2.0 2.5
\"Species one\" 3 1.0 1.5
\"Species one\" B 2.0 3.5", header = TRUE, stringsAsFactors = FALSE, fill = TRUE)| OTU | chrName | shortArmSize | longArmSize |
|---|---|---|---|
| Species one | 1 | 1.5 | 2.0 |
| Species one | 2 | 2.0 | 2.5 |
| Species one | 3 | 1.0 | 1.5 |
| Species one | B | 2.0 | 3.5 |
loading saved data:
If you use RStudio, in the menu “Session”, use “Set working directory” for choosing your desired folder or:
setwd("~/folder/subfolder")Open your chromosome data data.frame importing it from a .csv (read.csv) or .xls file (readxl).
mydfChrSize<-read.csv("somefile.csv")Editing a data.frame:
bigdfOfChrSize <- edit(bigdfOfChrSize, edit.row.names = FALSE)For fixing column names use:
colnames(mydfChrSize)<-c("OTU", "chrName","shortArmSize","longArmSize")Marks’ position data
Open or write your mark positions in a data.frame. This data.frame has the marks present in all karyotypes with position info. This data.frame has also the centromeric marks present in all karyotypes.
Column chrRegion defines the arm or region of occurrence
(p, q, w, cen).
Distance to centromere is defined in markDistCen.
# We will use column OTU if data.frame because chromosome size df has it
mydfOfMarks <- read.table(text =
" OTU chrName markName chrRegion markSize markDistCen
\"Species one\" 1 45S p NA NA # no measure (NA) means whole arm
\"Species one\" 1 5S q 0.5 0.5
\"Species one\" B \"B mark\" w NA NA # w for whole chromosome
\"Species one\" B \"cB mark\" q NA 1.0
\"Species one\" 2 cgene4 p 1 1.0
\"Species one\" 2 cgene1 q 1 1
\"Species one\" 2 cgene2 q 0.5 2.0
\"Species one\" 3 DAPI q NA 1
\"Species one\" 3 cgene3 p NA 0.5
\"Species one\" 1 DAPI pcen
\"Species one\" 3 CMA qcen
\"Species one\" 2 CMA cen", header = TRUE, stringsAsFactors = FALSE, fill = TRUE)| OTU | chrName | markName | chrRegion | markSize | markDistCen |
|---|---|---|---|---|---|
| Species one | 1 | 45S | p | NA | NA |
| Species one | 1 | 5S | q | 0.5 | 0.5 |
| Species one | B | B mark | w | NA | NA |
| Species one | B | cB mark | q | NA | 1.0 |
| Species one | 2 | cgene4 | p | 1.0 | 1.0 |
| Species one | 2 | cgene1 | q | 1.0 | 1.0 |
| Species one | 2 | cgene2 | q | 0.5 | 2.0 |
| Species one | 3 | DAPI | q | NA | 1.0 |
| Species one | 3 | cgene3 | p | NA | 0.5 |
| Species one | 1 | DAPI | pcen | NA | NA |
| Species one | 3 | CMA | qcen | NA | NA |
| Species one | 2 | CMA | cen | NA | NA |
For fixing column names use something like:
colnames(mydfMarkColor)<-c("OTU", "chrName","markName","chrRegion","markSize","markDistCen") Marks’ general data
This data.frame is optional. It has the marks present in all karyotypes without position info.
It includes color and style. If the style column is not
present, param. defaultStyleMark = "square" will be used
during plotting.
Note the cenStyle to make constrictions, mimicking
centromeres.
# From scratch:
mydfMarkColor <- read.table(text =
" markName markColor style
5S red dots
45S chartreuse3 square
cgene1 chocolate upArrow
cgene2 salmon downArrow
cgene3 \"#056522\" cMLeft
DAPI dodgerblue cM
\"cB mark\" black cenStyle
CMA darkgoldenrod1 square
\"B mark\" black square
cgene4 cornflowerblue exProtein", header = TRUE, stringsAsFactors = FALSE, fill = TRUE)| markName | markColor | style |
|---|---|---|
| 5S | red | dots |
| 45S | chartreuse3 | square |
| cgene1 | chocolate | upArrow |
| cgene2 | salmon | downArrow |
| cgene3 | #056522 | cMLeft |
| DAPI | dodgerblue | cM |
| cB mark | black | cenStyle |
| CMA | darkgoldenrod1 | square |
| B mark | black | square |
| cgene4 | cornflowerblue | exProtein |
For fixing column names use:
colnames(mydfMarkColor)<-c("markName", "markColor","style")
# if style column is not present it will be filled with "square"Add some text to the right
We will use column note to add a note to the right of the karyotype of the specified OTU (see column OTU)
notesdf<-read.table(text=
" OTU note
\"Species one\" \"Author notes\" ", header = TRUE, stringsAsFactors = FALSE, fill = TRUE)For adding just the OTU name (from column OTU of
data.frame of chr. size) to the right, use
OTUasNote = TRUE
Plotting
You can plot without marks (use only 1st data.frame), but we will use
all 4 data.frames created. By default the function will calculate
indices (Romero-Zarco, 1986; Watanabe et al., 1999) and
morphological categories of Guerra
(1986) and
Levan (1964).
Use parameters chrIndex and morpho of the
function plotIdiograms to modify that. See
?plotIdiograms.
The cM style of mark always adds the name as if
legend = "inline", even when legend = "aside"
(default).
# svg("mydfChrSize.svg",width = 12, height = 6 )
par(mar = c(0, 0, 0, 0))
plotIdiograms(dfChrSize = mydfChrSize, # chr. size data.frame
dfMarkPos = mydfOfMarks, # mark position data.frame (inc. cen.)
dfMarkColor = mydfMarkColor, # mark style d.f.
chrSpacing = .6, # separ. among chr.
distTextChr = .7, # separation among text and chr. names and ind.
orderChr = "name", # order chr. by name
karHeiSpace = 2 # vertical size of karyotype including spacer
, arrowhead = .5 # proportion of head of arrow
, fixCenBorder = TRUE # use chrColor as border color of cen. or cen. marks
, legendWidth = .8 # legend item width
, legendHeight = .5 # legend item height
, markLabelSpacer = 2 # legend spacer
, lwd.mimicCen = 2.5 # constric. mark line width
, rulerPos = 0 # ruler position
, ruler.tck = -0.01 # ticks of ruler size and orientation
, xPosRulerTitle = 2.5 # ruler units pos.
, markPer = "45S" # show mark % of chr. under kar.
, showMarkPos = TRUE # show position of marks under kar. See bToRemove
, bToRemove = c("B mark", "cB mark") # bands to remove from pos. calc. See showMarkPos
, notes = notesdf # data.frame with notes
, notesTextSize = 1.3 # font size of notes
, notesPosX = .2 # space from chr. (right) to note
, ylimBotMod = 2 # modify ylim bottom argument
, ylimTopMod = 0 # modify ylim top argument
, xlimLeftMod = 2 # modify left xlim
, xlimRightMod = 3 # modify right xlim
, lwd.cM = 2 # thickness of cM marks
, pattern = "^c" # regex pattern to remove from mark names
, remSimiMarkLeg = TRUE # remove pseudoduplicated mark names from legend (same after pattern removal)
, legendYcoord = -1.2
# ,legend = "inline" # legend next to chr.
, bannedMarkName = c("B mark", "cB mark") # remove from legends
) # ; dev.off() # close .svg
Vertices when centromereSize = 0 are rounded:
png("mydfChrSize2.png", width = 550, height = 550)
par(mar = c(0, 0, 0, 0))
plotIdiograms(dfChrSize = bigdfOfChrSize[1:8, ], # chr. size data.frame
dfMarkColor = mydfMarkColor, # mark style df
dfMarkPos = bigdfOfMarks, # mark position df
centromereSize = 0, # <- HERE
squareness = 3, # vertices squareness
chrSpacing = .7, # space among chr.
karHeight = 2, # karyotype rel. height
karHeiSpace = 4, # vertical size of karyotype including spacer
amoSepar = 2.5, # separation among karyotype
indexIdTextSize = .8, # font size of chr. name and indices
karIndexPos = .1, # position of kar. index
markLabelSize = .7, # font size of mark legends
fixCenBorder = FALSE, # do not use chrColor as border color of cen. or cen. marks
distTextChr = .8, # separation among chr. and ind.
rulerPos = 0, # ruler position
ruler.tck = -0.01, # ticks of ruler size and orientation
xPosRulerTitle = 2.6, # ruler units pos.
xlimLeftMod = 2, # modify xlim left argument
ylimBotMod = 0.4, # modify ylim bottom argument
ylimTopMod = 0 # modify ylim top argument
, lwd.cM = 2 # thickness of cM marks
)
dev.off()
There is no need to add dfMarkColor and you can also use
the parameter mycolors (optional too), to establish marks’
colors. Colors are assigned depending on the order of marks, i.e.:
unique(mydfOfMarks$markName) Let’s use the cM style of marks. A protruding line.
cM style does not apply to centromere marks. To make
something similar, use centromereSize = 0,
legend = "inline" and
fixCenBorder = FALSE.
charVectorCol <- c("tomato3", "darkolivegreen4", "dfsd", "dodgerblue", "chartreuse3")
# Modify size of kar. to use rulerInterval and ceilingFactor (>= 1.13)
quo <- 9
dfOfChrSize2 <- dfOfChrSize
dfOfChrSize2$shortArmSize <- dfOfChrSize$shortArmSize / quo
dfOfChrSize2$longArmSize <- dfOfChrSize$longArmSize / quo
dfOfMarks2b <- dfOfMarks2
dfOfMarks2b$markSize <- dfOfMarks2$markSize / quo
dfOfMarks2b$markDistCen <- dfOfMarks2$markDistCen / quo
png("dfOfChrSizeVector.png", width = 1000, height = 450)
par(mar = rep(0, 4))
plotIdiograms(dfChrSize = dfOfChrSize2, # d.f. of chr. sizes
dfMarkPos = dfOfMarks2b, # d.f. of marks' positions
defaultStyleMark = "cM", # forces "cM" style in d.f dfMarkColor (exc. 5S)
mycolors = charVectorCol, # colors to use
distTextChr = 0.5, # separ. text and chr.
markLabelSize = .7, # font size for labels (legend)
lwd.cM = 2, # width of cM marks
legendWidth = 0.9, # legend item width
legendHeight = .5,
rulerPos = 0, # ruler position
ruler.tck = -0.01, # ruler tick orientation and length
rulerNumberSize = .5 # ruler font size
, xPosRulerTitle = 2.8 # ruler units pos.
, xlimRightMod = 1 # modify xlim right arg.
)
dev.off() # close png
4.3 Plot holocentrics
Initially you have to put your chromosome data in data.frames.
Main three data.frames:
- One for chr. sizes (parameter
dfChrSize) - One for marks’ positions (parameter
dfMarkPos) - One (optional) for mark style (parameter
dfMarkColor)
For simplicity, I call a holocen. any karyotype without centromeres.
Accordingly, they lack the columns: shortArmSize and
longArmSize.
From scratch:
# Example data.frame written in R, use: (column OTU is optional if only 1 OTU)
mydfChrSizeHolo <- read.table(text =
" OTU chrName chrSize
\"Species one\" 1 6.5
\"Species one\" 2 5.0
\"Species one\" 3 4.0
\"Species one\" 4 4.0
\"Species one\" X 3.0 ", header = TRUE, stringsAsFactors = FALSE, fill = TRUE)| OTU | chrName | chrSize |
|---|---|---|
| Species one | 1 | 6.5 |
| Species one | 2 | 5.0 |
| Species one | 3 | 4.0 |
| Species one | 4 | 4.0 |
| Species one | X | 3.0 |
or loading saved data:
If you use RStudio, in menu “Session”, open “Set working directory” for choosing your desired folder or:
setwd("~/folder/subfolder")Open your chromosome data as data.frame importing it from a .csv (read.csv) or .xls file (readxl).
mydfChrSize<-read.csv("somefile.csv")For fixing column names use:
colnames(mydfChrSize)<-c("OTU", "chrName","chrSize")Get marks general data
Put your mark data in a data.frame. This data.frame has the marks
present in all karyotypes without position info. If the
style column is not present, param.
defaultStyleMark = "square" will be used during
plotting.
# From scratch:
mydfMarkColorHolo <- read.table(text =
" markName markColor style
5S red dots
45S chartreuse3 square
gene2 salmon downArrow
gene3 \"#056522\" cMLeft
gene4 darkmagenta cM
DAPI dodgerblue square
protein cornflowerblue exProtein
B black square
gene1 chocolate upArrow
CMA darkgoldenrod1 square", header = TRUE, stringsAsFactors = FALSE, fill = TRUE)| markName | markColor | style |
|---|---|---|
| 5S | red | dots |
| 45S | chartreuse3 | square |
| gene2 | salmon | downArrow |
| gene3 | #056522 | cMLeft |
| gene4 | darkmagenta | cM |
| DAPI | dodgerblue | square |
| protein | cornflowerblue | exProtein |
| B | black | square |
| gene1 | chocolate | upArrow |
| CMA | darkgoldenrod1 | square |
For fixing column names use:
colnames(mydfMarkColorHolo) <- c("markName", "markColor","style")
# if style column not present it will be filled with "square"Get marks positions data
Open or write your mark positions in a data.frame. This data.frame has the marks present in all karyotypes with position info.
For holocentrics, position is defined with column
markPos, while in monocentrics it is
markDistCen.
Column chrRegion can be absent for holocentrics.
# We will use column OTU if data.frame because chromosome size df has it
mydfMarkPosHolo <- read.table(text =
" OTU chrName markName markPos markSize chrRegion
\"Species one\" 4 B NA NA w # w = whole chromosome mark
\"Species one\" 3 DAPI 2.0 0.5
\"Species one\" 1 45S 2.0 0.5
\"Species one\" 2 protein 3.5 1.5
\"Species one\" 2 gene1 1.0 0.5
\"Species one\" 1 gene2 1.0 0.5
\"Species one\" 4 gene3 3.0 0.5
\"Species one\" 3 gene4 1.0 0.5
\"Species one\" X CMA 2.0 0.5
\"Species one\" X 5S 0.5 0.5
\"Species one\" X 5S 0.5 0.5", header = TRUE, stringsAsFactors = FALSE, fill = TRUE)| OTU | chrName | markName | markPos | markSize | chrRegion |
|---|---|---|---|---|---|
| Species one | 4 | B | NA | NA | w |
| Species one | 3 | DAPI | 2.0 | 0.5 | |
| Species one | 1 | 45S | 2.0 | 0.5 | |
| Species one | 2 | protein | 3.5 | 1.5 | |
| Species one | 2 | gene1 | 1.0 | 0.5 | |
| Species one | 1 | gene2 | 1.0 | 0.5 | |
| Species one | 4 | gene3 | 3.0 | 0.5 | |
| Species one | 3 | gene4 | 1.0 | 0.5 | |
| Species one | X | CMA | 2.0 | 0.5 | |
| Species one | X | 5S | 0.5 | 0.5 | |
| Species one | X | 5S | 0.5 | 0.5 |
For fixing column names use something like:
colnames(mydfMarkPosHolo)<-c("OTU", "chrName","markName","markPos","markSize") Plotting
You can plot without marks (passing only 1st data.frame), but we will use all 4 data.frames created:
# library(idiogramFISH)
# svg("mydfChrSizeHolo.svg",width = 13.5, height = 6 )
# png("mydChrSizeHolo.png", width = 600, height = 300)
par(mar = c(0, 0, 0, 1)) # bottom left top right
plotIdiograms(dfChrSize = mydfChrSizeHolo, # data.frame of chr. sizes
dfMarkColor = mydfMarkColorHolo, # df of mark style
dfMarkPos = mydfMarkPosHolo, # df of mark positions
chrSpacing = 1,
addOTUName = FALSE, # add OTU names
xlimLeftMod = 2, # modify xlim left argument
ylimTopMod = -1, # modify ylim top argument
ylimBotMod = -2 # modify ylim bottom argument
, rulerPos = 0 # ruler position
, ruler.tck = -0.01 # ruler ticks size and orient.
, xPosRulerTitle = 2.6,
legendWidth = 1 # width of legend
, legendHeight = .5 # height of legend item
, xModifier = 50 # separation among chromatids
)
It is not mandatory to use dfMarkColor and you can also
use the parameter mycolors (optional too), to establish
marks’ colors. When using mycolors, colors are assigned
depending on the order of marks, i.e.:
unique(dfMarkPosHolo$markName)
# [1] "5S" "DAPI" "45S" "CMA"
par(mar = rep(0, 4))
plotIdiograms(dfChrSize = dfChrSizeHolo, # d.f. of chr. size
dfMarkPos = dfMarkPosHolo, # d.f. of marks' positions
mycolors = c("red", "dodgerblue", "fdsjkfds", "chartreuse3", "darkgoldenrod1"), # colors for marks
addOTUName = FALSE, # do not add OTU name
ruler = FALSE, # do not add ruler
xlimLeftMod = 1, # modify left xlim arg.
xlimRightMod = 3, # modify right xlim arg.
ylimBotMod = .2 # modify bottom ylim
, chromatids = FALSE # do not show separ. chromatids
)
4.4 ggplot holocentrics
With function mapGGChrMark and the data.frames of chr.
(dfChrSizeHolo) and marks’ position
(dfMarkPosHolo) for one OTU, you get a list of data.frames
for ggplot (Wickham
et al., 2020)
chrAndMarksMap <- mapGGChrMark(dfChrSizeHolo, dfMarkPosHolo, chrSpacing = .5)
require(ggplot2)
myColors <- c("chartreuse3", "red", "darkgoldenrod1", "dodgerblue")
names(myColors) <- c("45S", "5S", "CMA", "DAPI")
ggplot() +
geom_polygon(aes(x = x,
y = y,
group = Chr
),
data = chrAndMarksMap$dataChr,
color = "gray",
fill = "gray"
) +
geom_polygon(aes(x = x, y = y,
group = id,
color = markName,
fill = markName
),
data = chrAndMarksMap$dataMark
) +
theme_classic() +
scale_color_manual(
values = myColors
) +
scale_fill_manual(
values = myColors
) +
scale_x_continuous(breaks = seq(1, nrow(dfChrSizeHolo), 1)
) +
scale_y_continuous(breaks = seq(0, 5, 0.5)
) +
geom_segment(aes(y = 0, yend = 5, x = -Inf, xend = -Inf)
) +
theme(axis.line = element_blank(),
axis.ticks.x = element_blank(),
axis.title = element_blank(),
title = element_blank()
)
require(svglite)
ggsave(file = "ggplot.svg", width = 6, height = 4)4.5 Plot holo. and mono. in the same karyotype
To accomplish this, we will use cenStyle marks in a
“holocen.” karyotype. The ruler is continuous as in holocen.
