The landscape of tolerated genetic variation in humans and primates

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 human. We show that these variants can be inferred to have non-deleterious effects in human 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. One Sentence Summary Deep learning classifier trained on 4.3 million common primate missense variants predicts variant pathogenicity in humans.

• Publication year

  2023

• Venue

  bioRxiv

• Publication date

  2023-05-02

• Fields of study

  Biology, Medicine

• Identifiers
  DOI 10.1126/science.abn8197PMID 37205491PMCID 10187174
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar, PubMed

• No claims are published for this paper.

• No concepts are published for this paper.

• A global catalog of whole-genome diversity from 233 primate species

  2023cited by this paper
• AlphaFold Protein Structure Database: massively expanding the structural coverage of protein-sequence space with high-accuracy models

  2021cited by this paper
• OUP accepted manuscript

  2021cited by this paper
• Accurate prediction of protein structures and interactions using a 3-track neural network

  2021cited by this paper
• Highly accurate protein structure prediction with AlphaFold

  2021cited by this paper
• Language models enable zero-shot prediction of the effects of mutations on protein function

  2021cited by this paper
• Acquired Resistance to KRASG12C Inhibition in Cancer.

  2021cited by this paper
• Disease variant prediction with deep generative models of evolutionary data

  2021influential reference
• MutationTaster2021

  2021cited by this paper
• SLCO1B1: Application and Limitations of Deep Mutational Scanning for Genomic Missense Variant Function

  2021cited by this paper
• The TOPMed genomic resource for human health

  2021influential reference
• CADD-Splice—improving genome-wide variant effect prediction using deep learning-derived splice scores

  2021cited by this paper
• Addendum: The mutational constraint spectrum quantified from variation in 141,456 humans

  2021cited by this paper
• MSA Transformer

  2021cited by this paper
• Testing Sex-Biased Admixture Origin of Macaque Species Using Autosomal and X-Chromosomal Genomic Sequences

  2020cited by this paper
• Evidence for 28 genetic disorders discovered by combining healthcare and research data

  2020cited by this paper
• The Human Gene Mutation Database (HGMD®): optimizing its use in a clinical diagnostic or research setting

  2020cited by this paper
• A comparative genomics multitool for scientific discovery and conservation

  2020cited by this paper
• The genetic landscape for amyloid beta fibril nucleation accurately discriminates familial Alzheimer’s disease mutations

  2020cited by this paper
• Deep Mutational Scanning Reveals the Structural Basis for α-Synuclein Activity

  2020cited by this paper
• Reanalysis and reclassification of rare genetic variants associated with inherited arrhythmogenic syndromes

  2020cited by this paper
• The mutational constraint spectrum quantified from variation in 141,456 humans

  2020cited by this paper
• Primate phylogenomics uncovers multiple rapid radiations and ancient interspecific introgression

  2020cited by this paper
• LIST-S2: taxonomy based sorting of deleterious missense mutations across species

  2020cited by this paper
• Multiplexed measurement of variant abundance and activity reveals VKOR topology, active site and human variant impact

  2020cited by this paper
• Distribution of CD36 deficiency in different Chinese ethnic groups.

  2020cited by this paper
• The role of CD36 in cardiovascular disease

  2020cited by this paper
• Massively parallel functional testing of MSH2 missense variants conferring Lynch syndrome risk

  2020cited by this paper
• dbNSFP v4: a comprehensive database of transcript-specific functional predictions and annotations for human nonsynonymous and splice-site SNVs

  2020cited by this paper
• Genomic mechanisms of physiological and morphological adaptations of limestone langurs to karst habitats.

  2019cited by this paper
• BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding

  2019cited by this paper
• Inferring Genome-Wide Correlations of Mutation Fitness Effects between Populations

  2019cited by this paper
• Elucidating the molecular determinants of Aβ aggregation with deep mutational scanning

  2019cited by this paper
• Clinical Utility of Reinterpreting Previously Reported Genomic Epilepsy Test Results for Pediatric Patients

  2019cited by this paper
• PanelApp crowdsources expert knowledge to establish consensus diagnostic gene panels

  2019cited by this paper
• ZeRO: Memory Optimization Towards Training A Trillion Parameter Models

  2019cited by this paper
• A high-quality genome assembly for the endangered golden snub-nosed monkey (Rhinopithecus roxellana)

  2019cited by this paper
• Elucidating the Molecular Determinants of Aβ Aggregation with Deep Mutational Scanning

  2019cited by this paper
• Flexible and scalable diagnostic filtering of genomic variants using G2P with Ensembl VEP

  2019cited by this paper
• Structural and functional characterization of G protein–coupled receptors with deep mutational scanning

  2019cited by this paper
• Challenges and Considerations in Sequence Variant Interpretation for Mendelian Disorders

  2019cited by this paper
• HH-suite3 for fast remote homology detection and deep protein annotation

  2019cited by this paper
• Sequencing of 53,831 diverse genomes from the NHLBI TOPMed Program

  2019cited by this paper
• Identification of Misclassified ClinVar Variants via Disease Population Prevalence.

