For all sequences in a cluster(s) calculate the frequency of separate words in either the sequence definitions or the reported feature name.
Usage
calc_wrdfrq(
phylota,
cid,
min_frq = 0.1,
min_nchar = 1,
type = c("dfln", "nm"),
ignr_pttrn = "[^a-z0-9]"
)
Details
By default, anything that is not alphanumeric is ignored. 'dfln' and 'nm' match the slot names in a SeqRec, see list_seqrec_slots().
See also
Other tools-public:
calc_mad()
,
drop_by_rank()
,
drop_clstrs()
,
drop_sqs()
,
get_clstr_slot()
,
get_nsqs()
,
get_ntaxa()
,
get_sq_slot()
,
get_stage_times()
,
get_tx_slot()
,
get_txids()
,
is_txid_in_clstr()
,
is_txid_in_sq()
,
list_clstrrec_slots()
,
list_ncbi_ranks()
,
list_seqrec_slots()
,
list_taxrec_slots()
,
plot_phylota_pa()
,
plot_phylota_treemap()
,
read_phylota()
,
write_sqs()
Examples
data('dragonflies')
# work out what gene region the cluster is likely representing with word freqs.
random_cids <- sample(dragonflies@cids, 10)
# most frequent words in definition line
(calc_wrdfrq(phylota = dragonflies, cid = random_cids, type = 'dfln'))
#> $`430`
#> named numeric(0)
#>
#> $`653`
#> named numeric(0)
#>
#> $`15`
#> named numeric(0)
#>
#> $`478`
#> wrds
#> rrna and
#> 0.1525424 0.1016949
#>
#> $`548`
#> wrds
#> gene sequence
#> 0.1411765 0.1294118
#>
#> $`161`
#> named numeric(0)
#>
#> $`498`
#> wrds
#> gene sequence
#> 0.15 0.15
#>
#> $`413`
#> named numeric(0)
#>
#> $`222`
#> wrds
#> h3 cds gene histone partial
#> 0.1528384 0.1135371 0.1135371 0.1135371 0.1135371
#>
#> $`29`
#> named numeric(0)
#>
# most frequent words in feature name
(calc_wrdfrq(phylota = dragonflies, cid = random_cids, type = 'nm'))
#> $`430`
#> numeric(0)
#>
#> $`653`
#> numeric(0)
#>
#> $`15`
#> barcode
#> 1
#>
#> $`478`
#> numeric(0)
#>
#> $`548`
#> numeric(0)
#>
#> $`161`
#> numeric(0)
#>
#> $`498`
#> numeric(0)
#>
#> $`413`
#> barcode
#> 1
#>
#> $`222`
#> numeric(0)
#>
#> $`29`
#> numeric(0)
#>