The human genome harbors a variety of genetic variations. Single-nucleotide changes that alter amino acids in protein-coding regions are one of the major causes of human phenotypic variation and diseases. These single-amino acid variations (SAVs) are routinely found in whole genome and exome sequencing. Evaluating the functional impact of such genomic alterations is crucial for diagnosis of genetic disorders. We developed DeepSAV, a deep-learning convolutional neural network to differentiate disease-causing and benign SAVs based on a variety of protein sequence, structural and functional properties. Our method outperforms most stand-alone programs, and the version incorporating population and gene-level information (DeepSAV+PG) has similar predictive power as some of the best available. We transformed DeepSAV scores of rare SAVs in the human population into a quantity termed "mutation severity measure" for each human protein-coding gene. It reflects a gene's tolerance to deleterious missense mutations and serves as a useful tool to study gene-disease associations. Genes implicated in cancer, autism, and viral interaction are found by this measure as intolerant to mutations, while genes associated with a number of other diseases are scored as tolerant. Among known disease-associated genes, those that are mutation-intolerant are likely to function in development and signal transduction pathways, while those that are mutation-tolerant tend to encode metabolic and mitochondrial proteins. Author summary: Human genetic variations in various forms are constantly found in whole genome and exome sequencing of general population and patients. It remains a challenging task to assess the functional impact of these variations. In this study, we performed comprehensive analysis of single-amino-acid variations (SAVs) in terms of their sequence, structure, and functional properties. We further developed a deep neural network-based method to predict the functional impact of SAVs. Our method is among the top performers compared to existing programs in differentiating pathogenic and benign SAVs. We designed a mutation severity measure for human protein-coding genes by aggregating the predicted scores of SAVs found in the human general population. Such a measure reflects a gene's tolerance to deleterious missense mutations and serves as a useful tool to study gene-disease associations. We found that genes implicated in cancer, autism, and viral interaction are more likely to be intolerant to mutations than genes with other diseases. Disease-associated genes with strong mutation intolerance tend to function in development and signal transduction pathways. On the other end of the mutation severity spectrum, mutation-tolerant genes often encode proteins functioning in mitochondria and metabolic pathways. [ABSTRACT FROM AUTHOR]