Skip to main content
Fig. 1 | Genome Biology

Fig. 1

From: MIRTH: Metabolite Imputation via Rank-Transformation and Harmonization

Fig. 1

Workflow for MIRTH Imputation of Metabolomics Data. a Individual datasets are normalized and rank-tranformed, accounting for left-censoring. b Preprocessed datasets (\(\varvec{D_i}\)) are combined into a sparse aggregate data matrix (\(\varvec{X}\)), which is then factorized into embedding matrices \(\varvec{W}\) and \(\varvec{H}\). The product \(\varvec{WH}\) yields an imputed data matrix (\(\varvec{\hat{X}}\)). c Aggregate data from 9 pan-cancer metabolomics datasets with tumor and normal samples reveals poor across-dataset metabolite feature overlap and high degree of missingness

Back to article page