Comprehensive functional annotation of metagenomes and microbial genomes using a deep learning-based method

Comprehensive protein function annotation is essential for understanding microbiome-related disease mechanisms in the host organisms. However, a large portion of human gut microbial proteins lack functional annotation. Here, we have developed a new metagenome analysis workflow integrating de novo genome reconstruction, taxonomic profiling, and deep learning-based functional annotations from DeepFRI. Using this workflow, we generated a sequence catalogue of 1.9 million nonredundant microbial genes. This improved microbial gene annotation coverage to 99% of the gene catalogue, although they are less specific than those from orthology-based approaches. This workflow will contribute to novel understanding of the functional signature of the human gut microbiome in health and disease as well as guiding future metagenomics studies.