Differentiable mass transfer modeling enables wet lab validated inverse analysis of liquid chromatography
- 1ChemLex
- 2School of Data Science
- 3Chinese University of Hong Kong
Abstract
Liquid chromatography (LC) is essential to organic synthesis and emerging selfdriving laboratories (SDLs), yet LC method development remains cost-intensive and dependent on expert intuition. Mechanistic chromatographic models offer a route to transferable and data-efficient method development, but their practical use is limited by the computational cost of inverse modeling and by the ill-posedness of parameter estimation from experimental chromatograms. Here we report a wet-lab-validated differentiable physics framework for LC inverse modeling. The framework integrates mechanistic column modeling with physics-informed machine learning (PIML) to enable efficient forward simulation and gradient-based inverse estimation of molecular transport and adsorption parameters from gradient-elution chromatograms. The primary PINN surrogate reproduces the mechanistic reference with a root-mean-square error of 10−3 in dimensionless concentration. To address the ill-posed nature of the inverse problem, we introduce an observability-guided experimental-design strategy that quantifies parameter identifiability and incorporates this information into the inverse objective to promote convergence toward the ground-truth parameters. Across 300 dry-lab simulation parameter combinations, the proposed strategy recovered the ground-truth parameters with relative errors ≤ 10% in 88.3% of cases using three gradient programs, compared with only 6.7% using a single gradient program. We further validate the framework against wet-lab LC 1 measurements, achieving an absolute retention-time error ≤ 10 s for 89.3% of samples and establishing a wet-lab database comprising 731 sets of transport and adsorption parameters extracted from 2,553 gradient-elution LC chromatograms. This work provides an observability-aware differentiable modeling foundation for autonomous LC method development and closed-loop analytical decision-making in AI-driven laboratories.
Related
- Use of Gas Chromatography, Nuclear Magnetic Resonance and Fluorescent methods to Estimate Enantiomeric Excess in Asymmetric Transfer Hydrogenation.
- MoSeS Enables Autonomous Chromatography Operation through Programmable Analytical Expertise
- From the Gut to the Brain: Modeling Intestinal Absorption and Assessing Blood–Brain-Barrier Permeability of Small-Molecule Drugs by IAM Chromatography
- Streamlined Ultrafast Chromatography for High-Throughput Discovery and Development Chemistry via Predictive Analytical Modeling
- Consistent Modeling of SEI Growth via Electron Diffusion Validated Across Diverse Cell Specifications and Operating Conditions in LFP/Graphite Cells
BibTeX
@misc{li2026differentiable,
title = {{Differentiable mass transfer modeling enables wet lab validated inverse analysis of liquid chromatography}},
author = {Baochen Li and Zihan Zhou and Yanqing Yu and Sen Lin and Peng Wang and Tianshu Yu and Xiaoxue Wang},
howpublished = {ChemRxiv},
year = {2026},
month = sep,
doi = {10.26434/chemrxiv.15009352/v1},
url = {https://chemrxiv.org/doi/full/10.26434/chemrxiv.15009352/v1},
note = {CC BY-NC-ND},
}
RIS
TY - UNPB
TI - Differentiable mass transfer modeling enables wet lab validated inverse analysis of liquid chromatography
AU - Baochen Li
AU - Zihan Zhou
AU - Yanqing Yu
AU - Sen Lin
AU - Peng Wang
AU - Tianshu Yu
AU - Xiaoxue Wang
PY - 2026
DA - 2026/09/23
PB - ChemRxiv
DO - 10.26434/chemrxiv.15009352/v1
UR - https://chemrxiv.org/doi/full/10.26434/chemrxiv.15009352/v1
AB - Liquid chromatography (LC) is essential to organic synthesis and emerging selfdriving laboratories (SDLs), yet LC method development remains cost-intensive and dependent on expert intuition. Mechanistic chromatographic models offer a route to transferable and data-efficient method development, but their practical use is limited by the computational cost of inverse modeling and by the ill-posedness of parameter estimation from experimental chromatograms. Here we report a wet-lab-validated differentiable physics framework for LC inverse modeling. The framework integrates mechanistic column modeling with physics-informed machine learning (PIML) to enable efficient forward simulation and gradient-based inverse estimation of molecular transport and adsorption parameters from gradient-elution chromatograms. The primary PINN surrogate reproduces the mechanistic reference with a root-mean-square error of 10−3 in dimensionless concentration. To address the ill-posed nature of the inverse problem, we introduce an observability-guided experimental-design strategy that quantifies parameter identifiability and incorporates this information into the inverse objective to promote convergence toward the ground-truth parameters. Across 300 dry-lab simulation parameter combinations, the proposed strategy recovered the ground-truth parameters with relative errors ≤ 10% in 88.3% of cases using three gradient programs, compared with only 6.7% using a single gradient program. We further validate the framework against wet-lab LC 1 measurements, achieving an absolute retention-time error ≤ 10 s for 89.3% of samples and establishing a wet-lab database comprising 731 sets of transport and adsorption parameters extracted from 2,553 gradient-elution LC chromatograms. This work provides an observability-aware differentiable modeling foundation for autonomous LC method development and closed-loop analytical decision-making in AI-driven laboratories.
ER -