<p><strong>🎤Dr. Steven Weinman </strong>(Associate Professor of Chemical and Biological Engineering at the University of Alabama)</p><p><strong>Steven shares his journey from chemical engineering student to membrane researcher, and explains how membranes are used not only for water purification, but also for sample preparation, pre-treatment, and concentration in analytical workflows. The conversation dives deep into PFAS removal, nanofiltration vs. reverse osmosis, and how chromatography and mass spectrometry are essential for validating membrane performance.</strong></p><h4><strong>Key topics discussed include:</strong></h4><ul><li>How membranes function as separation and concentration tools</li><li>Nanofiltration vs. reverse osmosis for salts and PFAS</li><li>The role of chromatography (LC-MS, GC-MS, ion chromatography) in verifying contaminant removal</li><li>Challenges in scaling academic separation technologies to industry</li><li>Sustainability in membrane manufacturing and PFAS-related regulations</li><li>Training students to balance fundamental science with real-world applications</li></ul><p>Whether you work in environmental analysis, chromatography, mass spectrometry, water quality, or separation science, this episode provides valuable insight into how different separation technologies complement each other—and where the field is heading next.</p><h3><strong>Video Transcription</strong></h3><h4><strong>Introduction</strong></h4><p>Membrane-based separations have become a central part of modern water treatment and resource recovery, offering energy-efficient routes for purification, concentration, and selective contaminant removal. In this discussion, Stephen reflects on his path into chemical engineering and membrane science, then explores how membrane technologies fit within broader separation science, how selectivity is designed into membrane systems, and why translation from academic research to industrial deployment remains challenging.</p><p>His perspective spans both fundamental membrane science and practical engineering, with particular emphasis on water treatment, contaminant removal, sustainable membrane manufacturing, and the realities of research funding and scale-up.</p><h4><strong>From Chemical Engineering to Membrane Research</strong></h4><p>Stephen’s route into membrane science began indirectly. Although his early interests were far removed from chemical engineering, he found himself drawn to chemistry and mathematics during high school, which led him to pursue chemical engineering at the University of Kentucky. His first direct exposure to research came through a cooperative placement with a university-affiliated research institute, where he worked on ceramic membrane systems for coal-fired power plant applications.</p><p>That experience introduced him to bench-scale research, scientific literature, and technical presentation, while also clarifying that research was more appealing to him than traditional industrial internships. He subsequently joined the laboratory of a membrane scientist at the University of Kentucky, where he began working on polymeric membranes for water treatment. This set the direction for graduate study, ultimately leading him to Clemson University, where he pursued PhD research on antifouling membranes using surface chemistry and patterning approaches.</p><p>Although his original career plan had been to join a membrane company after graduate school, that trajectory changed late in his doctoral training. Encouragement from colleagues and family led him to consider academia, where he could define his own research questions and continue mentoring students. He joined the University of Alabama immediately after graduation and has since built a research program focused on water treatment problems using membranes, solvents, and polymer-based sorbents.</p><h4><strong>Membrane Separation in the Broader Context of Analytical and Separation Science</strong></h4><p>Stephen frames membranes as one tool within a broader separation science landscape. Their role depends entirely on the feed composition, the desired product stream, and the ultimate process objective. In some cases, membranes are ideal for concentrating target species or dewatering mixtures. In others, they serve as pretreatment tools, removing particulates, unwanted macromolecules, or selected contaminants before downstream analytical or processing steps.</p><p>This logic parallels broader analytical workflows, including chromatographic and spectrometric methods, where sample preparation and matrix simplification are often critical. Even very routine laboratory operations, such as syringe filtration, rely on membrane principles. In that sense, membranes are already embedded in many analytical workflows, even when they are not the primary focus.</p><p>He also points out that certain membrane-based systems can begin to overlap conceptually with chromatographic approaches, particularly in applications such as protein and biologics purification, where membrane adsorbers and membrane chromatography can provide high-throughput alternatives to conventional packed columns.</p><h4><strong>Membrane Selectivity: Matching the Separation to the Problem</strong></h4><p>A recurring theme in the discussion is that membrane selection is application-specific. The right membrane depends on what must be retained, what must pass through, and whether the goal is purification, concentration, or fractionation.</p><p>Stephen distinguishes between several broad classes of membranes. Microfiltration and ultrafiltration operate largely through size exclusion, although charge effects may still contribute. These are useful when target species differ sufficiently in size. At the more selective end, nanofiltration and reverse osmosis are used for salts, small molecules, and persistent contaminants. Nanofiltration is often well suited for rejecting divalent ions while allowing more monovalent ions to pass, whereas reverse osmosis is required when more complete salt rejection is necessary.</p><p>For contaminants such as PFAS, nanofiltration can reject a substantial fraction of compounds, although shorter-chain and smaller species are more difficult. Reverse osmosis offers broader rejection, but also with higher pressure requirements. This highlights a central engineering tradeoff: tighter selectivity generally requires higher energy input.</p><p>He emphasizes that membrane systems always produce at least two streams: a permeate stream and a retentate or concentrate stream. Designing the separation therefore requires consideration not only of product quality but also of what happens to the reject stream. In many cases this becomes a waste stream; in others, it may represent a concentrated resource that requires additional processing or recovery.</p><h4><strong>Advances in Membrane Materials and System Performance</strong></h4><p>Over the course of more than a decade in membrane science, Stephen has seen important improvements in commercial membrane technology, particularly in the area of lower-pressure reverse osmosis. Traditionally, reverse osmosis has required higher operating pressures than nanofiltration. Recent developments have reduced that burden, allowing similar water productivity at lower pressure or smaller membrane area for a given throughput.</p><p>These advances matter because they reduce either energy demand or plant footprint, both of which are significant in industrial and municipal treatment systems. While pressure recovery devices have also improved overall system efficiency, he distinguishes those engineering gains from the membrane materials themselves.</p><p>On the research side, he highlights the emergence of membrane adsorbers and related hybrid technologies that can support faster, higher-throughput separations than conventional column-based workflows. These have gained particular traction in the purification of proteins and biologics, although he suggests that similar concepts may become increasingly relevant in water treatment and selective ion or molecule recovery.