Inductive Inference over MacroMolecules.
L. Allison, C. S. Wallace and C. N. Yee.
Department of Computer Science,
uucp: firstname.lastname@example.org xxx=[lloyd, csw, cyee]
Supported by Australian Research Council grant A48830856
Minimum message length (MML) encoding techniques
are applied to inductive inference problems over strings
derived from sequencing biological macro
molecules[1,2]. The paper is framed in terms of DNA
strings but the techniques apply to proteins and other
It is assumed that any one string is random in the sense
of Kolmogorov complexity. This is very nearly the case
for biological macromolecules and it is certainly very
difficult to encode a typical DNA string in much less than
two bits per character. The assumption is not essential to