Demo script for converting a data frame of nucleotide column to phydat format

df2phydat.r

rm(list = ls())
# Le Viet Thanh
# May 31st 2017
# Demo script for converting a data frame of nucleotide column to phydat format
# Asked by Dung Nguyen Chi

library(seqRFLP)
library(readr)
library(dplyr)

# source("https://bioconductor.org/biocLite.R")
# biocLite("DECIPHER")

library(DECIPHER)
library(phangorn)

seq_file <- read_csv("DNA.csv")

#Remove N/A seq
clean_seq <- seq_file %>%
  dplyr::filter(!is.na(seq)) %>%
  select(BC, seq) %>%
  as.data.frame()
# Covert from data frame to fasta format, and write it out to a fasta file
dataframe2fas(clean_seq, file = "dna.fasta")

# Read back using DECIPHER package for aligment
seq <- readDNAStringSet("dna.fasta", "fasta")
# Performing alignment
aligned <- AlignSeqs(seq)
# Write out the aligned seq

writeXStringSet(aligned,"dna_aligned.fasta")

# Read in phangorn
phydat <- read.phyDat("dna_aligned.fasta", "DNA", format = "fasta")