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

Abstract

Two kinds of structural characterization method as local descriptors and global descriptors were used to parameterize peptide structures, and several quantitative structure-retention relationship models were then constructed using partial least square (PLS), least-squares support vector machine (LS-SVM) and Gaussian process (GP) coupled with genetic algorithm-variable selection. These models were validated rigorously and investigated systematically by Tropsha et al. criteria, Monte Carlo cross-validation and one-way analysis of variance. Results show that regression models constructed using nonlinear approaches such as LS-SVM and GP are more robust and predictable than those by linear PLS method. By including linear and nonlinear terms in the covariance function, the GP is capable of handling both linear and nonlinear-mixed relationship, and thus presents a better performance than LS-SVM. Investigation of the optimal GP model revealed that diversified properties contribute to the retention behavior of peptides in immobilized metal-affinity chromatography. Particularly, coordination interaction, electrostatic factor, sovlation effect and hydrogen bonding are correlated significantly with the peptide retention ability.

Molecular design and genetic optimization of antimicrobial peptides containing unnatural amino acids against antibiotic‐resistant bacterial infections

“…This is not unexpected because the aggregated descriptors cannot reflect the structural details of peptide, such as residue pattern and property distribution along the peptide sequence. This is in line with previous studies that showed a general better tendency of local descriptors than global descriptors in peptide QSAR modeling …”

Predicting the Flexibility Profile of Ribosomal RNAs

“…In this procedure, the natural logarithms of g and s 2 were tuned simultaneously in a grid ranging from 0 to 10 with step size of 1 and the combination of g and s 2 that give rise to the RMSCV minimum was ultimately determined. [46] (iii) For the GP regression, we used a method proposed by Obrezanova et al [47] to assign the initial values for its hyperparameter set V consisting of 4 overall scales and m length scales (m = the number of variables used in the modeling), and these parameters were further optimized using the Polak-Ribiere conjugate gradient method to maximize its logarithmic marginal likelihood. A detailed description of this procedure can be found in our previous publications.…”

Genome‐wide Inference of Transcription Factor–DNA Binding Specificity in Cell Regeneration Using a Combination Strategy

“…It is clearly seen that the affinity profile presents a pronounced uneven distribution; most samples have low or moderate affinity to Gcn4p, of which the affinity values were generally overestimated by the model, whereas few ones that possess high binding capability were underestimated significantly. The phenomenon of prediction behavior of regression model differentiating systematically between high-and low-affinity samples is not uncommon, if reciting that there were several our previous works to which the similar problem was encountered (49)(50)(51). Undoubtedly, although complicated interactive effects involved in the system have been considered here, the nonlinear relationship between the internal interactive and external affinity of samples remained largely unconsidered.…”