</p><h4><strong>Chromatography and Mass Spectrometry as Tools for Membrane Research</strong></h4><p>Although many membrane processes target relatively simple separations such as desalination, more advanced membrane studies increasingly rely on analytical chemistry for validation and mechanistic insight. Stephen describes how chromatographic and mass spectrometric methods are essential when the separation targets are more complex than salts.</p><p>His group uses ion chromatography for specific ionic analytes, as well as GC-MS and electrospray-based methods for organic compounds and degradation products. One recent example involved a biocatalytic membrane designed to degrade phthalates, where GC-MS was used to detect both the parent phthalate and the resulting breakdown products. In such cases, analytical methods are not merely confirmatory; they are central to demonstrating that the membrane or membrane-coupled system is functioning as intended.</p><p>This reinforces the idea that membrane science and analytical chemistry are closely linked in emerging applications, especially where contaminant transformation, trace-level detection, or selective removal must be verified rigorously.</p><h4><strong>The Difficulty of Scale-Up</strong></h4><p>One of the most substantial barriers in membrane research is translation from academic bench-scale work to industrial or municipal scale. Stephen identifies two major constraints: time and cost.</p><p>Academic demonstrations often rely on reaction steps, modification procedures, or fabrication methods that work well on the laboratory scale but are far too slow for industrial practice. A protocol that takes hours or days in a research setting is rarely attractive to a manufacturer seeking cycle times measured in seconds or minutes. Likewise, materials that seem acceptable at gram scale may be prohibitively expensive at production scale, although the reverse may also be true if bulk pricing is favorable.</p><p>The more fundamental challenge is that academic research is not usually funded to perform pilot-scale development. The mission is often centered on fundamental science and student training, not industrial process engineering. Moving from proof-of-concept to deployable technology requires time, equipment, space, and funding that many university laboratories simply do not have.</p><p>For this reason, Stephen sees academia’s main role as laying the conceptual and technical groundwork. If a technology shows promise, the ideal outcome is that an industrial partner, start-up, or other translational pathway takes it further. In some cases, research can be designed from the start with scalability in mind. He cites current work on reverse osmosis membrane additives as an example, where the goal is not to reinvent membrane fabrication but to introduce a change that could plausibly fit existing manufacturing workflows.</p><h4><strong>Sustainability and Greener Membrane Science</strong></h4><p>Membrane processes themselves are often relatively energy efficient compared with thermal separations, but Stephen notes that membrane manufacturing still has significant room for improvement. Conventional membrane fabrication often relies on hazardous, petroleum-derived solvents, and one area of active research is the substitution of greener or bio-based alternatives.</p><p>Another direction is the use of waste plastics as feedstock for membrane fabrication. The rationale is pragmatic: if such plastics are already present in the environment, converting them into membranes may extend their useful lifetime and partially offset their environmental burden. More biodegradable or less petroleum-dependent polymers are also attractive, but they must still meet cost and performance requirements.</p><p>He also discusses an important regulatory issue involving polyvinylidene fluoride (PVDF), one of the most widely used membrane polymers. Debate over whether it should be treated as a PFAS-related material could have major implications for membrane manufacturing and use. From his perspective, classifying PVDF in that way would create significant disruption, especially given its central role in current membrane systems.</p><h4><strong>Funding, Student Training, and the Academic Mission</strong></h4><p>The final part of the discussion turns to the academic research environment itself. Stephen emphasizes that the most important responsibility of his laboratory is not simply generating new membrane concepts, but training students and ensuring that they can complete their degrees in a supportive research environment.</p><p>Funding uncertainty directly affects that mission. Reduced proposal success rates make it harder to maintain the number of graduate students needed for a healthy research group. This has implications beyond immediate staffing. Laboratories function best when experienced students train newer members, creating continuity in methods, culture, and technical knowledge. If groups shrink too far, that continuity is lost.</p><p>He views graduate research as both education and work experience. Students are not only learning theory; they are learning how to think as researchers, solve open-ended problems, and contribute to technologies that may eventually benefit industry. From that perspective, sustaining student support is one of the most important parts of maintaining a strong academic research ecosystem.</p><h4><strong>Conclusion</strong></h4><p>Stephen presents membrane science as a field that sits at the intersection of chemical engineering, separation science, and analytical chemistry. Membranes are already deeply integrated into both industrial treatment and laboratory workflows, but their future depends on continued progress in selectivity, sustainability, and manufacturability.</p><p>At the same time, the discussion makes clear that technical performance alone is not enough. For membrane technologies to move from the laboratory to practice, they must be scalable, economically realistic, and supported by strong analytical validation. Academic laboratories can provide the foundational science and early demonstrations, but broader adoption depends on partnerships, funding, and translational effort.</p><p>Perhaps most importantly, the conversation highlights that advances in membrane science are inseparable from the students and researchers who carry them forward. In that sense, the future of separations depends not only on materials and methods, but also on sustaining the people who develop them.</p><blockquote><p><strong>This text has been automatically transcribed from a video presentation using AI technology. It may contain inaccuracies and is not guaranteed to be 100% correct.</strong></p></blockquote><blockquote><h4><strong>Concentrating on Chromatography Podcast</strong></h4><p>Dive into the frontiers of chromatography, mass spectrometry, and sample preparation with host David Oliva. Each episode features candid conversations with leading researchers, industry innovators, and passionate scientists who are shaping the future of analytical chemistry. From decoding PFAS detection challenges to exploring the latest in AI-assisted liquid chromatography, this show uncovers practical workflows, sustainability breakthroughs, and the real-world impact of separation science. Whether you’re a chromatographer, lab professional, or researcher you'll discover inspiring content!</p><p>You can find <strong>Concentrating on Chromatography Podcast </strong>in podcast apps:</p><ul><li><a target="_blank" rel="noopener noreferrer" href="https://open.spotify.com/show/1wZg67rCjoGju4yhqxI3tL"><strong>Spotify</strong></a></li><li><a target="_blank" rel="noopener noreferrer" href="https://podcasts.apple.com/tz/podcast/concentrating-on-chromatography/id1788429185"><strong>Apple podcast</strong></a></li><li><a target="_blank" rel="noopener noreferrer" href="https://podscan.fm/podcasts/concentrating-on-chromatography"><strong>podscan</strong></a></li></ul><p>and on <a target="_blank" rel="noopener noreferrer" href="https://www.youtube.com/@ChromatographyTalk/videos"><strong>YouTube channel</strong></a></p></blockquote>

