Use of dual-filtering to create training sets leading to improved accuracy in quantitative structure-retention relationships modelling for hydrophilic interaction liquid chromatographic systems

International interlaboratory study to normalize liquid chromatography-based mycotoxin retention times through implementation of a retention index system

Monitoring for mycotoxins in food or feed matrices is necessary to ensure the safety and security of global food systems. Due to a lack of standardized methods and individual laboratory priorities, most institutions have developed their own methods for mycotoxin determinations. Given the diversity of mycotoxin chemical structures and physicochemical properties, searching databases, and comparing data between institutions is complicated. We previously introduced incorporating a retention index (RI) system into liquid chromatography mass spectrometry (LC-MS) based mycotoxin determinations. To validate this concept, we designed an interlaboratory study where each participating laboratory was sent N-alkylpyridinium-3-sulfonates (NAPS) RI standards, and 36 mycotoxin standards for analysis using their pre-optimized LC-MS methods. Data from 44 analytical methods were submitted from 24 laboratories representing various manufacturer platforms, LC columns, and mobile phase compositions. Mycotoxin retention times (tR) were converted to RI values based on their elution relative to the NAPS standards. Trichothecenes (deoxynivalenol, 3-acetyldeoxynivalenol, 15-acetyldeoxynivalenol) showed tR consistency (± 20-50 RI units, 1-5 % median RI) regardless of mobile phase or type of chromatography column in this study. For the remaining mycotoxins tested, the RI values were strongly impacted by the mobile phase composition and column chemistry. The ability to predict tR was evaluated based on the median RI mycotoxin values and the NAPS tR. These values were corrected using Tanimoto coefficients to investigate whether structurally similar compounds could be used as anchors to further improve accuracy. This study demonstrated the power of employing an RI system for mycotoxin determinations, further enhancing the confidence of identifications.

Application of artificial intelligence to quantitative structure-retention relationship calculations in chromatography

Quantitative structure-retention relationship (QSRR) is an important tool in chromatography. QSRR examines the correlation between molecular structures and their retention behaviors during chromatographic separation. This approach involves developing models for predicting the retention time (RT) of analytes, thereby accelerating method development and facilitating compound identification. In addition, QSRR can be used to study compound retention mechanisms and support drug screening efforts. This review provides a comprehensive analysis of QSRR workflows and applications, with a special focus on the role of artificial intelligence-an area not thoroughly explored in previous reviews. Moreover, we discuss current limitations in RT prediction and propose promising solutions. Overall, this review offers a fresh perspective on future QSRR research, encouraging the development of innovative strategies that enable the diverse applications of QSRR models in chromatographic analysis.

Machine learning models and performance dependency on 2D chemical descriptor space for retention time prediction of pharmaceuticals

The predictive modeling of liquid chromatography methods can be an invaluable asset, potentially saving countless hours of labor while also reducing solvent consumption and waste. Tasks such as physicochemical screening and preliminary method screening systems where large amounts of chromatography data are collected from fast and routine operations are particularly well suited for both leveraging large datasets and benefiting from predictive models. Therefore, the generation of predictive models for retention time is an active area of development. However, for these predictive models to gain acceptance, researchers first must have confidence in model performance and the computational cost of building them should be minimal. In this study, a simple and cost-effective workflow for the development of machine learning models to predict retention time using only Molecular Operating Environment 2D descriptors as input for support vector regression is developed. Furthermore, we investigated the relative performance of models based on molecular descriptor space by utilizing uniform manifold approximation and projection and clustering with Gaussian mixture models to identify chemically distinct clusters. Results outlined herein demonstrate that local models trained on clusters in chemical space perform equivalently when compared to models trained on all data. Through 10-fold cross-validation on a comprehensive set containing 67,950 of our company's proprietary analytes, these models achieved coefficients of determination of 0.84 and 3 % error in terms of retention time. This promising statistical significance is found to translate from cross-validation to prospective prediction on an external test set of pharmaceutically relevant analytes. The observed equivalency of global and local modeling of large datasets is retained with METLIN's SMRT dataset, thereby confirming the wider applicability of the developed machine learning workflows for global models.

