Run a blastn query.

This is a wrapper for blastn.

blast_n(query, database, out_file = NULL, outfmt = "6",
  other_args = NULL, echo = TRUE, wd, ...)

Arguments

query	Character vector of length one; the path to the fasta file to use as the query sequence(s).
database	Character vector of length one; the name of the blast database.
out_file	Character vector of length one; the name to use for the results file.
outfmt	Character vector of length one; value to pass to blastn outfmt argument. Default = "6".
other_args	Character vector; other arguments to pass on to blastn. For a list of options, run blastn -help.
echo	Logical; should standard error and output be printed?
wd	Character vector of length one; working directory. The blast search will be conducted here.
...	Additional other arguments. Not used by this function, but meant to be used by drake_plan for tracking during workflows.

Value

A tab-separated text file with the results of the blastn search, named with the value of out_file.

References

https://www.ncbi.nlm.nih.gov/books/NBK279690/

Examples

library(ape)

# Make temp dir for storing files
temp_dir <- fs::dir_create(fs::path(tempdir(), "baitfindR_example"))

# Write out ape::woodmouse dataset as DNA
data(woodmouse)
ape::write.FASTA(woodmouse, fs::path(temp_dir, "woodmouse.fasta"))

# Make blast database
build_blast_db(
  fs::path(temp_dir, "woodmouse.fasta"),
  db_type = "nucl",
  out_name = "wood",
  parse_seqids = TRUE,
  wd = temp_dir)
#> 
#> 
#> Building a new DB, current time: 05/15/2019 16:40:36
#> New DB name:   /tmp/RtmpeNC9nF/baitfindR_example/wood
#> New DB title:  /tmp/RtmpeNC9nF/baitfindR_example/woodmouse.fasta
#> Sequence type: Nucleotide
#> Keep MBits: T
#> Maximum file size: 1000000000B
#> Adding sequences from FASTA; added 15 sequences in 0.011471 seconds.
#> $status
#> [1] 0
#> 
#> $stdout
#> [1] "\n\nBuilding a new DB, current time: 05/15/2019 16:40:36\nNew DB name:   /tmp/RtmpeNC9nF/baitfindR_example/wood\nNew DB title:  /tmp/RtmpeNC9nF/baitfindR_example/woodmouse.fasta\nSequence type: Nucleotide\nKeep MBits: T\nMaximum file size: 1000000000B\nAdding sequences from FASTA; added 15 sequences in 0.011471 seconds.\n"
#> 
#> $stderr
#> [1] ""
#> 
#> $timeout
#> [1] FALSE
#> 

# Blast the original sequences against the database
blast_n(
  fs::path(temp_dir, "woodmouse.fasta"),
  database = "wood",
  out_file = "blastn_results",
  wd = temp_dir,
  echo = TRUE
)
#> $status
#> [1] 0
#> 
#> $stdout
#> [1] ""
#> 
#> $stderr
#> [1] ""
#> 
#> $timeout
#> [1] FALSE
#> 

# Take a look at the results.
readr::read_tsv(
  fs::path(temp_dir, "blastn_results"),
  col_names = FALSE
  )
#> Parsed with column specification:
#> cols(
#>   X1 = col_character(),
#>   X2 = col_character(),
#>   X3 = col_double(),
#>   X4 = col_double(),
#>   X5 = col_double(),
#>   X6 = col_double(),
#>   X7 = col_double(),
#>   X8 = col_double(),
#>   X9 = col_double(),
#>   X10 = col_double(),
#>   X11 = col_double(),
#>   X12 = col_double()
#> )
#> # A tibble: 225 x 12
#>    X1    X2         X3    X4    X5    X6    X7    X8    X9   X10   X11   X12
#>    <chr> <chr>   <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl>
#>  1 No305 No305   100     964     0     0     2   965     2   965     0  1773
#>  2 No305 No1103S  98.5   960    14     0     2   961     2   961     0  1700
#>  3 No305 No306    98.2   964    17     0     2   965     2   965     0  1694
#>  4 No305 No0912S  98.3   960    16     0     2   961     2   961     0  1688
#>  5 No305 No1206S  98.1   960    18     0     2   961     2   961     0  1677
#>  6 No305 No1202S  98.1   960    18     0     2   961     2   961     0  1677
#>  7 No305 No1007S  98.1   960    18     0     2   961     2   961     0  1677
#>  8 No305 No0909S  98.1   960    18     0     2   961     2   961     0  1677
#>  9 No305 No0908S  98.1   960    18     0     2   961     2   961     0  1677
#> 10 No305 No304    98.0   961    19     0     2   962     2   962     0  1677
#> # … with 215 more rows

# Cleanup.
fs::file_delete(temp_dir)