Part of our motivation comes from an ongoing project that
applies such structure learning methods to molecular biology
problems [ 1 0]. This project attempts to understand
transcription of genes: A gene is expressed via a process
that transcribes it into an RNA sequence, and this RNA
sequence is in tum translated into a protein molecule. Recent
technical breakthroughs in molecular biology enable
biologists to measure of the expression levels of thousands
of genes in one experiment [7, 20, 32]. The data generated
from these experiments consists of instances, each one
of which has thousands of attributes. These data sets can
help us understand how a gene's transcription is effected by
various aspects of the cell's metabolism, including the expression
levels of other genes. The challenge is to recover
this biological knowledge from such experiments (see, e.g.,
[ 18]).