Make on-disk BLAST DB from a FASTA file

Calls makeblastdb to create a BLAST DB of a FASTA file

MakeBLASTDB(ptr, input_file, database_name, parse_seqids = FALSE)

Arguments

ptr

(Rcpp::XPtr<QuickBLAST>) or (unsigned int) Pointer/ID of QuickBLAST instance

input_file

(string) Path to FASTA file.

database_name

(string) Name of the output DB.

parse_seqids

(bool) TRUE - Checks FASTA headers for malformations (Default: FALSE)

Value

(bool) DB name on success, FALSE - Otherwise.

Note

Faitful re-implementation of makeblastdb seemed pointless, hence the system.call() to a the program.

See also

GetInstanceID(), GetQuickBLASTInstance(), BLAST2DBs(), isBLASTDB()

Examples

blastp_inst <- QuickBLAST::CreateQuickBLASTInstance(
  seq_type = 1,
  strand = 0,
  program = "blastp",
  save_sequences = FALSE,
  save_hsp_sequences = FALSE
)
#> Using blastp Defaults...
QuickBLAST::MakeBLASTDB(
  blastp_inst,
  system.file(
    "extdata",
    "protein_query.fasta",
    package = "QuickBLAST",
    mustWork = TRUE
  ),
  "protein_query.db"
)
#> [MakeBLASTDB] Executing command: /home/runner/work/_temp/Library/QuickBLAST/bin//makeblastdb -in /home/runner/work/_temp/Library/QuickBLAST/extdata/protein_query.fasta -dbtype prot -out protein_query.db 
#> makeblastdb finished successfully
#> [1] "protein_query.db"
QuickBLAST::MakeBLASTDB(
  blastp_inst,
  system.file(
    "extdata",
    "protein_subject.fasta",
    package = "QuickBLAST",
    mustWork = TRUE
  ),
  "protein_subject.db"
)
#> [MakeBLASTDB] Executing command: /home/runner/work/_temp/Library/QuickBLAST/bin//makeblastdb -in /home/runner/work/_temp/Library/QuickBLAST/extdata/protein_subject.fasta -dbtype prot -out protein_subject.db 
#> makeblastdb finished successfully
#> [1] "protein_subject.db"
QuickBLAST::BLAST2DBs(
  ptr=blastp_inst,
  query="protein_query.db",
  subject="protein_subject.db",
  num_threads=24,
  out_file="test.db.arrow",
  return_values = TRUE
)
#> Q :/home/runner/work/QuickBLAST/QuickBLAST/docs/reference/protein_query.db
#> S :/home/runner/work/QuickBLAST/QuickBLAST/docs/reference/protein_subject.db
#> Writing to : test.db.arrow
#> Output Format : parquet
#> Num Threads: 2
#> Total Records (Q + S): 2 (1 + 1)
#> Batch Size: 3
#> Batch Hits: 1
#> Done writing to file.
#> Processed Batches:1
#> Total Records Processed: 1
#> Clock : 0.0506452 seconds
#> RecordBatchVector size: 1
#> Total rows across all batches: 1
#> [[1]]
#>   seq_info_num_alignments seq_info_seqids_qseqid seq_info_seqids_sseqid
#> 1                       1                  QUERY                  QUERY
#>   seq_info_seqs_qseq seq_info_seqs_sseq seq_info_strands seq_info_lengths_qlen
#> 1                                                    */*                   758
#>   seq_info_lengths_slen hsps_qhsp hsps_shsp hsps_pident hsps_pident_gap
#> 1                   758                             100             100
#>   hsps_frames hsps_evalue hsps_length hsps_length01 hsps_qstart hsps_qend
#> 1         0/0           0         758             1           0       757
#>   hsps_sstart hsps_send hsps_bitscore hsps_score hsps_qcovhsp hsps_blast_score
#> 1           0       757      1496.871       3874            0             3874
#>   hsps_gaps hsps_nident hsps_mismatch hsps_positive hsps_n_splices hsps_hsp_num
#> 1         0         758             0           758              0            1
#>   hsps_sum_evalue hsps_product_coverage hsps_overall_identity
#> 1               0                     0                     0
#>   hsps_negative_count hsps_matches hsps_high_quality_percent_coverage
#> 1                   0            0                                  0
#>   hsps_exon_identity hsps_consensus_splices hsps_comp_adj_method
#> 1                  0                      0                    2
#> 
unlink("protein_query.db.*")
unlink("protein_subject.db.*")
unlink("test.db.arrow")