# mark general characteristics' data.frame:
mydfMarkColorHolo2 <- read.table(text =
" markName markColor style
5S red dots
45S chartreuse3 square
gene2 salmon downArrow
gene3 \"#056522\" cMLeft
gene4 darkmagenta cM
DAPI dodgerblue square
protein cornflowerblue exProtein
B black square
gene1 chocolate upArrow
CMA darkgoldenrod1 square
c45S chartreuse3 cenStyle # <- simulate Cen.
myCen2 red cenStyle
myCen chartreuse2 cenStyle
constr NA cenStyle", header = TRUE, stringsAsFactors = FALSE, fill = TRUE)
# add new cenStyle marks to data.frame of marks' position, created above
mydfMarkPosHolo2 <- plyr::rbind.fill(mydfMarkPosHolo,
data.frame(OTU = "Species one",
chrName = c(1:3, "X"),
markName = c("c45S", "myCen2", "constr", "myCen"), # <- use new mark
markPos = c(rep(2.5, 3), 1),
markSize = NA
)
)
# png("mydChrSizeHolo.png", width = 600, height = 300)
par(mar = c(0, 0, 0, 1)) # bottom left top right
plotIdiograms(dfChrSize = mydfChrSizeHolo, # data.frame of chr. sizes
dfMarkColor = mydfMarkColorHolo2, # df of mark style
dfMarkPos = mydfMarkPosHolo2, # df of mark positions
addOTUName = FALSE, # add OTU names
xlimLeftMod = 2, # modify xlim left argument
ylimTopMod = -1, # modify ylim top argument
ylimBotMod = -2 # modify ylim bottom argument
, rulerPos = 0,
ruler.tck = -0.01,
xPosRulerTitle = 2.6,
legendWidth = 1 # width of legend
, legendHeight = .5 # height of legend item
, lwd.mimicCen = 2.5 # line width of const. mark
, pattern = "^c" # regex pattern to remove from mark names
, remSimiMarkLeg = TRUE # remove pseudoduplicated mark names (got equal after pattern removal)
, bannedMarkName = c("myCen", "myCen2", "B") # hide label
# ,legend = "inline" # legends inline
) # ; dev.off() closes png
5 Multiple OTUs
Jupyter interactive version:|
Github
|
Raw |
5.1 Example with several species (OTUs) - mono.
To illustrate this, we will load some data.frames from the package
- Chromosome sizes
require(idiogramFISH)
head(bigdfOfChrSize, 15)| OTU | chrName | shortArmSize | longArmSize |
|---|---|---|---|
| Species 1 | 1 | 1.5 | 2.0 |
| Species 1 | 2 | 2.0 | 2.5 |
| Species 1 | 3 | 1.0 | 2.0 |
| Species 2 | 1 | 3.0 | 4.0 |
| Species 2 | 2 | 4.0 | 5.0 |
| Species 2 | 3 | 2.0 | 3.0 |
| Species 2 | X | 1.0 | 2.0 |
| Species 2 | 4 | 3.0 | 4.0 |
| Species 3 | 1 | 3.2 | 4.0 |
| Species 3 | 2 | 4.5 | 5.0 |
| Species 3 | 3 | 2.0 | 3.0 |
| Species 3 | 4 | 1.5 | 2.0 |
| Species 3 | 5 | 4.8 | 6.0 |
| Species 3 | 6 | 6.1 | 7.0 |
| Species 4 | 1 | 1.5 | 2.0 |
- Mark characteristics, does not require OTU
- df optional for ver > 1.0.0
data("dfMarkColor")| markName | markColor | style |
|---|---|---|
| 5S | red | dots |
| 45S | chartreuse3 | square |
| DAPI | blue | square |
| CMA | darkgoldenrod1 | square |
- Mark position
data("bigdfOfMarks")| OTU | chrName | markName | chrRegion | markDistCen | markSize |
|---|---|---|---|---|---|
| Species 1 | 1 | 5S | p | 0.5 | 1 |
| Species 1 | 1 | 45S | q | 0.5 | 1 |
| Species 1 | 2 | 45S | p | 1.0 | 1 |
| Species 1 | 3 | DAPI | q | 1.0 | 1 |
| Species 3 | 3 | 5S | p | 1.0 | 1 |
| Species 3 | 3 | DAPI | q | 1.0 | 1 |
| Species 3 | 4 | 45S | p | NA | NA |
| Species 3 | 4 | DAPI | q | 1.0 | 1 |
| Species 3 | 5 | CMA | q | 2.0 | 1 |
| Species 3 | 6 | 5S | q | 0.5 | 1 |
| Species 2 | 1 | DAPI | cen | NA | NA |
| Species 2 | 4 | CMA | cen | NA | NA |
Plotting
# png("bigdfOfChrSize.png", width = 650, height = 1300)
par(mar = c(0, 0, 0, 0))
plotIdiograms(dfChrSize = bigdfOfChrSize, # chr. sizes
dfMarkColor = dfMarkColor, # mark characteristics, optional in dev version. see above.
dfMarkPos = bigdfOfMarks, # mark positions (inc. cen. marks)
karHeight = 2.5, # karyotype rel. height
karHeiSpace = 6, # karyotype vertical size with spacing
chrWidth = .35, # chr. width
amoSepar = 2, # Vertical separation of kar. when karSepar = TRUE
squareness = 4, # squareness of chr. vertices
distTextChr = .8, # distance of chr. to text
chrIndex = "AR", # add arm ratio only. For v. >=1.12
nameChrIndexPos = 3,
morpho = "Guerra", # add chr. morphology by Guerra, see above. For v. >=1.12
indexIdTextSize = .6, # font size of indices and chr. name
OTUTextSize = .9, # font size of OTU names
markLabelSize = .7, # font size of legend
fixCenBorder = TRUE, # use chrColor as border color of cen. or cen. marks
legendHeight = 2, # height of labels
rulerPos = -1, # position of ruler
ruler.tck = -0.004, # size and orient. of ticks in ruler
rulerNumberPos = .4, # position of numbers of ruler
rulerNumberSize = .4, # font size of ruler
xPosRulerTitle = 5, # ruler units pos.
rulerTitleSize = .5, # ruler font size of units (title)
xlimRightMod = 3, # modify xlim left argument
xlimLeftMod = 2, # modify xlim left argument
ylimBotMod = 0, # modify ylim bottom argument
ylimTopMod = -.3 # modify ylim top argument
)
5.2 Example with several species (OTUs) - holo.
To illustrate this, we will load some data.frames from the package
- Chromosome sizes
data(bigdfChrSizeHolo)| OTU | chrName | chrSize |
|---|---|---|
| species one | 1 | 5.1 |
| species one | 2 | 5.0 |
| species one | 3 | 4.9 |
| species one | 4 | 5.2 |
| species two | 1 | 3.0 |
| species two | 2 | 4.0 |
| species two | 3 | 2.0 |
| species two | 4 | 5.0 |
| species three | 1 | 1.5 |
| species three | 2 | 2.0 |
| species three | 3 | 6.0 |
| species three | 4 | 8.0 |
- Mark characteristics, does not require OTU
- d.f optional for ver. > 1.0.0
data(dfMarkColorIn) | markName | markColor | style |
|---|---|---|
| 5S | red | dots |
| 45S | chartreuse3 | square |
| DAPI | blue | square |
| CMA | darkgoldenrod1 | square |
| proteinD | darkgreen | inProtein |
- Mark position
data(bigdfMarkPosHolo2)| OTU | chrName | markName | markPos | markSize | chrRegion |
|---|---|---|---|---|---|
| species two | 3 | 5S | 1.0 | 0.5 | NA |
| species two | 3 | DAPI | 1.5 | 0.5 | NA |
| species two | 1 | 45S | 2.0 | 0.5 | NA |
| species two | 2 | DAPI | 2.0 | 0.5 | NA |
| species two | 4 | CMA | 2.0 | 0.5 | NA |
| species two | 4 | 5S | 0.5 | 0.5 | NA |
| species one | 1 | proteinD | NA | NA | w |
| species one | 2 | proteinD | NA | NA | w |
| species one | 3 | proteinD | NA | NA | w |
| species one | 4 | proteinD | NA | NA | w |
| species two | 1 | proteinD | NA | NA | w |
| species two | 2 | proteinD | NA | NA | w |
| species two | 3 | proteinD | NA | NA | w |
| species two | 4 | proteinD | NA | NA | w |
| species three | 1 | proteinD | NA | NA | w |
| species three | 2 | proteinD | NA | NA | w |
| species three | 3 | proteinD | NA | NA | w |
| species three | 4 | proteinD | NA | NA | w |
Plotting
library(idiogramFISH)
# fig.width = 6, fig.height = 6
png("bigdfChrSizeHolo.png", width = 600, height = 600)
par(mar = rep(0, 4))
plotIdiograms(dfChrSize = bigdfChrSizeHolo, # chr. size data.frame
dfMarkColor = dfMarkColorIn, # df of mark style
dfMarkPos = bigdfMarkPosHolo2, # df of marks' position
markDistType = "cen", # measure towards center of mark
squareness = 6, # vertices squareness of chr. and marks
karHeiSpace = 4, # karyotype height including spacing
karSepar = TRUE, # reduce vertical space among karyotypes
amoSepar = 1, # separation among karyotypes
distTextChr = .5, # distance text to chr.
legendWidth = 1 # width of legend labels
, chrId = "simple", # numbering of chr., not using "original" name
indexIdTextSize = .9, # font size of chr names and indices
markLabelSize = .9, # font size of legends
rulerPos = 0, # position of ruler
rulerNumberSize = .9, # font size of ruler
ruler.tck = -.004, # tick length and orient.
xPosRulerTitle = 3, # position of ruler units (title)
ylimBotMod = .4 # modify ylim bottom argument
, xModifier = 50 # separation among chromatids
)
dev.off()
6 Changing Units
Jupyter interactive version:|
Github
|
Raw |
6.1 Using bases instead of micrometers - no. cen.
Create some data in millions of bases:
require(idiogramFISH)
# transform data.frames for simplicity
bigdfChrSizeHoloMb <- bigdfChrSizeHolo # included in idiogramFISH
bigdfChrSizeHoloMb$chrSize <- bigdfChrSizeHoloMb$chrSize * 98000000
bigdfMarkPosHoloMb <- bigdfMarkPosHolo
bigdfMarkPosHoloMb$markPos <- bigdfMarkPosHoloMb$markPos * 98000000
bigdfMarkPosHoloMb$markSize <- bigdfMarkPosHoloMb$markSize * 98000000Plotting
In the plot length is shown in Mb
png("bigdfChrSizeHolo2.png", width = 700, height = 600)
# par(mar = c(1, 1,1, 1))
par(mar = rep(0, 4))
plotIdiograms(dfChrSize = bigdfChrSizeHoloMb, # chr. size data.frame
dfMarkColor = dfMarkColor, # df of mark style
dfMarkPos = bigdfMarkPosHoloMb, # df of mark positions
markDistType = "cen", # distance to mark is to its center
squareness = 4, # vertices squareness of chr. and marks
distTextChr = .5, # separ. chr. to text
karHeight = 2, # rel. karyotype height
karHeiSpace = 4, # karyotype height including spacing
karSepar = TRUE, # reduce spacing among karyotypes
amoSepar = 1, # depends on karSepar, amount of sep.
chrId = "simple", # chr. names not "original"
chrSize = TRUE, # show chr. size under chr.
indexIdTextSize = .9, # font size of chr names and indices
karIndex = FALSE, # do not add karyotype asymmetry index
rulerNumberSize = .9, # font size of ruler
rulerPos = 0, # position of ruler
ruler.tck = -.004, # ruler tick length and orient.
xPosRulerTitle = 3.5, # modifies position of ruler title (Mb)
markLabelSize = .9, # font size of legend
legendWidth = 1.2, # width of legends
xlimLeftMod = 1, # modify left argument of xlim
ylimBotMod = .4 # modify bottom argument of ylim
, chromatids = FALSE # do not show chromatids
, OTUfont = 3 # italics
)
dev.off()
For another example see: https://stackoverflow.com/questions/33727432/how-to-plot-positions-along-a-chromosome-graphic/57153497#57153497
6.2 Using
threshold to fix scale
The default value of 35 for threshold may
shrink one of the OTUs of this example more than expected. In this case
threshold must be bigger.
# fig.width = 7, fig.height = 7
bigdfOfChrSize3_100Mb <- bigdfOfChrSize3Mb
bigdfOfChrSize3_100Mb$chrSize <- bigdfOfChrSize3Mb$chrSize * 33
bigdfOfMarks3_100Mb <- bigdfOfMarks3Mb
bigdfOfMarks3_100Mb$markPos <- bigdfOfMarks3_100Mb$markPos * 33
bigdfOfMarks3_100Mb$markSize <- bigdfOfMarks3_100Mb$markSize * 33
par(mar = rep(0, 4))
plotIdiograms(dfChrSize = bigdfOfChrSize3_100Mb, # chr. size data.frame
dfMarkPos = bigdfOfMarks3_100Mb, # mark position df
chrWidth = .6, # width of chr.
chrSpacing = .6, # space among chr.
karHeight = 3, # kar. height without interspace
karHeiSpace = 5, # vertical size of karyotype including spacer
amoSepar = 2, # separ. among kar.
indexIdTextSize = .6, # font size of chr. name and indices
markLabelSize = .7, # font size of mark legends
distTextChr = .65, # separation among chr. names and indices
fixCenBorder = TRUE # use chrColor as border color of cen. or cen. marks
, legendWidth = 1.5 # legend items width
, xPosRulerTitle = 3.5 # position of Mb (title) in ruler
, rulerPos = 0, # ruler position
ruler.tck = -0.005, # ticks of ruler size and orientation
rulerNumberPos = .7, # position of numbers in ruler
rulerNumberSize = .7, # font size of ruler numbers
rulerInterval = 1.5, # ruler interval for micrometeres
rulerIntervalMb = 50, # ruler interval for Mb
ylimBotMod = 0.4, # modify ylim bottom argument
ylimTopMod = 0 # modify ylim top argument
, chromatids = FALSE # do not show chromatids
#### NEW #####
, threshold = 90 # this will allow to not to shrink data greater than 350 Mb
)
6.3 Plot data in micrometers and bases
Info in number of bases can be combined in the same plot with info. in micrometers.
Here the new mark style cenStyle is used to add
centromeres to “holocen.” (genomes).
To make the rules fit better, having less excess of length over chr.,
use ceilingFactor.
# fig.width = 10, fig.height = 10
# modify data in millions to hundreds of millions of Mb
bigdfOfChrSize3_100Mb <- bigdfOfChrSize3Mb[1:8, ]
bigdfOfChrSize3_100Mb$chrSize <- bigdfOfChrSize3_100Mb$chrSize * 100
bigdfOfMarks3_100Mb <- bigdfOfMarks3Mb
bigdfOfMarks3_100Mb$markPos <- bigdfOfMarks3_100Mb$markPos * 100
bigdfOfMarks3_100Mb$markSize <- bigdfOfMarks3_100Mb$markSize * 100
# merge data.frames in micrometers and number of bases
mixedThreeSpChrSize <- plyr::rbind.fill(bigdfOfChrSize[1:8, ], bigdfOfChrSize3_100Mb)
# sort by OTU name
mixedThreeSpChrSize <- mixedThreeSpChrSize[order(mixedThreeSpChrSize$OTU), ]
# add cenStyle marks to simulate centromeres in karyo. in Mb (holocen.)
# compare rulers
bigdfSimCenMarks <- bigdfOfChrSize3_100Mb
bigdfSimCenMarks$markPos <- bigdfSimCenMarks$chrSize / 2
bigdfSimCenMarks$markName <- "sim. cen."
bigdfSimCenMarks$chrSize <- NULL
# merge marks in micrometers and bases
mixedThreeSpMarks <- plyr::rbind.fill(bigdfOfMarks, bigdfOfMarks3_100Mb, bigdfSimCenMarks)
# remove cenStyle mark info.
mixedThreeSpMarks <- mixedThreeSpMarks[which(!(mixedThreeSpMarks$OTU %in% "Species 2 genome" &
mixedThreeSpMarks$chrName %in% c(1, 4) &
mixedThreeSpMarks$markName %in% "sim. cen.")), ]
# constric. marks
mixedThreeSpMarks[which(mixedThreeSpMarks$OTU %in% "Species 2 genome" &
mixedThreeSpMarks$chrName %in% c(1, 4)), ]$markName <- c("cDAPI", "cCMA")
# add arrow mark
mixedThreeSpMarks <- dplyr::bind_rows(mixedThreeSpMarks, mixedThreeSpMarks[nrow(mixedThreeSpMarks), ])
mixedThreeSpMarks[nrow(mixedThreeSpMarks), ]$markName <- "S58A"
mixedThreeSpMarks[nrow(mixedThreeSpMarks), ]$markPos <- .7e+08
mixedThreeSpMarks[nrow(mixedThreeSpMarks), ]$markSize <- .7e+08
dfMarkColorAndStyle <- makedfMarkColorMycolors(unique(mixedThreeSpMarks$markName),
c("red", "chartreuse3", "dodgerblue", "darkgoldenrod1", "dodgerblue", "darkgoldenrod1", "black")
)
# d.f. of marks'styles
dfMarkColorAndStyle$style[5:7] <- "cenStyle"
dfMarkColorAndStyle$markColor[7] <- NA
dfMarkColorAndStyle$style[8] <- "upArrow"
dfMarkColorAndStyle
# markName markColor style
# 1 5S red dots
# 2 45S chartreuse3 square
# 3 DAPI dodgerblue square
# 4 CMA darkgoldenrod1 square
# 5 cDAPI dodgerblue cenStyle
# 6 cCMA darkgoldenrod1 cenStyle
# 7 sim. cen. <NA> cenStyle
# 8 S58A red upArrow
par(mar = rep(0, 4))
plotIdiograms(dfChrSize = mixedThreeSpChrSize, # chr. size data.frame
dfMarkPos = mixedThreeSpMarks, # mark position df
dfMarkColor = dfMarkColorAndStyle,
chrWidth = .6, # width of chr.
chrSpacing = .6, # space among chr.
karHeight = 3, # kar. height without interspace
karHeiSpace = 5, # vertical size of karyotype including spacer
amoSepar = 2, # separ. among kar.
indexIdTextSize = .6, # font size of chr. name and indices
markLabelSize = .7, # font size of mark legends
distTextChr = .65, # separation among chr. names and indices
lwd.mimicCen = 1.5, # constric. line width
legendWidth = 1.5, # legend items width
fixCenBorder = TRUE, # use chrColor as border color of cen. or cen. marks
xPosRulerTitle = 3.7, # position of Mb (title) in ruler
rulerPos = 0, # ruler position
ruler.tck = -0.005, # ticks of ruler size and orientation
rulerNumberPos = .7, # position of numbers in ruler
rulerNumberSize = .7, # font size of ruler numbers
rulerInterval = 1.5, # ruler interval for micrometeres
rulerIntervalMb = 150, # ruler interval for Mb
ceilingFactor = 1, # affects rounding for ruler max. value
ylimBotMod = 0.4, # modify ylim bottom argument
ylimTopMod = 0 # modify ylim top argument
, holocenNotAsChromatids = TRUE # do not use chromatids in holocen.
