“…While metabolome studies have become increasingly used in characterizing emerging properties of the metabolome and in relating metabolomic change to host pathological states [32,33,34,35,36,37,38,39,40,41,42], metabolome based ML also has its limitations: (1) high cost; (2) extremely high dimension of input (i.e., number of different metabolites vs the number of samples), especially in untargeted studies [22]; (3) a large number of unknown metabolites that have a molecular composition, but no known function [43,44]; (4) large variability of nomenclature and experimental protocols among different studies [45,46]. Three approaches can be proposed to combine microbiome and metabolome data to cope with the limitations of each information source by itself: (1) Qualitative microbiome-metabolites relations.…”