Fast Local Alignment in Julia

sw.jl

module main

using BioSequences
using BioAlignments
using BenchmarkTools

struct AlignmentResults
    align::BioAlignments.PairwiseAlignmentResult
    name::String
end

function generate_fasta_db(fasta_path::String)::Dict{String, BioSequences.BioSequence}
    db = Dict{String, BioSequences.BioSequence}()
    reader =  BioSequences.FASTA.Reader(open(fasta_path, "r"))
    for record in reader
        sequence = BioSequences.FASTA.sequence(record)
        id::String = BioSequences.FASTA.identifier(record)
        db[id] = sequence
    end
    close(reader)
    return db
end

const PS1 = BioSequences.dna"TAACTTACGGAGTCGCTCTACG"

function sw_alignments()
    fasta = "sampled_50000.fasta"
    fasta_db = generate_fasta_db(fasta)
    
    problem = BioAlignments.LocalAlignment() #smith-waterman local alignment
    scoremodel = BioAlignments.AffineGapScoreModel(match=5, mismatch=-4, gap_open=-4, gap_extend=-1)
    global i = 1
    for (name, seq) in fasta_db
        align = pairalign(problem, seq, PS1, scoremodel)
        i += 1
    end
    @show("Processed $i alignments in total")
end

for i in 1:10
    @time main.sw_alignments()
end

end

julia> include("sw_alignment.jl")
WARNING: replacing module main.
"Processed $(i) alignments in total" = "Processed 55275 alignments in total"
  1.071445 seconds (942.09 k allocations: 381.156 MiB, 6.12% gc time)
"Processed $(i) alignments in total" = "Processed 55275 alignments in total"
  1.330422 seconds (942.09 k allocations: 381.156 MiB, 22.41% gc time)
"Processed $(i) alignments in total" = "Processed 55275 alignments in total"
  1.086053 seconds (942.09 k allocations: 381.156 MiB, 5.71% gc time)
"Processed $(i) alignments in total" = "Processed 55275 alignments in total"
  1.080862 seconds (942.09 k allocations: 381.156 MiB, 6.04% gc time)
"Processed $(i) alignments in total" = "Processed 55275 alignments in total"
  1.064474 seconds (942.09 k allocations: 381.156 MiB, 5.38% gc time)
"Processed $(i) alignments in total" = "Processed 55275 alignments in total"
  1.326917 seconds (942.09 k allocations: 381.156 MiB, 22.05% gc time)
"Processed $(i) alignments in total" = "Processed 55275 alignments in total"
  1.098568 seconds (942.09 k allocations: 381.156 MiB, 6.33% gc time)
"Processed $(i) alignments in total" = "Processed 55275 alignments in total"
  1.068314 seconds (942.09 k allocations: 381.156 MiB, 5.94% gc time)
"Processed $(i) alignments in total" = "Processed 55275 alignments in total"
  1.078697 seconds (942.09 k allocations: 381.156 MiB, 5.26% gc time)
"Processed $(i) alignments in total" = "Processed 55275 alignments in total"
  1.637824 seconds (942.09 k allocations: 381.156 MiB, 29.16% gc time)
Main.main