, pattern = "^c" # regex pattern to remove from mark names
, remSimiMarkLeg = TRUE # remove pseudoduplicate names arising from pattern removal
)
Let’s explore those data.frames
head(mixedThreeSpChrSize, 6)| OTU | chrName | shortArmSize | longArmSize | chrSize | |
|---|---|---|---|---|---|
| 1 | Species 1 | 1 | 1.5 | 2.0 | NA |
| 2 | Species 1 | 2 | 2.0 | 2.5 | NA |
| 3 | Species 1 | 3 | 1.0 | 2.0 | NA |
| 9 | Species 1 genome | 1 | NA | NA | 3.5e+08 |
| 10 | Species 1 genome | 2 | NA | NA | 4.5e+08 |
| 11 | Species 1 genome | 3 | NA | NA | 2.5e+08 |
mixedThreeSpMarks[which(mixedThreeSpMarks$OTU %in% c("Species 1","Species 1 genome") ),] | OTU | chrName | markName | chrRegion | markDistCen | markSize | markPos | |
|---|---|---|---|---|---|---|---|
| 1 | Species 1 | 1 | 5S | p | 0.5 | 1 | NA |
| 2 | Species 1 | 1 | 45S | q | 0.5 | 1 | NA |
| 3 | Species 1 | 2 | 45S | p | 1.0 | 1 | NA |
| 4 | Species 1 | 3 | DAPI | q | 1.0 | 1 | NA |
| 13 | Species 1 genome | 1 | 5S | NA | NA | 100000000 | 250000000 |
| 14 | Species 1 genome | 1 | 45S | NA | NA | 100000000 | 50000000 |
| 15 | Species 1 genome | 2 | 45S | NA | NA | 100000000 | 350000000 |
| 16 | Species 1 genome | 3 | DAPI | NA | NA | 100000000 | 0 |
| 25 | Species 1 genome | 1 | sim. cen. | NA | NA | NA | 175000000 |
| 26 | Species 1 genome | 2 | sim. cen. | NA | NA | NA | 225000000 |
| 27 | Species 1 genome | 3 | sim. cen. | NA | NA | NA | 125000000 |
6.4 Use cM as units
Info in cM can be combined in the same plot with info. in micrometers.
To make the rules fit better, having less excess of length over chr.,
use ceilingFactor.
# fig.width = 10, fig.height = 10
# merge data.frames in micrometers and cM
bigdfOfChrSize3cM <- bigdfOfChrSize3Mb[1:8, ]
bigdfOfChrSize3cM$chrSize <- bigdfOfChrSize3cM$chrSize / 100000
mixedThreeSpChrSize2 <- plyr::rbind.fill(bigdfOfChrSize[1:8, ], bigdfOfChrSize3cM)
# sort by OTU name
mixedThreeSpChrSize2 <- mixedThreeSpChrSize2[order(mixedThreeSpChrSize2$OTU), ]
# create data with cM. markSize col. is not necessary because style is cM
bigdfOfMarks3cM <- bigdfOfMarks3Mb
bigdfOfMarks3cM$markPos <- bigdfOfMarks3Mb$markPos / 100000
bigdfOfMarks3cM$markSize <- NA
# As we want only the cM idiograms to be plotted as cM (lines), change mark names
bigdfOfMarks3cM$markName <- paste0("cM", bigdfOfMarks3cM$markName)
# d.f of all marks
mixedThreeSpMarks2 <- plyr::rbind.fill(bigdfOfMarks, bigdfOfMarks3cM)
# create a data.frame with mark characteristics
mixedDfMarkStyle <- makedfMarkColorMycolors(unique(mixedThreeSpMarks2$markName),
c("red", "chartreuse3", "dodgerblue", "darkgoldenrod1")
)
# mark names of cM marks with "cM" style (lines): not dots, not squares
mixedDfMarkStyle[which(mixedDfMarkStyle$markName %in%
grep("cM", mixedDfMarkStyle$markName, value = TRUE)), ]$style <- "cM"
par(mar = rep(0, 4))
plotIdiograms(dfChrSize = mixedThreeSpChrSize2, # chr. size data.frame
dfMarkPos = mixedThreeSpMarks2, # mark position data.frame
dfMarkColor = mixedDfMarkStyle, # mark style data.frame
chrWidth = .6, # width of chr.
chrSpacing = .7, # space among chr.
specialOTUNames = bigdfOfMarks3cM$OTU, # OTUs in this object will have different ruler units
specialyTitle = "cM", # ruler title for specialOTUNames
specialChrWidth = .2, # modify chr width of OTUs in specialOTUNames
specialChrSpacing = 1.1, # modify chr spacing of OTUs in specialOTUNames
karHeight = 3, # kar. height without interspace
karHeiSpace = 6, # vertical size of karyotype including spacer
amoSepar = 3, # separ. among kar.
chrSize = TRUE, # show chr. size under chr.
indexIdTextSize = .6, # font size of chr. name and indices
distTextChr = .85, # separation among chr. names and indices
protruding = 1, # extension of cM mark type
pattern = "cM", # regex pattern to remove from mark names
markLabelSize = .7 # font size of mark legends
, legendWidth = 2 # legend items width
, fixCenBorder = TRUE # use chrColor as border color of cen. or cen. marks
, lwd.cM = 2 # thickness of cM marks
, holocenNotAsChromatids = TRUE # do not use chromatids in holocen. kar.
, xPosRulerTitle = 3.2 # position of Mb or cM (title) in ruler
, rulerPos = 0, # ruler position
ruler.tck = -0.005, # ticks of ruler size and orientation
rulerNumberPos = .7, # position of numbers in ruler
rulerNumberSize = 0.7, # font size of ruler numbers
rulerIntervalcM = 12, # ruler interval for OTU in specialOTUnames and MbThreshold not met
ceilingFactor = 1, # affects max. value in ruler. See also rulerInterval
ylimBotMod = 0.4, # modify ylim bottom argument
ylimTopMod = 0 # modify ylim top argument
)
7 GISH
Jupyter interactive version:|
Github
|
Raw |
7.1 GISH of monocentric chromosomes
You need the data.frame of chr. sizes, and a d.f. of marks
Chr. sizes:
parentalAndHybChrSize| OTU | chrName | shortArmSize | longArmSize | |
|---|---|---|---|---|
| 1 | Parental 1 | 1 | 3.2 | 4 |
| 2 | Parental 1 | 4 | 1.5 | 2 |
| 3 | Parental 1 | 5 | 4.8 | 6 |
| 4 | Parental 1 | 6 | 6.1 | 7 |
| 8 | Allopolyploid | 1 | 3.2 | 4 |
| 9 | Allopolyploid | 2 | 4.5 | 5 |
| 10 | Allopolyploid | 3 | 2.0 | 3 |
| 11 | Allopolyploid | 4 | 1.5 | 2 |
| 12 | Allopolyploid | 5 | 4.8 | 6 |
| 13 | Allopolyploid | 6 | 6.1 | 7 |
| 5 | Parental 2 | 1 | 3.2 | 4 |
| 6 | Parental 2 | 2 | 4.5 | 5 |
| 7 | Parental 2 | 3 | 2.0 | 3 |
Marks’ positions data
dfAlloParentMarks| OTU | chrName | markName | chrRegion | |
|---|---|---|---|---|
| 1 | Allopolyploid | 1 | Parental 2 | qcen |
| 17 | Allopolyploid | 1 | Parental 1 | pcen |
| 16 | Allopolyploid | 1 | Parental 1 | p |
| 2 | Allopolyploid | 1 | Parental 2 | q |
| 4 | Allopolyploid | 2 | Parental 2 | w |
| 5 | Allopolyploid | 3 | Parental 2 | w |
| 6 | Allopolyploid | 4 | Parental 1 | w |
| 7 | Allopolyploid | 5 | Parental 1 | w |
| 8 | Allopolyploid | 6 | Parental 1 | w |
| 9 | Parental 1 | 6 | Parental 1 | w |
| 10 | Parental 1 | 5 | Parental 1 | w |
| 11 | Parental 1 | 1 | Parental 1 | w |
| 12 | Parental 1 | 4 | Parental 1 | w |
| 13 | Parental 2 | 2 | Parental 2 | w |
| 14 | Parental 2 | 1 | Parental 2 | w |
| 15 | Parental 2 | 3 | Parental 2 | w |
We will use column note to add a note to the right of the karyotype of the OTU (column)
notesdf2<-read.table(text=
" OTU note
\"Parental 1\" \"Parental One\"
\"Parental 2\" \"Parental Two\"
\"Allopolyploid\" Allopolyploid ", header = TRUE, stringsAsFactors = FALSE, fill = TRUE)7.1.1 Plotting
# svg("gish.svg",width = 7, height = 9 )
# png("parentalAndHybChrSize.png", width = 700, height = 900)
# REORDER OTUs
parentalAndHybChrSize$OTU <- factor(parentalAndHybChrSize$OTU, levels = c("Parental 1", "Allopolyploid", "Parental 2"))
parentalAndHybChrSize <- parentalAndHybChrSize[order(parentalAndHybChrSize$OTU), ]
par(mar = rep(0, 4))
plotIdiograms(dfChrSize = parentalAndHybChrSize, # d.f. of chr. sizes
dfMarkPos = dfAlloParentMarks, # d.f. of marks' positions
cenColor = NULL, # no cen. color for GISH
karHeiSpace = 5, # karyotype height including spacing
karSepar = FALSE, # equally sized (height) karyotypes
legend = "" # no legend
, notes = notesdf2 # data.frame with notes NEW
# ,OTUasNote = TRUE # TRY THIS (OTU name to the right)
, notesTextSize = 1.3,
notesPosX = 1.5 # space from chr. (right) to note
, ruler = FALSE,
moveKarHor = "Allopolyploid" # OTU to move to the right
, mkhValue = 7 # amount to move to right
, anchor = TRUE # show anchor for moveKarHor OTUs
, moveAnchorV = 4 # modify anchor Vertical portion position
, moveAnchorH = -1.5 # modify anchor Horizon. portion position
, ylimBotMod = 1 # ylim bottom argument mod.
, xlimRightMod = 4
)
7.2 GISH of holocentric chromosomes
You need the data.frame of chr. sizes, and a d.f. of marks
Chr. sizes:
parentalAndHybHoloChrSize| OTU | chrName | chrSize |
|---|---|---|
| Parental 1 | 7 | 4 |
| Parental 1 | 4 | 2 |
| Parental 1 | 5 | 6 |
| Parental 1 | 6 | 7 |
| Parental 2 | 1 | 4 |
| Parental 2 | 2 | 5 |
| Parental 2 | 3 | 3 |
| Allopolyploid | 7 | 4 |
| Allopolyploid | 2 | 5 |
| Allopolyploid | 3 | 3 |
| Allopolyploid | 4 | 2 |
| Allopolyploid | 5 | 6 |
| Allopolyploid | 6 | 7 |
Marks’ positions data
dfAlloParentMarksHolo| OTU | chrName | markName | chrRegion | |
|---|---|---|---|---|
| 1 | Allopolyploid | 7 | Parental 1 | w |
| 4 | Allopolyploid | 2 | Parental 2 | w |
| 5 | Allopolyploid | 3 | Parental 2 | w |
| 6 | Allopolyploid | 4 | Parental 1 | w |
| 7 | Allopolyploid | 5 | Parental 1 | w |
| 8 | Allopolyploid | 6 | Parental 1 | w |
| 9 | Parental 1 | 6 | Parental 1 | w |
| 10 | Parental 1 | 5 | Parental 1 | w |
| 11 | Parental 1 | 7 | Parental 1 | w |
| 12 | Parental 1 | 4 | Parental 1 | w |
| 13 | Parental 2 | 2 | Parental 2 | w |
| 14 | Parental 2 | 1 | Parental 2 | w |
| 15 | Parental 2 | 3 | Parental 2 | w |
Plotting
# svg("gish.svg",width = 8, height = 7 )
par(mar = c(0, 0, 0, 0))
plotIdiograms(dfChrSize = parentalAndHybHoloChrSize, # d.f. of chr. sizes
dfMarkPos = dfAlloParentMarksHolo, # d.f. of marks' positions
chrColor = "gray", # chr. color
cenColor = NULL, # cen. color when GISH
karHeight = 3, # karyotype height without spacing
karHeiSpace = 5, # karyotype height including spacing
distTextChr = 0.8 # separation among chr. and text
, ruler = FALSE # no ruler
, legend = "" # no legend
, xlimRightMod = 0 # xlim right arg. modif.
, xModifier = 100 # separ. among chromatids
)
7.3 GISH of Citrus as Yasuda et al. (2010)
For more details on the use of Citrus functions go to chapter Citrus
Parental C. schweinfurthii: 14D + 4F (using Guerra nomenclature).
{
#
# c. schweinfurthii chr sizes d.f.
#
cschweinformula <- "14D + 4F"
require(idiogramFISH)
citrusschwein <- citrusSize(D = 14,
F = 4,
OTU = "C. schweinfurthii",
longArm = 1.2)
#
# c. schweinfurthii CMA and GISH marks
#
citrusschweinMarkPosDF <- citrusMarkPos(citrusschwein)
#
# data.frame of genomic marks
#
citrusschweinMarkPosDF2 <- data.frame(chrName = c(paste0("D_", 1:7), paste0("F_", 1:2)),
chrRegion = "w",
markName = "schweingenome",
OTU = unique(citrusschwein$OTU)
)
#
# merge marks pos.
#
citrusschweinMarkPosDF <- dplyr::bind_rows(citrusschweinMarkPosDF2, citrusschweinMarkPosDF)
#
# Inversion of some chr. (D marks up)
#
csSwap <- swapChrRegionDfSizeAndMarks(citrusschwein, citrusschweinMarkPosDF, c(paste0("D_", 1:14)))
citrusschwein <- csSwap$dfChrSize
citrusschweinMarkPosDF <- csSwap$dfMarkPos
#
# mark style
#
unique(citrusschweinMarkPosDF$markName)
{
markStyleschweinDF <- makedfMarkColorMycolors(
unique(citrusschweinMarkPosDF$markName), c("chartreuse3", "darkgoldenrod1"))
}
#
# d.f. of notes
#
leftNotesschwein <- data.frame(OTU = unique(citrusschwein$OTU), note = paste0("Female gamete: 7D + 2E"))
leftNotesschweinUp <- data.frame(OTU = unique(citrusschwein$OTU), note = paste0(unique(citrusschwein$OTU), " (", cschweinformula, ")"))
notesschwein <- data.frame(OTU = unique(citrusschwein$OTU), note = "Yasuda et al. (2010)")
}
Parental ‘Nanpu’ tangor
{
cnanpuformula <- "1A + 4C + 5D + 8F" # Guerra nom.
#
# 'Nanpu' tangor chr. sizes
#
citrusnanpu <- citrusSize(A = 1, C = 4, D = 5, F = 8 #
, OTU = "nanpu tangor",
longArm = 1.2)
#
# c. nanpu CMA marks
#
citrusnanpuMarkPosDF <- citrusMarkPos(citrusnanpu)
#
# d.f. of genomic marks
#
citrusnanpuMarkPosDF2 <- data.frame(chrName = c("A", "C_1", paste0("D_", 1:4), paste0("F_", 1:3)),
chrRegion = "w",
markName = "nanpugenome",
OTU = unique(citrusnanpu$OTU)
)
#
# merge marks pos.
#
citrusnanpuMarkPosDF <- dplyr::bind_rows(citrusnanpuMarkPosDF2, citrusnanpuMarkPosDF)
#
# mark style d.f.
#
unique(citrusnanpuMarkPosDF$markName)
{
markStylenanpuDF <- makedfMarkColorMycolors(
unique(citrusnanpuMarkPosDF$markName), c("chocolate", "darkgoldenrod1"))
}
#
# invert some chr.
#
csSwap <- swapChrRegionDfSizeAndMarks(citrusnanpu, citrusnanpuMarkPosDF, c(paste0("D_", 1:5)))
citrusnanpu <- csSwap$dfChrSize
citrusnanpuMarkPosDF <- csSwap$dfMarkPos
#
# notes data.frames
#
leftNotesnanpu <- data.frame(OTU = unique(citrusnanpu$OTU), note = paste0("Male gamete: 1A + 1C + 4D + 3E"))
leftNotesnanpuUp <- data.frame(OTU = unique(citrusnanpu$OTU), note = paste0("'Nanpu' tangor (", cnanpuformula, ")"))
notesnanpu <- data.frame(OTU = unique(citrusnanpu$OTU), note = "Yasuda et al. (2010)")
}
Merge data.frames from parentals
{
bothParentalsChr <- dplyr::bind_rows(citrusnanpu, citrusschwein)
bothParentalsMarks <- dplyr::bind_rows(citrusschweinMarkPosDF, citrusnanpuMarkPosDF)
bothPmarkStyle <- unique(dplyr::bind_rows(markStyleschweinDF, markStylenanpuDF))
bothPleftNotesUp <- dplyr::bind_rows(leftNotesschweinUp, leftNotesnanpuUp)
bothPleftNotes <- dplyr::bind_rows(leftNotesschwein, leftNotesnanpu)
}data.frames of the hybrid
{
cschnanpuformula <- "1A + 1C + 11D + 5F"
require(idiogramFISH)
#
# hybrid chr. size
#
citrusschnanpu <- citrusSize(A = 1, C = 1, D = 11, F = 5 #
, OTU = "schweinfurthii + nanpu",
longArm = 1.2)
#
# hybrid CMA marks
#
citrusschnanpuMarkPosDF <- citrusMarkPos(citrusschnanpu)
#
# invert some chr.
#
csSwap <- swapChrRegionDfSizeAndMarks(citrusschnanpu, citrusschnanpuMarkPosDF, c(paste0("D_", 1:11)))
citrusschnanpu <- csSwap$dfChrSize
citrusschnanpuMarkPosDF <- csSwap$dfMarkPos
#
# d.f. of gish marks
#
citrusschnanpuMarkPosDF2 <- data.frame(chrName = c(paste0("D_", 5:11), paste0("F_", 1:2)),
chrRegion = "w",
markName = "schweingenome",
OTU = unique(citrusschnanpu$OTU)
)
citrusschnanpuMarkPosDF3 <- data.frame(chrName = c("A", "C", paste0("D_", 1:4), paste0("F_", 3:5)),
chrRegion = "w",
markName = "nanpugenome",
OTU = unique(citrusschnanpu$OTU)
)
#
# merge marks
#
citrusschnanpuMarkPosDF <- dplyr::bind_rows(citrusschnanpuMarkPosDF2, citrusschnanpuMarkPosDF3, citrusschnanpuMarkPosDF)
#
# style of marks d.f.
#
unique(citrusschnanpuMarkPosDF$markName)
{
markStyleschnanpuDF <- makedfMarkColorMycolors(
unique(citrusschnanpuMarkPosDF$markName), c("chartreuse3", "chocolate", "darkgoldenrod1"))
}
#
# notes for hybrid
#
# italics! # rest: \" to \"
name <- paste0("italic('C. schweinfurthii'), \" × 'Nanpu' tangor (CN3) (", cschnanpuformula, ")\"")
# to parse italics, use parseStr2lang = TRUE
leftNotesschnanpuUp <- data.frame(OTU = unique(citrusschnanpu$OTU), note = name)
notesschnanpu <- data.frame(OTU = unique(citrusschnanpu$OTU), note = "'Yasuda et al. (2010)'")
}Plot
#
# plot of parentals only
#
{
par(mar = rep(0, 4), oma = rep(0, 4))
plotIdiograms(callPlot = TRUE,
dfChrSize = bothParentalsChr, # chr. size data.frame
dfMarkPos = bothParentalsMarks, # mark position data.frame
dfMarkColor = bothPmarkStyle, # mark style d.f.
orderChr = "original" # order of chr. as in d.f.