Selective Separations: What Membrane Science Can Teach Chromatographers

<p><strong>This study introduces LCMS-Net, a deep learning model designed for direct analysis of raw LC-HRMS data without the need for manual preprocessing. By modeling spatial features of the data, the approach improves reproducibility and detection performance in untargeted metabolomics workflows.</strong></p><p>LCMS-Net demonstrated improved performance in forensic cause-of-death screening and colon cancer detection, outperforming existing methods while reducing batch effects across instruments. Its simplified architecture and lack of pretraining requirements enable faster and more efficient data analysis, highlighting its potential for routine metabolomics and forensic applications.</p><blockquote><h4><strong>The original article</strong></h4><h4><a target="_blank" rel="noopener noreferrer" href="https://pubs.acs.org/doi/10.1021/acs.analchem.5c05404"><strong>LCMS-Net: Deep Learning for Raw High Resolution Mass Spectrometry Data Applied to Forensic Cause-of-Death Screening</strong></a></h4><p>Lisa M. Menacher, Liam J. Ward, Fredrik Heintz, Henrik Green, and Oleg Sysoev*</p><p>Anal. Chem. 2026, 98, 9, 6589–6597</p><p><a target="_blank" rel="noopener noreferrer" href="https://doi.org/10.1021/acs.analchem.5c05404">https://doi.org/10.1021/acs.analchem.5c05404</a></p><h6>licensed under <a target="_blank" rel="noopener noreferrer" href="https://creativecommons.org/licenses/by/4.0/"><strong>CC-BY 4.0</strong></a></h6></blockquote><p><strong>Selected sections from the article follow. Formats and hyperlinks were adapted from the original.</strong></p><div><p>Metabolomics is the study of all low-molecular-weight substances in a biological specimen. <a href="javascript:void(0);">(1)</a> As this is closely linked to cellular functions and biochemical processes, it offers a comprehensive view of the current physiological state of an organism. This makes metabolomics a promising tool for a broad range of applications, including diagnostics, precision medicine, and toxicology. <a href="javascript:void(0);">(1−3)</a> However, large-scale large-scale liquid chromatography-high resolution mass spectrometry (LC-HRMS) studies are difficult due to the complex and labor-intensive data preprocessing. This typically involves peak picking, peak alignment, gap filling, and normalization, to simplify the data structure, extract biologically relevant features, and improve the interpretability for subsequent analyses. <a href="javascript:void(0);">(4−7)</a> Although tools like XCMS or MZmine offer widely used implementations of this workflow, the preprocessing of LC-HRMS data remains challenging, for a number of reasons: (1) The preprocessing of LC-HRMS data can be time-consuming due to computational constraints for large datasets. <a href="javascript:void(0);">(4,8,9)</a> (2) Domain knowledge is necessary to select suitable parameters for the used preprocessing software, and thus to obtain reliable features. <a href="javascript:void(0);">(4,7,8)</a> (3) The reproducibility of the extracted features is often limited across software libraries, especially for low-abundant metabolites. <a href="javascript:void(0);">(4,8)</a> (4) Preprocessing tools may fail to detect some metabolites entirely, resulting in the loss of potentially important information. <a href="javascript:void(0);">(4)</a></p><p>In the past few years, deep learning models have emerged as promising alternatives to the traditional preprocessing workflow for LC-HRMS data. While many publications in this field have been focused on enhancing a particular step of the preprocessing, such as peak identification or peak alignment, end-to-end deep learning has also gained popularity. <a href="javascript:void(0);">(9,10)</a> In end-to-end deep learning, a model is trained to extract useful information directly from raw data without explicit feature engineering. Often, this is less time-consuming than conventional methods and improves the predictive accuracy of the downstream task. This was demonstrated by Cadow et al., who converted raw MS data from prostate biopsies into pseudoimages through binning. They then applied pretrained deep learning models for image processing to extract feature vectors from the pseudoimages and trained a classifier to discriminate between tumor and healthy cases. <a href="javascript:void(0);">(11)</a> A similar approach was also used by Shen et al. to predict the gestational age of pregnant women. To address data scarcity, they proposed a data augmentation strategy that simulates retention time (RT) drifts during the data acquisition. As a result, several pseudoimages can be produced from a single LC-HRMS sample, which substantially increases the size of the training set. <a href="javascript:void(0);">(12)</a> Furthermore, Wang et al. developed an end-to-end deep learning model to detect esophageal squamous cell carcinoma based on raw LC-HRMS data. By decomposing a sample into multiple tiles instead of just one down-scaled pseudoimage, their approach preserves more details of the raw LC-HRMS data. <a href="javascript:void(0);">(13)</a> Most recently, Deng et al. used an ensemble of pretrained image classification models for lung cancer detection. Their approach enables more robust predictions for multiclass classification tasks. Furthermore, model explainability was addressed through the analysis of contributing factors. <a href="javascript:void(0);">(14)</a> Although, these studies collectively highlight the potential of end-to-end deep learning for metabolomics-based analyses, they also show its limitations. For example, the use of pretrained architectures for image classification may be flawed due to the substantially different topology of LC-HRMS data and natural images. Natural images typically contain hierarchically structured objects with geometrical properties such as size or patterns while objects in LC-HRMS pseudoimages are essentially represented as one-dimensional peaks along the retention time axis and are sharply localized in <i>m</i>/<i>z</i>-value. <a href="javascript:void(0);">(6,15)</a> Existing deep learning methods for metabolomics primarily use 2D-convolutions and thus do not take into account such spatial properties of LC-HRMS data. Consequently, there remains a need for more robust methods that are specifically tailored to LC-HRMS data. This is particularly relevant for real-world applications, where batch effects and diverse study populations are common and difficult to mitigate.</p><p>This study presents LCMS-Net, a fully automated end-to-end deep learning model for the analysis of LC-HRMS data. By directly processing the raw data and taking into account its spatial properties by using 1D-convolutions, LCMS-Net mitigates the need for time-intensive, manual feature engineering and improves the classification performance of downstream tasks. This is demonstrated through comprehensive benchmarking for two different applications, forensic CoD screening and colon cancer detection. To the best of our knowledge, it is the first time end-to-end deep learning is applied to post-mortem metabolomics and in the context of forensic science. Furthermore, LCMS-Net achieves robust results even in the presence of severe batch effects, as shown by training and evaluating the CoD screening model with data from different measurement instruments. Lastly, LCMS-Net does not rely on large pretrained deep learning models, and thus requires less computational resources than previous end-to-end learning approaches for the analysis of LC-HRMS data.</p><h4><strong>Methods</strong></h4><h5><strong>Cause-of-Death Screening Dataset</strong></h5><p>The cause-of-death screening study was approved by the Swedish Ethical Review Authority (Dnr 2019–04530 &amp; Dnr 2025–0249–02). All samples were collected from autopsy cases admitted to the Swedish National Board of Forensic Medicine between July 2017 and December 2024, which had undergone routine toxicological screening via HRMS. Screening was performed from femoral whole blood samples, in accordance with standardized procedures reported previously. <a href="javascript:void(0);">(32)</a> Sample separation was performed using gradient elution on a C18 column (150 mm × 2.1 mm, 1.8 μm; <a target="_blank" rel="noopener noreferrer" href="https://lcms.labrulez.com/products/1952"><strong>Waters Acquity HSS T3 column</strong></a>, Water Sverige AB, Sweden). MS-data was collected in positive mode and the total acquisition time for each sample was 12 min. Samples admitted between July 2017 and November 2020 were run using an <a target="_blank" rel="noopener noreferrer" href="https://lcms.labrulez.com/library?mainauthorItems=10&amp;search=6540+Q-TOF"><strong>Agilent 6540 Q-TOF system</strong></a> in MS-mode only, and samples admitted afterward using an <a target="_blank" rel="noopener noreferrer" href="https://lcms.labrulez.com/library?mainauthorItems=10&amp;search=6546+Q-TOF"><strong>Agilent 6546 Q-TOF system</strong></a> with data-dependent acquisition mode (autoMSMS). Aside from these differences in acquisition strategy, source settings and TOF parameters (e.g., gas temperatures, voltages, and mass ranges) were kept consistent between platforms. Henceforth, we will refer to the former as <i>Dataset A</i> and the latter as <i>Dataset B</i> for clarity.