MACIE (Multi-dimensional Annotation Class Integrative Estimation) is an unsupervised multivariate mixed model framework to assess multi-dimensional functional impacts for both coding and non-coding variants in the human genome. MACIE integrates a variety of functional annotations, including protein function scores, evolutionary conservation scores, and epigenetic annotations from ENCODE and Roadmap Epigenomics, and estimates the joint posterior probabilities of each genetic variant being functional. For each non-synonymous coding variant, the MACIE score is a vector of length 4, representing the estimated joint posterior probabilities of ���not damaging protein functional and evolutionarily conserved��� (MACIE01); ���damaging protein functional and not evolutionarily conserved��� (MACIE10); ���not damaging protein functional and not evolutionarily conserved��� (MACIE00); ���both damaging protein functional and evolutionarily conserved��� (MACIE11). MACIE_protein is the estimated posterior probability of ���damaging protein functional���, which is the sum of MACIE10 and MACIE11; MACIE_conserved is the estimated posterior probability of ���evolutionarily conserved���, which is the sum of MACIE01 and MACIE11; MACIE_anyclass is the estimated posterior probability of ���damaging protein functional��� or ���evolutionarily conserved���, which is the sum of MACIE01, MACIE10, and MACIE11. For each non-coding and synonymous coding variant, the MACIE score is a vector of length 4, representing the estimated joint posterior probabilities of ���not evolutionarily conserved and regulatory functional��� (MACIE01); ���evolutionarily conserved and not regulatory functional��� (MACIE10); ���not evolutionarily conserved and not regulatory functional��� (MACIE00); ���both evolutionarily conserved and regulatory functional (MACIE11). MACIE_conserved is the estimated posterior probability of ���evolutionarily conserved���, which is the sum of MACIE10 and MACIE11; MACIE_regulatory is the estimated posterior probability of ���regulatory functional���, which is the sum of MACIE01 and MACIE11; MACIE_anyclass is the estimated posterior probability of ���evolutionarily conserved��� or ���regulatory functional���, which is the sum of MACIE01, MACIE10, and MACIE11.