Contribution of a combined approach using refined enterotyping and non-negative matrix factorization (NMF) to the characterization of the gut microbiota in Tunisia, North Africa

Abstract

Abstract This pilot study aimed to assess the enhanced capabilities of a combined approach using refined enterotyping and non-negative matrix factorization (NMF) for identifying specific microbiota patterns in healthy adults in Tunisia. Shotgun metagenomic sequencing was performed on 21 stool samples. Taxonomic classification was carried out using Kraken2, followed by Bracken analysis. Enterotype (ET) assignment was performed using a publicly available, reference-based classification tool involving Fuzzy-k-means (FKM) clustering. Next, NMF was applied to identify ‘enterosignatures’ (ESs). The FKM approach revealed a co-dominance of Prevotella-ET (P-ET, 57%) and Firmicutes-ET (F-ET, 38%) with 41% of P-ET samples exhibiting a significant deviation from the reference enterotype center. These latter had a lower proportion of Prevotella-ES and a higher proportion of Bacteroides/Phocaeicola-, Firmicutes- and/or Bifidobacterium-enriched ESs. The F-ET samples were differentially enriched by Blautia (p=0.007) and Vescimonas (p=0.007). NMF revealed within this group, a candidate Firmicutes-associated ES driven by Blautia and encompassing Vescimonas, Akkermansia, and Methanobrevibacter. These findings demonstrate the combined power of refined enterotyping and NMF in characterizing gut microbiota, providing a key methodology for future large-scale research. However, our relatively small sample size limits statistical power and biological interpretation, making this study exploratory in nature. Candidate ES requires validation in larger independent datasets.