</p><p>Dataset A was primarily used for the implementation and evaluation of LCMS-Net and includes 4282 autopsy cases processed in over 641 analytical runs. All cases belong to one of the following five CoD groups: acidosis (<i>n</i> = 100), drug intoxication (<i>n</i> = 1385), ischemic heart disease (IHD) (<i>n</i> = 1362), hanging (<i>n</i> = 1200), and pneumonia (<i>n</i> = 235). A detail summary of the inclusion criteria and study population was previously described by Ward et al. <a href="javascript:void(0);">(26)</a> Dataset B was used to evaluate the sensitivity of LCMS-Net to batch effects and includes additional 5485 autopsy cases with the same inclusion criteria and CoD groups as Dataset A.</p><h4><strong>Overview of LCMS-Net</strong></h4><p>LCMS-Net is a end-to-end deep learning model for the analysis of raw LC-HRMS data. First, a data preparation pipeline transforms the raw LC-HRMS data into pseudoimages. Afterward, convolutional neural networks (CNNs) specifically designed to take the spatial properties of LC-HRMS data into account are used to extract relevant features for the downstream task. <a target="_blank" rel="noopener noreferrer" href="https://pubs.acs.org/doi/10.1021/acs.analchem.5c05404#fig1">Figure 1</a> shows an overview of this workflow for CoD screening, as well as the architecture of LCMS-Net.</p><p><img src="https://storage.googleapis.com/labrulez-bucket-strapi-h3hsga3/Anal_Chem_2026_98_9_6589_6597_Figure_1_Overview_of_LCMS_Net_applied_to_Co_D_screening_6db285c40d.jpg" alt="Anal. Chem. 2026, 98, 9, 6589–6597: Figure 1. Overview of LCMS-Net applied to CoD screening. Binning is used to reduce the size of the raw LC-HRMS data and to ensure equally shaped input matrices. Afterward, the input matrices are processed by an ensemble of 1D-CNNs consisting of a depthwise 1D convolutional layer, followed by max pooling and spatial dropout. The results of the CNNs are flattened and dense layers are used to predict the class labels of the input data." srcset="https://storage.googleapis.com/labrulez-bucket-strapi-h3hsga3/thumbnail_Anal_Chem_2026_98_9_6589_6597_Figure_1_Overview_of_LCMS_Net_applied_to_Co_D_screening_6db285c40d.jpg 238w," sizes="100vw" width="1500" height="986"></p><h4><strong>Results and Discussion</strong></h4><h5><strong>Evaluation of Prediction Performance for CoD Screening</strong></h5><p>First, LCMS-Net was evaluated on the CoD screening dataset (Dataset A). <a target="_blank" rel="noopener noreferrer" href="https://pubs.acs.org/doi/10.1021/acs.analchem.5c05404#fig2">Figure 2</a> shows the results of the model comparison for the CoD screening dataset. With an average accuracy of 70.8%, LCMS-Net outperformed all four benchmark models trained on preprocessed LC-HRMS data. In comparison, our previously published OPLS-DA model for CoD screening achieved only 65.0% accuracy (<i>p</i>-value = 0.0010). Furthermore, LCMS-Net also achieved a better F1-score and sensitivity than these models, while maintaining a high specificity score. The deep learning benchmark model, DeepMSProfiler, achieved a similar accuracy to LCMS-Net. However, LCMS-Net outperformed DeepMSProfiler in terms of both F1-score (<i>p</i>-value = 0.0122) and sensitivity (<i>p</i>-value = 0.0010). This indicates that our method maintains a better balance between true positives and false positives across the five CoD groups, which is especially important for high-stakes applications like forensic science. It should be noted that traditional cross-validation was used for the estimation of p-values, as our purpose was to compare models with fixed hyperparameters. When instead comparing frameworks (e.g., RF vs SVM), nested cross-validation would be more appropriate.</p><p><img src="https://storage.googleapis.com/labrulez-bucket-strapi-h3hsga3/Anal_Chem_2026_98_9_6589_6597_Figure_2_Evaluation_of_Co_D_screening_prediction_performance_of_LCMS_Net_in_comparison_to_benchmark_models_11eef68bb7.jpg" alt="Anal. Chem. 2026, 98, 9, 6589–6597: Figure 2. Evaluation of CoD screening prediction performance of LCMS-Net in comparison to benchmark models. The prediction performance of a classifier is measured by accuracy, macro F1-score, macro sensitivity, and macro specificity over five model runs. The error bars represent the standard deviations between model runs." srcset="https://storage.googleapis.com/labrulez-bucket-strapi-h3hsga3/thumbnail_Anal_Chem_2026_98_9_6589_6597_Figure_2_Evaluation_of_Co_D_screening_prediction_performance_of_LCMS_Net_in_comparison_to_benchmark_models_11eef68bb7.jpg 245w," sizes="100vw" width="1500" height="709"></p><p>Notably, LCMS-Net achieves its high classification performance without pretraining on natural images. This shows that although transfer learning is often useful, it may fail if the source (e.g., natural images) and target data distribution (e.g., LC-HRMS data) are too different. Such domain mismatch can lead to negative transfer, where features from a pretrained model negatively impact the classification performance of the downstream task, resulting in a lower accuracy than training a simpler model from scratch. <a href="javascript:void(0);">(42)</a> By employing an architecture tailored to LC-HRMS data, LCMS-Net is also computationally more efficient, with fewer than 500,000 trainable parameters compared to over 7 million trainable parameters in DeepMSProfiler. <a href="javascript:void(0);">(14)</a> This makes our method accessible to researchers with limited computational resources.</p><h5><strong>Application for Colon Cancer Detection</strong></h5><p>Lastly, we have tested the potential of LCMS-Net in another application domain, by assessing its prediction performance on the CRC dataset. The cancer detection task has been previously used by Deng et al. to show that DeepMSProfiler can be successfully applied to different application areas, making it a suitable benchmark task. We trained a separate instance of LCMS-Net for the model evaluation on the CRC dataset due to differences in sample preparation, analytical protocols, and instrument setup compared to the CoD screening dataset. The hyperparameter settings remained unchanged, as we assumed similar structural properties for both datasets.</p><p>LCMS-Net outperforms DeepMSProfiler with an F1-score of 97.3% compared to 95.5% on the colon cancer detection task. Furthermore, sensitivity and specificity improvements of 2.8% were observed. These results underline the relevance of LCMS-Net for other application areas than CoD screening. A detailed overview of the evaluation metrics for the colon cancer prediction can be found in <a target="_blank" rel="noopener noreferrer" href="https://pubs.acs.org/doi/suppl/10.1021/acs.analchem.5c05404/suppl_file/ac5c05404_si_001.pdf">Supporting Table 7</a>.</p><h4><strong>Conclusion</strong></h4><p>Current preprocessing workflows for untargeted metabolomics are often time-consuming, require extensive domain knowledge, lack reproducibility, or fail to detect some metabolites entirely. LCMS-Net offers an alternative end-to-end approach by operating directly on the raw LC-HRMS data and explicitly modeling its spatial properties. The deep learning model enables faster processing and does not require manual parameter selection. Furthermore, it has been shown through two case studies, CoD screening and cancer detection, that our method extracts a higher amount of relevant information from the raw data and thus outperforms existing models for the analysis of metabolomics data. Specifically, LCMS-Net achieves an average F1-score of 65.5% for CoD screening and 97.3% for colon cancer detection. The previous state-of-the-art models achieved 56.1% (OPLS-DA) and 95.5% (DeepMSProfiler) respectively. The prediction performance of LCMS-Net is consistent even when applied to data from different measurement instruments than those used for the training of the deep learning model, showing its robustness toward batch effects. However, the interpretability of LCMS-Net remains limited and future development is needed to assess which metabolites are learned by the model and which remain undetected. Despite this, LCMS-Net opens up new opportunities for large-scale analyses of LC-HRMS data, potentially driving innovation across numerous application domains.</p></div>

