Background Gut microbiome is gaining interest because its links with several diseases, including colorectal cancer (CRC). Results Here we performed a meta-analysis of 851 fecal metagenomic samples from five publicly available studies. We used an interpretable machine learning approach based on functional profiles, instead of the conventional taxonomic profiles, to produce a highly accurate predictor of CRC with better precision than those of previous proposals. Moreover, this approach is also able to discriminate samples with adenoma, which makes this approach very promising for CRC prevention by detecting early stages in which intervention is easier and more effective. In addition, interpretable machine learning methods allows extracting features relevant for the classification, which reveals basic molecular mechanisms accounting for the changes underwent by the microbiome functional landscape in the transition from healthy gut to adenoma and CRC conditions. Conclusion Functional profiles provide superior accuracy in predicting CCR and adenoma conditions than taxonomic profiles and additionally, in a context of explainable machine learning, provide useful hints on the molecular mechanisms operating in the microbiota behind these conditions.