Statistical learning of peptide retention behavior in chromatographic separations: a new kernel-based approach for computational proteomics

Abstract

Background: High-throughput peptide and protein identification technologies have benefited tremendously from strategies based on tandem mass spectrometry (MS/MS) in combination with database searching algorithms. A major problem with existing methods lies within the significant number of false positive and false negative annotations. So far, standard algorithms for protein identification do not use the information gained from separation processes usually involved in peptide analysis, such as retention time information, which are readily available from chromatographic separation of the sample. Identification can thus be improved by comparing measured retention times to predicted retention times. Current prediction models are derived from a set of measured test analytes but they usually require large amounts of training data.

A Computational Tool to Detect and Avoid Redundancy in Selected Reaction Monitoring

“…The retention time constraint significantly decreases the number of interferences and mirrors experimental conditions of scheduled SRM measurements more closely. SSRCalc is used by several other SRM assay design and simulation programs (17,41), and we validate our use of SSRCalc in the supplementary discussion with a large data set and also discuss other predictors based on support vector machines (27). We showed that the effect of using retention time scheduling with a window size of 4 SSRCalc units (corresponding to roughly 2 min on a 30-min gradient) can be comparable with adding one more transition to an assay.…”

Modeling the separation of small peptides by cation‐exchange chromatography

“…On the contrary, proteomic scientists who widely use LC are now interested in simulating peptide separations to improve their protein identifications. However, published studies deal essentially with peptide retention prediction in RP-HPLC [30,31]. Proteomics deals with a virtually unlimited number of peptides, and these are mainly long ones, over 15, and up to 50 amino acid residues stemming from known proteins, that is completely different from our study, dealing with complex mixtures of several dozens to hundred various short peptides (less than ten residues) obtained from unknown proteins or protein mixtures.…”

“…The type of groups determines the type and strength of the ion exchanger, whereas their total number and availability determine the capacity. Regarding the nature of the functional groups, it was evidenced that increasing the size of substituent groups (R) on anion-exchange phases like -NR 31 increased the elution volumes of large ions, and the addition of more hydrophilic groups increased the selectivity [25].…”

Standardization of retention time data for AMT tag proteomics database generation

“…While any of the sequence-dependent RT prediction algorithms [3][4][6][7][19][20][21] can be used for the purpose of this work, we have selected the additive model pioneered by Meek [22] and recently refined by Krokhin et al [4], and the BioLCCC model proposed by Gorshkov et al [6]. Both models performed equally well.…”