LCMS-Net: Deep Learning for Raw High Resolution Mass Spectrometry Data Applied to Forensic Cause-of-Death Screening

<p><strong>In the week of April 20, the following webinars await you in the field of liquid phase and especially HPLC and LC/MS.</strong></p><blockquote><h4><a target="_blank" rel="noopener noreferrer" href="https://lcms.labrulez.com/webinars"><strong>👉 DETAILS AND REGISTRATION IN THE WEBINARS SECTION</strong></a></h4><p><strong>👉 Search and filter in the largest global database</strong> with over <strong>5 500 GC, LC, MS and spectroscopy webinars</strong>.</p></blockquote><h5><strong>1. Metrohm: Copper deposition baths: Advanced analytical solutions for development and monitoring</strong></h5><ul><li>Tu, 21.4.2026 09:00 CEST</li><li><a target="_blank" rel="noopener noreferrer" href="https://lcms.labrulez.com/webinar/6123">Registration</a></li></ul><p>Discover a multi-method approach to copper plating bath analysis combining titration, CVS, XRF, and pH measurement for improved process control, data reliability, and production quality.</p><h5><strong>2. Bruker: Exploring the Caenorhabditis elegans lipidome in 4D</strong></h5><ul><li>Tu, 21.4.2026 10:00 CEST</li><li><a target="_blank" rel="noopener noreferrer" href="https://lcms.labrulez.com/webinar/6106">Registration</a></li></ul><p>Combining chromatography, trapped ion mobility, accurate mass and fragment information enables confident discovery and annotation of novel lipids in this key model organism.</p><h5><strong>3. Technology Networks: Episode 3: PFAS in Food – Addressing Contamination in the Food Supply Chain</strong></h5><ul><li>Tu, 21.4.2026 17:00 CEST</li><li><a target="_blank" rel="noopener noreferrer" href="https://lcms.labrulez.com/webinar/6108">Registration</a></li></ul><p>PFAS contamination in food is an emerging analytical and regulatory challenge, especially as testing expands beyond water into complex food and animal protein matrices.</p><h5><strong>4. Agilent Technologies: Getting the Most from Your Agilent LCMS System</strong></h5><ul><li>Tu, 21.4.2026 17:00 CET</li><li><a target="_blank" rel="noopener noreferrer" href="https://lcms.labrulez.com/webinar/5740">Registration</a></li></ul><p>In this webinar, we will discuss best practices and preventative maintenance tips to help maximize your instrument’s uptime.</p><h5><strong>5. Thermo Fisher Scientific: Mass spectrometry strategies to power drug discovery</strong></h5><ul><li>Tu, 21.4.2026 19:00 CEST</li><li><a target="_blank" rel="noopener noreferrer" href="https://lcms.labrulez.com/webinar/6097">Registration</a></li></ul><p>In this first master class session, explore how advanced mass spectrometry strategies are powering the next generation of drug discovery through chemoproteomics.</p><h5><strong>6. SCIEX: PFAS first steps: A roundtable for new analysts</strong></h5><ul><li>We, 22.4.2026 10:00 CEST</li><li><a target="_blank" rel="noopener noreferrer" href="https://lcms.labrulez.com/webinar/6103">Registration</a></li></ul><p>PFAS roundtable webinar for new analysts covering troubleshooting, workflow optimization, and regulatory readiness with expert insights from LC-MS specialists and industry professionals.</p><h5><strong>7. SelectScience: What’s in your hydrogen? Analytical toolkits for fuel purity analysis</strong></h5><ul><li>We, 22.4.2026 10:00 CEST</li><li><a target="_blank" rel="noopener noreferrer" href="https://lcms.labrulez.com/webinar/6055">Registration</a></li></ul><p>Join this dual-session webinar on hydrogen impurity testing and ISO 14687 fuel quality. Learn how GC, GC-MS, IC, and FTIR workflows support safe, compliant hydrogen production and fuel-cell applications.</p><h5><strong>8. Separation Science: Testing PFAS in Biosolids: From Sample Preparation to Interference Separation</strong></h5><ul><li>We, 22.4.2026 11:00 CEST</li><li><a target="_blank" rel="noopener noreferrer" href="https://lcms.labrulez.com/webinar/6124">Registration</a></li></ul><p>Learn how robust analytical approaches can deliver confident results, even in the most challenging wastewater and biosolid samples.</p><h5><strong>9. Thermo Fisher Scientific: Automated direct mRNA sequence mapping using online partial RNase T1 digestion and 2D LC-MS</strong></h5><ul><li>We, 22.4.2026 11:00 CEST</li><li><a target="_blank" rel="noopener noreferrer" href="https://lcms.labrulez.com/webinar/6110">Registration</a></li></ul><p>This webinar highlights a fully automated 2D LC-MS workflow for rapid, high-coverage mRNA characterization.</p><h5><strong>10. SCIEX: Unlocking SCIEX OS software: automating acquisition, analysis, and 21 CFR part 11 compliance reporting</strong></h5><ul><li>We, 22.4.2026 15:00 CEST</li><li><a target="_blank" rel="noopener noreferrer" href="https://lcms.labrulez.com/webinar/6125">Registration</a></li></ul><p>Join us to discover how the powerful capabilities of SCIEX OS Software help laboratories improve efficiency, reduce manual steps, and maintain data integrity.</p><h5><strong>11. Thermo Fisher Scientific: From experts to applications: Screening protein-drug interactions with HT-PELSA</strong></h5><ul><li>We, 22.4.2026 19:00 CEST</li><li><a target="_blank" rel="noopener noreferrer" href="https://lcms.labrulez.com/webinar/6098">Registration</a></li></ul><p>Part 2 of the Chemoproteomics Master Class explores HT-PELSA with Orbitrap Astral MS, showing peptide-level ligand binding analysis for target discovery, specificity, and drug pipeline insights.</p><h5><strong>12. Agilent Technologies: Pesticide Residues &amp; Fumigants Edition</strong></h5><ul><li>Th, 23.4.2026 08:30 CET</li><li><a target="_blank" rel="noopener noreferrer" href="https://lcms.labrulez.com/webinar/5955">Registration</a></li></ul><p>Food Safety Webinar Series – Part 2: Pesticide Residues &amp; Fumigants Edition. Explore LC-MS/MS and GC-MS/MS workflows, QuEChERS extraction, and regulatory reporting under Codex and EU frameworks.</p><h5><strong>13. Agilent Technologies: Enhancing Peptide and Oligonucleotide Analysis with Ultra Inert HPLC Technology</strong></h5><ul><li>Th, 23.4.2026 11:00 CEST</li><li><a target="_blank" rel="noopener noreferrer" href="https://lcms.labrulez.com/webinar/6134">Registration</a></li></ul><p>Learn how ultra-inert HPLC columns improve LC analysis of peptides and oligonucleotides by minimizing metal interactions and enhancing peak shape, sensitivity, and reproducibility.</p><h5><strong>14. Thermo Fisher Scientific: Chromeleon Admin Console III: Data management and automation</strong></h5><ul><li>Th, 23.4.2026 11:00 CEST</li><li><a target="_blank" rel="noopener noreferrer" href="https://lcms.labrulez.com/webinar/6126">Registration</a></li></ul><p>In this practical session, we’ll dive into more Administration Console capabilities that help you manage and standardize your setup at scale.</p><h5><strong>15. Waters Corporation: Informatics series #31 Empower Advanced Custom Fields - Examples</strong></h5><ul><li>Th, 23.4.2026 11:00 CET</li><li><a target="_blank" rel="noopener noreferrer" href="https://lcms.labrulez.com/webinar/5923">Registration</a></li></ul><p>Learn how to use Advanced Custom Fields in Empower to streamline calculations, improve reporting, and ensure validation-ready, compliant data processing.</p><h5><strong>16. Waters Corporation: A Multi-Residue Approach - Pesticides, Pharmaceuticals, and Personal Care Products</strong></h5><ul><li>Th, 23.4.2026 15:00 CEST</li><li><a target="_blank" rel="noopener noreferrer" href="https://lcms.labrulez.com/webinar/6112">Registration</a></li></ul><p>Navigating challenges and opportunities for environmental testing labs under the revised EU Water Framework Directive.</p><h5><strong>17. Waters Corporation: Analysis of Glyphosate, Glyphosinate and AMPA in water without the need of derivatisation</strong></h5><ul><li>Th, 23.4.2026 15:00 CET</li><li><a target="_blank" rel="noopener noreferrer" href="https://lcms.labrulez.com/webinar/5926">Registration</a></li></ul><p>Learn about required method conditions and instrumentation for Glyphosate, Glyphosinate and AMPA analysis in water without the need of derivatisation.</p><h5><strong>18. Thermo Fisher Scientific: Insights from an IC specialist: Are you using the right eluent?</strong></h5><ul><li>Th, 23.4.2026 16:00 CEST</li><li><a target="_blank" rel="noopener noreferrer" href="https://lcms.labrulez.com/webinar/6127">Registration</a></li></ul><p>Join the IC Ask the Experts session to learn practical eluent management strategies, optimize ion chromatography workflows, and get answers to your real-world analytical challenges.</p><h5><strong>19. Waters Corporation: Managing Process Performance in Stage 3 Process Validation: Regulatory Expectations for Continued Process Verification</strong></h5><ul><li>Th, 23.4.2026 17:00 CEST</li><li><a target="_blank" rel="noopener noreferrer" href="https://lcms.labrulez.com/webinar/6060">Registration</a></li></ul><p>Join this webinar to gain practical insights into regulatory expectations for CPV and strengthen your approach to maintaining process performance throughout the product lifecycle.</p><h5><strong>20. Thermo Fisher Scientific: High-throughput activity based protein profiling - Systematic mapping of covalent drug-protein interactions on a proteome-wide scale</strong></h5><ul><li>Th, 23.4.2026 19:00 CEST</li><li><a target="_blank" rel="noopener noreferrer" href="https://lcms.labrulez.com/webinar/6099">Registration</a></li></ul><p>Part 3 of the Chemoproteomics Master Class highlights activity-based proteome profiling and covalent screening to accelerate target identification and drug discovery using scalable MS workflows.</p><h5><strong>21. Agilent Technologies: Advancing and Characterizing Next-Gen Antibody Conjugates: Insights from BBB-Targeting Antibody Platforms</strong></h5><ul><li>Fr, 24.4.2026 08:00 CEST</li><li><a target="_blank" rel="noopener noreferrer" href="https://lcms.labrulez.com/webinar/6128">Registration</a></li></ul><p>Discover next-generation antibody therapeutics, BBB-targeting platforms, and LC-QTOF workflows for advanced characterization of complex antibody-drug and oligonucleotide conjugates.</p>

Webinars LabRulezLCMS Week 17/2026

Article

Webinars

Video

Scientists

Scientific article

Interview

Science and research

Everything from the world of analytical chemistry in one place. We connect people in solving their problems. At Labrulez you will find all the necessary information easily, quickly and clearly. Stop searching and start finding.

LabRulez

Organomation, founded in 1959, designs and manufactures high-quality nitrogen evaporators and extraction systems. Known for innovation and durability, their lab instruments are used globally for efficient sample preparation with strong customer support.

