vectorize function

[nshervt]

Thanks for the great work!

I was wondering what exactly does

Xs, X = vectorize(list_seq, char_set)

do? It seems that it is turning the SMILES inputs to a matrix of one-hot vectors. But it also adds 4 additional lines: an empty line at the beginning and 3 lines at the end. Then it returns 0:-1 and 1: as Xs and X. What's the point in doing so?