Fig. 7
From: SMILE: systems metabolomics using interpretable learning and evolution
Synergy network of top 3% most common metabolite pairs in the AD metabolomic data. Metabolite pairs with the most frequent co-occurrences are represented as edges and their two end points. The edge width is proportional to pairwise co-occurrence frequency, also labeled on each edge. The vertex size is proportional to individual feature’s occurrence frequency