Organomation

Tosoh Bioscience

Separation Science

Agilent Technologies

GERSTEL

Phenomenex

Thermo Fisher Scientific

Waters Corporation

<p><strong>Discover the GERSTEL ChroMOH software, our powerful evaluation software for MOSH/MOAH data, in our informative webinar! See how this software simplifies and accelerates the quantitative analysis of complex MOSH/MOAH chromatograms.</strong></p><p><strong>Highlights of the webinar:</strong></p><ul><li>Intuitive workflow for efficient and fast evaluation of complex chromatograms</li><li>Detailed insights into the natural and accurate integration of MOSH/MOAH Humps</li><li>Transparent and customizable reporting</li></ul><p>Register today and revolutionize your data analysis!</p><blockquote><p><strong>Presenters:</strong> Isabelle Heker &amp; Timo Köhler, Ph.D.</p></blockquote>

GERSTEL:  Precise results within seconds  The future of MOSH/MOAH data analysis

Precise results within seconds  The future of MOSH/MOAH data analysis

Discover the GERSTEL ChroMOH software, our powerful evaluation software for MOSH/MOAH data, in our informative webinar!

 Precise MOSH/MOAH analysis in seconds

<h5><strong>By attending this discussion, you will:</strong></h5><ul><li>Discover how automated control algorithms enhance precision and reduce titration times without compromising accuracy.</li><li>Understand how advanced drift management tools ensure reliable results, even in demanding conditions.</li><li>Explore how modern titration systems address safety and sustainability goals with features such as remote operation and support for greener solvents.</li></ul><h5><strong>Event Overview</strong></h5><p>For nearly a century, Karl Fischer titration has been the trusted method for determining water content in products ranging from pharmaceuticals to processed snacks. However, even reliable techniques face challenges. For example, antibiotics can be difficult to analyze due to their limited solubility in conventional solvents, often requiring additional heating steps to ensure accurate measurements. Environmental factors, such as humidity, can further complicate workflows by introducing drift and reducing precision.</p><p>Join us for an expert discussion exploring how the latest innovations in Karl Fischer titration technology tackle these issues head-on. Panelists Nicolas Monney (Application Chemist, Mettler-Toledo) and Matteo Stefanoni (Senior Scientist, Mettler-Toledo) will answer questions related to advancements such as high-resolution sensors, low-dead-volume burets, and modular designs that improve accuracy, safety, and workflow efficiency. Learn how the EVA KF Titrator’s Fast Feedback Algorithm redefines titration workflows by adapting in real time to reaction conditions.</p><h5><strong>Who Should Attend:</strong></h5><ul><li>Scientists, lab managers, and analysts working in water determination across industries, including pharmaceuticals, food, biopharma, and materials science.</li><li>Professionals seeking practical solutions to improve accuracy, efficiency, and reproducibility in Karl Fischer titration workflows.</li><li>Anyone facing challenges with complex samples, drift, or evolving regulatory requirements in moisture analysis.</li></ul><h5><strong>Share Your Challenges Across Industries</strong></h5><p>Water determination plays a pivotal role in advancing quality and innovation. Do you struggle with reactive compounds, complex sample matrices, or meeting regulatory demands? This event offers the chance to have your specific questions addressed by experts.</p><p><strong>Submit your questions through the webinar registration form</strong>, and our panel will address selected challenges during the broadcast.</p><blockquote><p><strong>Presenter: </strong>Nicolas Monney (Application chemist, Mettler-Toledo)</p><p>Nicolas Monney holds a Ph.D. in Physical Chemistry. His research focused on studying electron transfer through proteins using low-temperature spectroscopy and ab-initio simulations.</p><p>Nicolas began his career at Mettler-Toledo nearly ten years ago, taking on the role of Applications Specialist for Titration. In this role, he develops innovative titration applications and collaborates closely with the R&amp;D department to facilitate the development of new products. Additionally, he supports the sales force of Mettler-Toledo and its partners on titration projects worldwide</p><p><strong>Presenter: </strong>Matteo Stefanoni (Senior Scientist, Mettler-Toledo International)</p><p>Matteo is a scientist with a strong academic background and experience in the fields of chemistry and material science. He earned his Master’s degree in Chemistry from the University of Milano and a PhD from ETH Zürich, focusing on electrochemistry. After completing his doctoral studies, Matteo spent two years as a postdoctoral researcher, further enhancing his expertise in the field. Currently, Matteo serves as a Senior Scientist at Mettler-Toledo, where he has spent the last five years developing advanced control algorithms for automatic titration instruments. Notably, he has dedicated four of those years to developing an innovative model-based control algorithm for Karl Fischer titration analysis, significantly improving the efficiency of this analytical technique.</p></blockquote>

Separation Science: Rethinking Karl Fischer Titration: How Smarter Algorithms Tackle Complex Water Determinations

Rethinking Karl Fischer Titration: How Smarter Algorithms Tackle Complex Water Determinations

Join us for an expert discussion exploring how the latest innovations in Karl Fischer titration technology tackle issues.

KF Titration: Smarter Algorithms Tackle Water Determinations

<p id="isPasted"><span name="summary"><strong>The presentations on Orbitrap Astral highlight significant advancements in proteomics and metabolomics. The first presentation from Alexey Chernobrovkin focuses on the integration of high throughput and high sensitivity mass spectrometry, demonstrating how the latest generation of mass spectrometers, coupled with advanced LC systems like the Vanquish Neo, can significantly increase sample processing speeds while maintaining robust protein coverage. This setup allows for efficient and reproducible results in quantitative proteomics, even with high sample loads, making it ideal for large-scale screening and clinical applications.&nbsp;</strong></span></p><p><span name="summary">The second presentation from Giada Marino delves into the predictive capabilities of machine learning models in retention time prediction for LC-MS experiments. It showcases the development and application of models like DeepLC, which use neural networks to predict retention times, collision cross sections, and fragment densities. These predictions enhance the identification and quantification of biomolecules, offering a more comprehensive understanding of proteomic and metabolomic profiles. The integration of modifications and transfer learning further improves the accuracy and applicability of these predictions across different experimental setups.&nbsp;</span></p><p><strong>Learning points :</strong></p><ul><li id="isPasted"><span name="summary"><strong fr-original-style="">High Throughput and Sensitivity:</strong> The integration of high-throughput mass spectrometry with advanced LC systems like the Vanquish Neo significantly enhances sample processing speeds and maintains robust protein coverage. This setup is ideal for large-scale proteomics and clinical applications, enabling the processing of up to 200 samples per day.&nbsp;</span></li><li><span name="summary"><strong fr-original-style="">Machine Learning for Retention Time Prediction:</strong> The development and application of machine learning models, such as DeepLC, improve the prediction of retention times, collision cross sections, and fragment densities. These predictions enhance the identification and quantification of biomolecules, providing a more comprehensive understanding of proteomic and metabolomic profiles.&nbsp;</span></li><li><span name="summary"><strong fr-original-style="">Optimization and Flexibility in Chromatography:</strong> The use of optimized LC setups and tailored columns ensures maximum performance and reproducibility in quantitative proteomics. The flexibility to choose the right column for specific project needs, coupled with extensive QC and optimization, allows for efficient and reliable results in various experimental conditions.</span></li></ul><p><strong>Who should attend?</strong></p><ul><li id="isPasted"><span name="summary"><strong fr-original-style="">Proteomics and Metabolomics Researchers:</strong> Scientists working in the fields of proteomics and metabolomics will gain insights into the latest advancements in mass spectrometry and chromatography, enhancing their research capabilities.&nbsp;</span></li><li><span name="summary"><strong fr-original-style="">Clinical Laboratory Professionals:</strong> Those involved in clinical diagnostics and large-scale screening will benefit from understanding how high-throughput and high-sensitivity mass spectrometry can improve sample processing and data accuracy.&nbsp;</span></li><li><span name="summary"><strong fr-original-style="">Data Scientists and Bioinformaticians:</strong> Professionals focused on developing and applying predictive models in biological research will learn about the integration of machine learning for retention time prediction, enhancing their analytical toolkit.&nbsp;</span></li></ul><h5><strong>Additional Webinars</strong></h5><p>Take advantage of our growing library of convenient and educational recorded webinars and resources. <a target="_blank" rel="noopener noreferrer" href="https://www.thermofisher.com/cz/en/home/about-us/events/industrial/analytical-innovations-webinars.html?cid=E.24CMD.EL112.21227.01"><strong>Visit our webinars page</strong></a></p><blockquote><p><strong>Presenter: </strong>Alexey Chernobrovkin (<span>Principal Scientist, Pelago Bioscience AB)​</span></p><div><p><span>Alexey Chernobrovkin, Principal Scientist at Pelago Bioscience. With a background in ​applied physics (MSc, MIPT, Moscow), got his PhD in Bioinformatics (Institute of ​Biomedical Chemistry, Moscow) and thenmoved for a postdoc at Karolinska Institutet, ​Stockholm in the group of prof. Roman Zubarev. At Pelago Bioscience AC leads ​development of MS-based platform for proteome-wide deconvolution of targets and ​mechanism of action (MoA) of bioactive compounds.​</span></p><p><strong>Presenter: </strong>Giada Marino​ (<span>Senior Research Scientist, Evotec)</span></p><div><p><span>Dr. Giada Marino is a Senior Research Scientist at Evotec working on high sensitivity ​and high throughput proteomics applications. Giada has more than 10 years of ​experience in proteomics and mass spectrometry. After a postdoc in Chris Overall ​lab at UBC (Vancouver, Canada) focusing on N-terminomics applications, she managed ​the mass spectrometry core facility in the Biology Department at the Ludwig-Maximilian ​University working on a wide range of protein and peptide mass spectrometry projects.​</span></p></div></div></blockquote>