  2018cited by this paper
• Multiplex Assessment of Protein Variant Abundance by Massively Parallel Sequencing

  2018cited by this paper
• Predicting the clinical impact of human mutation with deep neural networks

  2018influential reference
• Mutational processes shape the landscape of TP53 mutations in human cancer

  2018cited by this paper
• Dating genomic variants and shared ancestry in population-scale sequencing data

  2018cited by this paper
• Deep generative models of genetic variation capture the effects of mutations

  2018cited by this paper
• The UK Biobank resource with deep phenotyping and genomic data

  2018influential reference
• Genome-wide de novo risk score implicates promoter variation in autism spectrum disorder

  2018cited by this paper
• Ancient hybridization and admixture in macaques (genus Macaca) inferred from whole genome sequences.

  2018cited by this paper
• TF-Ranking: Scalable TensorFlow Library for Learning-to-Rank

  2018cited by this paper
• Clinical sequencing: From raw data to diagnosis with lifetime value

  2018cited by this paper
• A saturation mutagenesis approach to understanding PTEN lipid phosphatase activity and genotype-phenotypes relationships

  2018cited by this paper
• Estimating the Selective Effects of Heterozygous Protein Truncating Variants from Human Exome Data

  2017cited by this paper
• Prevalence and architecture of de novo mutations in developmental disorders

  2017cited by this paper
• A framework for exhaustively mapping functional missense variants

  2017cited by this paper
• TERT promoter mutations in telomere biology.

  2017cited by this paper
• Deconstruction of the Ras switching cycle through saturation mutagenesis

  2017cited by this paper
• Inferring the Joint Demographic History of Multiple Populations: Beyond the Diffusion Approximation

  2017influential reference
• Evolving health care through personal genomics

  2017cited by this paper
• Impending extinction crisis of the world’s primates: Why primates matter

  2017cited by this paper
• Contribution of rare inherited and de novo variants in 2,871 congenital heart disease probands

  2017influential reference
• PERCH: A Unified Framework for Disease Gene Prioritization

  2017cited by this paper
• Speciation over the edge: gene flow among non-human primate species across a formidable biogeographic barrier

  2017cited by this paper
• DEOGEN2: prediction and interactive visualization of single amino acid variant deleteriousness in human proteins

  2017cited by this paper
• Mixed Precision Training

  2017cited by this paper
• Phenotypic Characterization of a Comprehensive Set of MAPK1/ERK2 Missense Mutants.

  2016cited by this paper
• Using high-resolution variant frequencies to empower clinical genome interpretation

  2016cited by this paper
• The UCSC Genome Browser database: 2017 update

  2016cited by this paper
• RaptorX-Property: a web server for protein structure property prediction

  2016cited by this paper
• Identification of misclassified ClinVar variants using disease population prevalence

  2016cited by this paper
• Biallelic CACNA1A mutations cause early onset epileptic encephalopathy with progressive cerebral, cerebellar, and optic nerve atrophy

  2016cited by this paper
• Chimpanzee genomic diversity reveals ancient admixture with bonobos

  2016cited by this paper
• REVEL: An Ensemble Method for Predicting the Pathogenicity of Rare Missense Variants.

  2016cited by this paper
• A reference data set of 5.4 million phased human variants validated by genetic inheritance from sequencing a three-generation 17-member pedigree

  2016cited by this paper
• The population genetics of human disease: The case of recessive, lethal mutations

  2016cited by this paper
• Uniclust databases of clustered and deeply annotated protein sequences and alignments

  2016cited by this paper
• dbNSFP v3.0: A One‐Stop Database of Functional Predictions and Annotations for Human Nonsynonymous and Splice‐Site SNVs

  2016cited by this paper
• Genomic analysis of snub-nosed monkeys (Rhinopithecus) identifies genes and processes related to high-altitude adaptation

  2016cited by this paper
• Gaussian Error Linear Units (GELUs)

  2016cited by this paper
• M-CAP eliminates a majority of variants of uncertain significance in clinical exomes at high sensitivity

  2016cited by this paper
• KBG Syndrome: A Case Report and Longitudinal Assessment of Long‐Acting Recombinant Human Growth Hormone Therapy

  2015cited by this paper
• Massively Parallel Functional Analysis of BRCA1 RING Domain Variants

  2015cited by this paper
• ClinGen and Genetic Testing.

