Localised quantitative structure–retention relationship modelling for rapid method development in reversed-phase high performance liquid chromatography

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.

In-silico method development and optimization of on-line comprehensive two-dimensional liquid chromatography via a shortcut model

Comprehensive two-dimensional liquid chromatography (LCxLC) represents a valuable alternative to conventional single column, or one-dimensional, liquid chromatography (1D-LC) for resolving multiple components in a complex mixture in a short time. However, developing LCxLC methods with trial-and-error experiments is challenging and time-consuming, which is why the technique is not dominant despite its significant potential. This work presents a novel shortcut model to in-silico predicting retention time and peak width within an RPLCxRPLC separation system (i.e., LCxLC systems that use reversed-phase columns (RPLC) in both separation dimensions). Our computationally effective model uses the hydrophobic-subtraction model (HSM) to predict retention and considers limitations due to the sample volume, undersampling and the maximum pressure drop. The shortcut model is used in a two-step strategy for sample-dependent optimization of RPLCxRPLC separation systems. In the first step, the Kendall's correlation coefficient of all possible combinations of available columns is evaluated, and the best column pair is selected accordingly. In the second step, the optimal values of design variables, flow rate, pH and sample loop volume, are obtained via multi-objective stochastic optimization. The strategy is applied to method development for the separation of 8, 12 and 16 component mixtures. It is shown that the proposed strategy provides an easy way to accelerate method development for full-comprehensive 2D-LC systems as it does not require any experimental campaign and an entire optimization run can take less than two minutes.

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.

Prediction of a Large-Scale Database of Collision Cross-Section and Retention Time Using Machine Learning to Reduce False Positive Annotations in Untargeted Metabolomics

Metabolite identification in untargeted metabolomics is complex, with the risk of false positive annotations. This work aims to use machine learning to successively predict the retention time (Rt) and the collision cross-section (CCS) of an open-access database to accelerate the interpretation of metabolomic results. Standards of metabolites were tested using liquid chromatography coupled with high-resolution mass spectrometry. In CCSBase and QSRR predictor machine learning models, experimental results were used to generate predicted CCS and Rt of the Human Metabolome Database. From 542 standards, 266 and 301 compounds were detected in positive and negative electrospray ionization mode, respectively, corresponding to 380 different metabolites. CCS and Rt were then predicted using machine learning tools for almost 114,000 metabolites. R² score of the linear regression between predicted and measured data achieved 0.938 and 0.898 for CCS and Rt, respectively, demonstrating the models' reliability. A CCS and Rt index filter of mean error ± 2 standard deviations could remove most misidentifications. Its application to data generated from a toxicology study on tobacco cigarettes reduced hits by 76%. Regarding the volume of data produced by metabolomics, the practical workflow provided allows for the implementation of valuable large-scale databases to improve the biological interpretation of metabolomics data.

The secret of reversed-phase/weak cation exchange retention mechanisms in mixed-mode liquid chromatography applied for small drug molecule analysis

Resolving complex sample mixtures by liquid chromatography in a single run is challenging. The so-called mixed-mode liquid chromatography (MMLC) which combines several retention mechanisms within a single column, can provide resource-efficient separation of solutes of diverse nature. The Acclaim Mixed-Mode WCX-1 column, encompassing hydrophobic and weak cation exchange interactions, was employed for the analysis of small drug molecules. The stationary phase's interaction abilities were assessed by analysing molecules of different ionisation potentials. Mixed Quantitative Structure-Retention Relationship (QSRR) models were developed for revealing significant experimental parameters (EPs) and molecular features governing molecular retention. According to the plan of Face-Centred Central Composite Design, EPs (column temperature, acetonitrile content, pH and buffer concentration of aqueous mobile phase) variations were included in QSRR modelling. QSRRs were developed upon the whole data set (global model) and upon discrete parts, related to similarly ionized analytes (local models) by applying gradient boosted trees as a regression tool. Root mean squared errors of prediction for global and local QSRR models for cations, anions and neutrals were respectively 0.131; 0.105; 0.102 and 0.042 with the coefficient of determination 0.947; 0.872; 0.954 and 0.996, indicating satisfactory performances of all models, with slightly better accuracy of local ones. The research showed that influences of EPs were dependant on the molecule's ionisation potential. The molecular descriptors highlighted by models pointed out that electrostatic and hydrophobic interactions and hydrogen bonds participate in the retention process. The molecule's conformation significance was evaluated along with the topological relationship between the interaction centres, explicitly determined for each molecular species through local models. All models showed good molecular retention predictability thus showing potential for facilitating the method development.

