Novel approaches to predict the retention of histidine‐containing peptides in immobilized metal‐affinity chromatography

Abstract

The new method lazy learning method-local lazy regression (LLR) was first used to model the quantitative structure-retention relationship (QSRR) for predicting and explaining the retention behaviors of peptides in the nickel column in immobilized metal-affinity chromatography (IMAC). The best multilinear regression (BMLR) method implemented in the CODESSA was used to select the most appropriate molecular descriptors from a large set and build a linear regression model. Based on the selected five descriptors, another two approaches, projection pursuit regression (PPR) and LLR were used to build more accurate QSRR models. The coefficients of determination (R 2 ) of the best model developed based on LLR were 0.9446 and 0.9252 for the training set and the test set, respectively. By comparison, it was proved that the novel local learning method LLR was a very promising tool for QSRR modeling with excellent predictive capability for the prediction of imidazole concentration (IMC) values of histidine-containing peptides in IMAC. It could be used in other chromatography research fields and that should facilitate the design and purification of peptides and proteins.

Retracted: Isocratic Method for Affinity Enrichment of Covalently‐linked Peptides in Cyanogen Bromide Cleavage of Proteins

“…In designing isocratic method for the enrichment of covalently linked peptides, the key concern was to differentiate the binding strength of two affinity tags against one affinity tag. Therefore, the polyhistidine tag with moderate dissociation constant (10 À7 to 10 -8 ), for example, tetrahistidine tag, was designed for the enrichment of covalently linked peptides [32][33][34]. In contrast to conventional methods that rely on crosslinking reagents with built-in enrichment functionalities, isocratic purification method restricts enrichment to covalently linked peptides, as opposed to internally linked or merely derivatized peptides [29].…”

Modeling and prediction of retention behavior of histidine‐containing peptides in immobilized metal‐affinity chromatography

“…Previous studies suggested the linear model is insufficient to capture all the dependencies of the peptide IMC system [18,19]. Here we employed LS-SVM to investigate the nonlinear relationship between local descriptors and peptide IMC.…”

“…Based on support vector machine (SVM) approach, an optimized model was constructed by them to predict peptide IMC values, with the correlation coefficients r 2 for training and test sets of 0.78 and 0.77, respectively. Recently, Du et al [19] employed several regression methods such as best multilinear regression, projection pursuit regression and local lazy regression, to model the quantitative structure-retention relationship (QSRR) for predicting and explaining the retention behavior of peptides in IMAC. The QSRR development was based on the assumption that peptide elution behavior would substantially depend on molecular structure characteristics and amino acid compositions.…”

A Multi-Scale Parameterization Approach of Peptides for Quantitative Sequence-Activity Models

“…Total 28 compounds were discarded as the method [58] from the original 306 peptides, because they had either repeated values or different responding imidazole concentration values to the same peptide. Then, the remaining 278 peptides ranging in size from 10 to 17 amino acid residues and the corresponding imidazole concentration values were studied.…”