These five datasets were converted into numerical input using the coding in Table 2 and input to five perceptrons with architectures 140 �� 72 �� 1, 123 �� 72 �� 1, 128 �� 72 �� 1, 133 �� 72 �� 1, and 109 �� 72 �� 1, respectively (step (d) above). The ANN experiment was repeated for 10-folds using Calcitriol molecular weight the same 50% training, 50% testing regime, and learning parameters as for the benchmark results, leading to the figures displayed in Table 3. Also, DAR1�CDAR5 were input to J48 and Naive Bayes in Weka using the same train-test ratios and numbers of folds. The results of the benchmarking (no alignment) and all doubly aligned analysis are provided in Table 3. Table 3Results of 50:50 train-test ratio, 10-fold cross-validation on all five representations, non-aligned and aligned, using perceptrons, J48 and Naive Bayes.

For rule extraction purposes, DAR1�CDAR5 were input to PRISM (all samples used for maximum knowledge extraction) to produce the following metasignatures for each representation (where ��pos�� stands for position in the doubly aligned sequence):R1: Virus signature if pos5 = A, pos20 = N, pos32 = G or A, pos33 = N or C, pos34 = N, pos60 = C. pos5 = A, pos20 = N, pos21 = D, pos28 = E, pos30 = L, pos32 = A, pos36 = P, pos53 = A.R1: Worm signature if pos16 = G, pos37 = M, pos93 = I, pos94 = I, pos96 = A, pos100 = C or M, pos104 = D, pos149 = C. pos10 = L, pos41 = C, pos44 = I, pos45 = D or L, pos46 = R, pos51 = H, pos54 = L, pos59 = S, pos70 = G or R, pos71 = S, pos72 = L or M, pos73 = D or P. R2: Virus signature. No rules found except involving gaps W and Y.

pos4 = Q or R, pos43 = K, pos69 = F or Q, pos84 = K.R2: Worm signature if pos5 = C, pos8 = H, pos11 = C or L, pos27 = G or N, pos28 = D or E, pos43 = A, pos45 = R, pos67 = S. pos5 = C, pos7 = P, pos27 = I, pos28 = D or G, pos29 = C, pos31 = K, pos83 = F.R3: Virus signature if pos12 = A, post13 = A, pos65 = F.R3: Worm signature if pos11 = A, pos33 = I, pos55 = L or Drug_discovery M, pos88 = M, pos119 = N, pos122 = A, pos124 = H or M.R4: Virus signature if pos9 = K, pos18 = I, pos21 = K. No rules found for virus or worm signatures except those involving W and Y.R5: Virus signature if pos51 = E or M, pos52 = C, pos53 = P, pos54 = F, pos57 = D, pos58 = F, pos59 = D.R5: Worm signature if pos13 = H then 1.Converting these metasignatures back into hexadecimal patterns produces (where ��..�� means any number of hexadecimal characters and ��[]�� gives alternatives):R1: Virus signature if ��..2..[df]..[61][b2]b..2..�� ��..1..b3..4..0..1..c..1..��; Worm signature if ��..6..a..88..1..[2a]..3..2..�� ��..0..2..8[30]e..7..0..f..[6e]f[0a][3c]..��R2: Virus signature if ��..[32]..8..[b3]..8..�� Worm signature if ��..6..1..[67]..[25][5c]..f..2..1..�� ��..e..4..9[ad]e..8..b..