Advances in AI-Driven Retention Prediction for Different Chromatographic Techniques: Unraveling the Complexity

Retention prediction through Artificial intelligence (AI)-based techniques has gained exponential growth due to their abilities to process complex sets of data and ease the crucial task of identification and separation of compounds in most employed chromatographic techniques. Numerous approaches were reported for retention prediction in different chromatographic techniques, and consistent results demonstrated that the accuracy and effectiveness of deep learning models outclassed the linear machine learning models, mainly in liquid and gas chromatography, as ML algorithms use fewer complex data to train and predict information. Support Vector machine-based neural networks were found to be most utilized for the prediction of retention factors of different compounds in thin-layer chromatography. Cheminformatics, chemometrics, and hybrid approaches were also employed for the modeling and were more reliable in retention prediction over conventional models. Quantitative Structure Retention Relationship (QSRR) was also a potential method for predicting retention in different chromatographic techniques and determining the separation method for analytes. These techniques demonstrated the aids of incorporating QSRR with AI-driven techniques acquiring more precise retention predictions. This review aims at recent exploration of different AI-driven approaches employed for retention prediction in different chromatographic techniques, and due to the lack of summarized literature, it also aims at providing a comprehensive literature that will be highly useful for the society of scientists exploring the field of AI in analytical chemistry.

Current trends in chromatographic prediction using artificial intelligence and machine learning

Artificial intelligence (AI) and machine learning (ML) gained tremendous growth and are rapidly becoming popular in various fields of prediction due to their potential abilities, accuracy, and speed. Machine learning algorithms employ historical data to analyze or predict information using patterns or trends. AI and ML were most employed in chromatographic predictions and particularly attractive options for liquid chromatography method development, as they can help achieve desired results faster, more accurately, and more efficiently. This review aims at exploring various AI and ML models employed in the determination of chromatographic characteristics. This review also aims to provide deep insight into reported artificial neural network (ANN) associated techniques which maintained better accuracy and significant possibilities for chromatographic characteristics prediction in liquid chromatography over classical linear models and also emphasizes the integration of a fuzzy system with an ANN, as this integrated study provides more efficient and accurate methods in chromatographic prediction than other linear models. This study also focuses on the retention prediction of a target molecule employing QSRR methodology combined with an ANN, highlighting a more effective technique than the QSRR alone. This approach showed the benefits of combining AI or ML algorithms with the QSRR to obtain more accurate retention predictions, emphasizing the potential of artificial intelligence and machine learning for overcoming adversities in analytical chemistry.

Machine Learning-Based Retention Time Prediction of Trimethylsilyl Derivatives of Metabolites

In gas chromatography–mass spectrometry-based untargeted metabolomics, metabolites are identified by comparing mass spectra and chromatographic retention time with reference databases or standard materials. In that sense, machine learning has been used to predict the retention time of metabolites lacking reference data. However, the retention time prediction of trimethylsilyl derivatives of metabolites, typically analyzed in untargeted metabolomics using gas chromatography, has been poorly explored. Here, we provide a rationalized framework for machine learning-based retention time prediction of trimethylsilyl derivatives of metabolites in gas chromatography. We compared different machine learning paradigms, in addition to exploring the influence of the computational molecular structure representation to train the prediction models: fingerprint class and fingerprint calculation software. Our study challenged predicted retention time when using chemical ionization and electron impact ionization sources in simulated and real cases, demonstrating a good correct identity ranking capability by machine learning, despite observing a limited false identity filtering power in cases where a spectrum or a monoisotopic mass match to multiple candidates. Specifically, machine learning prediction yielded median absolute and relative retention index (relative retention time) errors of 37.1 retention index units and 2%, respectively. In addition, fingerprint class and fingerprint calculation software, as well as the molecular structural similarity between the training and test or real case sets, showed to be critical modulators of the prediction performance. Finally, we leveraged the structural similarity between the training and test or real case set to determine the probability that the prediction error is below a specific threshold. Overall, our study demonstrates that predicted retention time can provide insights into the true structure of unknown metabolites by ranking from the most to the least plausible molecular identity, and sets the guidelines to assess the confidence in metabolite identification using predicted retention time data.

Strategies for structure elucidation of small molecules based on LC–MS/MS data from complex biological samples

LC–MS/MS is a major analytical platform for metabolomics, which has become a recent hotspot in the research fields of life and environmental sciences. By contrast, structure elucidation of small molecules based on LC–MS/MS data remains a major challenge in the chemical and biological interpretation of untargeted metabolomics datasets. In recent years, several strategies for structure elucidation using LC–MS/MS data from complex biological samples have been proposed, these strategies can be simply categorized into two types, one based on structure annotation of mass spectra and for the other on retention time prediction. These strategies have helped many scientists conduct research in metabolite-related fields and are indispensable for the development of future tools. Here, we summarized the characteristics of the current tools and strategies for structure elucidation of small molecules based on LC–MS/MS data, and further discussed the directions and perspectives to improve the power of the tools or strategies for structure elucidation.