, chrWidth = .5 # chr. width
, chrSpacing = .5 # separ. among chr.
, karHeight = 4 # kar. height
, karHeiSpace = 5 # anchor height
, chromatids = FALSE # don't use chromatids
, chrColor = "white" # chr. color
, ruler = FALSE # don't use ruler
, chrId = "" # don't use chr. name
, chrIndex = "" # don't use chr. indices
, morpho = "" # don't use morphology
, karIndex = FALSE # don't use kar. indices
, colorBorderMark = "black" # color of border of marks
, addOTUName = FALSE # do not add OTU names
, lwd.chr = 1.6 # border width
, lwd.marks = 1 # border width marks
, gishCenBorder = TRUE # cen. border of gish as mark color
, hideCenLines = 1.75 # hide cen. border
, legend = "" # no legend for marks
, leftNotes = bothPleftNotes # data.frame with left notes
, leftNotesUp = bothPleftNotesUp # data.frame with Up left notes
, leftNoteFontUp = 3 # italics
, leftNotesTextSize = 1.3 # font size of notes
, leftNotesUpTextSize = 1.3 # font size of notes
, leftNotesPosX = 0 # horizontal pos. of left notes
, leftNotesPosY = 0 # vertical pos. of left down notes
, leftNotesUpPosX = 0 # horizontal pos. of left up notes
, leftNotesUpPosY = 2 # vertical pos. of left up notes
, verticalPlot = FALSE # horizontal plot
, karSpaceHor = 3 # horizontal spacing among kar.
, karAnchorLeft = "C. schweinfurthii" # anchor to the left of
, anchor = TRUE # add anchor
, ylimBotMod = 1 # modify ylim bottom argument
, ylimTopMod = 0 # modify ylim top argument
, xlimLeftMod = 0 # modify left xlim
, xlimRightMod = 2 # modify right xlim
)
}
# add plot of hybrid over parents plot
{
plotIdiograms(callPlot = FALSE, # plot over previous plot
dfChrSize = citrusschnanpu, # chr. size data.frame
dfMarkPos = citrusschnanpuMarkPosDF, # mark position data.frame
dfMarkColor = markStyleschnanpuDF, # mark style d.f.
orderChr = "original", # order of chr. as in d.f.
chrWidth = .5, # chr. width
chrSpacing = .5, # separ. among chr.
karHeight = 4 # kar. height
, chromatids = FALSE # don't use chromatids
, chrColor = "white" # chr. color
, ruler = FALSE # don't use ruler
, chrId = "" # don't use chr. name
, chrIndex = "" # don't use chr. indices
, morpho = "" # don't use morphology
, karIndex = FALSE # don't use kar. indices
, colorBorderMark = "black" # color of border of marks
, addOTUName = FALSE # don't add OTU name
, lwd.chr = 1.6 # border width
, lwd.marks = 1 # border width marks
, leftNotesUp = leftNotesschnanpuUp # up notes: name of hybrid
, parseStr2lang = TRUE # for italics, see notes data.frame
, notesTextSize = 1.3 # font size of notes
, leftNotesUpTextSize = 1.3 # font size of notes
, leftNotesPosX = 0 # horizontal pos. of notes
, leftNotesUpPosY = 2 # vertical pos. left up notes
, notes = notesschnanpu # right notes - authors
, notesPosX = 3 # notes hor. pos
, ylimBotMod = 1 # modify ylim bottom argument
, ylimTopMod = -5 # modify ylim top argument
, xlimLeftMod = 0 # modify left xlim
, xlimRightMod = 2 # modify right xlim
, gishCenBorder = TRUE # cen. border as mark color
, legend = "" # no legend for marks
, hideCenLines = 1.75 # hide cen. lines
, moveAllKarValueHor = 9.5 # move kar. to right
, moveAllKarValueY = -10 # move kar. down
)
} # hybrid
8 Groups
Jupyter interactive version:|
Github
|
Raw |
8.1 monocentrics
Adding the column group
Open your chromosome data - Chr. size - as data.frame and add column
| chrName | shortArmSize | longArmSize | group |
|---|---|---|---|
| 1 | 3.0 | 5.0 | 1 |
| 1 | 3.2 | 5.5 | 1 |
| 1 | 3.5 | 4.8 | 1 |
| 4 | 1.0 | 3.0 | NA |
| 5 | 3.0 | 5.0 | NA |
| X | 4.0 | 6.0 | NA |
Heteromorphic pairs
It can be used to plot heteromorphic pairs, see pair 1| chrName | shortArmSize | longArmSize | group | |
|---|---|---|---|---|
| 1 | 1A | 3 | 5 | 1 |
| 2 | 1B | 3 | 5 | 1 |
| 4 | 2 | 1 | 3 | NA |
| 5 | 3 | 3 | 5 | NA |
| 6 | 4 | 4 | 6 | NA |
| chrName | markName | chrRegion | markSize | markDistCen |
|---|---|---|---|---|
| 1A | 5S | p | 1 | 0.9 |
| 1B | 45S | p | 1 | 0.9 |
| 2 | CMA | q | 1 | 1.0 |
| 3 | DAPI | q | 1 | 1.0 |
Plot
require(idiogramFISH)
# svg("dfwithHetero.svg",width = 13.5, height = 8 )
par(mar = rep(0, 4))
dfwithHetero$OTU <- "hetero"
dfwithgroups$OTU <- "first"
both <- plyr::rbind.fill(dfwithHetero, dfwithgroups)
dfOfMarksHetero$OTU <- "hetero"
plotIdiograms(dfChrSize = both, # chr. sizes
dfMarkPos = dfOfMarksHetero, # position of marks
karHeiSpace = 4,
chrId = "original", # chr. name in df.
chrIndex = "", # do not add chr. indices
morpho = "", # do not add chr. morphologies
karIndex = FALSE, # do not add karyotype indices
distTextChr = .8, # distance from text to chr.
markDistType = "cen", # mark position measured to center of mark
orderChr = "name", # order chr. by name
ruler = FALSE # do not plot ruler
, ylimBotMod = 1 # modify ylim bottom argument
, legendWidth = 1 # width of legend
)
8.2 Holocentrics
Let’s modify some data.frames to add a group
data("dfChrSizeHolo")
data("dfMarkPosHolo")
dfMarkPosHoloHetero <- dfMarkPosHolo
dfMarkPosHoloHetero$chrName <- c(3, 3, "1A", 2, "1B", "1B")
dfMarkPosHoloHetero$OTU <- "heteromorphic"
dfChrSizeHoloHetero <- dfChrSizeHolo
dfChrSizeHoloHetero$chrName <- c("1A", "1B", 2, 3)
dfChrSizeHoloHetero$OTU <- "heteromorphic"
# Adding the group column
dfChrSizeHoloHetero$group <- c(1, 1, NA, NA)Creating a new data.frame for holocentrics
| OTU | chrName | chrSize | group |
|---|---|---|---|
| Species name | 1 | 3.1 | 1 |
| Species name | 1 | 3.2 | 1 |
| Species name | 1 | 3.3 | 1 |
| Species name | 1 | 3.4 | 1 |
| Species name | 2 | 4.0 | NA |
| Species name | 3 | 5.0 | NA |
| Species name | 4 | 6.0 | NA |
par(mar = rep(0, 4))
mergedChrSize <- plyr::rbind.fill(dfChrSizeHoloGroup, dfChrSizeHoloHetero)
plotIdiograms(dfChrSize = mergedChrSize, # data.frame of chr. sizes
dfMarkPos = dfMarkPosHoloHetero, # d.f. of marks
orderChr = "name", # order chr. by name
karIndex = FALSE, # do not add karyotype indices
addOTUName = TRUE, # add OTU name
karHeiSpace = 4, # height of kar. with spacing
ruler = FALSE, # no ruler
xlimLeftMod = -1, # modify left argument of xlim
xlimRightMod = 0, # modify right argument of xlim
ylimBotMod = 1.3 # modify bottom argument of ylim
, xModifier = 100 # separ. among chromatids
)
9 Circular Plots
Jupyter interactive version:|
Github
|
Raw |
visit gitlab for installation instructions https://gitlab.com/ferroao/idiogramFISH
9.1 Example with monocen. and holocen.
{
require(idiogramFISH)
require(plyr)
dfOfChrSize$OTU <- "Species mono"
dfChrSizeHolo$OTU <- "Species holo"
monoholoCS <- plyr::rbind.fill(dfOfChrSize, dfChrSizeHolo)
dfOfMarks2$OTU <- "Species mono"
dfMarkPosHolo$OTU <- "Species holo"
monoholoMarks <- plyr::rbind.fill(dfOfMarks2, dfMarkPosHolo)
monoholoMarks[which(monoholoMarks$markName == "5S"), ]$markSize <- .5
monoholoMarks[10, ]$markName <- "prot"
monoholoMarks[10, ]$markSize <- 1
dfMarkColor <- rbind(dfMarkColor, c("prot", "black", "exProtein"))
}
plotIdiograms(dfChrSize = monoholoCS, # data.frame of chr. size
dfMarkColor = dfMarkColor, # df of mark style
dfMarkPos = monoholoMarks, # df of mark positions, includes cen. marks
squareness = 5, # vertices squareness
addOTUName = TRUE, # add OTU names
distTextChr = .5, # separ. among chr. and text and among chr. name and indices
chrId = "original", # use original name of chr.
OTUTextSize = .7, # size of OTU name
legendHeight = 1, # height of legend labels
legendWidth = 1, # width of legend labels
# ,legend = "inline"
fixCenBorder = TRUE, # use chrColor as border color of cen. or cen. marks
xlimLeftMod = 1, # modify xlim left argument of plot
xlimRightMod = 2, # modify xlim right argument of plot
ylimBotMod = .2 # modify ylim bottom argument of plot
, useOneDot = FALSE
# GRAPHICAL PARAMETERS FOR CIRCULAR PLOT
, circularPlot = TRUE # circularPlot
, shrinkFactor = .9 # percentage 1 = 100% of circle with chr.
, circleCenter = 3 # X coordinate of circleCenter (affects legend pos.)
, chrLabelSpacing = .9 # chr. names spacing
, OTUsrt = 0 # angle for OTU name (or number)
, OTUplacing = "number" # Use number and legend instead of name. See OTUcentered
, OTUjustif = 0 # OTU names justif. left.
, OTULabelSpacerx = -0.5 # modify position of OTU label, when OTUplacing = "number" or "simple"
, OTUlegendHeight = 1.5 # space among OTU names when in legend - OTUplacing
, separFactor = 0.75
)
9.2 Recreating circular karyotype of (Golczyk et al., 2005)
# First swap short and long arms to show the same rotation of the article
listradfs <- swapChrRegionDfSizeAndMarks(traspadf, traspaMarks, c("3", "6", "7", "9", "12"))
# Create marks' characteristics
dfMarkColor5S25S <- read.table(text = " markName markColor style
5S black dots
25S white dots", header = TRUE, stringsAsFactors = FALSE, fill = TRUE)
plotIdiograms(dfChrSize = listradfs$dfChrSize, # d.f. of chr. sizes
dfMarkPos = listradfs$dfMarkPos, # d.f. of marks' positions
dfMarkColor = dfMarkColor5S25S, # d.f. of mark characteristics
cenColor = "black", # cen. color
squareness = 5, # corner squareness
chrWidth = 1, # chr. width
orderChr = "name" # order chr. by name
, addOTUName = FALSE # do not add OTU name
, legendHeight = 3 # labels separ. y axis
# circular plot parameters
, circularPlot = TRUE,
radius = 5 # basic radius
, useOneDot = FALSE # use two dots in dot marks
, chrLabelSpacing = 1 # chr. name spacing
, rotation = 0.1 # anti-clockwise start site in x*pi radians, from top (0)
, shrinkFactor = .95 # % of circle use
)
9.3 Plasmid data from genBank
Using upArrow and downArrow styles,
clockwise and anti-clockwise, respectively.
# data from: https://www.ncbi.nlm.nih.gov/nuccore/NZ_CP009939.1
# install.packages("rentrez")
library(rentrez)
# search string
bcereus <- "Bacillus cereus strain 03BB87 plasmid pBCN, complete sequence"
bcereus_search <- rentrez::entrez_search(db = "nuccore", term = bcereus)
# get summaries
esummaries <- rentrez::entrez_summary(db = "nuccore", id = bcereus_search$ids)
# download plasmid data
# From the entrez formats:
# https://www.ncbi.nlm.nih.gov/books/NBK25499/table/chapter4.T._valid_values_of__retmode_and/
# idiogramFISH can read only:
rentrezDownloadPlas <- rentrez::entrez_fetch(db = "nuccore",
id = bcereus_search$ids[1],
rettype = "gbwithparts",
retmode = "text")
mylist <- genBankReadIF(rentrezDownloadPlas)
# data.frames in mylist
names(mylist)
# [1] "gbdfMain" "gbdfAssemblyMeta" "source" "gene"
# [5] "CDS"
# mylist$source
# View(mylist$gbdfMain)
# View(mylist$gbdfAssemblyMeta)
# mylist$gbdfAnnoMeta
# View(mylist$CDS)
# View(mylist$gene)
# Authors of plasmid sequence
paste(mylist$gbdfMain[which(mylist$gbdfMain$field == "AUTHORS"), ][1, 2])
# [1] "Johnson,S.L., Minogue,T.D., Teshima,H., Davenport,K.W., Shea,A.A.,; Miner,H.L., Wolcott,M.J. and Chain,P.S."
# create plasmid size data data.frame
{
myPlasmiddf <- data.frame(chrName = 1, chrSize = mylist$source$end)
myPlasmiddf$OTU <- mylist$gbdfMain[which(mylist$gbdfMain$field == "DEFINITION"), ]$value
myPlasmiddf$OTU <- gsub(", complete sequence.", "", myPlasmiddf$OTU)
# Creating mark info data.frame
mylistSel <- mylist[which(names(mylist) %in% "gene")]
mylistSelDF <- dplyr::bind_rows(mylistSel, .id = "feature")
mylistSelDF$markPos <- pmin(as.numeric(mylistSelDF$begin), as.numeric(mylistSelDF$end))
mylistSelDF$markSize <- abs(as.numeric(mylistSelDF$end) - as.numeric(mylistSelDF$begin))
mylistSelDF$markName <- mylistSelDF$locus_tag
# orientation of arrows
mylistSelDF$style <- ifelse(mylistSelDF$isComplement, "downArrow", "upArrow")
# Replace codes with names
mylistSelDF[which(!is.na(mylistSelDF$gene)), ]$markName <-
mylistSelDF[which(!is.na(mylistSelDF$gene)), ]$gene
# subset columns
marksDfPlas <- mylistSelDF[, c("markName", "markPos", "markSize", "style"), ]
# add OTU name
marksDfPlas$OTU <- myPlasmiddf$OTU
# add mandatory column
marksDfPlas$chrName <- myPlasmiddf$chrName
# organize inner arrows (downArrow) in two columns avoiding overlap
protVal <- .5 # this values (and others) must be the same
circVal <- TRUE # in plotIdiograms function
rotaVal <- 0
marksDfPlasCols <- namesToColumns(marksDfPlas, myPlasmiddf,
markType = c("downArrow"),
amountofSpaces = 10, colNumber = 2,
protrudingInt = 1.3, protruding = protVal,
circularPlot = circVal,
rotation = rotaVal
)
# add marker for start pos.
colnames(marksDfPlasCols)
marksDfPlasCols <- rbind(marksDfPlasCols, c(paste0("START", paste0(rep(" ", 0), collapse = "")), 1, NA, "square", myPlasmiddf$OTU, 1, NA))
# create mark general data data.frame
markStyle <- makedfMarkColorMycolors(
unique(marksDfPlasCols$markName), c("black", "forestgreen", "cornflowerblue"))
# arrows
markStyle$style <- marksDfPlasCols$style[match(markStyle$markName, marksDfPlasCols$markName)]
markStyle$protruding <- marksDfPlasCols$protruding[match(markStyle$markName, marksDfPlasCols$markName)]
# prefix to remove from marks
mypattern <- sub("([[:alnum:]]+_).*", "\\1", trimws(marksDfPlas$markName[1]))
}
library(idiogramFISH)
par(mar = rep(0, 4), oma = rep(0, 4))
plotIdiograms(dfChrSize = myPlasmiddf, # plasmid size d.f.
dfMarkPos = marksDfPlasCols, # mark pos d.f.
dfMarkColor = markStyle, # mark style d.f.
chromatids = FALSE,
squareness = 21, # corners not rounded
chrWidth = 0.5, # chr. width
chrId = "", # no chr. name
markLabelSize = .7, # font size of labels
pattern = mypattern, # remove pattern from mark names
cMBeginCenter = TRUE,
legend = "inline",
protruding = protVal,
ylimBotMod = 0, # modify plot size
ylimTopMod = 0,
xlimLeftMod = 2,
# circular params.
circularPlot = circVal, # circular
rotation = rotaVal, # begin plasmid in top
radius = 2.5,
shrinkFactor = 1, # use 100% of circle
labelSpacing = 1.7, # label spacing from chr.
labelOutwards = TRUE, # label projected based on mark angle
OTUjustif = 0.5, # OTU name justif. centered.
