Assisted Active Learning for Model-Based Method Development in Liquid Chromatography.

In recent decades, there has been a growing interest in fully automated methods for tackling complex optimization problems across various fields. Active learning (AL) and its variant, assisted active learning (AAL), incorporating guidance or assistance from external sources into the learning process, play key roles in this automation by enabling the autonomous selection of optimal experimental conditions to efficiently explore the problem space. These approaches are particularly valuable in situations wherein experimentation is costly or time-consuming. This study explores the application of AAL in model-based method development (MD) for liquid chromatography (LC) by using Bayesian statistics to incorporate historical data and analyte information for the generation of initial retention models. The process involves updating the model parameters based on new experiments, coupled with an active data selection method to choose the most informative experiment to run in a subsequent step. This iterative process balances model exploitation and experimental exploration until a satisfactory separation is achieved. The effectiveness of this approach is demonstrated via two practical examples, resulting in optimized separations in a limited number of experiments by optimizing the gradient slope. It is shown that the ability of AAL to leverage past knowledge and compound information to improve accuracy and reduce experimental runs offers a flexible alternative approach to fixed design methods.

Comprehensive two-dimensional liquid chromatography with high resolution mass spectrometry to investigate the photoelectrochemical degradation of environmentally relevant pharmaceuticals and their degradation products in water.

The widespread presence of organic micropollutants in the environment reflects the inability of traditional wastewater treatment plants to remove them. In this context, advanced oxidation processes (AOPs) have emerged as promising quaternary wastewater treatment technologies since they efficiently degrade recalcitrant components by generating highly reactive free radicals. Nonetheless, the chemical characterization of potentially harmful byproducts is essential to avoid the contamination of natural water bodies with hazardous substances. Given the complexity of wastewater matrices, the implementation of comprehensive analytical methodologies is required. In this work, the simultaneous photoelectrochemical degradation of seven environmentally relevant pharmaceuticals and one metabolite from the EU Watch List 2020/1161 was examined in ultrapure water and simulated wastewater, achieving excellent removal efficiencies (overall >95%) after 180 min treatment. The reactor unit was linked to an online LC sample manager, allowing for automated sampling every 15 min and near real-time process monitoring. Online comprehensive two-dimensional liquid chromatography (LC × LC) coupled with high resolution mass spectrometry (HRMS) was subsequently used to tentatively identify degradation products after photoelectrochemical degradation. Two reversed-phase liquid chromatography (RPLC) columns were used: an SB-C18 column operated with 5 mM ammonium formate at pH 5.8 (1A) and methanol (1B) as the mobile phases in the first dimension and an SB-Aq column using acidified water at pH 3.1 (2A) and acetonitrile (2B) as the mobile phases in the second dimension. This resulted in a five-fold increase in peak capacity compared to one-dimensional LC while maintaining the same total analysis time of 50 min. The LC x LC method allowed the tentative identification of 12 venlafaxine, 7 trimethoprim and 10 ciprofloxacin intermediates. Subsequent toxicity predictions suggested that some of these byproducts were potentially harmful. This study presents an effective hybrid technology for the simultaneous removal of pharmaceuticals from contaminated wastewater matrices and demonstrates how multidimensional liquid chromatography techniques can be applied to better understand the degradation mechanisms after the treatment of micropollutants with AOPs.

A perspective on the use of deep deterministic policy gradient reinforcement learning for retention time modeling in reversed-phase liquid chromatography.

Artificial intelligence and machine learning techniques are increasingly used for different tasks related to method development in liquid chromatography. In this study, the possibilities of a reinforcement learning algorithm, more specifically a deep deterministic policy gradient algorithm, are evaluated for the selection of scouting runs for retention time modeling. As a theoretical exercise, it is investigated whether such an algorithm can be trained to select scouting runs for any compound of interest allowing to retrieve its correct retention parameters for the three-parameter Neue-Kuss retention model. It is observed that three scouting runs are generally sufficient to retrieve the retention parameters with an accuracy (mean relative percentage error MRPE) of 1 % or less. When given the opportunity to select additional scouting runs, this does not lead to a significantly improved accuracy. It is also observed that the agent tends to give preference to isocratic scouting runs for retention time modeling, and is only motivated towards selecting gradient scouting runs when penalized (strongly) for large analysis/gradient times. This seems to reinforce the general power and usefulness of isocratic scouting runs for retention time modeling. Finally, the best results (lowest MRPE) are obtained when the agent manages to retrieve retention time data for % ACN at elution of the compound under consideration that spread the entire relevant range of ACN (5 % ACN to 95 % ACN) as well as possible, i.e., resulting in retention data at a low, intermediate and high % ACN. Based on the obtained results, we believe reinforcement learning holds great potential to automate and rationalize method development in liquid chromatography in the future.

Deep reinforcement learning for the direct optimization of gradient separations in liquid chromatography.

