A Probabilistic Model to Predict Clinical Phenotypic Traits from Genome Sequencing

Genetic screening is becoming possible on an unprecedented scale. However, its utility remains controversial. Although most variant genotypes cannot be easily interpreted, many individuals nevertheless attempt to interpret their genetic information. Initiatives such as the Personal Genome Project (PGP) and Illumina's Understand Your Genome are sequencing thousands of adults, collecting phenotypic information and developing computational pipelines to identify the most important variant genotypes harbored by each individual. These pipelines consider database and allele frequency annotations and bioinformatics classifications. We propose that the next step will be to integrate these different sources of information to estimate the probability that a given individual has specific phenotypes of clinical interest. To this end, we have designed a Bayesian probabilistic model to predict the probability of dichotomous phenotypes. When applied to a cohort from PGP, predictions of Gilbert syndrome, Graves' disease, non-Hodgkin lymphoma, and various blood groups were accurate, as individuals manifesting the phenotype in question exhibited the highest, or among the highest, predicted probabilities. Thirty-eight PGP phenotypes (26%) were predicted with area-under-the-ROC curve (AUC)>0.7, and 23 (15.8%) of these were statistically significant, based on permutation tests. Moreover, in a Critical Assessment of Genome Interpretation (CAGI) blinded prediction experiment, the models were used to match 77 PGP genomes to phenotypic profiles, generating the most accurate prediction of 16 submissions, according to an independent assessor. Although the models are currently insufficiently accurate for diagnostic utility, we expect their performance to improve with growth of publicly available genomics data and model refinement by domain experts.Author Summary: The Personal Genome Project (PGP) is an emerging community whose goal is to collect and publicly share genomes, environmental data, medical records, and clinical traits from tens of thousands of volunteers. This information may enable computer software to establish the relationships between patterns of alterations in human genomes and clinical phenotypic traits. We describe a novel, Bayesian mathematical model to predict such traits from genome sequence and population prevalence. The core of the model is a set of phenotypic penetrance estimates for aggregated genetic variants, which are learned without any information about particular individuals in a cohort of interest. We illustrate the model's utility in ranking individuals in the PGP cohort, according to their probability of having 146 phenotypes.