An insightful 20-year recollection since the birth of pseudo amino acid components

With the avalanche of biological sequences discovered in the postgenomic era, one of the most important but also most difficult problems in computational biology is how to express a biological sequence with a discrete model or a vector, yet still keep its considerable sequence-order information or special pattern. To deal with this problem, the idea of "pseudo amino acid components" or "PseAAC" was proposed in 2001. In this paper, the author has recalled the proposal of "pseudo amino acid components" and its significant and substantial impacts on proteome and genome analyses as well as developing novel and effective drugs, particularly peptide drugs.