Skip to content
DraconiticResearch
Search Sources API
197,768 studies31 sourcesUpdated 7 min ago
PreprintCC BYChemRxiv

Guiding chromatographic purification through data-driven condition recommendations

  • Yuki Murakami1
  • Nobuo Cho2
  • Kosei Egami2
  • Hiroto Yamazaki2
  • Shoichi Ishida1,3
  • Aoi Hirano4,5
  • Yuri Fukushima4,5
  • Masato Sumita3,6
  • Ai Kohata2
  • Kazushi Kinbara2,7
  • Kei Terayama1,2,3,4,5,6
7 affiliations
  1. 1Graduate School of Medical Life Science, Yokohama City University, 1-7-29,Suehiro-cho, Yokohama, Kanagawa, Japan, 230-0045
  2. 2School of Life Science and Technology, Institute of Science Tokyo, 4259 Nagatsuta-cho, Yokohama, Kanagawa, Japan, 226-8501
  3. 3MolNavi LLC, #402 Wizard Building 1-4-3 Sengen-cho, Yokohama, Kanagawa, Japan, 220-0072
  4. 4School of Science
  5. 5Yokohama City University
  6. 6RIKEN Center for Advanced Intelligence Project, 1-4-1, Nihonbashi,, Tokyo, Japan, 103-0027
  7. 7Research Center for Autonomous Systems Materialogy (ASMat), Institute of Innovative
Open at sourcePDFDOICite

Abstract

Purification is essential for isolating compounds for reliable characterization and subsequent experiments; however, suitable chromatographic conditions are often still selected through trial and error. Herein, we present a data-driven framework that recommends a stationary phase or separation mode, solvent, and solvent ratio to support thin-layer chromatography (TLC) screening and column chromatography (CC) purification. Using purification records from publications and laboratory notebooks, we developed models to predict TLC and CC conditions. Models using product structures alone or in combination with reactant and agent information were compared across prediction tasks and data sources. Experimental evaluation of 11 previously unreported compounds demonstrated that ranked recommendations could guide TLC screening and the selection of CC purification conditions. Additionally, a web application was developed to provide users with flexible access to the prediction models. The proposed framework supports the selection of practical purification conditions and provides a foundation for integrating purification planning into future autonomous experimental workflows.

Related

  1. Extraction of some pesticides from grape juice samples using an amide-based polymer as a sorbent followed by gas chromatographic determination
    Fatemeh Ershad, Mir Ali Farajzadeh, Sina Mohammad Mehri +1
    RSC advancesPeer-reviewedCC BYFull textGeneral chemistryEurope PMC
  2. Application of Hansen Solubility Parameters for Green Solvent Extraction of Flavonoids from Oroxylum indicum (L.) Kurz and Chromatographic Profiling Across Plant Organs
    Prommin Suphanakron, Rutchaphol Sookjitt, Wullapa Jittachai +2
    MoleculesPeer-reviewedCC BY 4.0Analytical chemistryCrossref
  3. Chromatographic Peak Shape beyond the High-Péclet Approximation: Analytic Time-Domain Expression and Derivatives
    Hernán R. Sánchez
    arXivPreprintarXiv licenceFull textPhysical chemistryarXiv
  4. Designing Ideal Denoisers for Chromatographic and Spectroscopic Signals
    M. Farooq Wahab
    ChemRxivPreprintCC BY-NC-NDGeneral chemistryChemRxiv
  5. Multi-Dimensional Benchmarking of Liquid Chromatographic Methods for Parabens Determination in Cosmetic Products: Toward Sustainable Analysis
    Abdulmalik M. Alqarni, Heba Shaaban, Ahmed Mostafa +6
    MoleculesPeer-reviewedCC BY 4.0Analytical chemistryCrossref

Cite

BibTeXRIS
BibTeX
@misc{murakami2026guiding,
  title = {{Guiding chromatographic purification through data-driven condition recommendations}},
  author = {Yuki Murakami and Nobuo Cho and Kosei Egami and Hiroto Yamazaki and Shoichi Ishida and Aoi Hirano and Yuri Fukushima and Masato Sumita and Ai Kohata and Kazushi Kinbara and Kei Terayama},
  howpublished = {ChemRxiv},
  year = {2026},
  month = oct,
  doi = {10.26434/chemrxiv.15009978/v1},
  url = {https://chemrxiv.org/doi/full/10.26434/chemrxiv.15009978/v1},
  note = {CC BY},
}
RIS
TY  - UNPB
TI  - Guiding chromatographic purification through data-driven condition recommendations
AU  - Yuki Murakami
AU  - Nobuo Cho
AU  - Kosei Egami
AU  - Hiroto Yamazaki
AU  - Shoichi Ishida
AU  - Aoi Hirano
AU  - Yuri Fukushima
AU  - Masato Sumita
AU  - Ai Kohata
AU  - Kazushi Kinbara
AU  - Kei Terayama
PY  - 2026
DA  - 2026/10/06
PB  - ChemRxiv
DO  - 10.26434/chemrxiv.15009978/v1
UR  - https://chemrxiv.org/doi/full/10.26434/chemrxiv.15009978/v1
AB  - Purification is essential for isolating compounds for reliable characterization and subsequent experiments; however, suitable chromatographic conditions are often still selected through trial and error. Herein, we present a data-driven framework that recommends a stationary phase or separation mode, solvent, and solvent ratio to support thin-layer chromatography (TLC) screening and column chromatography (CC) purification. Using purification records from publications and laboratory notebooks, we developed models to predict TLC and CC conditions. Models using product structures alone or in combination with reactant and agent information were compared across prediction tasks and data sources. Experimental evaluation of 11 previously unreported compounds demonstrated that ranked recommendations could guide TLC screening and the selection of CC purification conditions. Additionally, a web application was developed to provide users with flexible access to the prediction models. The proposed framework supports the selection of practical purification conditions and provides a foundation for integrating purification planning into future autonomous experimental workflows.
ER  -