Multigram Encoding
There are only 70 different characters can occur in a valid SMILES string.
ABCDEFGHIKLMNOPRSTUVWXYZ[\]
Allowing for a (null) terminator character, there are 185 byte values that cannot normally occur in a SMILES.
Multigram compression uses these unused values to represent commonly occurring SMILES substrings.
Compression occurs because the entire substring (or multigram) is encoded as a single byte.