Retention time prediction in hydrophilic interaction liquid chromatography with graph neural network and transfer learning

The combination of retention time (RT), accurate mass and tandem mass spectra can improve the structural annotation in untargeted metabolomics. However, the incorporation of RT for metabolite identification has received less attention because of the limitation of available RT data, especially for hydrophilic interaction liquid chromatography (HILIC). Here, the Graph Neural Network-based Transfer Learning (GNN-TL) is proposed to train a model for HILIC RTs prediction. The graph neural network was pre-trained using an in silico HILIC RT dataset (pseudo-labeling dataset) with ∼306 K molecules. Then, the weights of dense layers in the pre-trained GNN (pre-GNN) model were fine-tuned by transfer learning using a small number of experimental HILIC RTs from the target chromatographic system. The GNN-TL outperformed the methods in Retip, including the Random Forest (RF), Bayesian-regularized neural network (BRNN), XGBoost, light gradient-boosting machine (LightGBM), and Keras. It achieved the lowest mean absolute error (MAE) of 38.6 s on the test set and 33.4 s on an additional test set. It has the best ability to generalize with a small performance difference between training, test, and additional test sets. Furthermore, the predicted RTs can filter out nearly 60% false positive candidates on average, which is valuable for the identification of compounds complementary to mass spectrometry.

Suspect screening of environmental contaminants by UHPLC-HRMS and transposable Quantitative Structure-Retention Relationship modelling

A Quantitative Structure-Retention Relationship (QSRR) model is proposed and aims at increasing the confidence level associated to the identification of organic contaminants by Ultra-High Performance Liquid Chromatography hyphenated to High Resolution Mass Spectrometry (UHPLC-HRMS) in environmental samples under a suspect screening approach. The model was built from a selection of 8 easily accessible physicochemical descriptors, and was validated from a set of 274 organic compounds commonly found in environmental samples. The proposed predictive figure approach is based on the mobile phase composition at solute elution (expressed as % acetonitrile), that has the major advantage of making the model reusable by other laboratories, since the elution composition is independent of both the column geometry and the UHPLC-system. The model quality was assessed and was altered neither by the columns from different lots, nor by the complex matrices of environmental water samples. Then, the solute retention of any organic compound present in water samples is expected to be predicted within ± 14.3% acetonitrile by our model. Solute retention can therefore be used as a supplementary tool for the identification of environmental contaminants by UHPLC-HRMS, in addition to mass spectrometry data already used in the suspect screening approach.

Perspective on the Future Approaches to Predict Retention in Liquid Chromatography

The demand for rapid column screening, computer-assisted method development and method transfer, and unambiguous compound identification by LC/MS analyses has pushed analysts to adopt experimental protocols and software for the accurate prediction of the retention time in liquid chromatography (LC). This Perspective discusses the classical approaches used to predict retention times in LC over the last three decades and proposes future requirements to increase their accuracy. First, inverse methods for retention prediction are essentially applied during screening and gradient method optimization: a minimum number of experiments or design of experiments (DoE) is run to train and calibrate a model (either purely statistical or based on the principles and fundamentals of liquid chromatography) by a mere fitting process. They do not require the accurate knowledge of the true column hold-up volume V₀, system dwell volume V_dwell (in gradient elution), and the retention behavior (k versus the content of strong solvent φ, temperature T, pH, and ionic strength I) of the analytes. Their relative accuracy is often excellent below a few percent. Statistical methods are expected to be the most attractive to handle very complex retention behavior such as in mixed-mode chromatography (MMC). Fundamentally correct retention models accounting for the simultaneous impact of φ, I, pH, and T in MMC are needed for method development based on chromatography principles. Second, direct methods for retention prediction are ideally suited for accurate method transfer from one column/system configuration to another: these quality by design (QbD) methods are based on the fundamentals and principles of solid-liquid adsorption and gradient chromatography. No model calibration is necessary; however, they require universal conventions for the accurate determination of true retention factors (for 1 < k < 30) as a function of the experimental variables (φ, T, pH, and I) and of the true column/system parameters (V₀, V_dwell, dispersion volume, σ, and relaxation volume, τ, of the programmed gradient profile at the column inlet and gradient distortion at the column outlet). Finally, when the molecular structure of the analytes is either known or assumed, retention prediction has essentially been made on the basis of statistical approaches such as the linear solvation energy relationships (LSERs) and the quantitative structure retention relationships (QSRRs): their ability to accurately predict the retention remains limited within 10-30%. They have been combined with molecular similarity approaches (where the retention model is calibrated with compounds having structures similar to that of the targeted analytes) and artificial intelligence algorithms to further improve their accuracy below 10%. In this Perspective, it is proposed to adopt a more rigorous and fundamental approach by considering the very details of the solid-liquid adsorption process: Monte Carlo (MC) or molecular dynamics (MD) simulations are promising tools to explain and interpret retention data that are too complex to be described by either empirical or statistical retention models.

