
Max Besenhard explains how hybrid mechanistic and machine learning models can make HPLC method development quicker, more robust and ready for autonomous digital twins.
Alasdair Matheson Is Executive Editor on LCGC International and has worked in science publishing for thirty years. He has a Masters Degree in Instrumental Methods of Analysis from Strathclyde University, Glasgow, UK and a Postgraduate Diploma in Marine Pollution Chemistry from Liverpool University, Liverpool UK. He also worked as an environmental research scientist at the Torry Research Centre in Aberdeen and as an industrial research scientists at the ICI Wilton Research Centre in Wilton.

Max Besenhard explains how hybrid mechanistic and machine learning models can make HPLC method development quicker, more robust and ready for autonomous digital twins.


Sebastian Böcker discusses taking retention prediction beyond reversed-phase to HILIC, what changes elution order in method transfer, and sharing data via RepoRT.

Sebastian Böcker discusses how predicting retention order, not time, makes liquid chromatography retention time prediction transferable across laboratories.

How feasible is it to integrate this Bayesian graph-theory methodology into existing commercial chromatography software workflows for semi-automated data curation in routine analytical laboratories?

Gabriel Vivó-Truyols outlines the benefits and challenges of combining graph theory with Bayesian statistics to automate peak assignment and alignment.

Gabriel Vivó-Truyols from the Spanish Council for Scientific Research, Madrid, Spain. discusses his work on using graph theory and Bayesian statistics for peak assignment and chromatographic alignment.

How can advanced separations, inert hardware, orthogonal methods, and AI solve key challenges in reliable GLP-1 peptide analysis workflows?

Leon Niezen and Gert Desmet discuss uncertainty-driven LC method development, peak overlap, and moving from in silico to real data.

Leon Niezen and Gert Desmet describe how predictive uncertainty can make automated LC method development more reliable.

Sam Whitmarsh explores how retention-time models handle interlaboratory data, novel chemotypes, unusual phases and ionisable compounds, and what labs need to do to build useful in-house models.

Sam Whitmarsh describes a practical workflow for predicting reversed-phase LC retention times using ensemble machine learning and open chromatographic data.

Viktoriia Turkina discusses toxicity prediction for unknown LC–HRMS features using machine learning.

ChromSoc’s Data Analytics and AI in Chromatography symposium will debate whether AI could ever replace chromatographers, alongside pharma case studies.

Recent EU legislation on PFAS shifts from monitoring individual compounds toward managing them as a chemical class.

Nicolai Zederkopff explores chromatography’s role to help implement the maximum tolerable level (MTL) framework for food adulteration to translate analytical results into compliance decisions.

Ed Ahearne highlights the benefits of ML-driven chromatography for the development of biopharmaceutical products

Ed Ahearne combined automation, machine learning, and Bayesian optimization to speed up method development for siRNA medicines.

Gert Desmet offers his insights on the potential benefits AI/ML could offer the separation science community in the future.

Quantitative non-targeted screening with predicted response factors is not for regulation, but can rank environmental chemicals by concentration and toxicity.

Gert Desmet explores the current role of AI/ML in separation science.

Multidimensional chromatography cuts ion suppression in complex environmental samples by separating salts and coeluting compounds from target analytes.

Tony Edge explains how SPE optimization improves oligonucleotide LC–MS data.

Perfusion chromatography offers improved separation of oligonucleotide biotherapeutics at ultra-high velocities.

Steven Ray Wilson's AFFL LC–MS system runs thousands of injections per column, but he calls validation and standardization the field's real barrier.

Justin Miller-Schulze and Smith Purdum explain how machine learning and chemometrics can improve fire debris classification in forensic science applications.

As PFAS analysis pushes into trace-level territory, laboratories face a fast-moving mix of vast chemical scope, method fragmentation, and background contamination.

Steven Ray Wilson defines organ-on-a-chip as organoids on microfluidic devices, tracing their small, complex samples to the case for automated online LC–MS.

Lorna Nisbet from the Leverhulme Research Centre for Forensic Science, discusses a GC–MS. technique developed to detect anabolic-androgenic steroids in e-cigarettes seized from Scottish prisons.

Gérard Hopfgartner explains why pairing SFC with dopant-assisted APPI can match, or even beat, electrospray sensitivity, even at microflow LC rates.

Published: November 9th 2026 | Updated: November 8th 2027

Published: July 16th 2026 | Updated: July 15th 2027

Published: October 23rd 2026 | Updated: October 26th 2026

Published: October 14th 2026 | Updated: October 15th 2026

October 8th 2024

June 16th 2025