Part I: Fasta File Import
myFA <- read.FASTA("MT103168.fasta") # This line of code reads the fasta file into R and stores it as a list of 1 sequence in binary format.
head(myFA) # This line of code returns the first six elements of the data list.
## 1 DNA sequence in binary format stored in a list.
##
## Sequence length: 1560
##
## Label:
## MT103168.1 Bifidobacterium longum strain BB536 cell division...
##
## Base composition:
## a c g t
## 0.156 0.319 0.289 0.236
## (Total: 1.56 kb)
str(myFA) # This line of code returns the structure of the data in a compact format.
## List of 1
## $ MT103168.1 Bifidobacterium longum strain BB536 cell division protein FtsW (rodA) gene, complete cds: raw [1:1560] 88 18 48 88 ...
## - attr(*, "class")= chr "DNAbin"
Part II: FASTQ File Import
myFQ <- read.fastq("ERR1072710.fastq") # This line of code reads the fastq file into R and stores it as a list of 3 sequences in binary format.
head(myFQ) # This line of code returns the first six elements of the data list.
## 3 DNA sequences in binary format stored in a list.
##
## Mean sequence length: 183.667
## Shortest sequence: 146
## Longest sequence: 259
##
## Labels:
## ERR1072710.1 10317.000001315_0 length=151
## ERR1072710.2 10317.000001315_1 length=116
## ERR1072710.4 10317.000001315_3 length=151
##
## Base composition:
## a c g t
## 0.318 0.208 0.254 0.219
## (Total: 551 bases)
str(myFQ) # This line of code returns the structure of the data in a compact format.
## List of 3
## $ ERR1072710.1 10317.000001315_0 length=151: raw [1:146] 18 18 88 88 ...
## $ ERR1072710.2 10317.000001315_1 length=116: raw [1:259] 18 28 18 28 ...
## $ ERR1072710.4 10317.000001315_3 length=151: raw [1:146] 28 28 88 28 ...
## - attr(*, "class")= chr "DNAbin"
## - attr(*, "QUAL")=List of 7
## ..$ ERR1072710.1 10317.000001315_0 length=151: num [1:11] 32 38 51 34 32 34 32 34 32 38 ...
## ..$ ERR1072710.2 10317.000001315_1 length=116: num [1:11] 30 30 30 30 30 30 30 30 30 30 ...
## ..$ ERR1072710.4 10317.000001315_3 length=151: num [1:42] 10 36 49 49 16 15 22 17 22 16 ...
## ..$ NA : num [1:70] 51 32 34 38 38 32 38 38 38 51 ...
## ..$ NA : num [1:67] 30 30 30 30 30 30 30 30 30 30 ...
## ..$ NA : num [1:11] 32 51 51 32 38 32 38 34 34 51 ...
## ..$ NA : num [1:11] 30 30 30 30 30 30 30 30 30 30 ...
Part III: VCF Imports
myVCF<- read.table("TwoVariants.vcf") # This line of code reads in the vcf file and stores it as a dataframe.
myLINES<- read.csv("TwoVariants.vcf", sep="\n") # This line of code reads in the vcf file and stores it in csv format.
colnames(myVCF)<-c('CHROM','tPOS','tID','tREF','tALT','tQUAL','tFILTER','tINFO','tFORMAT','t__NONE__') # This line of code renames the columns from the myVCF dataframe with the column headers from the myLines csv.
head(myVCF) # This line of code returns the first six elements of the dataframes.
## CHROM tPOS tID tREF tALT tQUAL tFILTER tINFO
## 1 NZ_BCYL01000006.1 29 . A G . . AC=84;AF=1.0;SB=0.0
## 2 NZ_BCYL01000006.1 145 . A G . . AC=114;AF=1.0;SB=0.0
## tFORMAT t__NONE__
## 1 GT:AC:AF:SB:NC 1:84:1.0:0.0:+G=37,-G=47,
## 2 GT:AC:AF:SB:NC 1:114:1.0:0.0:+G=42,-G=72,
str(myVCF) # This line of code returns the structure of the data in a compact format.
## 'data.frame': 2 obs. of 10 variables:
## $ CHROM : chr "NZ_BCYL01000006.1" "NZ_BCYL01000006.1"
## $ tPOS : int 29 145
## $ tID : chr "." "."
## $ tREF : chr "A" "A"
## $ tALT : chr "G" "G"
## $ tQUAL : chr "." "."
## $ tFILTER : chr "." "."
## $ tINFO : chr "AC=84;AF=1.0;SB=0.0" "AC=114;AF=1.0;SB=0.0"
## $ tFORMAT : chr "GT:AC:AF:SB:NC" "GT:AC:AF:SB:NC"
## $ t__NONE__: chr "1:84:1.0:0.0:+G=37,-G=47," "1:114:1.0:0.0:+G=42,-G=72,"