Fig. 1
From: Probabilistic metabolite annotation using retention time prediction and meta-learned projections
RTs measured in different CMs (y-axis) compared with the predictions of a machine learning model trained on SMRT (x-axis). The figure also shows the RTs of the same molecule (PubChem ID 10742) in the different CMs (shown with the star shapes), which illustrates the variability in the times measured with different experimental configurations. Since the model has been trained on a single Chromatographic Method (CM), the experimental RTs on different CMs do not match its predictions (dashed line). This figure illustrates the need for a projection method able to translate the predictions of a model trained on a specific Chromatographic Method (CM) to different CMs