A Novel Bioinformatics Method for Efficient Knowledge Discovery by BLSOM from Big Genomic Sequence Data

Figure 4

BLSOMs for 100 kb repeat and unique sequences derived from the human and mouse genomes. (a) DegPenta. Lattice points containing sequences from more than one category are indicated in black and those containing sequences from a single category are indicated in color as shown in the keys. (b) Human repeat sequences. Human Sz-H1 and Sz-H2 sequences defined in Figure 3(b) are mapped and indicated in green and gray, respectively. (c) 𝑈-matrix for the DegPenta listed in (a). (d) Diagnostic pentanucleotides responsible for species-specific clustering. The observed/expected ratio for each pair of complimentary pentanucleotides is calculated as described in Figure 1(c) and indicated in color presented under the panel.