The athlete microbiome project: integrating deep learning to reveal microbial associations of physical fitness

Regular physical training improves human fitness and health through direct effects on muscle and metabolism and indirect effects via alterations in gut microbiome composition. To determine whether athletes harbor a distinct gut microbiome and whether microbiome composition associates with established markers of physical fitness, maximum oxygen uptake (Vo_2max) and percent fat-free mass, we conducted a secondary analysis of amplicon sequencing data and metadata from published human microbiota studies across three continents. Participants were categorized as athletes (n = 656) or nonathletes (n = 199). Using multivariate statistics, random forest models, and a multilayer perceptron neural network, we identified structured differences in gut microbiome composition associated with fitness metrics and athletic status. Random forest regression models explained up to 63% of the variance in percent fat-free mass and 45% in Vo_2max, with taxa such as Faecalibacterium, Megamonas, Bifidobacterium, and Blautia ranking among the most informative predictive features across analyses. Classification models further demonstrated that athletic status could be predicted from microbiome composition: a mixed-effects-informed random forest achieved a balanced accuracy of 71%, whereas a multilayer perceptron captured coordinated, multivariate microbial patterns and achieved stable performance across stratified fivefold cross-validation and an independent held-out test set comprising 20% of samples not used during model training [balanced accuracy = 0.91; area under the receiver operating characteristic curve (AUC) = 0.97]. Together, these findings indicate that athletic status and fitness-related traits are associated with gut microbiome compositional patterns, highlighting candidate taxa for mechanistic validation and demonstrating the utility of integrative machine learning for distinguishing athletes from nonathletes.NEW & NOTEWORTHY From 855 gut microbiome samples spanning three continents, we identify microbial patterns associated with athletic status and physical fitness. We show that athletic status can be predicted from microbiome signatures [balanced accuracy ≈ 91%; area under the receiver operating characteristic curve (AUC) = 0.97]. Key taxa identified across models were linked to maximum oxygen uptake (Vo_2max) and % fat-free mass, highlighting multivariate microbiome features relevant to human performance.