OTUplacing = "simple" # plasmid name place. See OTUcentered
, OTUTextSize = .8 # font size of OTU name
)
9.4 Prokaryote chromosome from genBank
# Option 1: Download prokaryote genome data from:
# https://www.ncbi.nlm.nih.gov/nuccore/NC_014248.1
# Choose Customize View -> Basic Features -> genes, CDS
# Send To -> File -> Create File
# Use your file name:
dataChr.gb <- "nostoc.gb" # 5 Mbytes
# Option 2: Download with rentrez package
library(rentrez)
# search string
nostoc <- "'Nostoc azollae' 0708, complete"
nostoc_search <- rentrez::entrez_search(db = "nuccore", term = nostoc)
# get summaries
esummariesNostoc <- rentrez::entrez_summary(db = "nuccore", id = nostoc_search$ids)
# select only perfect matches
select <- numeric()
for (i in seq_along(esummariesNostoc)) {
print(esummariesNostoc[[i]]$title)
if (esummariesNostoc[[i]]$title %in% grep(nostoc, esummariesNostoc[[i]]$title, value = TRUE)) {
select <- c(select, i)
}
}
select
# 3 8
# download chr. data
dataChr.gb <- rentrez::entrez_fetch(db = "nuccore",
id = nostoc_search$ids[select][1],
rettype = "gbwithparts",
retmode = "text")
# START:
library(idiogramFISH)
mylistChr <- genBankReadIF(dataChr.gb) # 9 seconds
names(mylistChr)
# "gbdfMain" "gbdfAnnoMeta" "source" "gene" "CDS" "tRNA"
# "regulatory" "ncRNA" "rRNA" "misc_feature" "tmRNA"
# Authors of sequence
paste(mylistChr$gbdfMain[which(mylistChr$gbdfMain$field == "AUTHORS"), ][1, 2])
# [1] "Ran, L., Larsson, J., Vigil-Stenman, T., Nylander, J.A., Ininbergs, K.,;
# Zheng, W.W., Lapidus, A., Lowry, S., Haselkorn, R. and Bergman, B."
# create chr. size data data.frame
# columns chrName and chrSize
myProkaryotedf <- data.frame(chrName = 1, chrSize = mylistChr$source$end)
# column with OTU name
myProkaryotedf$OTU <- mylistChr$gbdfMain[which(mylistChr$gbdfMain$field == "DEFINITION"), ]$value
myProkaryotedf$OTU <- gsub(", complete genome.", "", myProkaryotedf$OTU)
# Creating mark info data.frame excluding some features
mylistChrSel <- mylistChr[which(names(mylistChr) %in%
setdiff(names(mylistChr), c("gbdfMain", "gbdfAnnoMeta", "source", "CDS")))]
# or:
# mylistSel<- mylistChr[which(names(mylistChr) %in% "CDS")]
# transform list into data.frame
mylistChrDF <- dplyr::bind_rows(mylistChrSel, .id = "feature")
# add necessary columns
mylistChrDF$markPos <- pmin(as.numeric(mylistChrDF$begin), as.numeric(mylistChrDF$end))
mylistChrDF$markSize <- abs(as.numeric(mylistChrDF$end) - as.numeric(mylistChrDF$begin))
mylistChrDF$markName <- mylistChrDF$locus_tag
# Replace codes with genes, and replace NAs in markNames (locus_tag)
mylistChrDF[which(!is.na(mylistChrDF$gene)), ]$markName <-
mylistChrDF[which(!is.na(mylistChrDF$gene)), ]$gene
mylistChrDF[which(!is.na(mylistChrDF$regulatory_class)), ]$markName <-
mylistChrDF[which(!is.na(mylistChrDF$regulatory_class)), ]$regulatory_class
# make unique names, otherwise some marks may share style and color
mylistChrDF$markName <- make.uniqueIF(mylistChrDF$markName)
# when no markName and note available:
mylistChrDF[which(is.na(mylistChrDF$markName)), ]$markName <-
sub("([[:alpha:] ]+);.*", "\\1", mylistChrDF[which(is.na(mylistChrDF$markName)), ]$note)
# orientation of arrows
mylistChrDF$style <- ifelse(mylistChrDF$isComplement, "downArrow", "upArrow")
# select main columns for data.frame of marks' positions
marksDfChr <- mylistChrDF[, c("markName", "markPos", "markSize", "feature", "isJoin", "style"), ]
marksDfChr$OTU <- myProkaryotedf$OTU
# add mandatory column
marksDfChr$chrName <- myProkaryotedf$chrName
# Organize mark names in columns to avoid overlap
rotaVal <- 0
marksDfChrCols <- namesToColumns(marksDfChr, myProkaryotedf,
markType = c("downArrow", "upArrow"),
amountofSpaces = 13, colNumber = 4,
protrudingInt = 0.5,
rotation = rotaVal)
{
# add marker for start pos.
colnames(marksDfChrCols)
marksDfChrCols <- rbind(marksDfChrCols,
c(" START", 1, NA,
"start", FALSE, "square", myProkaryotedf$OTU, 1, NA)
)
# unique(marksDfChrCols$markName)
# create mark general data data.frame
markStyleNostoc <- makedfMarkColorMycolors(
unique(marksDfChrCols$markName), c("black", "forestgreen", "cornflowerblue"))
unique(marksDfChrCols$feature)
# [1] "gene" "tRNA" "regulatory" "ncRNA" "rRNA" "tmRNA" "start"
unique(marksDfChrCols$isJoin)
# [1] "FALSE"
# change some colors depending on feature
markStyleNostoc[which(markStyleNostoc$markName %in%
marksDfChrCols[which(marksDfChrCols$feature %in% c("tRNA", "tmRNA")), ]$markName
), ]$markColor <- "magenta"
markStyleNostoc[which(markStyleNostoc$markName %in%
marksDfChrCols[which(marksDfChrCols$feature %in% c("regulatory", "ncRNA")), ]$markName
), ]$markColor <- "tomato3"
markStyleNostoc[which(markStyleNostoc$markName %in%
marksDfChrCols[which(marksDfChrCols$feature %in% "rRNA"), ]$markName
), ]$markColor <- "red2"
markStyleNostoc[which(markStyleNostoc$markName %in%
marksDfChrCols[which(marksDfChrCols$feature %in% c("misc_binding", "misc_feature")), ]$markName
), ]$markColor <- "lightsalmon"
# or:
# When isJoin is TRUE (CDS feature included)
# markStyleNostoc[which(markStyleNostoc$markName %in%
# marksDfChrCols[which(marksDfChrCols$isJoin==TRUE),]$markName
# ),]$markColor<-"red"
# arrows info. to d.f. of charac.
markStyleNostoc$style <- marksDfChrCols$style[match(markStyleNostoc$markName, marksDfChrCols$markName)]
markStyleNostoc$protruding <- marksDfChrCols$protruding[match(markStyleNostoc$markName, marksDfChrCols$markName)]
mypattern <- sub("([[:alnum:]]+_).*", "\\1", trimws(marksDfChrCols$markName[1]))
}
png("NOSTOC.png", width = 2795, height = 2795) # 2.7 Mb increase size to increase resolution
# pdf("NOSTOC.pdf", width = 2795/80, height = 2795/80)
# svg("NOSTOC.svg", width = 2795/80, height = 2795/80) # 42 Mb vectorized
par(mar = rep(0, 4))
plotIdiograms(dfChrSize = myProkaryotedf, # chr. data d.f.
dfMarkPos = marksDfChrCols, # mark pos d.f.
dfMarkColor = markStyleNostoc, # mark style d.f. style
squareness = 21, # corners not rounded
n = 150, # number of vertices in rounded items.
markN = 2,
chromatids = FALSE,
chrWidth = 4, # chr. width
lwd.chr = 0.1,
chrId = "none", # no chr. name
legend = "inline", # for arrows, this mimics cM and cMLeft marks
#
markLabelSize = 0.25, # font size of labels
pattern = mypattern, # remove pattern from mark names
#
ylimBotMod = 5, # modify plot size
ylimTopMod = 5,
xlimLeftMod = 5,
xlimRightMod = 5,
#
# # circular plot params.
circularPlot = TRUE, # circular
shrinkFactor = 1, # use 100% of circle
labelSpacing = 1, # label spacing from chr.
rotation = rotaVal, # begin chr. in top
labelOutwards = TRUE # label projected based on mark angle
#
, OTUjustif = 0.5 # OTU name centered
, OTUplacing = "simple" # location of OTU name, see OTUcentered
, radius = 8 # radius of circle
, OTUTextSize = 3 # font size of OTU name
, cMBeginCenter = TRUE # label of arrows (inline) start in the middle
)
dev.off()
10 Plotting alongside phylogeny
Jupyter interactive version:|
Github
|
Raw |
This guide shows the files to plot idiograms alongside a phylogeny
10.1 Load package
visit gitlab for installation instructions https://gitlab.com/ferroao/idiogramFISH
#load package
library(idiogramFISH) 10.2 ggtree of iqtree and monocentrics
idiogramFISH comes with two trees and data.frames with chr. and marks’ data for the correspondent OTUs, first we will plot a tree produced with iqtree (Nguyen et al., 2015)
Load the iqtree:
We will use phytools for that (Revell, 2012)
require(ggplot2)
require(phytools)
require(ggpubr)
require(grid) # pushViewport
require(ggtree)
# list.files(system.file('extdata', package = 'my_package') )
# find path of iqtree file
iqtreeFile <- system.file("extdata", "eightSpIqtree.treefile", package = "idiogramFISH")
# load file as phylo object
iqtreephylo <- read.newick(iqtreeFile) # phytools
# transform tree
iqtreephyloUM <- force.ultrametric(iqtreephylo, method = "extend") # phytoolsMake a ggtree (Yu et al., 2018)
ggtreeOf8 <- ggtree(iqtreephyloUM) + geom_tiplab(size = 6)Modify optionally graphical parameters with ggplot and ggpubr: (Wickham, 2016; Kassambara, 2019)
gbuil2 <- ggplot_build(ggtreeOf8) # get ggplot_built
gtgbuild <- ggplot_gtable(gbuil2) # get gtable from ggplot_built
gtgbuild$layout$clip[gtgbuild$layout$name == "panel"] <- "off" # modify gtable
ggtreeOf8b <- as_ggplot(gtgbuild) # back to ggplot
gtgbuildgg2 <- ggtreeOf8b + theme(plot.margin = unit(c(1, 9.5, 3, 1.5), "cm")) # top right bottom left - modify marginsOrder OTUs in data.frame of chr. data
Apply order of phylogeny to the data.frame
# Let's get the order of species in tree
ggtreeOf8TIPS <- ggtreeOf8$data[which(ggtreeOf8$data$isTip), ]
desiredOrder <- rev(ggtreeOf8TIPS[order(ggtreeOf8TIPS$y), ]$label)
# make a vector without missing OTUs
desiredFiltered <- intersect(desiredOrder, allChrSizeSample$OTU)
# establish desired order
allChrSizeSample$OTU <- factor(allChrSizeSample$OTU, levels = desiredFiltered)
# order
allChrSizeSample <- allChrSizeSample[order(allChrSizeSample$OTU), ]Now we have to establish where are the OTUs in the tree, that don’t have chr. data
# Establish position of OTUs before missing data OTUs
matchres <- match(desiredOrder, desiredFiltered)
matchres[is.na(matchres)] <- "R"
reps <- rle(matchres)
posOTUsBeforeMissing <- as.numeric(matchres[which(matchres == "R") - 1][which(matchres[which(matchres == "R") - 1] != "R")])
# This are the OTUs that come before missing chr. data OTUs
BeforeMissing <- desiredFiltered[posOTUsBeforeMissing]
# This is the amount of missing OTUs, spaces to add (ghost karyotypes)
valuesOfMissRepsBefore <- reps$lengths[which(reps$values == "R")]Plotting
Now we are ready to plot adding those arguments for
addMissingOTUAfter and missOTUspacings
# plot to png file
png(file = "firstplot.png", width = 962, height = 962)
par(omi = rep(0, 4),
mar = c(0, 1, 2, 1),
mfrow = c(1, 2)) # one row two columns
par(fig = c(0, .3, 0, 1)) # location of left ghost plot
plot.new() # ghost plot to the left
par(fig = c(.3, 1, 0, 1)) # location of right plot
plotIdiograms(dfChrSize = allChrSizeSample, # data.frame of Chr. Sizes
dfMarkPos = allMarksSample, # d.f. of Marks (inc. cen. marks)
dfMarkColor = mydfMaColor, # d.f. of mark characteristics
squareness = 4, # squareness of vertices
lwd.chr = .5, # width of lines
orderChr = "name", # order chr. by name
centromereSize = 1.3, # apparent cen. size
chrWidth = .75, # width of chr.
chrSpacing = .25, # horizontal spacing of chr.
indexIdTextSize = .4, # font size of indices and chr. names
karHeight = 4.8, # karyotype vertical relative size without spacing
karHeiSpace = 6.5, # karyotype vertical relative size with spacing
nameChrIndexPos = 4, # move the name of chr. indexes to left
morpho = "both", # add chr. morphology
chrIndex = "both", # add chr. indices
karIndex = TRUE, # add karyotype indices
yTitle = "", # remove units title of ruler
markLabelSpacer = 0 # spaces from rightmost chr. to legend
, ylimTopMod = -.1 # modify ylim top margin
, ylimBotMod = 2.6 # modify ylim bottom margin
, rulerPos = -0.5 # position of rulers
, rulerNumberSize = .35 # font size of ruler number
, rulerNumberPos = .4 # position of ruler numbers
, ruler.tck = -.004 # tick size and orient.
, addMissingOTUAfter = BeforeMissing # OTUs after which there are ghost karyotypes - empty spaces
, missOTUspacings = valuesOfMissRepsBefore # number of ghost karyotypes
)
# plot to the left the ggtree
pushViewport(viewport(layout = grid.layout(1, 2)))
pushViewport(viewport(layout.pos.col = 1, layout.pos.row = 1))
print(gtgbuildgg2, newpage = FALSE)
# close png
dev.off()
10.3 plot of revBayes tree and holocentrics
Now we are going to plot a tree from revBayes (Höhna et al., 2017)
First, load the revBayes tree:
require(ggplot2)
require(phytools)
require(ggpubr)
require(grid) # pushViewport
require(ggtree)
require(treeio)
# find path of iqtree file
revBayesFile <- system.file("extdata", "revBayesTutorial.tree", package = "idiogramFISH")
# load file as phylo object
revBayesPhylo <- read.beast(revBayesFile) # ggtree or treeio
# transform tree
revBayesPhyloUM <- force.ultrametric(revBayesPhylo@phylo, method = "extend") # phytoolsOrder OTUs in data.frame of chr. data
# Get order of OTUs in tree
is_tip <- revBayesPhyloUM$edge[, 2] <= length(revBayesPhyloUM$tip.label)
ordered_tips <- revBayesPhyloUM$edge[is_tip, 2]
desiredorderRevB <- rev(revBayesPhyloUM$tip.label[ordered_tips])
# Ceate some holocentrics' data
allChrSizeSampleHolo <- allChrSizeSample
allChrSizeSampleHolo <- allChrSizeSampleHolo[, c("OTU", "chrName", "longArmSize")]
colnames(allChrSizeSampleHolo)[which(names(allChrSizeSampleHolo) == "longArmSize")] <- "chrSize"
allMarksSampleHolo <- allMarksSample
allMarksSampleHolo <- allMarksSampleHolo[which(allMarksSampleHolo$chrRegion != "cen"), ]
allMarksSampleHolo <- allMarksSampleHolo[c("OTU", "chrName", "markName", "markDistCen", "markSize")]
colnames(allMarksSampleHolo)[which(names(allMarksSampleHolo) == "markDistCen")] <- "markPos"
allMarksSampleHolo[which(allMarksSampleHolo$markName == "5S"), ]$markSize <- .5
# Apply order of phylogeny to data.frame
# make a vector without missing OTUs
desiredFiltered <- intersect(desiredorderRevB, allChrSizeSampleHolo$OTU)
# establish desired order
allChrSizeSampleHolo$OTU <- factor(allChrSizeSampleHolo$OTU, levels = desiredFiltered)
# order
allChrSizeSampleHolo <- allChrSizeSampleHolo[order(allChrSizeSampleHolo$OTU), ]
Now we have to establish where are the OTUs in the tree, that
don’t have chr. data
# Establish position of OTUs before missing data OTUs
matchres <- match(desiredorderRevB, desiredFiltered)
matchres[is.na(matchres)] <- "R"
reps <- rle(matchres)
posOTUsBeforeMissing <- as.numeric(matchres[which(matchres == "R") - 1][which(matchres[which(matchres == "R") - 1] != "R")])
# This are the OTUs that come before missing chr. data OTUs
BeforeMissingPlot2 <- desiredFiltered[posOTUsBeforeMissing]
# This is the amount of missing OTUs, spaces to add (ghost karyotypes)
valuesOfMissRepsBeforePlot2 <- reps$lengths[which(reps$values == "R")]Plotting
Now we are ready to plot adding those arguments for
addMissingOTUAfter and missOTUspacings
# plot to png file
png(file = paste0("secondplot.png"), width = 962, height = 700)
{
par(omi = rep(0, 4), mar = c(0, 0, 0, 0), mfrow = c(1, 2))
par(fig = c(0, .27, 0, 1))
par(mar = c(2, 0, 2, 0)) # b l t r
plot(revBayesPhyloUM)
par(fig = c(0.27, 1, 0, 1), new = TRUE)
par(mar = c(0, 0, 0, 0)) # b l t r
plotIdiograms(allChrSizeSampleHolo, # chr. size data.frame
dfMarkPos = allMarksSampleHolo, # data.frame of marks' positions
dfMarkColor = mydfMaColor, # d.f. of mark characteristics
squareness = 4, # vertices squareness
karHeight = 2.8, # karyotype height
karHeiSpace = 4.5, # vertical size of kar. including spacing
yTitle = "",
karIndex = TRUE, # add karyotype index
indexIdTextSize = .4 # font size of indices and chr. names
, addMissingOTUAfter = BeforeMissingPlot2 # add ghost OTUs after these names
, missOTUspacings = valuesOfMissRepsBeforePlot2 # how many ghosts, respectively
, lwd.chr = .5 # line width
, markLabelSpacer = 0 # dist. of legend to rightmost chr.
, legendWidth = 2.3 # width of square or dots of legend
, rulerPos = -0.5 # position of ruler
, rulerNumberSize = .35 # font size of number of ruler
, rulerNumberPos = .4 # position of ruler number
, ruler.tck = -.004 # tick of ruler size and orient.