  2015cited by this paper
• ClinVar: public archive of interpretations of clinically relevant variants

  2015influential reference
• Identification of cis-suppression of human disease mutations by comparative genomics

  2015cited by this paper
• UK Biobank: An Open Access Resource for Identifying the Causes of a Wide Range of Complex Diseases of Middle and Old Age

  2015influential reference
• Analysis of protein-coding genetic variation in 60,706 humans

  2015cited by this paper
• Insights into Autism Spectrum Disorder Genomic Architecture and Biology from 71 Risk Loci.

  2015cited by this paper
• ClinGen and Genetic Testing.

  2015cited by this paper
• DANN: a deep learning approach for annotating the pathogenicity of genetic variants

  2015cited by this paper
• An integrative approach to predicting the functional effects of non-coding and coding sequence variation

  2015cited by this paper
• ClinGen--the Clinical Genome Resource.

  2015cited by this paper
• CACNA1A haploinsufficiency causes cognitive impairment, autism and epileptic encephalopathy with mild cerebellar symptoms

  2015cited by this paper
• Guidelines for investigating causality of sequence variants in human disease

  2014cited by this paper
• No evidence that selection has been less effective at removing deleterious mutations in Europeans than in Africans

  2014cited by this paper
• Peutz-Jeghers syndrome with germline mutation of STK11

  2014cited by this paper
• Medical genomics: The intricate path from genetic variant identification to clinical interpretation

  2014cited by this paper

• MissenseHMM: state-based annotations for missense variants through joint modeling of pathogenicity scores

  2026influential citation
• Bridging structure and function: artificial intelligence-based modelling of kidney proteins.

  2026cites this paper
• Integration of genetic information into the digital ecosystems of modern primate biobanks: opportunities and challenges

  2025cites this paper
• Leveraging protein language models to identify complex trait associations with previously inaccessible classes of functional rare variants

  2025cites this paper
• When genotype and phenotype disagree: rethinking thrombophilia testing in the genomic era.

  2025cites this paper
• Machine learning models incorporating genotype and ancestry improve severe asthma risk prediction

  2025cites this paper
• A case of late-onset carbamoyl phosphate synthetase 1 deficiency: diagnostic challenges and management in a low-resource setting.

  2025cites this paper
• Estimation and mapping of the missing heritability of human phenotypes

  2025cites this paper
• Physical Activity and Cardiovascular Outcomes in Phenotype-Negative Cardiomyopathy Variant Carriers.

  2025cites this paper
• Flexibly Modeling Rare Variant Pathogenicity Improves Gene Discovery for Complex Traits

  2025influential citation
• Reflections on the Presence of Human Cancer Genes in Primate Genomes

  2025influential citation
• Functional Characterization of Variants of Unknown Significance of Fibroblast Growth Factor Receptors 1-4 and Comparison With AI Model–Based Prediction

  2025cites this paper
• BayesRVAT enhances rare-variant association testing through Bayesian aggregation of functional annotations

  2025cites this paper
• Comprehensive molecular impact mapping of common and rare variants at GWAS loci

  2025cites this paper
• Genomic heterogeneity inflates the performance of variant pathogenicity predictions

  2025cites this paper
• Borzoi-informed fine mapping improves causal variant prioritization in complex trait GWAS

  2025cites this paper
• The structural context of mutations in proteins predicts their effect on antibiotic resistance

  2025cites this paper
• Predicting protein-protein interactions in the human proteome.

  2025cites this paper
• Phenotypic pleiotropy of missense variants in human B cell confinement receptor P2RY8

  2025cites this paper
• A DNA language model based on multispecies alignment predicts the effects of genome-wide variants

  2025cites this paper
• Evolutionary constrained genes associated with autism spectrum disorder across 2,054 nonhuman primate genomes

  2025cites this paper
• Big data and transformative bioinformatics in genomic diagnostics and beyond.

