To understand the impact of genome sequence variation (the genotype) responsible for biological diversity and human health (the phenotype) including cystic fibrosis and Alzheimer’s disease, we developed a Gaussian-process-based machine learning (ML) approach, variation spatial profiling (VSP). VSP uses a sparse collection of known variants found in the population that perturb the protein fold to define unknown variant function based on the emergent general principle of spatial covariance (SCV). SCV quantitatively captures the role of proximity in genotype-to-phenotype spatial-temporal relationships. Phenotype landscapes generated through SCV provide a platform that can be used to describe the functional properties that drive sequence-to-function-to-structure design of the polypeptide fold at atomic resolution. We provide proof of principle that SCV can enable the use of population-based genomic platforms to define the origins and mechanism of action of genotype-to-phenotype transformations contributing to the health and disease of an individual. Display omitted •We develop VSP, a Gaussian-process-based approach to interpret genomic diversity•VSP is based on spatial covariance (SCV) in the genotype-to-phenotype transformation•SCV uses population genomics to inform individualized phenotypes at atomic resolution•Phenotype landscapes generated through SCV enable high-definition medicine Wang and Balch develop variation spatial profiling (VSP), a machine learning approach to integrate genomics and phenomics of the population to inform on the phenotype of the individual at atomic resolution. VSP is based on the principle of spatial covariance (SCV) that defines central dogma as matrices to track information flow from the genotype-to-phenotype to facilitate high-definition medicine.