, ylimTopMod = -4 # modify ylim of top
, ylimBotMod = -4 # modify ylim of bottom
, xlimRightMod = 3 # modify xlim right argument
, xModifier = 100 # separ. among chromatids
)
}
# close png
dev.off()
10.4 plot of revBayes tree and holocentrics and monocentrics
Create data.frames with both types of karyotypes (Wickham, 2011)
require(plyr)
# Select this OTU from the monocen.
monosel <- c("Species_F", "Species_C", "Species_A")
# chr.
allChrSizeSampleSel <- allChrSizeSample [which(allChrSizeSample$OTU %in% monosel), ]
# marks
allMarksSampleSel <- allMarksSample [which(allMarksSample$OTU %in% monosel), ]
# Select the others from the holocen.
holosel <- setdiff(unique(allChrSizeSampleHolo$OTU), monosel)
# chr.
allChrSizeSampleHoloSel <- allChrSizeSampleHolo[which(allChrSizeSampleHolo$OTU %in% holosel), ]
# marks
allMarksSampleHoloSel <- allMarksSampleHolo [which(allMarksSampleHolo$OTU %in% holosel), ]
# merge chr d.fs
mixChrSize <- plyr::rbind.fill(allChrSizeSampleSel, allChrSizeSampleHoloSel)
# merge marks' d.fs
mixMarks <- plyr::rbind.fill(allMarksSampleSel, allMarksSampleHoloSel)
Order data.frame and determine missing karyotypes
# make a vector without missing OTUs
desiredFiltered <- intersect(desiredorderRevB, mixChrSize$OTU)
# establish desired order
mixChrSize$OTU <- factor(mixChrSize$OTU, levels = desiredFiltered)
# order data.frame
mixChrSize <- mixChrSize[order(mixChrSize$OTU), ]
# Establish position of OTUs before missing data OTUs
matchres <- match(desiredorderRevB, desiredFiltered)
matchres[is.na(matchres)] <- "R"
reps <- rle(matchres)
posOTUsBeforeMissing <- as.numeric(matchres[which(matchres == "R") - 1][which(matchres[which(matchres == "R") - 1] != "R")])
# This are the OTUs that come before missing chr. data OTUs
BeforeMissingPlot2 <- desiredFiltered[posOTUsBeforeMissing]
# This is the amount of missing OTUs, spaces to add (ghost karyotypes)
valuesOfMissRepsBeforePlot2 <- reps$lengths[which(reps$values == "R")]Plotting
Now we are ready to plot adding those arguments for
addMissingOTUAfter and missOTUspacings
# plot to png file
png(file = paste0("thirdplot.png"), width = 1100, height = 1000)
{
par(omi = rep(0, 4), mar = c(0, 0, 0, 0), mfrow = c(1, 2))
par(fig = c(0, .25, 0, 1))
par(mar = c(1, 0, 0, 0))
plot(revBayesPhyloUM)
par(fig = c(0.25, 1, 0, 1), new = TRUE)
par(mar = c(0, 0, 0, 0))
plotIdiograms(mixChrSize, # chr. size data.frame
dfMarkPos = mixMarks, # data.frame of marks' positions (inc. cen. marks)
dfMarkColor = mydfMaColor, # d.f. of mark characteristics
origin = "b", # position measured from bottom of chr.
karHeight = 2.8, # vertical size of kar. including spacing
karHeiSpace = 4.5, # vertical size of kar. including spacing
squareness = 5, # vertices squareness
chrSpacing = .25, # horizontal spacing among chr.
yTitle = "",
karIndex = TRUE # add karyotype index
, indexIdTextSize = .4 # font size of indices and chr. names
, distTextChr = 0.7 # dist. among chr. and chr. name
, addMissingOTUAfter = BeforeMissingPlot2 # add ghost OTUs after these names
, missOTUspacings = valuesOfMissRepsBeforePlot2 # how many ghosts, respectively
, lwd.chr = .5 # line width
, markLabelSpacer = 0 # dist. of legend to rightmost chr.
, legendWidth = 2 # width of square or dots of legend
, ylimTopMod = -2 # modify ylim of top
, ylimBotMod = -2 # modify ylim of bottom
, rulerPos = -0.5 # position of ruler
, rulerNumberSize = .35 # font size of number of ruler
, rulerNumberPos = .4 # position of ruler number
, ruler.tck = -.004 # ruler tick size and orient.
, OTUfont = 3 # italics
, OTUfamily = "Courier New" # for OTU name
, xModMonoHoloRate = 5 # factor (quotient) to shrink separation of chromatids of holocen.
)
}
# close png
dev.off()
11 Citrus
Jupyter interactive version:|
Github
|
Raw |
11.1 C. maxima as da-Costa-Silva et al. (2019)
master data.frame of chr. size and marks
From this special data.frame citrusMaximaChrMark we will
get two of the three canonical data.frames:
- One for chr. sizes (parameter
dfChrSize) - One for marks’ positions (parameter
dfMarkPos) - One (optional) for mark style (parameter
dfMarkColor)
Column chrNameUp will be used in this case for unifying
the chr. names (chrName) in the 1st and 2nd
data.frames.
# C. maxima 'pink'
# 4A 2C 4D 6F 2FL
{
citrusMaximaChrMark <- read.table(text = "
chrName chrNameUp shortArmSize longArmSize markName chrRegion markDistCen markSize
FL 1 67 97 24c13 p 52 10
D 2 62 75 21L13 q 35 8
D 2 62 75 CMA q 43 32
A 3 70 103 45S p 6 16
A 3 70 103 14A12 p 32 8
A 3 70 103 CMA p 40 30
A 3 70 103 28A07 q 54 10
A 3 70 103 CMA q 64 39
D 4 59 84 02C12 p 31 10
D 4 59 84 20C13 q 32 9
D 4 59 84 cma q 48 36
F 5 52 74 5s p 18 10
C 6 62 86 28A05 p 22 9
C 6 62 86 cma p 40 22
C 6 62 86 cma q 61 25
A 7 57 96 45S p 6 18
A 7 57 96 cma p 38 19
A 7 57 96 cma q 62 34
F 8 41 72 01b09 q 47 8
F 9 40 72 55b01/59C23 q 24 13", header = TRUE)
}data.frame of chr. sizes
Main columns: chrName, shortArmSize,
longArmSize, OTU (optional when only one OTU),
group (optional)
Column chrNameUp will be used in this case for unifying
the chr. names (chrName) between data.frames.
{
require(idiogramFISH)
# column and row subset
citrusMaxima <- citrusMaximaChrMark[, 1:4][!duplicated(citrusMaximaChrMark[, 1:4]), ]
# chr. name change (unique)
citrusMaxima$chrName <- make.uniqueIF(citrusMaxima$chrName)
# chr. size in pixels
chrSizes <- citrusMaxima$shortArmSize + citrusMaxima$longArmSize
# max. size in μm.
maxSize <- 3.6
maxPixel <- max(chrSizes)
# pixel to microm.
citrusMaxima$shortArmSize <- citrusMaxima$shortArmSize / (maxPixel / maxSize)
citrusMaxima$longArmSize <- citrusMaxima$longArmSize / (maxPixel / maxSize)
citrusMaxima$OTU <- "C. maxima 'Pink'"
# add groups (pairs)
citrusMaxima$group <- 1:9
}data.frame of marks’ positions
Main columns: chrName, markName,
chrRegion (arm), markDistCen (mark distance to
centr.), markSize
Column chrNameUp will be used in this case for unifying
the chr. names (chrName) between data.frames.
Column OTU is mandatory because is present in first
data.frame (citrusMaxima)
{
# Select columns
citrusMaximaMarkPos <- citrusMaximaChrMark[, c(1:2, 5:8)][!duplicated(citrusMaximaChrMark[, c(1:2, 5:8)]), ]
# transcribe chr.names - changed above. needs common column (i.e. chrNameUp)
citrusMaximaMarkPos$chrName <- citrusMaxima$chrName[match(citrusMaximaMarkPos$chrNameUp, citrusMaxima$chrNameUp)]
# pixel to μm.
citrusMaximaMarkPos$markDistCen <- citrusMaximaMarkPos$markDistCen / (maxPixel / maxSize)
citrusMaximaMarkPos$markSize <- citrusMaximaMarkPos$markSize / (maxPixel / maxSize)
# OTU column
citrusMaximaMarkPos$OTU <- unique(citrusMaxima$OTU)
# fix case
citrusMaximaMarkPos$markName <- toupper(citrusMaximaMarkPos$markName)
}data.frame of marks’ style
Optional data.frame. Add color and style for marks present in
citrusMaximaMarkPos
{
unique(citrusMaximaMarkPos$markName)
# "24C13" "21L13" "CMA" "45S" "14A12" "28A07" "02C12" "20C13" "5S" "28A05" "01B09" "55B01/59C23"
# make d.f. of styles of marks
markStyleDF <- makedfMarkColorMycolors(
unique(citrusMaximaMarkPos$markName),
c("chocolate", "chocolate", "darkgoldenrod1", "chartreuse3", rep("chocolate", 4), "red", rep("chocolate", 3))
)
}Notes and plot
Two optional data.frames for adding notes to plot with columns
OTU and note.
Parameters: leftNotes and notes
# notes
{
# formula
maxima <- "4A + 2C + 4D + 6F + 2FL [4A/45S, 2F/5S]"
leftNotesdf <- data.frame(OTU = unique(citrusMaxima$OTU), note = maxima)
# authors
notesdf <- data.frame(OTU = unique(citrusMaxima$OTU), note = "da-Costa-Silva et al. 2019")
}
# add group column to show that each one is a pair
{
par(mar = rep(0, 4), oma = rep(0, 4))
plotIdiograms(dfChrSize = citrusMaxima, # chr. size data.frame
dfMarkPos = citrusMaximaMarkPos, # mark position data.frame
dfMarkColor = markStyleDF, # mark style d.f.
orderChr = "original", # order of chr. as in d.f.
chrIdPatternRem = "_.*", # regex pattern to remove from chr. names
classChrName = "Type", # chr. names title
chrWidth = 0.3, # chr. width
chrSpacing = 0.40, # separ. among chr.
groupSepar = 1 # factor to multiply chr. spacing among groups
, chromatids = FALSE # don't use chromatids
, chrColor = "white" # chr. color
, classGroupName = "Pair" # groups title
, chrBorderColor = "black" # border color
, lwd.chr = 0.5 # border width
, legend = "inline" # label location
, bannedMarkName = c("CMA", "45S", "5S") # don't show this (inline)
, bMarkNameAside = TRUE # show banned marks "aside"
, legendHeight = 1.7 # height of labels (aside)
, colorBorderMark = "black" # color of border of marks
, markNewLine = "/" # split mark name to new line
, ruler = FALSE # don't use ruler
, threshold = 40 # fix scale, when too much shrinking
, distTextChr = .7 # distance text to chr.
, chrIndex = "" # don't use chr. indices
, morpho = "" # don't use morphology
, karIndex = FALSE # don't use kar. indices
, OTUfont = 3 # OTU name in italics
, leftNotesTextSize = 1.3 # font size of notes
, notesTextSize = 1.3 # font size of notes
, leftNotes = leftNotesdf # data.frame with left notes
, leftNotesPosX = 0 # horizontal pos. of formula
, leftNotesPosY = 0.5,
notes = notesdf # right notes - authors
, ylimBotMod = 1 # modify ylim bottom argument
, ylimTopMod = 0 # modify ylim top argument
, xlimLeftMod = 2 # modify left xlim
, xlimRightMod = 3 # modify right xlim
)
}
11.2 C. reticulata as da-Costa-Silva et al. (2015)
Chr. size data.frame
#
# chr. size - arms in pixels
#
{
citrusReticulata <- read.table(text = "
chrName shortArmSize longArmSize totalMicro Mbp group
f 67 91 2.65 50.96 1
d 61 77 2.32 44.60 2
c 59 78 2.18 41.81 3
d 61 83 2.49 47.75 4
d 34 63 1.87 35.90 5
d 34 63 1.87 35.90 5
d 50 66 1.93 37 6
d 50 83 2.28 43.72 7
f 42 77 2.02 38.78 8
f 28 67 1.70 32.57 9", header = TRUE)
citrusReticulata$pixeltotal <- citrusReticulata$shortArmSize + citrusReticulata$longArmSize
# pixel to micrometers
citrusReticulata$shortArmSize <- citrusReticulata$shortArmSize / (citrusReticulata$pixeltotal / citrusReticulata$totalMicro)
citrusReticulata$longArmSize <- citrusReticulata$longArmSize / (citrusReticulata$pixeltotal / citrusReticulata$totalMicro)
# change chr. names avoiding duplicates
citrusReticulata$chrName <- toupper(citrusReticulata$chrName)
citrusReticulata$chrName <- make.uniqueIF(citrusReticulata$chrName)
# add OTU
citrusReticulata$OTU <- "C. reticulata 'Cravo'"
# replicate name for plotting it over chrs.
citrusReticulata$chrNameUp <- citrusReticulata$chrName
}Marks
citrusReticulataMarkPosDF <- read.table(text = "
chrName chrRegion markName markDistCen markSize
F_1 p 24C13 0.87 0.12
C p CMA 0.64 0.30
C q CMA 0.84 0.40
C p 14A12 0.48 0.11
C q 28A07 0.77 0.14
C p 45S 0.00 0.10
D_1 q CMA 0.54 0.75
D_1 p 21L13 0.67 0.14
D_2 q CMA 0.88 0.55
D_2 p 02C12 0.5 0.14
D_2 q 20C13 0.42 0.14
D_3 p CMA 0.35 0.30
D_3 p c45S 0.35 0.35
D_3 p CMA 0.8 0.15
D_3 p c45S 0.8 0.15
D_4 p CMA 0.35 0.30
D_4 p 45S 0.35 0.30
D_5 p 28A05 0.66 0.14
D_5 q CMA 0.50 0.60
D_6 q CMA 0.72 0.70
F_2 q 01B09 0.8 0.14
F_3 q 55B01 0.3 0.18
F_3 q 59C23 0.3 0.18", header = TRUE, stringsAsFactors = FALSE)
# marks' style data.frame
unique(citrusReticulataMarkPosDF$markName)
# [1] "24C13" "CMA" "14A12" "28A07" "45S" "21L13" "02C12" "20C13" "c45S"
# [10] "28A05" "01B09" "55B01" "59C23"
markStyleDF <- makedfMarkColorMycolors(
unique(citrusReticulataMarkPosDF$markName),
c("chocolate", "darkgoldenrod1", "chocolate", "chocolate", "chartreuse3", rep("chocolate", 3), "chartreuse3", rep("chocolate", 4))
)
# square mark with label to the left (squareLeft style)
markStyleDF[which(markStyleDF$markName == "59C23"), ]$style <- "squareLeft"
# add OTU!
citrusReticulataMarkPosDF$OTU <- unique(citrusReticulata$OTU)Plotting
# notes to the left
reticulata <- "2C + 10D + 6F [2C/45S, 2D/45S]"
leftNotesdf <- data.frame(OTU = unique(citrusReticulata$OTU), note = reticulata)
# authors in notes (right side)
notesdf <- data.frame(OTU = unique(citrusReticulata$OTU), note = "da-Costa-Silva et al. (2015)")
par(mar = rep(0, 4), oma = rep(0, 4))
{
require(idiogramFISH)
plotIdiograms(dfChrSize = citrusReticulata, # chr. size data.frame
dfMarkPos = citrusReticulataMarkPosDF, # mark position data.frame (inc. cen.)
dfMarkColor = markStyleDF, # mark style d.f.
orderChr = "original", # order of chr. as in d.f.
chrIdPatternRem = "_.*", # pattern to remove from chr. names
chrColor = "white" # color of chr.
, chrBorderColor = "black" # borders
, chrIndex = "AR" # add index r
, morpho = "" # don't add morphology cat.
, karIndex = FALSE # don't add kar. indeex
, chrNameUp = TRUE # add. info. of col. chrNameUp over kar.
, centromereSize = 0 # size of cen.
, colorBorderMark = "black" # color of border of marks
, lwd.chr = 1 # border width
, OTUfont = 3 # OTU name in italics
, leftNotes = leftNotesdf # data.frame with notes
, leftNotesTextSize = 1 # font size of notes
, notesTextSize = 1 # font size of notes
, leftNotesPosX = 0 # horizontal pos. of formula- left notes
, leftNotesPosY = 1.9 # y pos. of left notes
, notes = notesdf # authors in notes (right)
, notesPosX = 1 # move right notes to right
, rulerInterval = .5 # ruler label int.
, ruler.tck = -.01 # ruler ticks
, rulerPos = -0.5 # ruler pos.
, xPosRulerTitle = 7 # move title (units) of ruler, beginning in 1st chr.
, ylimBotMod = 2 # modify ylim bottom argument
, ylimTopMod = 1 # modify ylim top argument
, xlimLeftMod = 1 # modify left xlim
, xlimRightMod = 2 # modify right xlim
, chromatids = FALSE # do not plot chromatids
, squareness = 2 # corners rounded
, useMinorTicks = TRUE # ruler minor ticks
, miniTickFactor = 5 # number of small ticks per big ticks
, distTextChr = .7 # distance indices to chr.
, chrId = "" # don't add chr. names (below)
, chrSize = TRUE # add chr. size
, chrSizeMbp = TRUE # add info of col. Mbp
, nsmall = 2 # significative digits for indices
, markPer = "CMA" # calculate % of chr. for this mark
, showMarkPos = TRUE # show mark. position as fraction, under kar.
, bToRemove = c("CMA", "45S", "c45S") # do not use these in showMarkPos
, legend = "inline" # labels inline
, legendHeight = 1.5 # legend height (right)
, bannedMarkName = "CMA" # do not add label of this mark
, bMarkNameAside = TRUE # add banned mark aside
, forbiddenMark = "c45S" # do not add this mark label
, groupSepar = 1.8 # separation among groups, see col. group (x chrSpacing)
, chrSpacing = .20 # separ. among chr.
, chrWidth = .20 # chr. width
, nameChrIndexPos = 4 # move name of indices to the left
)
}
Download Citrus scripts from: https://ferroao.gitlab.io/idiogramfishhelppages/citrushelp.R{target = “_blank”}
11.3 Exploring Citrus functions
Details of functions can be found with:
?citrusSize
?citrusMarkPos
?markOverCMAOr in: https://ferroao.gitlab.io/idiogramFISH/reference/citrusSize.html{target = “_blank”}
Published by Carvalho et al. (2005)
C. jambhiri/ C. volkameriana
1B + 11D + 4F + 2FL0
Create data.frame of chr. size
{
library(idiogramFISH)
citrusSizeDF <- citrusSize(B = 1, D = 11, F = 4, FL0 = 2,
OTU = "C. jambhiri")
# add simple secondary names
citrusSizeDF$chrNameUp <- seq_len(nrow(citrusSizeDF))
head(citrusSizeDF, 3)
tail(citrusSizeDF, 3)
# Editing data.frame:
# citrusSizeDF <- edit(citrusSizeDF)
# Initial plot, only sizes:
par(mar = rep(0, 4), oma = rep(0, 4))
plotIdiograms(dfChrSize = citrusSizeDF, # chr. size data.frame
orderChr = "original", # order of chr.
ruler = FALSE,
ylimBotMod = 2, # modify bottom margin
ylimTopMod = 1,
chrNameUp = TRUE, # use col. chrNameUp
classChrName = "Type", # change default title of inferior name
classChrNameUp = "Chr." # change default title of upper name
)
}
Use the group column to define pairs
citrusSizeDF$chrName
[1] "B" "D_1" "D_2" "D_3" "D_4" "D_5" "D_6" "D_7" "D_8"
[10] "D_9" "D_10" "D_11" "F_1" "F_2" "F_3" "F_4" "FL0_1" "FL0_2"
# " "B" "D_1" "D_2" "D_3" "D_4" "D_5" "D_6" "D_7" "D_8" "D_9" "D_10" "D_11" "F_1" "F_2" "F_3" "F_4" "FL0_1" "FL0_2"
# ------- --------- --------- --------- ----------- ------------ ----------- ------------ -------------
# " 1 2 3 4 5 6 7 8 9
citrusSizeDF$group <- unlist(lapply(1:9, function(x) rep(x, 2)))
citrusSizeDF$group
[1] 1 1 2 2 3 3 4 4 5 5 6 6 7 7 8 8 9 9
# make secondary names
citrusSizeDF$chrNameUp <- unlist(lapply(1:9, function(x) rep(x, 2)))
citrusSizeDF$chrNameUp <- make.uniqueIF(citrusSizeDF$chrNameUp, sep = "", letter = TRUE)data.frame of marks’ position
# CMA bands
citrusMarkPosDF <- citrusMarkPos(citrusSizeDF)
head(citrusMarkPosDF, 3)
# chrName chrRegion markName markDistCen markSize OTU
# 1 B p CMA 0.00 0.35 C. jambhiri
# 2 B q CMA 1.35 0.35 C. jambhiri
# 3 D_1 q CMA 1.35 0.35 C. jambhiri
tail(citrusMarkPosDF, 3)
# chrName chrRegion markName markDistCen markSize OTU
# 11 D_7 q CMA 1.35 0.35 C. jambhiri
# 12 D_8 q CMA 1.35 0.35 C. jambhiri
# 13 D_9 q CMA 1.35 0.35 C. jambhiri
# marks with overlap with CMA
# add mark of 45S rDNA in B, short arm (p)
citrusMarkPosDF45S <- markOverCMA(citrusMarkPosDF, # d.f. of CMA bands
chrType = "B", # chr. of new mark
chrRegion = "p", # arm of new mark
markName = "45S") # name of mark
# add 45S in D (D_1) long arm
citrusMarkPosDF45S <- markOverCMA(citrusMarkPosDF45S, # d.f. including CMA bands
chrName = "D_1",
chrRegion = "q",
markName = "45S")
# creating additional data.frames of marks (non-CMA overlap)
citrusMarkPosDF45S_D11 <- data.frame(chrName = "D_11", # cr.
chrRegion = "q", # arm
markName = "45S",
markDistCen = 1, # dist. to centrom.
markSize = 0.2, # mark size
OTU = "C. jambhiri")
citrusMarkPosDF45S_F4 <- data.frame(chrName = "F_4",
chrRegion = "q",
markName = "45S",
markDistCen = 1,
markSize = 0.2,
OTU = "C. jambhiri")
# fuse data.frames
citrusMarkPosDF45S <- dplyr::bind_rows(citrusMarkPosDF45S, # CMA marks and overlapped
citrusMarkPosDF45S_D11, # 45S in D (no overlap)
citrusMarkPosDF45S_F4) # 45S in F (no overlap)data.frame of mark style
Add karyotype formulas
notesdf<- data.frame(OTU = unique(citrusSizeDF$OTU), note = "1B + 11D + 4F + 2FL0") # spacing mattersPlot
par(mar = rep(0, 4), oma = rep(0, 4))
library(idiogramFISH)
plotIdiograms(dfChrSize = citrusSizeDF, # chr. size data.frame
dfMarkPos = citrusMarkPosDF45S, # mark position data.frame (inc. cen.)
dfMarkColor = markStyleDF, # mark style d.f.
orderChr = "original", # preserve order of chr. of d.f.
