Knowledge discovery for precision medicine big data is an important aspect in promoting clinical translational applications. By mining biomedical knowledge, it is possible to drive the discovery of new biomedical knowledge. We have implemented a series of methods and tools, including: (1) for the first time, implementing biological theme comparison for complex experimental designs, (2) universal enrichment analysis methods for interpreting omics data, (3) measuring semantic similarity to assist in biological knowledge discovery, (4) cistromic data mining to aid in the discovery of (unknown) co-regulators, (5) integration of biological knowledge to enhance the biological interpretability of single-cell clustering, and (6) characterization of single-cell functional states and identification of spatial specific biological functions. This series of methods and software enables a more diverse range of biomedical knowledge to be applied at a greater variety of species, allowing biomedical knowledge to support biological big data mining and extract novel and potential disoveries.
