Retention Index Prediction Using Quantitative Structure–Retention Relationships for Improving Structure Identification in Nontargeted Metabolomics

Abstract

Structure identification in nontargeted metabolomics based on liquid-chromatography coupled to mass spectrometry (LC-MS) remains a significant challenge. Quantitative structure-retention relationship (QSRR) modeling is a technique capable of accelerating the structure identification of metabolites by predicting their retention, allowing false positives to be eliminated during the interpretation of metabolomics data. In this work, 191 compounds were grouped according to molecular weight and a QSRR study was carried out on the 34 resulting groups to eliminate false positives. Partial least squares (PLS) regression combined with a Genetic algorithm (GA) was applied to construct the linear QSRR models based on a variety of VolSurf+ molecular descriptors. A novel dual-filtering approach, which combines Tanimoto similarity (TS) searching as the primary filter and retention index (RI) similarity clustering as the secondary filter, was utilized to select compounds in training sets to derive the QSRR models yielding R of 0.8512 and an average root mean square error in prediction (RMSEP) of 8.45%. With a retention index filter expressed as ±2 standard deviations (SD) of the error, representative compounds were predicted with >91% accuracy, and for 53% of the groups (18/34), at least one false positive compound could be eliminated. The proposed strategy can thus narrow down the number of false positives to be assessed in nontargeted metabolomics.

The METLIN small molecule dataset for machine learning-based retention time prediction

“…The fact that a naïve approach that considered only molecular similarity was capable of achieving a similar exactitude to the DLM suggests a strong influence of the structural similarity in the RT prediction. Previous studies have already observed that RT prediction performance improved when the training set included structurally similar molecules to those in the validation set 45,46 . Still, for highly similar molecules (similarity of 95 or above), results showed that there are no statistically significant differences between the predicted and naïve approach mean error (Fig.…”

Method Optimisation in Hydrophilic-Interaction Liquid Chromatography by Design of Experiments Combined with Quantitative Structure–Retention Relationships

“…[7,8,27] Tanimoto similarity searching provides a perfect starting point for the application of t R similarity filtering in the determination of chromatographic similarity. [28,37] In the present study, prediction performance of the model was examined on a test set of 16 nucleosides under 11 mobile phase compositions corresponding to a full factorial design matrix and over four different HILIC stationary phases. Each nucleoside was successively removed from the dataset and retained as the test target and was not used during the training course.…”

Mechanistic Chromatographic Column Characterization for the Analysis of Flavonoids Using Quantitative Structure-Retention Relationships Based on Density Functional Theory

“…Prior to modeling, the Kennard and Stone algorithm [46] was employed for stratified dataset sampling into 23 training (70%) and 10 external validation (30%) analytes. Genetic algorithm-partial least squares (GA-PLS), recently shown to be effective in QSRR [10,16,22], was used for simultaneous modeling and selection of the most informative molecular descriptors. However, instead of a mixed-integer formulation (with a fixed number of selected variables), the binary implementation of GA [47,48] was employed instead.…”

“…Quantitative structure retention relationships (QSRRs), introduced by the pioneering research of Professor Roman Kaliszan, relate solute retention and their molecular structure [4]. Since the inception of QSRRs in the early 1970s, numerous applications have been reported, such as (i) prediction of retention time [5], (ii) estimation of the lipophilic character of analytes [6,7], (iii) determination of biological activities of analytes [8,9], (iv) metabolite identification in non-targeted metabolomics [10], and (v) columns characterization and selection [11][12][13].…”

“…In this work, we presented a novel approach for predicting the retention of 30 structurally-different flavonoids on three chemically-bonded stationary phases (classical octadecyl chain, pentafluorophenyl, and diacylated phosphatidylcholine) using genetic algorithms-partial least squares QSRR modeling [10,16,22] based on DFT-derived QM molecular descriptors. Mechanistic interpretations were given for the first time based on a comprehensive analysis of underlying relationships between the DFT-derived QM descriptors and retention inferring valuable physicochemical meaning.…”