Thermo Fisher Scientific: iHUPO 2024 Reloaded Webinar series

Breakthroughs in Proteomics and Metabolomics

The presentations on Orbitrap Astral highlight significant advancements in proteomics and metabolomics.

<p><strong>The (EU) 2020/2184 directive has highlighted panels of Endocrine-Disrupting Chemicals (EDCs) that pose high risk to the population if present in drinking &nbsp;water above regulated levels. Furthermore, these EDCs are often biologically active even at trace levels, making their ultra-sensitive detection in drinking water a fundamental requirement.</strong></p><p>This webinar will delve into the advanced analytical techniques used for the identification and quantification of EDCs, with a focus on Liquid Chromatography-Mass Spectrometry (LC-MS) to monitor and maintain a safe drinking water supply.</p><div><blockquote><p><strong>Presenter:&nbsp;</strong> Susanne Sölter (Field Application Specialist LC/MS, Agilent Technologies)</p><p>Susanne has a doctorate degree in organic chemistry from the University of Hamburg and has over 20 years’ experience in the application and implementation of LC/MS methods. In her current position as a Field Application Specialist, Susanne develops new methods and provides technical application customer support, with a specialized focus on food and environmental food applications.</p></blockquote></div>

Agilent Technologies: Watertight Analytical Workflows to Meet EU Directive 2020-2184

Analysis of Endocrine Disrupting Chemicals in Drinking Water by LC/MS According to Directive (EU) 2020/2184

The analytical techniques used for the identification and quantification of EDCs, with a focus on LC-MS to monitor and maintain a safe drinking water supply.

Endocrine Disrupting Chemicals in Drinking Water by LC/MS

<p><strong>This webinar will provide insights on column selection for clinical research applications based on analyte properties, stationary phase characteristics, and instrumentation. Reversed phase separation mechanisms and stationary phase modifications, and how they affect retention and selectivity will be presented. How particle size and porosity affect chromatographic efficiency will be explained. Fully porous vs superficially porous HPLC and UHPLC columns and their use in clinical research will be discussed. LC column selection based on analyte and column properties will be described. Lastly, several studies will be presented to demonstrate how to select the best column.</strong></p><h4><strong>Key Learning Points</strong></h4><ul><li>Explain how analyte properties affect LC column choice</li><li>Review differences in column chemistry and its impact on separation</li><li>Describe criteria for choosing the best LC column for clinical research applications</li></ul><h4><strong>Who Should Attend</strong></h4><p>Researchers, scientists and analysts who want to learn more about LC column selection for LC-MS/MS Methods. Lab managers looking to start or increase use of LC-MS/MS in their laboratories. Laboratorians doing method development and implementation for clinical research.</p><blockquote><p><strong>Presenter:</strong> Stephanie J. Marin Ph.D (Global Market Development Manager, Phenomenex)</p><p>Stephanie J. Marin is the Clinical and Forensics Global Market Development Manager at Phenomenex. She received her Ph.D. in chemistry from Arizona State University, and has expertise in sample preparation, liquid chromatography and mass spectrometry. She has over 10 years of experience developing and validating clinical methods from her tenure at the ARUP Institute for Clinical and Experimental Pathology. &nbsp;Dr Marin has worked in marketing, product development, and applications development, in addition to customer facing roles in customer and technical support and service and customer education and training. She has also held positions at Hamilton Company, Selerity Technologies and Biotage, and in analytical services for specialty chemicals and polymers at Rohm and Haas (now Dow). She was also a supervisor at an EPA certified laboratory. She is the author of over 30 peer reviewed publications and book chapters and over 100 abstracts presented at national and international meetings.&nbsp;</p></blockquote>

Phenomenex: Insights on Column Selection for LC-MS/MS Clinical Research

Insights on Column Selection for LC-MS/MS Clinical Research

This webinar provide insights on column selection for clinical research applications based on analyte properties, stationary phase and instrumentation.

<p><strong>Are you looking for PFAS in air, water, or food samples?&nbsp;</strong></p><p><strong>Discover how to automate analytical methods for PFAS determination, including ASTM D8591-24, EPA methods 533, 537.1, and 1633, and FDA method C-010.03. Join us for our webinar, “Determination of PFAS in Various Sample Types, including Air, Water, and Food, Using GC-MS or LC-MS”.&nbsp;</strong></p><p>The webinar will feature the following presentations:</p><h5><strong>You're Breathing it Too: Emerging Standards and Methods for Measuring Fluorotelomer Alcohols and Other PFAS Species in Air</strong></h5><blockquote><p><strong>Presenter: </strong>Kurt Thaxton (International Product Manager, GERSTEL GmbH &amp; Co.KG.)</p></blockquote><h5><strong>Automated Sample Preparation for the LC-MS/MS Determination of PFAS Compounds in Water and Food</strong></h5><blockquote><p><strong>Presenter:</strong> Fred Foster (Applications Scientist, GERSTEL, Inc.)</p></blockquote>

GERSTEL:  Determination of PFAS in Various Sample Types, including Air, Water, and Food, Using GC-MS or LC-MS

Determination of PFAS in Various Sample Types, including Air, Water, and Food, Using GC-MS or LC-MS

