Plot a nucleotide chain in R - r

Question

I am interested in plotting this sample figure in R. Sample figure was generated in Illustrator.
Essentially, my data is structured as such:
> dput(data)
structure(list(FirstPos = structure(c(1L, 1L, 1L, 2L, 2L, 2L), .Label = c("pos1",
"pos2"), class = "factor"), SecondPos = structure(c(1L, 1L, 1L,
2L, 2L, 2L), .Label = c("pos2", "pos3"), class = "factor"), FirstPosseq = structure(c(1L,
1L, 1L, 2L, 3L, 3L), .Label = c("A", "C", "T"), class = "factor"),
SecondPosseq = structure(c(2L, 4L, 1L, 1L, 3L, 4L), .Label = c("A",
"C", "G", "T"), class = "factor"), Count = c(10L, 100L, 1L,
100L, 100L, 100L)), .Names = c("FirstPos", "SecondPos", "FirstPosseq",
"SecondPosseq", "Count"), class = "data.frame", row.names = c(NA,
-6L))
This is a list of positions (original position and partner position). For each row, the "count" column signifies how likely the 2 nucleotides co-occur. I want a way to display that probability and the order (on the x-axis). In the example, I tried varying the line thickness based on the 'Count'.
Looking through the ggplot2 library, I couldn't find figures like this and was hoping to get your advice on potential packages/ways I could use.
Thank you!

Answer 1

One possible solution is to use the igraph package. Below is a basic example of how to get started with your data set.
# Assign your data to variable 'dat'.
dat = structure(list(FirstPos = structure(c(1L, 1L, 1L, 2L, 2L, 2L),
.Label = c("pos1", "pos2"), class = "factor"),
SecondPos = structure(c(1L, 1L, 1L, 2L, 2L, 2L),
.Label = c("pos2", "pos3"), class = "factor"),
FirstPosseq = structure(c(1L, 1L, 1L, 2L, 3L, 3L),
.Label = c("A", "C", "T"), class = "factor"),
SecondPosseq = structure(c(2L, 4L, 1L, 1L, 3L, 4L),
.Label = c("A", "C", "G", "T"), class = "factor"),
Count = c(10L, 100L, 1L, 100L, 100L, 100L)),
.Names = c("FirstPos", "SecondPos", "FirstPosseq",
"SecondPosseq", "Count"), class = "data.frame",
row.names = c(NA, -6L))
library(igraph)
# Create unique names/ids for each vertex in the graph.
dat$node1 = paste(dat$FirstPos, dat$FirstPosseq, sep="_")
dat$node2 = paste(dat$SecondPos, dat$SecondPosseq, sep="_")
# Use last two column of data as an edge list matrix, create graph.
g = graph_from_edgelist(as.matrix(dat[, c(6, 7)]))
# Add edge weights to graph.
E(g)$weight = dat$Count
# Plot using 'layout_as_tree' to control layout.
plot(g, layout=layout_as_tree(g, root=1), edge.width=log10(E(g)$weight + 1) * 5,
vertex.size=30, vertex.color="white", edge.color="black",
edge.arrow.mode=0L, vertex.label.color="black")