Skip to content
DraconiticResearch
Search Sources API
203,203 studies31 sourcesUpdated 13 min ago
Peer-reviewedCC BY 4.0Nature Methods

Times are changing but order matters: transferable prediction of small-molecule liquid chromatography retention times

  • Fleming Kretschmer1
  • Eva-Maria Harrieder2,3
  • Michael A. Witting4,2,5,3
  • Sebastian Böcker6
6 affiliations
  1. 1Chair for Bioinformatics, Institute for Computer Science, Friedrich Schiller University Jena, Jena, Germany
  2. 2Labor Becker MVZ eGbR, Munich, Germany
  3. 3Research Unit Analytical BioGeoChemistry, Helmholtz Zentrum München, Neuherberg, Germany
  4. 4Chair of Analytical Food Chemistry, TU München, Freising, Germany
  5. 5Metabolomics and Proteomics Core, Helmholtz Zentrum München, Neuherberg, Germany
  6. 6Chair for Bioinformatics, Institute for Computer Science, Friedrich Schiller University Jena, Jena, Germany. [email protected]
Read full textPDFDOICite

Abstract

Liquid chromatography is a predominant technology for the separation of small molecules. Hundreds of retention time prediction models have been published over the past decades, yet truly transferable prediction (requiring no training data from the target chromatographic system) remains an open challenge. Unfortunately, retention times may change massively, even for nominally identical chromatographic conditions. Retention order is considerably more conserved; but even retention order may change if chromatographic conditions vary. Here we present 2-step, a two-step method for the prediction of retention times in reversed-phase chromatography. In the first step, a machine-learning model predicts a retention order index, taking into account chromatographic conditions. In the second step, we map predicted indices to absolute retention times. Disentangling these two tasks finally enables transferable retention time prediction across chromatographic conditions and compound classes, without requiring any target-system training data. Our 2-step method outperforms existing methods that were trained on the target dataset. Finally, we systematically study what chromatographic conditions result in notable changes of retention order.

Related

  1. Simulation-Supervised Foundation Models for Retention Time Prediction in High-Performance Liquid Chromatography beyond Experimental Data Coverage
    Stephen Wu, Yufeng Han, Yasuhiro Mito +5
    arXivPreprintCC BY-NC-ND 4.0Full textPhysical chemistryStatisticsarXiv
  2. From the Gut to the Brain: Modeling Intestinal Absorption and Assessing Blood–Brain-Barrier Permeability of Small-Molecule Drugs by IAM Chromatography
    Stefan Simić, Predrag Kalaba, Judith Wackerlig +1
    ACS OmegaPeer-reviewedCC BYFull text5 citedMedicinal chemistry & drug discoveryNeurologyOpenAlex
  3. Investigating the Role of Ligand Hydrophobicity and Ionization on Protein Retention in Mixed-Mode Chromatography
    Janani Ram, Adel Nematipour, Raghav Kasi +4
    ChemRxivPreprintCC BYFull textPhysical chemistryChemRxiv
  4. Lactic Acid Related Molecule Reaction Outcome Prediction via AI Chatbots
    Atharva Sahu
    ChemRxivPreprintCC BYFull textMaterials & polymersChemRxiv
  5. StructRSMA: A Proof-of-Concept Framework for PDB-Derived Contact-Supervised Transfer in RNA-Small Molecule Binding Affinity Prediction
    Yuxin Wen, Yi Tian, Nguyen Quoc Khanh Le +1
    ACS OmegaPeer-reviewedCC BY 4.0Full textGeneral chemistryCrossref

Cite

BibTeXRIS
BibTeX
@article{kretschmer2026times,
  title = {{Times are changing but order matters: transferable prediction of small-molecule liquid chromatography retention times}},
  author = {Fleming Kretschmer and Eva-Maria Harrieder and Michael A. Witting and Sebastian Böcker},
  journal = {Nature Methods},
  year = {2026},
  month = oct,
  doi = {10.1038/s41592-026-03243-2},
  url = {https://doi.org/10.1038/s41592-026-03243-2},
  note = {CC BY 4.0},
}
RIS
TY  - JOUR
TI  - Times are changing but order matters: transferable prediction of small-molecule liquid chromatography retention times
AU  - Fleming Kretschmer
AU  - Eva-Maria Harrieder
AU  - Michael A. Witting
AU  - Sebastian Böcker
PY  - 2026
DA  - 2026/10/01
JO  - Nature Methods
DO  - 10.1038/s41592-026-03243-2
UR  - https://doi.org/10.1038/s41592-026-03243-2
AB  - Liquid chromatography is a predominant technology for the separation of small molecules. Hundreds of retention time prediction models have been published over the past decades, yet truly transferable prediction (requiring no training data from the target chromatographic system) remains an open challenge. Unfortunately, retention times may change massively, even for nominally identical chromatographic conditions. Retention order is considerably more conserved; but even retention order may change if chromatographic conditions vary. Here we present 2-step, a two-step method for the prediction of retention times in reversed-phase chromatography. In the first step, a machine-learning model predicts a retention order index, taking into account chromatographic conditions. In the second step, we map predicted indices to absolute retention times. Disentangling these two tasks finally enables transferable retention time prediction across chromatographic conditions and compound classes, without requiring any target-system training data. Our 2-step method outperforms existing methods that were trained on the target dataset. Finally, we systematically study what chromatographic conditions result in notable changes of retention order.
SN  - 1548-7091
SN  - 1548-7105
ER  -