While Reinforcement Learning (RL) has already proven successful in performing complex tasks, such as controlling large-scale epidemics, mitigating influenza and playing computer games beyond expert level, it is currently largely unexplored in the field of separation sciences. This paper therefore aims to introduce RL, specifically proximal policy optimization (PPO), in liquid chromatography, and evaluate whether it can be trained to optimize separations directly, based solely on the outcome of a single generic separation as input, and a reward signal based on the resolution between peak pairs (taking a value between [-1,1]). More specifically, PPO algorithms or agents were trained to select linear (1-segment) or multi-segment (2-, 3-, or 16-segment) gradients in 1 experiment, based on the outcome of an initial, generic linear gradient (ϕstart=0.3, ϕend=1.0, and tg=20min), to improve separations. The size of the mixtures to be separated varied between 10 and 20 components. Furthermore, two agents, selecting 16-segment gradients, were trained to perform this optimization using either 2 or 3 experiments, in sequence, to investigate whether the agents could improve separations further, based on previous outcomes. Results showed that the PPO agent can improve separations given the outcome of one generic scouting run as input, by selecting ϕ-programs tailored to the mixture under consideration. Allowing agents more freedom in selecting multi-segment gradients increased the reward from 0.891 to 0.908 on average; and allowing the agents to perform an additional experiment increased the reward from 0.908 to 0.918 on average. Finally, the agent outperformed random experiments as well as standard experiments (ϕstart=0.0, ϕend=1.0, and tg=20min) significantly; as random experiments resulted in average rewards between 0.220 and 0.283, and standard experiments resulted in average rewards of 0.840. In conclusion, while there is room for improvement, the results demonstrate the potential of RL in chromatography and present an interesting future direction for the automated optimization of separations.

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.

Detailed comparison of in-house developed and commercially available heart-cutting and selective comprehensive two-dimensional liquid chromatography systems.

Recently, two-dimensional liquid chromatography (2D-LC) has become a popular approach to analyze complex samples. This is partly due to the introduction of commercial 2D-LC systems. In the past, 2D-LC was carried out on in-house developed setups, typically consisting of several switching valves and sample loops as the interface between the two dimensions. Commercial systems usually offer different 2D-LC modes in combination with specialized software to operate the instrument and analyze the data. This makes them highly user-friendly, however, at an increased cost compared to in-house developed setups. This study aims to make a comparison between an in-house developed 2D-LC setup and a commercially available 2D-LC instrument. The comparison is made based on experimental differences, in addition to more general differences, including cost price, flexibility, and ease of operation. Special attention is also paid to the different strategies to deal with the mobile phase incompatibility between the highly orthogonal separation mechanisms considered in this work: hydrophilic interaction liquid chromatography (HILIC) and reversed-phase LC (RPLC). For the commercial 2D-LC instrument, this is done using active solvent modulation (ASM), a valve-based approach allowing the on-line dilution of the effluent eluting from the first dimension column before transfer to the second dimension (2D) column. For the in-house developed setup, a combination of restriction capillaries and a trap column is used. Using a sample of 28 compounds with a large polarity range, peak shapes and recoveries of the 2D-chromatograms are compared for both setups. For early eluting compounds, the selective comprehensive approach, currently only possible on the commercial 2D-LC instrument, results in the best peak shapes and recoveries, however, at the cost of an increased analysis time. In general, depending on the analytical goal (single heart-cut versus full-comprehensive 2D-LC), an in-house developed system can be satisfactory for the analysis of specific target compounds/samples. For more complex problems, it can be interesting to use a more specialized commercial 2D-LC instrument. Overall, this comparison study provides advice for analytical scientists, who are considering to use 2D-LC, on the type of equipment to consider, depending on the needs of their particular applications.

Electrochemical degradation of diclofenac generates unexpected thyroidogenic transformation products: Implications for environmental risk assessment.

Diclofenac (DCF) is an environmentally persistent, nonsteroidal anti-inflammatory drug (NSAID) with thyroid disrupting properties. Electrochemical advanced oxidation processes (eAOPs) can efficiently remove NSAIDs from wastewater. However, eAOPs can generate transformation products (TPs) with unknown chemical and biological characteristics. In this study, DCF was electrochemically degraded using a boron-doped diamond anode. Ultra-high performance liquid chromatography coupled with high-resolution mass spectrometry was used to analyze the TPs of DCF and elucidate its potential degradation pathways. The biological impact of DCF and its TPs was evaluated using the Xenopus Eleutheroembryo Thyroid Assay, employing a transgenic amphibian model to assess thyroid axis activity. As DCF degradation progressed, in vivo thyroid activity transitioned from anti-thyroid in non-treated samples to pro-thyroid in intermediately treated samples, implying the emergence of thyroid-active TPs with distinct modes of action compared to DCF. Molecular docking analysis revealed that certain TPs bind to the thyroid receptor, potentially triggering thyroid hormone-like responses. Moreover, acute toxicity occurred in intermediately degraded samples, indicating the generation of TPs exhibiting higher toxicity than DCF. Both acute toxicity and thyroid effects were mitigated with a prolonged degradation time. This study highlights the importance of integrating in vivo bioassays in the environmental risk assessment of novel degradation processes.