One of the most powerful formulations uses binary variables to represent the presence of a rotamer and edges in the final solution, and constraints the solution to have exactly one rotamer for each residue and one pairwise interaction for each pair of residues:
32.
Now, we must make the central assumption of the piling-up lemma : the binary variables we are dealing with are "'independent "'; that is, the state of one has no effect on the state of any of the others.
33.
When used in the constraints themselves, one of the many uses of Big M, for example, refers to ensuring equality of variables only when a certain binary variable takes on one value, but to leave the variables " open " if the binary variable takes on its opposite value.
34.
When used in the constraints themselves, one of the many uses of Big M, for example, refers to ensuring equality of variables only when a certain binary variable takes on one value, but to leave the variables " open " if the binary variable takes on its opposite value.
35.
Consider a standard table showing the association between two binary variables with frequencies a = true positives = 49005929, b = false positives = 50994071, c = false negatives = 50994071 and d = true negatives = 849005929 . In this case the odds ratio ( OR ) is equal to 16 and the relative risk ( RR ) is equal to 8, 65.
36.
This equation clearly has the same "'form "'as the ( blue ) equation expressing the mutual information between the feature set and the category variable; the difference is that the sum \ textstyle \ sum _ { f _ i \ in F } in the " category utility " equation runs over independent binary variables F = \ { f _ i \ }, \ i = 1 \ ldots n, whereas the sum \ textstyle \ sum _ { v _ i \ in F _ a } in the mutual information runs over " values " of the single m ^ n-ary variable F _ a.