 GC-MS or LC-MS PFAS Determination in Air, Water, Food

<p><strong>Developing targeted small molecule quantitative workflows for clinical research presents many challenges to researchers. From determining the optimum methods needed to enhance selectivity and specificity, to achieving improved limits of detection and quantitation, the Thermo Scientific™ Stellar™ mass spectrometer is an ideal instrument to overcome those challenges. This revolutionary instrument features a quadrupole mass filter, dual-purpose ion concentrating routing multipole, and a dual-pressure linear ion trap that expands effective data acquisition schemes to maintain the quantitative sensitivity for both large and small molecules.</strong><br><br>This live webinar will cover method development considerations for applied workflows such as toxicology research, implementing fast chromatography, and automated intelligent instrument control. Participants will learn how to leverage higher energy dissociation (HCD) and resonant collisional dissociation (CID) using tMS<sup>2</sup> and tMS<sup>3</sup> acquisition to improve quantitative selectivity, sensitivity, and specificity in complex biological matrices.<br><br><strong>Learning Objectives</strong></p><ul><li>Increasing productivity through streamlined method creation</li><li>How to create targeted MS2 and MS3 methods in one analytical method</li></ul><p>The benefits of Adaptive RT for scheduled PRM acquisition for small molecules<br><br><i>Webinars will be available for unlimited on-demand viewing after live event.</i></p><blockquote><p><strong>Presenter: </strong>Courtney Patterson, MSc. (Product Specialist in the Clinical Vertical Marketing Group, Thermo Fisher Scientific)</p><p>Courtney Patterson is an Application Scientist in Clinical and Forensic Toxicology at Thermo Fisher Scientific based out of San Jose, CA. She has a background in forensic toxicology, receiving her master’s in forensic chemistry from The Pennsylvania State University. Her previous role was working as a Forensic Toxicologist for the US Army in their Forensic Toxicology Drug Testing Laboratory (FTDTL) in Fort Meade, MD. Recently, she has been developing fast, quantitative LCMS workflows for drugs of abuse and novel psychoactive substances (NPS) to be utilized by forensic labs in a production setting.</p><p><strong>Presenter: </strong>Jingshu Guo, Ph.D (Sr. Product Application Specialist in the Clinical Vertical Marketing Group, Thermo Fisher Scientific)</p><p>Dr. Jingshu Guo is a trained mass spectrometrist with 10+ years of experience in LC-MS-based qualitative and quantitative analyses of small molecules, nucleosides, peptides, and intact protein. After joining Thermo Fisher Scientific, she worked on the method development, implementation, and optimization in healthcare, clinical and toxicology-related fields. One of her current focuses is to develop fast quantification methods in small molecules, such as biomarkers, therapeutic drugs, and drugs of abuse in biofluids using LC coupled to triple quadrupole MS, ion trap MS, or high-resolution MS, and LC-free MS platforms.</p><div><p>&nbsp;</p></div></blockquote>

Thermo Fisher Scientific: Next-generation workflows for small molecule quantitation using the Thermo Scientific Stellar mass spectrometer

Next-generation workflows for small molecule quantitation using the Thermo Scientific Stellar mass spectrometer

The webinar cover method development for applied workflows, toxicology research, implementing fast chromatography.

 Small molecule quantitation by Stellar mass spectrometer

<div><div><p><strong>Waters is proud to introduce the Andrew+™ Pod, a dedicated enclosure for the </strong><a target="_blank" rel="noopener noreferrer" href="https://lcms.cz/products/208"><strong>Andrew+ Robot</strong></a><strong>. Join us for an exclusive webinar unveiling this latest innovation from the Waters Lab Automation team. This compact and adaptable enclosure is designed to elevate your benchtop automation workflows by integrating seamlessly with the Andrew+ Robot, offering unparalleled user and sample safety for a wide range of applications.</strong></p><p>In this session, you’ll learn how the Andrew+ Pod provides efficient air-filtration capabilities for various sample preparation workflows, while enabling labs to do more with their automation solutions thanks to user-centric features and unmatched flexibility - all while maintaining the compact footprint of the Andrew+ liquid handler.</p><p>From protecting your samples with HEPA filtration and a true vertical laminar flow to ensuring user safety with advanced chemical filtration, the Andrew+ Pod is the ultimate solution for labs seeking optimized automation without compromise.&nbsp;</p><blockquote><p><strong>Presenter: </strong>Jasper Eaton (Senior Product Marketing Manager, Waters Corporation)</p><p>Jasper is Senior Product Marketing Manager at Waters for laboratory automation and software. He joined Waters in 2020 after having worked at Andrew Alliance as European Sales Manager since he started his career in 2017. Jasper has a Master’s degree in Molecular and Cellular Biology, complemented with a dual-competence Master’s II degree in Biology and Sales/Marketing during which he worked at Roche Diagnostics as a Product Manager Intern.</p><p><strong>Presenter:&nbsp;</strong>Matthias Bittner (Consultant Standards &amp; Cleanroom Technology, SKAN AG)</p><p>Matthias Bittner first travelled the world as a pure water specialist, before switching to air in 2002. Since then, he has worked in cleanroom technology for SKAN AG, a global manufacturer of isolators and clean benches (1,500 employees). For 14 years, as head of the Swiss service team, he was responsible for the development of the group that now counts 20 service technicians. Since 2016, he has been working as a consultant in cleanroom technology. He works in R&amp;D and he is an active member of the Swiss Association for Standardization, standardizing technologies of laboratory equipment, isolators and cleanrooms, for ISO and for CEN.</p></blockquote></div></div>

Waters Corporation: New Andrew+ Pod - Protect Your Sample. Protect Yourself

New Andrew+ Pod - Protect Your Sample. Protect Yourself

Join us for an exclusive webinar unveiling this latest innovation from the Waters Lab Automation team. 

<div><div><p><strong>Let's go back to the Basics of Chromatography, Mass Spectrometry, Data Analysis and Trouble-shooting: understanding the importance of the basics will enable you to be more effective in your daily laboratory life.</strong></p><p>This journey started in 2024 and we are now pleased to invite you to join us to go deeper in fundamentals, troubleshooting and application specific topics.</p><h3><strong>EPISODE 1: SPE Troubleshooting - Keys to Success!</strong></h3><p><strong>What will you learn?</strong></p><ul><li>What are the critical steps in a SPE protocol</li><li>How to overcome the most common challenges</li></ul><p><strong>What's next?</strong></p><ul><li>Check out the full Webinar Series Episodes List <a target="_blank" rel="noopener noreferrer" href="https://event.on24.com/eventRegistration/EventLobbyServlet?target=reg20.jsp&amp;eventid=4817889&amp;sessionid=1&amp;key=B9182AE813B3F8A30217606156F96B75&amp;groupId=5901784&amp;sourcepage=register"><strong>here</strong></a></li></ul><p><strong>Not sure to be able to attend live sessions?&nbsp;</strong></p><ul><li>Register today and watch the webinars on-demand</li></ul><blockquote><p><strong>Presenter: </strong>Xavier Rodriguez (Principal Applications Specialist, Chemistry, Europe, Waters Corporation)</p><p>Xavier is part of the European Market Development Team. He works as an Application Specialist with focus on sample prep and has more than 20 years of experience in solving sample prep challenges.</p></blockquote></div></div>

Waters Corporation: Back to Basics Advanced Webinar Series 2025

Back to Basics Advanced - Troubleshooting: Sample Prep

What are the critical steps in a SPE protocol and how to overcome the most common challenges 

<p><strong>Christian Rohrer, Director Sales and Support at Tosoh Bioscience GmbH, will present the next edition of Tosoh Tuesday, a webinar series held by Chromatography Experts.&nbsp;</strong></p><p>On Tuesday February 18, Andrea Krumm, Product Manager at Tosoh Bioscience, explores the versatility of hydrophobic interaction chromatography (HIC) for analyzing small and large proteins, as well as nucleic acid-based molecules.&nbsp;</p><p>Discover how the availability of diverse stationary phases extends HIC beyond ADC analysis, unlocking its potential for a broader range of applications.</p><p><strong>After the webinar, ask your questions during the live Q&amp;A session</strong>.&nbsp;</p><blockquote><p><strong>Presenter: </strong>Christian Rohrer (Director Sales and Support at Tosoh Bioscience GmbH)</p><p><strong>Presenter:</strong> Andrea Krumm (Product Manager at Tosoh Bioscience)</p></blockquote>

Tosoh Bioscience: Tosoh Tuesday - Analytical HIC for Diverse Biomolecules: Selectivity is Key!

Tosoh Tuesday - Analytical HIC for Diverse Biomolecules: Selectivity is Key!

Learn how analytical HIC extends beyond ADCs to analyze proteins and nucleic acid molecules, offering unique selectivity and versatile applications.

Related content

Webinars LabRulezLCMS Week 17/2026

LCMS-Net: Deep Learning for Raw High Resolution Mass Spectrometry Data Applied to Forensic Cause-of-Death Screening

Selective Separations: What Membrane Science Can Teach Chromatographers