# chrId = "", # remove name of chr.
chrIdPatternRem = "_.*", # regex pattern for removal of names of chr.
chrSpacing = 0.2, # separ. among chr.
chrColor = "dodgerblue",
chrNameUp = TRUE, # use col. chrNameUp
classChrName = "Type", # change default title of inferior name
classChrNameUp = "Chr." # change default title of upper name
, legendWidth = .8 # legend item width
, legendHeight = 3 # legend item height
, markLabelSpacer = 2 # legend spacer
, ruler = FALSE # no ruler
, chrIndex = "" # no chr. index
, morpho = "" # no morpho.
, karIndex = FALSE # no kar. ind.
, leftNotes = notesdf # data.frame with notes
, leftNotesTextSize = 1.3 # font size of notes
, leftNotesPosX = 10.2 # pos. formula x axis
, leftNotesPosY = 0 # pos. formula y axis
, ylimBotMod = 1 # modify ylim bottom argument
, xlimRightMod = 4 # modify right xlim
)
11.4 Representing only one chromosome per pair
As in the article (Carvalho et al., 2005)
C. jambhiri/ C. volkameriana
1B + 11D + 4F + 2FL0
{
# data.frame of chr. sizes
citrusSizeDF_2 <- citrusSize(B = 1, D = 8, F = 3, FL0 = 1, # MODIFIED, SEE ABOVE
OTU = "C. jambhiri_2")
head(citrusSizeDF_2)
# data.frame of CMA band pos.
citrusMarkPosDF_2 <- citrusMarkPos(citrusSizeDF_2)
head(citrusMarkPosDF_2)
# marks with overlap with CMA
# 45S in B, short arm
citrusMarkPosDF45S_2 <- markOverCMA(citrusMarkPosDF_2,
chrType = "B",
chrRegion = "p",
markName = "45S")
# 45S in D (D_1), long arm
citrusMarkPosDF45S_2 <- markOverCMA(citrusMarkPosDF45S_2,
chrName = "D_1",
chrRegion = "q",
markName = "45S")
# add mark from scratch (no overlap with CMA)
citrusMarkPosDF45S_D8 <- data.frame(chrName = "D_8", # name of chr.
chrRegion = "q", # arm
markName = "45S", #
markDistCen = 1, # dist. to centrom.
markSize = 0.2, # mark size
OTU = "C. jambhiri_2")
citrusMarkPosDF45S_F3 <- data.frame(chrName = "F_3",
chrRegion = "q",
markName = "45S",
markDistCen = 1,
markSize = 0.2,
OTU = "C. jambhiri_2")
# fuse data.frames
citrusMarkPosDF45S_2 <- dplyr::bind_rows(citrusMarkPosDF45S_2,
citrusMarkPosDF45S_D8,
citrusMarkPosDF45S_F3
)
# current marks
unique(citrusMarkPosDF45S_2$markName)
# data.frame of mark style
markStyleDF <- makedfMarkColorMycolors(
unique(citrusMarkPosDF45S_2$markName), c("darkgoldenrod1", "chartreuse3"))
# modify styles
markStyleDF$style <- c("square", "dots")
# organize pairs, group
citrusSizeDF_2$chrName
# "B" "D_1" "D_2" "D_3" "D_4" "D_5" "D_6" "D_7" "D_8" "F_1" "F_2" "F_3" "FL0"
# ________ ____ ___ ________ ____ _________ ____ ________ ___
# 1 2 3 4 5 6 7 8 9
citrusSizeDF_2$group <- c(1, 1, 2, 3, 4, 4, 5, 6, 6, 7, 8, 8, 9)
# add names over chr.
citrusSizeDF_2$chrNameUp <- citrusSizeDF_2$group
citrusSizeDF_2$chrNameUp <- make.uniqueIF(citrusSizeDF_2$chrNameUp, sep = "", letter = TRUE)
# formula
notesdf <- data.frame(OTU = unique(citrusSizeDF_2$OTU), note = "1B + 11D + 4F + 2FL0") # keep spacing
}
par(mar = c(0, 0, 0, 0), oma = rep(0, 4))
library(idiogramFISH)
plotIdiograms(dfChrSize = citrusSizeDF_2, # d.f. of chr. size
dfMarkPos = citrusMarkPosDF45S_2, # d.f. of mark pos
dfMarkColor = markStyleDF, # d.f. of mark style
orderChr = "original", # chr. order as in d.f.
chrIdPatternRem = "_.*", # modif name of chr. removing this pattern
chrSpacing = .20, # separ. among chr.
chrColor = "dodgerblue",
legendWidth = .8 # legend item width
, legendHeight = 2.5 # legend item height
, markLabelSpacer = 2 # legend spacer
, ruler = FALSE,
chrIndex = "",
morpho = "",
karIndex = FALSE,
chrNameUp = TRUE # use col. chrNameUp
, classChrName = "Type" # change default title of inferior name
, classChrNameUp = "Chr." # change default title of upper name
, classGroupName = "Pair" # name for groups
, leftNotes = notesdf # data.frame with notes
, leftNotesTextSize = 1.3 # font size of notes
, leftNotesPosX = 10.2 # formula horiz. pos.
, leftNotesPosY = 0,
ylimBotMod = 1 # modify ylim bottom argument
, ylimTopMod = 0 # modify ylim top argument
, xlimLeftMod = 2 # modify left xlim
, xlimRightMod = 3 # modify right xlim
)
11.5 Several karyotypes per plot
Column OTU is mandatory for several OTU.
# data.frames of size - merge
bothSize <- dplyr::bind_rows(citrusSizeDF, citrusSizeDF_2)
# data.frames of band pos. merge
bothMarkPos <- dplyr::bind_rows(citrusMarkPosDF45S, citrusMarkPosDF45S_2)
# formulas
notesdf <- data.frame(OTU = unique(bothSize$OTU), note = "1B + 11D + 4F + 2FL0")
par(mar = rep(0, 4), oma = rep(0, 4))
plotIdiograms(dfChrSize = bothSize, # chr. size data.frame
dfMarkPos = bothMarkPos, # mark position data.frame (inc. cen.)
dfMarkColor = markStyleDF, # mark style d.f.
orderChr = "original", # order of chr. as in d.f.
chrIdPatternRem = "_.*", # pattern to remove from chr. names
karHeight = 2, # karyotype height
karHeiSpace = 5, # height + separ. among karyot.
chrSpacing = .20, # separ. among chr.
chrColor = "dodgerblue",
distTextChr = .9 # distance text to chr.
, legendWidth = .8 # legend item width
, legendHeight = 3 # legend item height
, markLabelSpacer = 2 # legend spacer
, ruler = FALSE,
chrIndex = "",
morpho = "",
karIndex = FALSE
# ,colorBorderMark = "black"# color of border of marks
, lwd.chr = 1 # border width
, chrNameUp = TRUE # use col. chrNameUp
, classChrName = "Type" # change default title of inferior name
, classChrNameUp = "Chr." # change default title of upper name
, groupName = FALSE # don't show group names
, OTUfont = 3 # OTU name in italics
, leftNotes = notesdf # data.frame with notes
, leftNotesTextSize = 1.3 # font size of notes
, leftNotesPosX = 10.2 # horizontal pos. of formula
, leftNotesPosY = 0,
ylimBotMod = 1 # modify ylim bottom argument
, ylimTopMod = 0 # modify ylim top argument
, xlimLeftMod = 2 # modify left xlim
, xlimRightMod = 3 # modify right xlim
)
11.6 C. leiocarpa as Yi et al. (2018)
#
# create data.frame of chr.
#
cleiocarpaChr <- citrusSize(A = 1, C = 1, D = 10, F = 6, # Using Guerra nom.
OTU = "C. leiocarpa",
shortArm = 1.7
)
#
# add groups
#
cleiocarpaChr$group <- gsub("_.*", "", cleiocarpaChr$chrName)
#
# marks data.frame
#
# CMA
cleiocarpaMarks <- citrusMarkPos(cleiocarpaChr)
# marks with overlap with CMA
# add mark of 45S rDNA in A, short arm (p)
cleiocarpaMarks <- markOverCMA(cleiocarpaMarks, # d.f. of CMA bands
chrType = "A", # chr. of new mark
chrRegion = "p", # arm of new mark
markName = "45S", # name of mark
shrinkMark = TRUE
)
# add 45S in Ds
cleiocarpaMarks <- markOverCMA(cleiocarpaMarks, # d.f. including CMA bands
chrName = paste0("D_", 1:4),
chrRegion = "q",
markName = "45S",
shrinkMark = TRUE
)
# creating additional data.frames of marks (non-CMA overlap)
cleiocarpaMarks_D3 <- data.frame(chrName = c("D_3", "D_4"), # cr.
chrRegion = "q", # arm
markName = "5S",
markDistCen = 1.1, # dist. to centrom.
markSize = 0.2, # mark size
OTU = "C. leiocarpa")
#
# merge marks d.fs
#
cleiocarpaMarks <- dplyr::bind_rows(cleiocarpaMarks, # CMA marks and overlapped 45S
cleiocarpaMarks_D3, # 5S in D (no overlap)
)
#
# mark style data.frame
#
# current marks
unique(cleiocarpaMarks$markName)
# [1] "CMA" "45S" "5S"
markStyleDF <- makedfMarkColorMycolors(
unique(cleiocarpaMarks$markName), c("darkgoldenrod1", "chartreuse3", "red")
)
# modify styles
markStyleDF$style <- c("square", "dots", "dots")
#
# swap chromosome arms of Ds (CMA marks originally in long arm)
#
dflist <- swapChrRegionDfSizeAndMarks(cleiocarpaChr,
cleiocarpaMarks,
paste0("D_", 1:10)
)
cleiocarpaChr <- dflist$dfChrSize
cleiocarpaMarks <- dflist$dfMarkPos
#
# Left notes Up data.frame
#
notesdf <- data.frame(OTU = unique(cleiocarpaChr$OTU),
note = "italic('Citrus leiocarpa'),' Hort. ex Tan.' " # use with parseStr2lang
)
par(mar = rep(0, 4), oma = rep(0, 4))
plotIdiograms(dfChrSize = cleiocarpaChr, # chr. size data.frame
dfMarkPos = cleiocarpaMarks, # mark position data.frame
dfMarkColor = markStyleDF, # mark style d.f.
orderChr = "original", # preserve order of chr. of d.f.
chrId = "", # do not add chr. names
addOTUName = FALSE, # remove name of OTU
chrIdPatternRem = "_.*", # regex pattern for removal of names of chr.
chrSpacing = 0.2, # separ. among chr.
chrColor = "dodgerblue", # chr. color
chromatids = FALSE, # do not use separ. chromatids
dotsAsOval = TRUE # use oval shape instead of dots marks
, legendWidth = .8 # legend item width
, legendHeight = 3 # legend item height
, markLabelSpacer = 2 # legend spacer
, ruler = FALSE # no ruler
, chrIndex = "" # no chr. index
, morpho = "" # no morpho.
, karIndex = FALSE # no kar. ind.
