A Reference-Guided Large Language Model Workflow for Mobile Phase Selection in Thin-Layer Chromatography Enabled by a Polarity-Space Tetrahedron Strategy

Wei-Song Kong

doi:10.1016/j.aca.2026.345859

A Reference-Guided Large Language Model Workflow for Mobile Phase Selection in Thin-Layer Chromatography Enabled by a Polarity-Space Tetrahedron Strategy

2026-06-18

0

PRE

AI

W

Wei-Song Kong

S

Song-Xue Shao

L

Li-Na Zhu *

X

Xi Yu *

DOI：10.1016/j.aca.2026.345859

Original

Original request for help

Save

Abstract

En 中文

• A reference-guided LLM workflow is developed for TLC mobile phase optimization. • A polarity-space tetrahedron strategy is proposed for reference compound selection. • Similarity-weighted tetrahedron selection improves recommendation reliability. • The best strategy achieves 81.48% availability in internal evaluation. • Experimental validation confirms an 92.16% separation success rate.

A Reference-Guided Large Language Model Workflow for Mobile Phase Selection in Thin-Layer Chromatography Enabled by a Polarity-Space Tetrahedron Strategy

Abstract

Journal

Organization

Cited Papers

Citing Papers