Genome sequencing is enabling precision medicine-tailoring treatment to the unique constellation of variants in an individual's genome. The impact of recurrent pathogenic variants is often understood, however there is a long tail of rare genetic variants that are uncharacterized. The problem of uncharacterized rare variation is especially acute when it occurs in genes of known clinical importance with functionally consequential variants and associated mechanisms. Variants of uncertain significance (VUSs) in these genes are discovered at a rate that outpaces current ability to classify them with databases of previous cases, experimental evaluation, and computational predictors. Clinicians are thus left without guidance about the significance of variants that may have actionable consequences. Computational prediction of the impact of rare genetic variation is increasingly becoming an important capability. In this paper, we review the technical and ethical challenges of interpreting the function of rare variants in two settings: inborn errors of metabolism in newborns and pharmacogenomics. We propose a framework for a genomic learning healthcare system with an initial focus on early-onset treatable disease in newborns and actionable pharmacogenomics. We argue that (1) a genomic learning healthcare system must allow for continuous collection and assessment of rare variants, (2) emerging machine learning methods will enable algorithms to predict the clinical impact of rare variants on protein function, and (3) ethical considerations must inform the construction and deployment of all rare-variation triage strategies, particularly with respect to health disparities arising from unbalanced ancestry representation.

Current genetic testenhancer and narrows the diagnostic intervals for rare diseases provide a diagnosis in only a modest proportion of cases. The Full-Genome Analysis method, FGA, combines long-range assembly and whole-genome sequencing to detect small variants, structural variants with breakpoint resolution, and phasing. We built a variant prioritization pipeline and tested FGA's utility for diagnosis of rare diseases in a clinical setting. FGA identified structural variants and small variants with an overall diagnostic yield of 40% (20 of 50 cases) and 35% in exome-negative cases (8 of 23 cases), 4 of these were structural variants. FGA detected and mapped structural variants that are missed by short reads, including non-coding duplication, and phased variants across long distances of more than 180 kb. With the prioritization algorithm, longer DNA technologies could replace multiple tests for monogenic disorders and expand the range of variants detected. Our study suggests that genomes produced from technologies like FGA can improve variant detection and provide higher resolution genome maps for future application.