Using support vector machine regression to model the retention of peptides in immobilized metal-affinity chromatography

Abstract

Retention of histidine-containing peptides in immobilized metal-affinity chromatography (IMAC) has been studied using several hundred model peptides. Retention in a Nickel column is primarily driven by the number of histidine residues; however, the amino acid composition of the peptide also plays a significant role. A regression model based on support vector machines was used to learn and subsequently predict the relationship between the amino acid composition and the retention time on a Nickel column. The model was predominantly governed by the count of the histidine residues, and the isoelectric point of the peptide.