+ HEALTH Rationale and objectives To propose a new imaging biomarker, the pulmonary artery-to-vein volume difference (…± HEALTH Rationale and objectives The international application of artificial intelligence (AI) for lesion detection b…± HEALTH Rationale and objectives To address the challenge of preoperative prediction of synchronous liver metastasis…± HEALTH Objectives To conduct a nationwide survey among professionals working in oncology departments in China to inv…+ HEALTH The utilization of deep convolutional neural networks for the purpose of diagnosing diseases in the skin area…± HEALTH BACKGROUND . Gadolinium-based contrast agents remain essential for MRI but carry risks. Deep learning (DL) me…+ SCIENCE Gas Chromatography is a versatile separation technique widely used in analytical chemistry for constituent de…+ HEALTH Background Intracardiac echocardiography (ICE) facilitates left atrial (LA) reconstruction during atrial fibr…
TruaceTracing the truth around AIThursday, August 27, 2026
Subscribe
Science·G Space·Evidence-backed gain·Published 2026-08-27

Separation of coeluted compounds in capillary gas chromatography: customization via machine learning retention time prediction

Abstract: Gas Chromatography is a versatile separation technique widely used in analytical chemistry for constituent determination. However, gas chromatography compound identification is not directly feasible unless the method is coupled with complementary techniques such as mass spectrometry or with referencing methods like retention indices. Statistical retention time prediction of compounds based on the gas chromatography experimental and instrumental parameters could facilitate the gas chromatography characterization…

TRV-2026-0903Peer-reviewedPermanent record — cite & verify
Separation of coeluted compounds in capillary gas chromatography: customization via machine learning retention time prediction

"High-performance chromatography" by oakridgelabnews is licensed under CC BY 2.0. To view a copy of this license, visit https://creativecommons.org/licenses/by/2.0/.

The quick read

Researchers built a machine learning pipeline to predict retention times in capillary gas chromatography, training six algorithms on 608 data points covering 73 instrument settings and 61 C1-C12 hydrocarbons from RESTEK chromatograms and literature. The adaptive boosting support vector regression model achieved R2 scores of 0.992-0.993 on validation and testing sets.

Accurate retention time prediction matters because GC alone cannot directly identify compounds without mass spectrometry or retention indices, and coelution limits isomer separation. The study demonstrates a data-driven route to optimize GC conditions, but remains bounded to the hydrocarbon range and settings represented in the training data, with broader applicability untested as of the August 2026 publication date.

Main points
  • Six algorithms were trained on 70% of 608 manually compiled data points from RESTEK chromatograms and literature.
  • Dataset covered 73 different GC settings and 61 compounds ranging from C1 to C12 hydrocarbons.
  • Chosen model was adaptive boosting support vector regression, outperforming tree-based ensemble methods.
  • Model achieved R2 scores of 0.992-0.993 across validation and testing sets.
  • Predicted settings are in strong agreement with a proposed gas chromatograph designed specifically for isomer separation.
Gain

Adaptive boosting support vector regression trained on GC parameters predicts retention times with high accuracy, enabling optimization of capillary gas chromatography to separate coeluted C1-C12 hydrocarbon isomers.

The rundown

The work compiled 608 data points from RESTEK company chromatograms and published literature, spanning 73 GC settings. Six algorithms were trained on 70% of the data, with adaptive boosting support vector regression selected after outperforming tree-based ensembles.

The selected model maintained R2 of 0.992-0.993 on validation and testing sets. Authors propose a pipeline that uses predicted retention times to facilitate characterization and to customize GC conditions, noting agreement between predicted settings and a GC design intended for isomer separation.

Sources

Reader signal

How should this claim be treated?

The debate