Bayesian optimization of comprehensive two-dimensional liquid chromatography separations

A new chromatographic response function with automatically adapting weight factor for automated method development

A critical factor for automated method development in chromatography is the maximization or minimization of an objective function describing the quality (and speed) of the separation. In chromatography, this function is commonly referred to as a chromatographic response function (CRF). Many CRFs have previously been introduced, but many have unfavourable properties such as featuring multiple optima, insufficient discriminatory power, and a too strong dependence on the weight factors needed to balance resolution and time penalty components. To overcome these problems, the present study introduces a new type of CRF wherein the relative weight of the time penalty term is a self-adaptive function of the separation quality. The ability to unambiguously identify the optimal gradient settings of this newly proposed CRF is compared to that of some of the most frequently used CRFs in a study covering 100 randomly composed in silico samples. Doing so, the new CRF is found to flawlessly lead to the correct solution (=linear gradient parameters providing the highest resolution in the shortest potential time) in 100 % of the cases, while the most frequently used literature CRFs were off-target for about 50 to 60 % of the samples, even when considering the availability of spectral peak shape data. Some slight alterations to the proposed CRF are introduced and discussed as well.

Enhancing LC×LC separations through multi-task Bayesian optimization

Method development in comprehensive two-dimensional liquid chromatography (LC×LC) is a challenging process. The interdependencies between the two dimensions and the possibility of incorporating complex gradient profiles, such as multi-segmented gradients or shifting gradients, make trial-and-error method development time-consuming and highly dependent on user experience. Retention modeling and Bayesian optimization (BO) have been proposed as solutions to mitigate these issues. However, both approaches have their strengths and weaknesses. On the one hand, retention modeling, which approximates true retention behavior, depends on effective peak tracking and accurate retention time and width predictions, which are increasingly challenging for complex samples and advanced gradient assemblies. On the other hand, Bayesian optimization may require many experiments when dealing with many adjustable parameters, as in LC×LC. Therefore, in this work, we investigate the use of multi-task Bayesian optimization (MTBO), a method that can combine information from both retention modeling and experimental measurements. The algorithm was first tested and compared with BO using a synthetic retention modeling test case, where it was shown that MTBO finds better optima with fewer method-development iterations than conventional BO. Next, the algorithm was tested on the optimization of a method for a pesticide sample and we found that the algorithm was able to improve upon the initial scanning experiments. Multi-task Bayesian optimization is a promising technique in situations where modeling retention is challenging, and the high number of adjustable parameters and/or limited optimization budget makes traditional Bayesian optimization impractical.

OptiMS: An Accessible Program for Automating Mass Spectrometry Parameter Optimization and Configuration

Mass spectrometers have an enormous number of user-changeable parameters that drastically affect the observed mass spectrum. Using optimal parameters can significantly improve mass spectrometric data by increasing signal stability and signal-to-noise ratio, which decreases the limit of detection, thus revealing previously unobservable species. However, ascertaining optimal parameters is time-consuming, tedious, and made further challenging by the fact that parameters can act dependently on each other. Consequently, suboptimal parameters are frequently used during characterization, reducing the quality of results. OptiMS, an open-source, cross-platform program, was developed to simplify, accelerate, and more accurately determine optimal mass spectrometer parameters for a given system. It addresses common difficulties associated with existing software such as slow performance, high costs, and limited functionality. OptiMS efficacy was demonstrated through its application to multiple systems, quickly and successfully optimizing instrument parameters unassisted to maximize a user-defined metric, such as the intensity of a particular analyte. Additionally, among other features, OptiMS allows running of a sequence of predefined parameter configurations, reducing the workload of users wishing to obtain mass spectra under multiple sets of conditions.

Simulation of gas chromatographic separations and estimation of distribution-centric retention parameters using linear solvation energy relationships

For method development in gas chromatography, suitable computer simulations can be very helpful during the optimization process. For such computer simulations retention parameters are needed, that describe the interaction of the analytes with the stationary phase during the separation process. There are different approaches to describe such an interaction, e.g. thermodynamic models like Blumberg's distribution-centric 3-parameter model (K-centric model) or models using chemical properties like the Linear Solvation Energy Relationships (LSER). In this work LSER models for a Rxi-17Sil MS and a Rxi-5Sil MS GC column are developed for different temperatures. The influences of the temperature to the LSER system coefficients are shown in a range between 40 and 200 °C and can be described with Clark and Glew's ABC model as fit function. A thermodynamic interpretation of the system constants is given and its contribution to enthalpy and entropy is calculated. An estimation method for the retention parameters of the K-centric model via LSER models were presented. The predicted retention parameters for a selection of 172 various compounds, such as FAMEs, PCBs and PAHs are compared to isothermal determined values. 40 measurements of temperature programmed GC separations are compared to computer simulations using the differently determined or estimated K-centric retention parameters. The mean difference (RSME) between the measured and predicted retention time is less than 8 s for both stationary phases using the isothermal retention parameters. With the LSER predicted parameters the difference is 20 s for the Rxi-5Sil MS and 38 s for the Rxi-17Sil MS. Therefore, the presented estimation method can be recommended for first method development in gas chromatography.