, leftNotesUp = notesdf # data.frame with notes
, parseStr2lang = TRUE # use italics, see notesdf above
, leftNotesUpTextSize = 1.3 # font size of notes
, leftNotesUpPosX = 0 # pos. left notes x axis
, leftNotesUpPosY = 1 # pos. left notes y axis
, ylimBotMod = 0 # modify ylim bottom argument
, xlimRightMod = 4 # modify right xlim
)
11.7 Citrus limon origin
With data from da-Costa-Silva et al. (2015), Mendes et al. (2016) and Carvalho et al. (2005)
11.7.1 Citrus reticulata (Parental 1)
data.frame of chr. sizes
# c. reticulata ----X---- c. aurantium
# |
# c. limon
# c. reticulata
#
# chr. size - arms in pixels
#
{
citrusReticulata <- read.table(text = "
chrName shortArmSize longArmSize totalTrue
f 67 91 2.65
d 61 77 2.32
c 59 78 2.18
d 61 83 2.49
d 34 63 1.87
d 50 66 1.93
d 50 83 2.28
f 42 77 2.02
f 28 67 1.70", header = TRUE)
citrusReticulata$pseudototal <- citrusReticulata$shortArmSize + citrusReticulata$longArmSize
# pixel to micrometers
citrusReticulata$shortArmSize <- citrusReticulata$shortArmSize / (citrusReticulata$pseudototal / citrusReticulata$totalTrue)
citrusReticulata$longArmSize <- citrusReticulata$longArmSize / (citrusReticulata$pseudototal / citrusReticulata$totalTrue)
citrusReticulata$chrName <- toupper(citrusReticulata$chrName)
citrusReticulata$chrName <- make.uniqueIF(citrusReticulata$chrName)
citrusReticulata$OTU <- "C. reticulata 'Cravo'"
}
Sort chromosomes
# sort chr. by name
citrusReticulata <- citrusReticulata[order(citrusReticulata$chrName), ]
# sort Ds by size
Ds <- citrusReticulata[which(citrusReticulata$chrName %in% grep("D", citrusReticulata$chrName, value = TRUE)
), ]
citrusReticulata[which(citrusReticulata$chrName %in% grep("D", citrusReticulata$chrName, value = TRUE)
), ] <- Ds[order(Ds$shortArmSize + Ds$longArmSize), ]
# sort Fs by size
Fs <- citrusReticulata[which(citrusReticulata$chrName %in% grep("F", citrusReticulata$chrName, value = TRUE)
), ]
citrusReticulata[which(citrusReticulata$chrName %in% grep("F", citrusReticulata$chrName, value = TRUE)), ] <-
Fs[order(Fs$shortArmSize + Fs$longArmSize), ]
# add group column to show that each one is a pair
citrusReticulata$group <- 1:9
data.frame of bands
#
# c. reticulata bands
#
{
citrusReticulataMarkPosDF <- citrusMarkPos(citrusReticulata)
# remove CMA terminal from D
citrusReticulataMarkPosDF <- citrusReticulataMarkPosDF[-which(citrusReticulataMarkPosDF$chrName == "D_3" &
citrusReticulataMarkPosDF$markName == "CMA"
), ]
# add marks in short arm of D
Sr_D_3 <- citrusReticulata[which(citrusReticulata$chrName == "D_3"), ]$shortArmSize
# 45S
citrusReticulataMarkPosDF_D45S <- data.frame(chrName = "D_3",
chrRegion = "p",
markName = "45S",
markDistCen = Sr_D_3 - (.15 + .15 / 2),
markSize = 0.15,
OTU = unique(citrusReticulata$OTU)
)
# CMA
citrusReticulataMarkPosDF_DCMA <- data.frame(chrName = "D_3",
chrRegion = "p",
markName = "CMA",
markDistCen = Sr_D_3 - .3,
markSize = 0.3,
OTU = unique(citrusReticulata$OTU)
)
# add 45S rDNA mark in short arm of C
citrusReticulataMarkPosDF_C45S <- data.frame(chrName = "C",
chrRegion = "p",
markName = "45S",
markDistCen = 0,
markSize = 0.1,
OTU = unique(citrusReticulata$OTU)
)
# fuse marks
citrusReticulataMarkPosDF <- dplyr::bind_rows(citrusReticulataMarkPosDF,
citrusReticulataMarkPosDF_D45S,
citrusReticulataMarkPosDF_DCMA,
citrusReticulataMarkPosDF_C45S
)
# change band sizes
# D_1
citrusReticulataMarkPosDF[which(citrusReticulataMarkPosDF$chrName == "D_1"), ]$markSize <- .75
LAD_1 <- citrusReticulata[which(citrusReticulata$chrName == "D_1"), ]$longArmSize
citrusReticulataMarkPosDF[which(citrusReticulataMarkPosDF$chrName == "D_1"), ]$markDistCen <-
LAD_1 - .75
# C short arm
citrusReticulataMarkPosDF[which(citrusReticulataMarkPosDF$chrName == "C" &
citrusReticulataMarkPosDF$markName == "CMA" &
citrusReticulataMarkPosDF$chrRegion == "p"), ]$markSize <- .3
SAC <- citrusReticulata[which(citrusReticulata$chrName == "C"), ]$shortArmSize
citrusReticulataMarkPosDF[which(citrusReticulataMarkPosDF$chrName == "C" &
citrusReticulataMarkPosDF$markName == "CMA" &
citrusReticulataMarkPosDF$chrRegion == "p"
), ]$markDistCen <- SAC - .3
# C LONG ARM
citrusReticulataMarkPosDF[which(citrusReticulataMarkPosDF$chrName == "C" &
citrusReticulataMarkPosDF$markName == "CMA" &
citrusReticulataMarkPosDF$chrRegion == "q"), ]$markSize <- .4
LAC <- citrusReticulata[which(citrusReticulata$chrName == "C"), ]$longArmSize
citrusReticulataMarkPosDF[which(citrusReticulataMarkPosDF$chrName == "C" &
citrusReticulataMarkPosDF$markName == "CMA" &
citrusReticulataMarkPosDF$chrRegion == "q"
), ]$markDistCen <- LAC - .4
# D_2
citrusReticulataMarkPosDF[which(citrusReticulataMarkPosDF$chrName == "D_2"), ]$markSize <- .55
LAD_2 <- citrusReticulata[which(citrusReticulata$chrName == "D_2"), ]$longArmSize
citrusReticulataMarkPosDF[which(citrusReticulataMarkPosDF$chrName == "D_2"), ]$markDistCen <-
LAD_2 - .55
# D_4
citrusReticulataMarkPosDF[which(citrusReticulataMarkPosDF$chrName == "D_4"), ]$markSize <- .6
LAD_4 <- citrusReticulata[which(citrusReticulata$chrName == "D_4"), ]$longArmSize
citrusReticulataMarkPosDF[which(citrusReticulataMarkPosDF$chrName == "D_4"), ]$markDistCen <-
LAD_4 - .6
# D_5
citrusReticulataMarkPosDF[which(citrusReticulataMarkPosDF$chrName == "D_5"), ]$markSize <- .7
LAD_5 <- citrusReticulata[which(citrusReticulata$chrName == "D_5"), ]$longArmSize
citrusReticulataMarkPosDF[which(citrusReticulataMarkPosDF$chrName == "D_5"), ]$markDistCen <-
LAD_5 - .7
}11.7.2 C. aurantium ‘common’ (Parental 2)
data.frame of chr. sizes
# From Mendes et al. 2016
# 1a + 1b + 1C + 8D + 7F
{
#
# chr .sizes
#
citrusaurantium <- read.table(text = "
chrName shortArmSize longArmSize
f 1.43333333333333 2.06666666666667
f 1.36666666666667 1.83333333333333
d 1.3 1.66666666666667
d 1.13333333333333 1.46666666666667
d 1 1.6
a 1.3 2
d 1.36666666666667 1.8
d 1.06666666666667 1.63333333333333
d 0.733333333333333 1.36666666666667
f 0.833333333333333 1.36666666666667
d 1.13333333333333 1.33333333333333
c 1.16666666666667 1.66666666666667
d 1.06666666666667 1.8
b 1 1.83333333333333
f 0.966666666666667 1.6
f 0.8 1.36666666666667
f 0.633333333333333 1.43333333333333
f 0.733333333333333 1.3
", header = TRUE)
# modify chr. names
citrusaurantium$chrName <- toupper(citrusaurantium$chrName)
citrusaurantium$chrName <- make.uniqueIF(citrusaurantium$chrName)
# add column
citrusaurantium$OTU <- "C. aurantium 'common'"
}
Order pairs based in BAC markers (not shown here - different to
45S / 5S rDNA )
{
# confirmed pairs
customOrder <- c("A", "D_3", "C", "D_7")
customOrder <- c(customOrder, sort(setdiff(citrusaurantium$chrName, customOrder)))
# sort
citrusaurantium$chrName <- factor(citrusaurantium$chrName, levels = customOrder)
citrusaurantium <- citrusaurantium[order(citrusaurantium$chrName), ]
# sort Ds by size
Ds <- citrusaurantium[which(citrusaurantium$chrName %in% grep("D", citrusaurantium$chrName, value = TRUE) &
!citrusaurantium$chrName %in% c("D_3", "D_7")), ]
citrusaurantium[which(citrusaurantium$chrName %in% grep("D", citrusaurantium$chrName, value = TRUE) &
!citrusaurantium$chrName %in% c("D_3", "D_7")), ] <- Ds[order(Ds$shortArmSize + Ds$longArmSize), ]
# sort Fs by size
Fs <- citrusaurantium[which(citrusaurantium$chrName %in% grep("F", citrusaurantium$chrName, value = TRUE)
), ]
citrusaurantium[which(citrusaurantium$chrName %in% grep("F", citrusaurantium$chrName, value = TRUE)), ] <-
Fs[order(Fs$shortArmSize + Fs$longArmSize), ]
# pairs:
groups <- c(1, 1, 2, 2)
citrusaurantium$group <- c(groups, rep(NA, 18 - length(groups)))
# secondary name
citrusaurantium$chrNameUp <- 1:18
}
data.frame of bands
Option 1. Write from scratch:
{
citrusaurantiumMarkPosDF <- read.table(text = "
chrName chrRegion markName markDistCen markSize
A p CMA 0.73 0.570
A p CMA 0.00 0.350
A q CMA 1.23 0.770
B p CMA 0.00 0.350
B q CMA 0.86 0.970
C p CMA 0.74 0.430
C q CMA 1.07 0.600
D_1 q CMA 0.60 1.070
D_2 q CMA 0.84 0.630
D_3 q CMA 1.07 0.530
D_4 q CMA 1.07 0.730
D_5 q CMA 0.86 0.770
D_7 q CMA 0.46 0.870
D_8 q CMA 0.90 0.900
B p 45S 0.09 0.175
A p 45S 0.09 0.175
D_6 p 45S 0.58 0.100
D_6 p CMA 0.53 0.200
", header = TRUE)
citrusaurantiumMarkPosDF$OTU <- "C. aurantium 'common'"
}
# this is equivalent to the following section
Option 2. Use functions:
{
#
# CMA bands
#
citrusaurantiumMarkPosDF <- citrusMarkPos(citrusaurantium)
# add 45S in B
citrusaurantiumMarkPosDF <- markOverCMA(citrusaurantiumMarkPosDF,
chrType = "B",
chrRegion = "p",
markName = "45S")
# add 45S in A p prox
citrusaurantiumMarkPosDF <- markOverCMA(citrusaurantiumMarkPosDF,
chrType = "A",
chrRegion = "p",
markName = "45S")
# D_6
# change D (D_6) band from long to short
SA_D_6 <- citrusaurantium[which(citrusaurantium$chrName == "D_6"), ]$shortArmSize
# 45S in short
citrusaurantiumMarkPosDF_D45S <- data.frame(chrName = "D_6",
chrRegion = "p",
markName = "45S",
markDistCen = SA_D_6 - .15,
markSize = 0.1,
OTU = unique(citrusaurantium$OTU)
)
# CMA in short
citrusaurantiumMarkPosDF_DCMA <- data.frame(chrName = "D_6",
chrRegion = "p",
markName = "CMA",
markDistCen = SA_D_6 - .2,
markSize = 0.2,
OTU = unique(citrusaurantium$OTU)
)
# remove CMA terminal from D_6 long
citrusaurantiumMarkPosDF <- citrusaurantiumMarkPosDF[which(citrusaurantiumMarkPosDF$chrName != "D_6"), ]
# change mark sizes according to publication
# D_1 band
# change mark size
citrusaurantiumMarkPosDF[which(citrusaurantiumMarkPosDF$chrName == "D_1"), ]$markSize <- 1.07
# arm size
LAD_1 <- citrusaurantium[which(citrusaurantium$chrName == "D_1"), ]$longArmSize
# change mark dist. to cen.
citrusaurantiumMarkPosDF[which(citrusaurantiumMarkPosDF$chrName == "D_1"), ]$markDistCen <-
LAD_1 - 1.07
# D_2
citrusaurantiumMarkPosDF[which(citrusaurantiumMarkPosDF$chrName == "D_2"), ]$markSize <- 0.63
LAD_2 <- citrusaurantium[which(citrusaurantium$chrName == "D_2"), ]$longArmSize
citrusaurantiumMarkPosDF[which(citrusaurantiumMarkPosDF$chrName == "D_2"), ]$markDistCen <-
LAD_2 - .63
# D_3
citrusaurantiumMarkPosDF[which(citrusaurantiumMarkPosDF$chrName == "D_3"), ]$markSize <- 0.53
LAD_3 <- citrusaurantium[which(citrusaurantium$chrName == "D_3"), ]$longArmSize
citrusaurantiumMarkPosDF[which(citrusaurantiumMarkPosDF$chrName == "D_3"), ]$markDistCen <-
LAD_3 - .53
# A p ter
citrusaurantiumMarkPosDF[which(citrusaurantiumMarkPosDF$chrName == "A" &
citrusaurantiumMarkPosDF$markDistCen == 1.05), ]$markSize <- 0.57
SAA <- citrusaurantium[which(citrusaurantium$chrName == "A"), ]$shortArmSize
citrusaurantiumMarkPosDF[which(citrusaurantiumMarkPosDF$chrName == "A" &
citrusaurantiumMarkPosDF$markDistCen == 1.05), ]$markDistCen <-
SAA - .57
# A q
citrusaurantiumMarkPosDF[which(citrusaurantiumMarkPosDF$chrName == "A" &
citrusaurantiumMarkPosDF$chrRegion == "q"), ]$markSize <- 0.77
LAA <- citrusaurantium[which(citrusaurantium$chrName == "A"), ]$longArmSize
citrusaurantiumMarkPosDF[which(citrusaurantiumMarkPosDF$chrName == "A" &
citrusaurantiumMarkPosDF$chrRegion == "q"), ]$markDistCen <-
LAA - .77
# D_4
citrusaurantiumMarkPosDF[which(citrusaurantiumMarkPosDF$chrName == "D_4"), ]$markSize <- 0.73
LAD_4 <- citrusaurantium[which(citrusaurantium$chrName == "D_4"), ]$longArmSize
citrusaurantiumMarkPosDF[which(citrusaurantiumMarkPosDF$chrName == "D_4"), ]$markDistCen <-
LAD_4 - .73
# D_5
citrusaurantiumMarkPosDF[which(citrusaurantiumMarkPosDF$chrName == "D_5"), ]$markSize <- 0.77
LAD_5 <- citrusaurantium[which(citrusaurantium$chrName == "D_5"), ]$longArmSize
citrusaurantiumMarkPosDF[which(citrusaurantiumMarkPosDF$chrName == "D_5"), ]$markDistCen <-
LAD_5 - .77
# D_7
citrusaurantiumMarkPosDF[which(citrusaurantiumMarkPosDF$chrName == "D_7"), ]$markSize <- 0.87
LAD_7 <- citrusaurantium[which(citrusaurantium$chrName == "D_7"), ]$longArmSize
citrusaurantiumMarkPosDF[which(citrusaurantiumMarkPosDF$chrName == "D_7"), ]$markDistCen <-
LAD_7 - .87
# C p
citrusaurantiumMarkPosDF[which(citrusaurantiumMarkPosDF$chrName == "C" &
citrusaurantiumMarkPosDF$chrRegion == "p"), ]$markSize <- .43
SAC <- citrusaurantium[which(citrusaurantium$chrName == "C"), ]$shortArmSize
citrusaurantiumMarkPosDF[which(citrusaurantiumMarkPosDF$chrName == "C" &
citrusaurantiumMarkPosDF$chrRegion == "p"), ]$markDistCen <-
SAC - .43
# C q
citrusaurantiumMarkPosDF[which(citrusaurantiumMarkPosDF$chrName == "C" &
citrusaurantiumMarkPosDF$chrRegion == "q"), ]$markSize <- .6
LAC <- citrusaurantium[which(citrusaurantium$chrName == "C"), ]$longArmSize
citrusaurantiumMarkPosDF[which(citrusaurantiumMarkPosDF$chrName == "C" &
citrusaurantiumMarkPosDF$chrRegion == "q"), ]$markDistCen <-
LAC - .6
# D_8
citrusaurantiumMarkPosDF[which(citrusaurantiumMarkPosDF$chrName == "D_8"), ]$markSize <- 0.9
LAD_8 <- citrusaurantium[which(citrusaurantium$chrName == "D_8"), ]$longArmSize
citrusaurantiumMarkPosDF[which(citrusaurantiumMarkPosDF$chrName == "D_8"), ]$markDistCen <-
LAD_8 - .9
# B q
citrusaurantiumMarkPosDF[which(citrusaurantiumMarkPosDF$chrName == "B" &
citrusaurantiumMarkPosDF$chrRegion == "q"), ]$markSize <- .97
LAB <- citrusaurantium[which(citrusaurantium$chrName == "B"), ]$longArmSize
citrusaurantiumMarkPosDF[which(citrusaurantiumMarkPosDF$chrName == "B" &
citrusaurantiumMarkPosDF$chrRegion == "q"), ]$markDistCen <-
LAB - .97
# fuse marks
citrusaurantiumMarkPosDF <- dplyr::bind_rows(citrusaurantiumMarkPosDF,
citrusaurantiumMarkPosDF_D45S,
citrusaurantiumMarkPosDF_DCMA
)
}11.7.3 C. limon
# from: Carvalho 2005
# C. limon - 1B(45Sprox) + 1C + 8D + 1D(45S) + 5F + 1FL0 + 1FL+
{
# data.frame of chr. sizes
citruslimon <- citrusSize(B = 1, C = 1, D = 9, F = 5, FL0 = 1, FL = 1,
OTU = "C. limon")
citruslimon
# modify sizes
citruslimon$shortArmSize[3] <- 1.1
citruslimon$longArmSize[3] <- 1.5
citruslimon$shortArmSize[4:5] <- 1.15
citruslimon$longArmSize[4:5] <- 1.6
citruslimon$shortArmSize[6:7] <- 1.1
citruslimon$longArmSize[6:7] <- 1.6
citruslimon$shortArmSize[8:9] <- 1.15
citruslimon$longArmSize[8:9] <- 1.65
citruslimon$shortArmSize[2] <- 1
citruslimon$longArmSize[2] <- 1.6
citruslimon$shortArmSize[12] <- 1
citruslimon$longArmSize[12] <- 1.5
citruslimon$shortArmSize[10:11] <- .95
citruslimon$longArmSize[10:11] <- 1.4
citruslimon$shortArmSize[13:14] <- 1
citruslimon$longArmSize[13:14] <- 1.5
citruslimon$shortArmSize[15:16] <- .95
citruslimon$longArmSize[15:16] <- 1.3
# sort Ds by size
Ds <- citruslimon[which(citruslimon$chrName %in% grep("D", citruslimon$chrName, value = TRUE)
), ]
citruslimon[which(citruslimon$chrName %in% grep("D", citruslimon$chrName, value = TRUE)
), ] <- Ds[order(Ds$shortArmSize + Ds$longArmSize), ]
# sort Fs by size
Fs <- citruslimon[which(citruslimon$chrName %in% grep("F", citruslimon$chrName, value = TRUE)
), ]
citruslimon[which(citruslimon$chrName %in% grep("F", citruslimon$chrName, value = TRUE)), ] <-
Fs[order(Fs$shortArmSize + Fs$longArmSize), ]
# secondary chr. name
citruslimon$chrNameUp <- 1:18
#
# data.frame of CMA band pos.
#
citruslimonMarkPosDF <- citrusMarkPos(citruslimon)
head(citruslimonMarkPosDF)
# marks with overlap with CMA
# 45S in B, short arm
citruslimonMarkPosDF <- markOverCMA(citruslimonMarkPosDF,
chrType = "B",
chrRegion = "p",
markName = "45S")
# 45S in D (D_1), long arm
citruslimonMarkPosDF <- markOverCMA(citruslimonMarkPosDF,
chrName = "D_1",
chrRegion = "q",
markName = "45S")
# add mark from scratch (no overlap with CMA)
}11.7.4 Merge data.frames from all OTUs
#
# data.frames of size - merge
#
threeSize <- dplyr::bind_rows(citrusReticulata, citruslimon, citrusaurantium)
#
# data.frames of band pos. merge
#
threeMarkPos <- dplyr::bind_rows(citruslimonMarkPosDF, citrusaurantiumMarkPosDF, citrusReticulataMarkPosDF)
#
# leftNotes with formulas
#
# formulas
limon <- "1B + 1C + 9D + 5F + 1FL0 + 1FL+ [1B/45S, 1D/45S]"
aurantium <- "1A + 1B + 1C + 8D + 7F [1A/45S, 1B/45S, 1D/45S]"
reticulata <- "2C + 10D + 6F [2C/45S, 2D/45S]"
leftNotesdf <- data.frame(OTU = unique(threeSize$OTU), note = c(reticulata, limon, aurantium))
# authors
notesdf <- data.frame(OTU = unique(threeSize$OTU),
note = c("da-Costa-Silva et al. (2015)", "Carvalho et al. (2005)", "Mendes et al. (in prep.)")
)
# marks' style data.frame
markStyleDF <- makedfMarkColorMycolors(
unique(citrusReticulataMarkPosDF$markName), c("darkgoldenrod1", "chartreuse3")
)
markStyleDF$style <- c("square", "dots")11.7.5 Plot
{
svg("climon.svg", width = 12, height = 10)
par(mar = rep(0, 4), oma = rep(0, 4))
plotIdiograms(dfChrSize = threeSize, # chr. size data.frame
dfMarkPos = threeMarkPos, # mark position data.frame (inc. cen.)
dfMarkColor = markStyleDF, # mark style d.f.
orderChr = "original", # order of chr. as in d.f.
chrIdPatternRem = "_.*", # pattern to remove from chr. names
karHeight = 2, # karyotype height
karHeiSpace = 6, # height + separ. among karyot.
chrSpacing = .20, # separ. among chr.
chrColor = "dodgerblue",
distTextChr = .9 # distance text to chr.
, legendWidth = .8 # legend item width
, legendHeight = 3 # legend item height
, markLabelSpacer = 2 # legend spacer
, ruler = FALSE # do not use ruler
, chrIndex = "" # do not print chr. index
, morpho = "" # do not print morphology
, karIndex = FALSE # do not print kar. index
# ,colorBorderMark = "black"# color of border of marks
, lwd.chr = 1 # border width
, OTUfont = 3 # OTU name in italics
, leftNotes = leftNotesdf # data.frame with notes (formula)
, leftNotesTextSize = 1.3 # font size of notes
, leftNotesPosX = 0 # horizontal pos. of formula
, leftNotesPosY = 1 # vertical pos. of formula
, notes = notesdf # authors
, classGroupName = "Pair" # name for groups
, chrNameUp = TRUE # use col. chrNameUp
, classChrName = "Type" # change default title of inferior name
, classChrNameUp = "Chr." # change default title of upper name
, ylimBotMod = 1 # modify ylim bottom argument
, ylimTopMod = 0 # modify ylim top argument
, xlimLeftMod = 2 # modify left xlim
, xlimRightMod = 5 # modify right xlim
, threshold = 40 # fixes shrinking of scale, needed because some chr. greater than 3.5 um
, moveKarHor = "C. limon" # kar. to move to right
, mkhValue = 5 # move cariótipo para direita
, anchor = TRUE # parental structure
, moveAnchorV = 1 # move anchor
, anchorVsizeF = .35 # anchor vertical size factor modifier
, karSepar = FALSE # modif. separ de karyo.
)
dev.off() # close svg
}For a plot of GISH of Citrus, visit the GISH chapter