Fig. 1: The scheme for chromatographic enantioseparation. | Nature Communications

Fig. 1: The scheme for chromatographic enantioseparation.

From: Retention time prediction for chromatographic enantioseparation by quantile geometry-enhanced graph neural network

Fig. 1

a The diagram for chiral molecules, which are mirror images of each other, but not superimposable. b The comparison between classic separation ways by multiple trials with different conditions and machine learning (ML) models that can recommend the most suitable conditions with the highest separation probability. c The generation procedure and contents of the chiral molecular retention time dataset (CMRT dataset) in this work. Experimental data of 25,847 molecules (including 11,720 pairs of enantiomers) are extracted from 644 articles about asymmetric catalysis, containing SMILES, experimental information, HPLC column information, and corresponding retention time.

Back to article page