DomBennett

library(phylotaR)
data("yeasts")
# not all info is stored on the seq object
str(yeasts@sqs@sqs[[1]])
# but the accession can be used to download extra info
accssn <- yeasts@sqs@sqs[[1]]@id
library(rentrez)
smmry_obj <- entrez_summary(db = 'nucleotide', id = accssn)
str(smmry_obj)
# e.g. getting country

DomBennett

# Libs ----
# devtools::install_github('ropensci/phylotaR', ref = 'multiple_ids')
library(phylotaR)
library(taxize)

# Txids ----
# look-up random selection of 60 aedes and culex spp
# 7158 -- Aedes genus
aedes_spp <- downstream(x = '7158', db = 'ncbi', downto = 'species')
# 7174 -- Culex genus

DomBennett

# http://genomicsclass.github.io/book/pages/dplyr_tutorial.html
# Libs ----
library(dplyr)

# Data ----
url <- "https://raw.githubusercontent.com/genomicsclass/dagdata/master/inst/extdata/msleep_ggplot2.csv"
filename <- "msleep_ggplot2.csv"
if (!file.exists(filename)) downloader::download(url,filename)
# forget head! Just make use it is a "tibble"
msleep <- as_tibble(read.csv("msleep_ggplot2.csv"))

DomBennett

# Installed
already_installed <- installed.packages()

# CRAN packages
cran_deps <- c("ape", "reshape2", "phangorn", "stringi", "stringr")
cran_deps <- cran_deps[!cran_deps %in% already_installed]
for (dep in cran_deps) {
  install.packages(dep)
}

DomBennett

# LIBS
library(rentrez)

# FUNCTIONS
connect_safely <- function(fnctn, args, wt_tms) {
  res <- NULL
  for (wt_tm in wt_tms) {
    query <- try(R.utils::withTimeout(do.call(fnctn, args),
                                      timeout = 3600),
                 silent = TRUE)

DomBennett

# LIB
library(ape)

# DATA
# tree string produced by `RAxML -J ` arg
trstr <- "(A,B,(C,((D,((E,F):1.0[80],((G,H):1.0[100],(I,J):1.0[100]):1.0[67]):1.0[58]):1.0[98],(K,(L,(M,N):1.0[89]):1.0[91]):1.0[100]):1.0[97]):1.0[97]);"

# FAIL
tree <- read.tree(text=trstr)
# node.label = NULL

DomBennett

# Take sequences from fasta file and write as separate files

# FUNCTION
readSqs <- function(fl) {
 all_data <- readLines(fl)
 sqs <- list()
 for(i in seq_along(all_data)) {
   bit <- all_data[[i]]
   if(grepl(pattern='^>', x=bit)) {
     nm <- sub(pattern='^>', '', x=bit)

DomBennett

# LIB
library(treeman)
library(doMC)
library(foreach)

# FUNCTION
randTreeList <- function(n) {
  res <- vector(mode='list', length=n)
  for(i in 1:n) {
    res[[i]] <- randTree(20, wndmtrx=TRUE)

DomBennett

getGroups <- function(tree, get_edges=TRUE) {
  .fillInRes <- function(i) {
    res <- vector('list', length=2)
    names(res) <- c('g1', 'g2')
    res[['g1']] <- which(edge.tips[i, ] == 1)
    res[['g2']] <- which(edge.tips[i, ] == 0)
    res
  }
  .addEdges <- function(i) {
    res[[i]][['edglngth']] <<- edglngths[[i]]

DomBennett

# EXAMPLE TEXT DISTANCES

# FUNCTIONS
justText <- function(txt) {
  # converts text to its readable form by removing punctuation and numbers
  gsub("[^a-zA-Z ]", "", txt)
}

calcStrDst <- function(txts) {
  # calculate the distance between vector of texts