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

Accurate prediction of the separation conditions for a set of target analytes with no retention data available is fundamental for routine analytical assays but remains a very challenging task. In this paper, a quality by design (QbD) optimisation workflow capable of discovering the optimal chromatographic conditions for separation of new compounds in hydrophilic-interaction liquid chromatography (HILIC) is introduced. This workflow features the application of quantitative structure−retention relationship (QSRR) methodology in conjunction with design of experiments (DoE) principles and was used to carry out a two-level full factorial DoE optimisation for a mixture of pharmaceutical analytes on zwitterionic, amide, amine, and bare silica HILIC stationary phases, with mobile phases containing varying acetonitrile content, mobile phase pH, and salt concentration. A dual-filtering approach that considers both retention time (tR) and structural similarity was used to identify the optimal set of analytes to train the QSRR in order to maximise prediction accuracy. Highly predictive retention models (average R2 of 0.98) were obtained and statistical analysis of the prediction performance of the QSRR models demonstrated their ability to predict the retention times of new compounds based solely on their molecular structures, with root-mean-square errors of prediction in the range 7.6–11.0 %. Further, the obtained retention data for pharmaceutical test compounds were used to compute their separation selectivity, which was used as input into a DoE optimiser in order to select the optimal separation conditions. Experimental separations performed under the chosen optimal working conditions showed good agreement with the theoretical predictions. To the best of our knowledge, this is the first study of a QbD optimisation workflow assisted with dual-filtering-based retention modelling to facilitate the method development process in HILIC.

Retip: Retention Time Prediction for Compound Annotation in Untargeted Metabolomics

Unidentified peaks remain a major problem in untargeted metabolomics by LC-MS/MS. Confidence in peak annotations increases by combining MS/MS matching and retention time. We here show how retention times can be predicted from molecular structures. Two large, publicly available data sets were used for model training in machine learning: the Fiehn hydrophilic interaction liquid chromatography data set (HILIC) of 981 primary metabolites and biogenic amines,and the RIKEN plant specialized metabolome annotation (PlaSMA) database of 852 secondary metabolites that uses reversed-phase liquid chromatography (RPLC). Five different machine learning algorithms have been integrated into the Retip R package: the random forest, Bayesian-regularized neural network, XGBoost, light gradient-boosting machine (LightGBM), and Keras algorithms for building the retention time prediction models. A complete workflow for retention time prediction was developed in R. It can be freely downloaded from the GitHub repository (https://www.retip.app). Keras outperformed other machine learning algorithms in the test set with minimum overfitting, verified by small error differences between training, test, and validation sets. Keras yielded a mean absolute error of 0.78 min for HILIC and 0.57 min for RPLC. Retip is integrated into the mass spectrometry software tools MS-DIAL and MS-FINDER, allowing a complete compound annotation workflow. In a test application on mouse blood plasma samples, we found a 68% reduction in the number of candidate structures when searching all isomers in MS-FINDER compound identification software. Retention time prediction increases the identification rate in liquid chromatography and subsequently leads to an improved biological interpretation of metabolomics data.

