Efficient mass spectrometric characterization and classification of methylmalonic aciduria subtypes through urinary and blood metabolic profiles fusion

Abstract

Efficient subtype classification utilizing multiple biological information sources is clinically practical for precision treatment of inborn errors of metabolism (IEMs). This study utilized urinary GC–MS and dried blood spot MS/MS to enable complementary mass spectrometric characterization of pathological information for methylmalonic aciduria (MMA) subtypes. A novel mid-level data fusion strategy was subsequently described to effectively detect their subtle metabolic perturbations. In the proposed strategy, multivariate advantage was extracted via considering variable relationships in individual data blocks, separately. Further, it was extended to exploiting partial correlation across multiple data blocks, which induced the models between one data block and the first principal component (PC1) of another one for more valuable information recovery. The continuous values of PC1 replaced the traditional binary class labels, enabling suitable representation of disease heterogeneity numerically and subsequent accurate disease detection. Based on the unique role in exploratory data analysis, partial least squares discriminant analysis (PLS-DA) was coupled with bootstrap to form ensemble feature selection framework. It allowed the novel mid-level data fusion strategy to screen stable significant features. Investigated by two common MMA subtypes (mut and cblC) using urinary and blood metabolic profiles, the results showed that the novel mid-level data fusion strategy outperformed the traditional data fusion approaches both in predictive accuracy and biological interpretation. Besides, correlation network of the identified stable informative metabolites was visualized by chord plots, revealing different between-block biological interaction pattern for mut and cblC. Especially, in mut subtype, strong interactions could be occurred between the urinary metabolite of 3-OH-propionic-2 and two blood metabolite ratios (C3/C2 and C3/C0), separately. The findings deepened the biological insights into the disease pathology of mut and cblC. The integration of multiple analytical sources combined with the proposed novel mid-level data fusion strategy thus opened the possibilities to achieve desirable subtype classification for MMA. It suitably guided the early and timely medical intervention for IEMs.