Decoding the link of microbiome niches with homologous sequences enables accurately targeted protein structure prediction

Significance Metagenome sequencing provides a useful repository to extract evolutionary information and assist protein structure predictions. The sequence-search process, however, becomes increasingly prohibitive due to the huge library size. We hypothesize that there exist inherent evolutionary linkages between microbial niches and protein families that can be used to construct precise multiple sequence alignments (MSAs). To examine the hypothesis, we built a model library of four major biomes containing 4.25 billion sequences. Large-scale protein folding experiments revealed that MSAs collected from individually linked microbiomes can generate more accurate contact and structure models than those from all microbiome sequences but use significantly fewer computing resources. These results demonstrate the potential to solve the metagenome-search problem using a microbiome targeted approach.