Serum lipidomic biomarkers for non-small cell lung cancer in nonsmoking female patients

Lung cancer (Lca) is one of the malignant tumors with the fastest morbidity and mortality increase and the greatest threat to human health and life. The incidence of non-small cell lung cancer (NSCLC) in the nonsmoking female has increased recently. However, its pathogenesis is still unclear, and there is an urgent need for clinical diagnostic biomarkers, especially for early diagnosis. A nontargeted lipidomic approach based on ultra-high-performance liquid chromatography coupled with quadrupole time-of-flight mass spectrometry (UHPLC-Q-TOF/MS), as well as two machine learning approaches (genetic algorithm and binary logistic regression) was used to screen candidate discriminating lipids and define a combinational lipid biomarker in serum samples to distinguish female patients with NSCLC from healthy controls. Moreover, the candidate biomarkers were verified by using an external validation sample set. Our result revealed that fatty acid (FA) (20:4), FA (22:0) and LPE (20:4) can serve as a combinational biomarker for distinguishing female patients with NSCLC from healthy control with good sensitivity and specificity. Furthermore, this combinational biomarker also showed good performance in distinguishing early-stage NSCLC female patients from a healthy control. We observed that levels of unsaturated fatty acids clearly decreased, while saturated fatty acids and lysophosphatidylethanolamines pronouncedly increased in Lca patients, compared with the healthy controls, which revealed significant disturbance of lipid metabolism in NSCLC females. Our results not only provide hints to the pathological mechanism of NSCLC in nonsmoking female but also supply a combinational lipid biomarker to aid the diagnosis of NSCLC at early-stage.

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

Machine learning has been extensively applied in small molecule analysis to predict a wide range of molecular properties and processes including mass spectrometry fragmentation or chromatographic retention time. However, current approaches for retention time prediction lack sufficient accuracy due to limited available experimental data. Here we introduce the METLIN small molecule retention time (SMRT) dataset, an experimentally acquired reverse-phase chromatography retention time dataset covering up to 80,038 small molecules. To demonstrate the utility of this dataset, we deployed a deep learning model for retention time prediction applied to small molecule annotation. Results showed that in 70\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$\%$$\end{document}% of the cases, the correct molecular identity was ranked among the top 3 candidates based on their predicted retention time. We anticipate that this dataset will enable the community to apply machine learning or first principles strategies to generate better models for retention time prediction.

The use of machine learning for identifying small molecules through their retention time’s predictions has been challenging so far. Here the authors combine a large database of liquid chromatography retention time with a deep learning approach to enable accurate metabolites’s identification.

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

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 R² 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.

Software Tools and Approaches for Compound Identification of LC-MS/MS Data in Metabolomics

The annotation of small molecules remains a major challenge in untargeted mass spectrometry-based metabolomics. We here critically discuss structured elucidation approaches and software that are designed to help during the annotation of unknown compounds. Only by elucidating unknown metabolites first is it possible to biologically interpret complex systems, to map compounds to pathways and to create reliable predictive metabolic models for translational and clinical research. These strategies include the construction and quality of tandem mass spectral databases such as the coalition of MassBank repositories and investigations of MS/MS matching confidence. We present in silico fragmentation tools such as MS-FINDER, CFM-ID, MetFrag, ChemDistiller and CSI:FingerID that can annotate compounds from existing structure databases and that have been used in the CASMI (critical assessment of small molecule identification) contests. Furthermore, the use of retention time models from liquid chromatography and the utility of collision cross-section modelling from ion mobility experiments are covered. Workflows and published examples of successfully annotated unknown compounds are included.

Chemometric-assisted method development in hydrophilic interaction liquid chromatography: A review

With an enormous growth in the application of hydrophilic interaction liquid chromatography (HILIC), there has also been significant progress in HILIC method development. HILIC is a chromatographic method that utilises hydro-organic mobile phases with a high organic content, and a hydrophilic stationary phase. It has been applied predominantly in the determination of small polar compounds. Theoretical studies in computer-aided modelling tools, most importantly the predictive, quantitative structure retention relationship (QSRR) modelling methods, have attracted the attention of researchers and these approaches greatly assist the method development process. This review focuses on the application of computer-aided modelling tools in understanding the retention mechanism, the classification of HILIC stationary phases, prediction of retention times in HILIC systems, optimisation of chromatographic conditions, and description of the interaction effects of the chromatographic factors in HILIC separations. Additionally, what has been achieved in the potential application of QSRR methodology in combination with experimental design philosophy in the optimisation of chromatographic separation conditions in the HILIC method development process is communicated. Developing robust predictive QSRR models will undoubtedly facilitate more application of this chromatographic mode in a broader variety of research areas, significantly minimising cost and time of the experimental work.