Skip to main content

Table 2 Performance comparison with and without an artificial neural network.

From: Genome-wide identification of specific oligonucleotides using artificial neural network and computational genomic analysis

Oligo length Procedure Sensitivity factor Success rate (%)a Cross homology b Execution time (hours)
70-mer IAB c 0.2 94 0.56 0.50
   0.3 95 0.56 0.71
   0.4 95 0.56 0.90
  BLAST with U d d 95 0.56 2.13
  Pure BLAST 95 0.61 3.69
50-mer IAB 0.2 91 0.64 0.20
   0.3 93 0.64 0.31
   0.4 93 0.64 0.32
  BLAST with U d 93 0.64 0.70
  Pure BLAST 93 0.69 2.19
25-mer W = 11e IAB 0.2 94 0.79 0.19
   0.3 94 0.79 0.26
   0.4 94 0.79 0.33
  BLAST with U d 94 0.79 0.78
  Pure BLAST 94 0.80 1.62
25-mer W = 8 IAB 0.2 93 0.80 0.36
   0.3 93 0.80 0.50
   0.4 93 0.80 0.64
  BLAST with U d 93 0.80 1.52
  Pure BLAST 93 0.81 3.51
25-mer W = 5 IAB 0.2 92 0.81 1.00
   0.3 92 0.81 1.39
   0.4 92 0.81 1.79
  BLAST with U d 92 0.81 4.25
  Pure BLAST 92 0.81 9.69
  1. aThe success rate is the percentage of tentative human consensus sequences on which the procedure can find the specific oligo (where the cross homology is less than the threshold). bThe cross homology of a specific oligo is determined by the similarity between the specific oligo and its best homology in the non-target sequence. cIAB, integration of artificial neural network (ANN) and basic local alignment search tool (BLAST).dBLAST with U d , BLAST search with the density of unique subsequences. eW is word length in the parameters of BLAST.