Fig. 2: Visualizing the encoding of chemical structures.
From: Towards inferring nanopore sequencing ionic currents from nucleotide chemical structures
A–C Atom similarity matrix, tSNE visualization, and chemical structure of the example canonical DNA 6mer CGACGT. In A, B, atoms were numbered and colored based on the chemical structure in (C). Carbon, nitrogen, oxygen, and phosphorus were colored as black, blue, red, and orange, respectively. Specifically, in A, nucleobases were highlighted by dashed boxes. D–F Atom similarity matrix, tSNE visualization, and chemical structure of the example 5mC-containing DNA 6mer GT(5mC)AGA. In D, E, atoms were numbered and colored based on the chemical structure in (F). Carbon, nitrogen, oxygen, and phosphorus were colored as black, blue, red, and orange, respectively. Specifically, in D, E, methyl group carbon atoms (#38 in T and #58 in 5mC) were highlighted.
