17 `Biostrings`包

DNAstringSet、RNAStringSet、AAStringSet、BStringSet
Code
# BiocManager::install("Biostrings") 
library(Biostrings) 
conflicts_prefer(Biostrings::setdiff)
dna_strings <- DNAStringSet(c("ATCG", "GCAT", "ATCGAT", "GCTA")) 
dna_strings
#> DNAStringSet object of length 4:
#>     width seq
#> [1]     4 ATCG
#> [2]     4 GCAT
#> [3]     6 ATCGAT
#> [4]     4 GCTA

rna_strings <- RNAStringSet(c("AUCG", "GCAU", "AUCGAU", "GCUA"))
rna_strings
#> RNAStringSet object of length 4:
#>     width seq
#> [1]     4 AUCG
#> [2]     4 GCAU
#> [3]     6 AUCGAU
#> [4]     4 GCUA

protein_strings <- AAStringSet(c("MATH", "GCAU", "MATHMATH", "CUMA"))
protein_strings
#> AAStringSet object of length 4:
#>     width seq
#> [1]     4 MATH
#> [2]     4 GCAU
#> [3]     8 MATHMATH
#> [4]     4 CUMA

# 二进制字符串存储 如seq_id、quality
binary_strings <- BStringSet(c("ERCC010101", "CRCC110011", "101010", "111000"))
binary_strings
#> BStringSet object of length 4:
#>     width seq
#> [1]    10 ERCC010101
#> [2]    10 CRCC110011
#> [3]     6 101010
#> [4]     6 111000