Variations in length and composition of the charged N-terminal, central hydrophobic and polar C-terminal regions in a large sample of signal sequences have been mapped, both as a function of the overall length of the sequence, and in an absolute sense, i.e. various "extremes" have been sought. The results show subtle differences between eukaryotic and prokaryotic sequences, but the general impression of signal sequences as being highly variable is reinforced. Criteria for a "minimal" signal sequence are suggested and discussed.