Seqinr

seqinr

Biological sequences retrieval and analysis.

Reading Sequences

library(seqinr)

# Read FASTA
seqs <- read.fasta("sequences.fasta")

# Get sequence
seq1 <- seqs[[1]]
getSequence(seq1)

# Get annotation
getAnnot(seq1)
getName(seq1)

Writing Sequences

# Write FASTA
write.fasta(sequences, names, file = "output.fasta")

# Multiple sequences
write.fasta(
  sequences = list(seq1, seq2),
  names = c("seq1", "seq2"),
  file.out = "output.fasta"
)

Sequence Properties

# GC content
GC(seq)

# Sequence length
length(seq)

# Count nucleotides
count(seq, wordsize = 1)

# Count codons
count(seq, wordsize = 3)

Codon Usage

# Codon usage table
uco(seq)

# Codon adaptation index
cai(seq, w = codon_weights)

# Effective number of codons
eff.nc(seq)

Translation

# Translate DNA to protein
translate(seq)

# With specific genetic code
translate(seq, numcode = 2)  # Vertebrate mitochondrial

Sequence Manipulation

# Reverse complement
comp(seq)
rev(comp(seq))

# Subsequence
seq[10:50]

# Convert to string
c2s(seq)

# Convert string to vector
s2c("ATCGATCG")

Dotplot

# Sequence comparison
dotPlot(seq1, seq2)

# With window
dotPlot(seq1, seq2, wsize = 10, wstep = 1)

Database Access

# Query GenBank
choosebank("genbank")
query <- query("myquery", "SP=Homo sapiens AND K=insulin")
seqs <- getSequence(query)
closebank()

Amino Acid Properties

# Amino acid composition
AAstat(protein_seq)

# Molecular weight
pmw(protein_seq)

# Isoelectric point
computePI(protein_seq)

Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

• Author: LeoLin990405
• Source: LeoLin990405/r-analytics-skill
• License: MIT

Install and usage instructions live in the source repository linked above.