Development of quantitative structure-retention relationship models to improve the identification of leachables in food packaging using non-targeted analysis

Quantitative structure-retention relationship (QSRR) models can be used to predict the chromatographic retention time of chemicals and facilitate the identification of unknown compounds, notably with non-targeted analysis. In this study, QSRR models were developed from the data obtained for 178 pure chemical standards and four types of analytical columns (C18, phenylhexyl, pentafluorophenyl, cyano) in liquid chromatography quadrupole time-of-flight mass spectrometry (LC-Q-TOF-MS). First, different data partitioning ratios and feature selection methods [random forest (RF) and support vector machine (SVM)] were tested to build models to predict chromatographic retention times based on 2D molecular descriptors. The internal and external performances of the non-linear (RF) and corresponding linear predictive models were systematically compared, and RF models resulted in better predictive capacities [p < 0.05, with an average PVE (proportion of variance explained) value of 0.89 ± 0.02] than linear models (0.79 ± 0.03). For each column, the resulting model was applied to identify leachables from actual plastic packaging samples. An in-depth investigation of the top 20 most intense molecular features revealed that all false-positives could be identified as outliers in the QSRR models (outside of the 95% prediction bands). Furthermore, analyzing a sample on multiple chromatographic columns and applying the associated QSRR models increased the capacity to filter false positives. Such an approach will contribute to a more effective identification of unknown or unexpected leachables in plastics (e.g. non-intended added substances), therefore refining our understanding of the chemical risks associated with food contact materials.

Simultaneous effect of different chromatographic conditions on the chromatographic retention of pentapeptide derivatives (HGRFG and NPNPT)

Introduction: Oligopeptides exhibit great prospects for clinical application and its separation is of great importance in new drug development. Methods: To accurately predict the retention of pentapeptides with analogous structures in chromatography, the retention times of 57 pentapeptide derivatives in seven buffers at three temperatures and four mobile phase compositions were measured via reversed-phase high-performance liquid chromatography. The parameters ( k H A , k A , and p K a ) of the acid-base equilibrium were obtained by fitting the data corresponding to a sigmoidal function. We then studied the dependence of these parameters on the temperature (T), organic modifier composition (φ, methanol volume fraction), and polarity ( P m N parameter). Finally, we proposed two six-parameter models with (1) pH and T and (2) pH and φ or P m N as the independent variables. These models were validated for their prediction capacities by linearly fitting the predicted retention factor k-value and the experimental k-value. Results: The results showed that log k H A and log k A exhibited linear relationships with 1 / T , φ or P m N for all pentapeptides, especially for the acid pentapeptides. In the model of pH and T, the correlation coefficient (R²) of the acid pentapeptides was 0.8603, suggesting a certain prediction capability of chromatographic retention. Moreover, in the model of pH and φ or P m N , the R² values of the acid and neutral pentapeptides were greater than 0.93, and the average root mean squared error was approximately 0.3, indicating that the k-values could be effectively predicted. Discussion: In summary, the two six-parameter models were appropriate to characterize the chromatographic retention of amphoteric compounds, especially the acid or neutral pentapeptides, and could predict the chromatographic retention of pentapeptide compounds.

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.