The landscape of tolerated genetic variation in humans and primates

Abstract

Personalized genome sequencing has revealed millions of genetic differences between individuals, but our understanding of their clinical relevance remains largely incomplete. To systematically decipher the effects of human genetic variants, we obtained whole-genome sequencing data for 809 individuals from 233 primate species and identified 4.3 million common protein-altering variants with orthologs in humans. We show that these variants can be inferred to have nondeleterious effects in humans based on their presence at high allele frequencies in other primate populations. We use this resource to classify 6% of all possible human protein-altering variants as likely benign and impute the pathogenicity of the remaining 94% of variants with deep learning, achieving state-of-the-art accuracy for diagnosing pathogenic variants in patients with genetic diseases.

PreMode predicts mode-of-action of missense variants by deep graph representation learning of protein sequence and structural context

“…In the past decade, many computaQonal methods have been developed [11][12][13][14][15][16][17][18][19][20][21][22] to predict variant effects in a binary manner aiming at disQnguishing pathogenic and benign variants. These methods showed that pathogenicity can be predicted by manually encoded or self-learned features based on sequence conservaQon, protein structures, and populaQon allele frequency.…”

Applications of artificial intelligence in clinical laboratory genomics

“…Newly described in a publication in Science, Primate-AI3D is a deep learning model that leverages natural variation in primates to make inferences about the impact of DNA variants in humans (Gao et al, 2023). Built on the premise that protein-altering variants commonly found in any non-human primate have been tolerated by natural selection-and are thus likely benign in humans-Primate-AI3D uses deep learning to map genetic variants onto 3D protein structures partially derived from AlphaFold (Jumper et al, 2021) to make predictions about their pathogenicity.…”

Artificial intelligence for neurodegenerative experimental models

“…Another application of ML models is to predict the effect of genetic variants by learning the mapping between DNA sequence and functional genomic annotations. Specifically, PrimateAI 114 and its successor PrimateAI‐3D 115 predict whether genetic variants observed in humans are likely to be deleterious or benign based on whether the variant is common in non‐human primate populations. The underlying premise being that if a variant is tolerated in species closely related to humans, it is more likely to be benign in humans as well.…”