roblanf

# Load necessary library
library(dplyr)
library(lexicon)
library(visNetwork)

# Step 1: List most common three-letter English words

data(sw_fry_1000)
three_letter_words <- sw_fry_1000[nchar(sw_fry_1000) == 3]

roblanf

Commit Message Guidelines

Short (72 chars or less) summary

More detailed explanatory text. Wrap it to 72 characters. The blank
line separating the summary from the body is critical (unless you omit
the body entirely).

Write your commit message in the imperative: "Fix bug" and not "Fixed
bug" or "Fixes bug." This convention matches up with commit messages

roblanf

``` r
library(ape)

# make 1K trees to ensure we get some that seem odd...
trees = lapply(rep(4, 1000), rtree, rooted = FALSE)

# test monophyly of all six possible pairs
m1 = unlist(lapply(trees, is.monophyletic, tips = c("t1", "t2")))
m2 = unlist(lapply(trees, is.monophyletic, tips = c("t1", "t3")))
m3 = unlist(lapply(trees, is.monophyletic, tips = c("t1", "t4")))

roblanf

 ID  gCF gDF1 gDF2 gN   sCF  sDF1  sDF2     sN bootstrap branchlength
327 1.15 3.45    0 87 37.34 29.98 32.68 350.19       100   0.00304084

     ID   gCF  gDF1  gDF2 gN   sCF  sDF1  sDF2     sN bootstrap branchlength       gEF_p        sEF_p
14  249 78.57  5.36  5.36 56 56.14 17.86 26.00 383.86       100   0.02134550 1.000000000 1.605600e-02
33  268 62.07  8.62 13.79 58 39.02 27.36 33.62 624.87       100   0.02370450 0.405380556 4.506223e-02
34  269 87.50  0.00  0.00 56 69.10 13.40 17.50 771.13       100   0.10990200 1.000000000 4.051930e-02
36  271 67.35  0.00  8.16 49 46.61 25.97 27.42 426.92       100   0.02632530 0.045500264 6.818018e-01
39  274 34.33 17.91 17.91 67 39.51 23.62 36.87 258.95       100   0.00694057 1.000000000 6.116524e-03

roblanf

library(viridis)
library(ggplot2)
library(dplyr)
library(ggrepel)
library(GGally)
library(entropy)

# read the data
d = read.delim("concord.cf.stat", header = T, comment.char=‘#')
               

roblanf

# infer the concatentated tree with 1000 ultrafast bootstraps and an edge-linked fully-partitioned model (-p is the same as -spp from version 1.7 onwards) 
iqtree -s alignment.nex -p alignment.nex --prefix concat -bb 1000 -nt AUTO

# infer the 88 single-locus trees
iqtree -s alignment.nex -S alignment.nex --prefix loci -nt 50

# calculate concordance factors
iqtree -t concat.treefile --gcf loci.treefile -s alignment.nex --scf 100 --prefix concord

roblanf

library(viridis)
library(ggplot2)
library(dplyr)
library(ggrepel)
library(GGally)
library(entropy)

# read the data
d = read.delim("concord.cf.stat", header = T, skip = 15)

roblanf

#NEXUS
begin DATA;
	dimensions ntax=235 nchar=137324;
	format datatype=nucleotide missing=? gap=-;
	matrix

roblanf

echo "copying source pics"
mkdir source_pics
cp ~/pikrellcam/media/timelapse/* source_pics
cd source_pics

echo "renaming"
mkdir renamed
counter=1
ls -1tr *.jpg | while read filename; do cp $filename renamed/$(printf %05d $counter)_$filename; ((cou\
nter++)); done

roblanf

# build the map for R9.5 flowcell, as a long-form dataframe that translates
# channels into rows and columns on the flowcell. Good for plotting in R.
p1 = data.frame(channel=33:64, row=rep(1:4, each=8), col=rep(1:8, 4))
p2 = data.frame(channel=481:512, row=rep(5:8, each=8), col=rep(1:8, 4))
p3 = data.frame(channel=417:448, row=rep(9:12, each=8), col=rep(1:8, 4))
p4 = data.frame(channel=353:384, row=rep(13:16, each=8), col=rep(1:8, 4))
p5 = data.frame(channel=289:320, row=rep(17:20, each=8), col=rep(1:8, 4))
p6 = data.frame(channel=225:256, row=rep(21:24, each=8), col=rep(1:8, 4))
p7 = data.frame(channel=161:192, row=rep(25:28, each=8), col=rep(1:8, 4))
p8 = data.frame(channel=97:128, row=rep(29:32, each=8), col=rep(1:8, 4))