In addition to data generated in our lab, we include highly curated raw data from the public domain in our SGKnowledgeBase™. Appropriate AWS cloud processing pipelines are triggered for metagenomics, metatransciptomics, RNA-Seq, meta-metabolomics or hybridization data followed by extensive data mining with StrainSelect™ to determine the precise strains and Savant™ to reveal novel gene products from microbial dark mater, chromosomes of completely novel coding regions. The resulting quantitative profiles of the microbial bioactives are then statistically evaluated and connected into the first of its kind microbiome therapeutic database from which we nominate the top assay candidates.