Current algorithms for the calculation of peptide or protein pI, based on the charge associated with individual amino acids, can calculate pI values to within +/- 0.2 pI units. Here, we present a new pI calculation algorithm that takes into account the effect of adjacent amino acids on the pI value. The algorithm accounts for the effect of adjacent amino acids 3 residues away from a charged aspartic or glutamic acid, as well as effects on the free C terminus, and applies a correction term to the corresponding pK values. The correction increments are derived from a 5000-peptide training set using a genetic optimization approach. The accuracy of the new pI values obtained with this method approaches the error associated with the manufacture of the IPG strip (< +/- 0.03 pI units). The approach is demonstrated for cytosolic cell extracts derived from the breast-cancer cell line DU4475, and from membrane preparations from human lung-tissue samples. One potential application of a more highly accurate pI calculation is data filtering of MS/MS outputs that will allow for more complex database searches including gene finding, and validation, and detection of coding single-nucleotide polymorphisms in their expressed form.