Automated method development in high-pressure liquid chromatography

Method development in liquid chromatography is a crucial step in the optimization of analytical separations for various applications. However, it is often a challenging endeavour due to its time-consuming, resource intensive and costly nature, which is further hampered by its complexity requiring highly skilled and experienced scientists. This review presents an examination of the methods that are required for a completely automated method development procedure in liquid chromatography, aimed at taking the human out of the decision loop. Some of the presented approaches have recently witnessed an important increase in interest as they offer the promise to facilitate, streamline and speed up the method development process. The review first discusses the mathematical description of the separation problem by means of multi-criteria optimization functions. Two different strategies to resolve this optimization are then presented; an experimental and a model-based approach. Additionally, methods for automated peak detection and peak tracking are reviewed, which, upon integration in an instrument, allow for a completely closed-loop method development process. For each of these approaches, various currently applied methods are presented, recent trends and approaches discussed, short-comings pointed out, and future prospects highlighted.

Computer-driven optimization of complex gradients in comprehensive two-dimensional liquid chromatography

Method development in comprehensive two-dimensional liquid chromatography (LC × LC) is a complicated endeavor. The dependency between the two dimensions and the possibility of incorporating complex gradient profiles, such as multi-segmented gradients or shifting gradients, renders method development by "trial-and-error" time-consuming and highly dependent on user experience. In this work, an open-source algorithm for the automated and interpretive method development of complex gradients in LC × LC-mass spectrometry (MS) was developed. A workflow was designed to operate within a closed-loop that allowed direct interaction between the LC × LC-MS system and a data-processing computer which ran in an unsupervised and automated fashion. Obtaining accurate retention models in LC × LC is difficult due to the challenges associated with the exact determination of retention times, curve fitting because of the use of gradient elution, and gradient deformation. Thus, retention models were compared in terms of repeatability of determination. Additionally, the design of shifting gradients in the second dimension and the prediction of peak widths were investigated. The algorithm was tested on separations of a tryptic digest of a monoclonal antibody using an objective function that included the sum of resolutions and analysis time as quality descriptors. The algorithm was able to improve the separation relative to a generic starting method using these complex gradient profiles after only four method-development iterations (i.e., sets of chromatographic conditions). Further iterations improved retention time and peak width predictions and thus the accuracy in the separations predicted by the algorithm.

Closed-loop automatic gradient design for liquid chromatography using Bayesian optimization

Contemporary complex samples require sophisticated methods for full analysis. This work describes the development of a Bayesian optimization algorithm for automated and unsupervised development of gradient programs. The algorithm was tailored to LC using a Gaussian process model with a novel covariance kernel. To facilitate unsupervised learning, the algorithm was designed to interface directly with the chromatographic system. Single-objective and multi-objective Bayesian optimization strategies were investigated for the separation of two complex (n>18, and n>80) dye mixtures. Both approaches found satisfactory optima in under 35 measurements. The multi-objective strategy was found to be powerful and flexible in terms of exploring the Pareto front. The performance difference between the single-objective and multi-objective strategy was further investigated using a retention modeling example. One additional advantage of the multi-objective approach was that it allows for a trade-off to be made between multiple objectives without prior knowledge. In general, the Bayesian optimization strategy was found to be particularly suitable, but not limited to, cases where retention modelling is not possible, although its scalability might be limited in terms of the number of parameters that can be simultaneously optimized.

Vibration prediction and analysis of strip rolling mill based on XGBoost and Bayesian optimization

The stable operation of strip rolling mill is the key factor to ensure the stability of product quality. The design capability of existing domestic imported and self-developed strip rolling mills cannot be fully developed, and the frequent occurrence of mill vibration and operation instability problems seriously restrict the equipment capacity and the production of high-end strip products. The vibration prediction analysis method for hot strip mill based on eXtreme gradient boosting (XGBoost) and Bayesian optimization (BO) is proposed. First, an XGBoost prediction model is developed based on a self-built data set to construct a complex functional relationship between process parameters and rolling mill vibration. Second, the important hyperparameters and parameters of XGBoost are optimized using Bayesian optimization algorithm to improve the prediction accuracy, computational efficiency, and stability of the model. Third, a comprehensive comparison is made between the prediction model in this paper and other well-known machine learning benchmark models. Finally, the prediction results of the model are interpreted using the SHapley Additive exPlanations (SHAP) method. The proposed model outperforms existing models in terms of prediction accuracy, computational speed and stability. At the same time, the degree of influence of each feature on rolling mill vibration is also obtained.

Perspectives on the Use of Retention Modeling to Streamline 2D-LC Method Development: Current State and Future Prospects

The history of multidimensional liquid chromatography (MDLC) has been dominated by methods that have been developed using highly empirical, experience-driven, trial-and-error approaches. These approaches have been sufficient in progressing the field forward scientifically, primarily in academic research laboratories. However, more widespread usage of multidimensional separations will require more systematic approaches to method development that rely less on user experience and lower the barriers to development and use of methods by a wider community of users. In this mini-review, we discuss recent research aimed at developing such systematic, model-driven approaches to streamline method development and speculate about likely advances in the same direction in the near future. It seems likely that such model-driven approaches would be particularly helpful for methods developed for analyzing biopharmaceutical molecules, which tend to be very sensitive to slight changes in method conditions (for example, mobile phase composition).