codonUsage {coRdon} | R Documentation |
Calculate values of the codon usage (CU) measure
for every sequence in the given codonTable
object.
The following methods are implemented:
MILC
, Measure Independent of Length and Composition
Supek & Vlahovicek (2005),
B
, codon usage bias (B)
Karlin et al. (2001),
ENC
, effective number of codons (ENC)
Wright (1990).
ENCprime
, effective number of codons prime (ENC')
Novembre (2002),
MCB
, maximum-likelihood codon bias (MCB)
Urrutia and Hurst (2001),
SCUO
, synonymous codon usage eorderliness (SCUO)
Wan et al. (2004).
MILC(cTobject, subsets = list(), self = TRUE, ribosomal = FALSE, id_or_name2 = "1", alt.init = TRUE, stop.rm = FALSE, filtering = "none", len.threshold = 80) ## S4 method for signature 'codonTable' MILC(cTobject, subsets = list(), self = TRUE, ribosomal = FALSE, id_or_name2 = "1", alt.init = TRUE, stop.rm = FALSE, filtering = "none", len.threshold = 80) B(cTobject, subsets = list(), self = TRUE, ribosomal = FALSE, id_or_name2 = "1", alt.init = TRUE, stop.rm = FALSE, filtering = "none", len.threshold = 80) ## S4 method for signature 'codonTable' B(cTobject, subsets = list(), self = TRUE, ribosomal = FALSE, id_or_name2 = "1", alt.init = TRUE, stop.rm = FALSE, filtering = "none", len.threshold = 80) MCB(cTobject, subsets = list(), self = TRUE, ribosomal = FALSE, id_or_name2 = "1", alt.init = TRUE, stop.rm = FALSE, filtering = "none", len.threshold = 80) ## S4 method for signature 'codonTable' MCB(cTobject, subsets = list(), self = TRUE, ribosomal = FALSE, id_or_name2 = "1", alt.init = TRUE, stop.rm = FALSE, filtering = "none", len.threshold = 80) ENCprime(cTobject, subsets = list(), self = TRUE, ribosomal = FALSE, id_or_name2 = "1", alt.init = TRUE, stop.rm = TRUE, filtering = "none", len.threshold = 80) ## S4 method for signature 'codonTable' ENCprime(cTobject, subsets = list(), self = TRUE, ribosomal = FALSE, id_or_name2 = "1", alt.init = TRUE, stop.rm = TRUE, filtering = "none", len.threshold = 80) ENC(cTobject, id_or_name2 = "1", alt.init = TRUE, stop.rm = TRUE, filtering = "none", len.threshold = 80) ## S4 method for signature 'codonTable' ENC(cTobject, id_or_name2 = "1", alt.init = TRUE, stop.rm = TRUE, filtering = "none", len.threshold = 80) SCUO(cTobject, id_or_name2 = "1", alt.init = TRUE, stop.rm = FALSE, filtering = "none", len.threshold = 80) ## S4 method for signature 'codonTable' SCUO(cTobject, id_or_name2 = "1", alt.init = TRUE, stop.rm = FALSE, filtering = "none", len.threshold = 80)
cTobject |
A |
subsets |
A (named) list of logical vectors, the length of each equal
to |
self |
Logical, if |
ribosomal |
Logical, if |
id_or_name2 |
A single string that uniquely identifies the genetic code to extract.
Should be one of the values in the |
alt.init |
logical, whether to use alternative initiation codons.
Default is |
stop.rm |
Logical, whether to remove stop codons. Default is
|
filtering |
Character vector, one of |
len.threshold |
Optional numeric, specifying sequence length, in codons, used for filtering. |
A matrix or a numeric vector with CU measure values.
For MILC
, B
, ENCprime
, the matrix has a column
with values for every specified subset
(subsets
, self
, ribosomal
).
A numeric vector for ENC
and SCUO
.
# load example DNA sequences exampledir <- system.file("extdata", package = "coRdon") cT <- codonTable(readSet(exampledir)) # - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - # In the examples below, MILC values are calculated for all sequences; # B and ENCprime can be caluclated in the same way. # - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - # calculate MILC distance to the average CU of the example DNA sequences milc <- MILC(cT) head(milc) # also calculate MILC distance to the average CU # of ribosomal genes among the example DNA sequences milc <- MILC(cT, ribosomal = TRUE) head(milc) # calculate MILC distance to the average CU # of the first 20 example DNA sequences # (i.e. the first half of the example DNA set) milc <- MILC(cT, self = FALSE, subsets = list(half = c(rep(TRUE, 20), rep(FALSE, 20)))) # alternatively, you can specify codonTable as a subset halfcT <- codonTable(codonCounts(cT)[1:20,]) milc2 <- MILC(cT, self = FALSE, subsets = list(half = halfcT)) all.equal(milc, milc2) # TRUE # filtering MILC(cT, filtering = "hard", len.threshold = 80) # MILC for 9 sequences sum(getlen(cT) > 80) # 9 sequences are longer than 80 codons milc1 <- MILC(cT, filtering = "none") # no filtering milc2 <- MILC(cT, filtering = "soft") # warning all.equal(milc1, milc2) # TRUE # options for genetic code milc <- MILC(cT, stop.rm = TRUE) # don't use stop codons in calculation milc <- MILC(cT, alt.init = FALSE) # don't use alternative start codons milc <- MILC(cT, id_or_name2 = "2") # use different genetic code, for help # see `?Biostrings::GENETIC_CODE` # - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - # In the examples below, ENC values are calculated for all sequences; # SCUO values can be caluclated in the same way. # - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - # calculate ENC enc <- ENC(cT) head(enc) # filtering ENC(cT, filtering = "hard", len.threshold = 80) # ENC for 9 sequences sum(getlen(cT) > 80) # 9 sequences are longer than 80 codons enc1 <- ENC(cT, filtering = "none") # no filtering enc2 <- ENC(cT, filtering = "soft") # warning all.equal(enc1, enc2) # TRUE # options for genetic code enc <- ENC(cT, stop.rm = TRUE) # don't use stop codons in calculation enc <- ENC(cT, alt.init = FALSE) # don't use alternative start codons enc <- ENC(cT, id_or_name2 = "2") # use different genetic code, for help # see `?Biostrings::GENETIC_CODE`