  2025cites this paper
• A curated dataset of great ape genome diversity

  2025cites this paper
• Leveraging protein structural information to improve variant effect prediction

  2025cites this paper
• Historical Demography and Species Distribution Models Shed Light on Speciation in Primates of Northeast India

  2025cites this paper
• Bayesian Aggregation of Multiple Annotations Enhances Rare Variant Association Testing

  2025cites this paper
• A Phylogenetic Approach to Genomic Language Modeling

  2025cites this paper
• Critical assessment of missense variant effect predictors on disease-relevant variant data

  2025influential citation
• Analysis of canine gene constraint identifies new variants for orofacial clefts and stature

  2025cites this paper
• Genomic basis of non-human-primate diversity and adaptation

  2025cites this paper
• Genome-wide allele-specific expression in multi-tissue samples from healthy male baboons reveals the transcriptional complexity of mammals

  2025cites this paper
• Whole-genome sequencing reveals rare and structural variants contributing to psoriasis and identifies CERCAM as a risk gene

  2025cites this paper
• The continued promise of genomic technologies and software in neurogenetics

  2025cites this paper
• Biallelic variants in the conserved ribosomal protein chaperone gene PDCD2 are associated with hydrops fetalis and early pregnancy loss

  2025cites this paper
• Guidelines for releasing a variant effect predictor

  2025cites this paper
• Functional characterization of all CDKN2A missense variants and comparison to in silico models of pathogenicity

  2025cites this paper
• Understanding Language Model Scaling on Protein Fitness Prediction

  2025cites this paper
• Restoring flowcell type and basecaller configuration from FASTQ files of nanopore sequencing data

  2025cites this paper
• Variant Classification Using Proteomics-Informed Large Language Models Increases Power of Rare Variant Association Studies and Enhances Target Discovery

  2025cites this paper
• The Maximum Genetic Diversity Theory: A Comprehensive Framework for Understanding Evolutionary Processes

  2025cites this paper
• From Likelihood to Fitness: Improving Variant Effect Prediction in Protein and Genome Language Models

  2025cites this paper
• Predicting expression-altering promoter mutations with deep learning.

  2025cites this paper
• Association of human-specific expanded short tandem repeats with neuron-specific regulatory features

  2025cites this paper
• Investigating the sources of variable impact of pathogenic variants in monogenic metabolic conditions

  2025cites this paper
• Prediction of Human Pathogenic Start Loss Variants Based on Multi-channel Features

  2025cites this paper
• Estimation of demography and mutation rates from one million haploid genomes.

  2025cites this paper
• Comparative Genomic Screening Identifies Developmental Constraint Loci Underscoring the Phenotypic Evolution of Syngnathids.

  2025cites this paper
• AlphaFold 3: an unprecedent opportunity for fundamental research and drug development

  2025cites this paper
• Prevalence and impact of molecular variation in the three-prime repair exonuclease 1 TREX1 and its implications for oncology

  2025cites this paper
• Multi-dimensional annotation of porcine variants using genomic and epigenomic features in pigs

  2025cites this paper
• MVmamba Deciphers Missense Variant Pathogenicity via Enhanced Bi-Mamba and Structure-Informed Protein Language Model

  2025cites this paper
• Estimation of demography and mutation rates from one million haploid genomes

  2024cites this paper
• A foundational large language model for edible plant genomes

  2024cites this paper
• The Potential Utility of Large Language Models in Molecular Pathology.

  2024cites this paper
• CADD v1.7: using protein language models, regulatory CNNs and other nucleotide-level scores to improve genome-wide variant predictions

  2024cites this paper
• PrimateAI-3D outperforms AlphaMissense in real-world cohorts

  2024cites this paper
• Functional genomics and small molecules in mitochondrial neurodevelopmental disorders

  2024cites this paper
• PRESCOTT: a population aware, epistatic, and structural model accurately predicts missense effects

  2024cites this paper
• Biallelic variation in the choline and ethanolamine transporter FLVCR1 underlies a pleiotropic disease spectrum from adult neurodegeneration to severe developmental disorders

  2024cites this paper
• Unifying approaches from statistical genetics and phylogenetics for mapping phenotypes in structured populations

  2024cites this paper
• Toward physics‐based precision medicine: Exploiting protein dynamics to design new therapeutics and interpret variants

  2024cites this paper
• Joint, multifaceted genomic analysis enables diagnosis of diverse, ultra-rare monogenic presentations

  2024cites this paper
• When Paul Berg meets Donald Crothers: an achiral connection through protein biosynthesis

  2024cites this paper
• MLe-KCNQ2: An Artificial Intelligence Model for the Prognosis of Missense KCNQ2 Gene Variants

  2024cites this paper
• PreMode predicts mode-of-action of missense variants by deep graph representation learning of protein sequence and structural context

  2024cites this paper
• High-throughput screening of human genetic variants by pooled prime editing

  2024cites this paper
• A multi-million-year natural experiment

  2024cites this paper
• The landscape of regional missense mutational intolerance quantified from 125,748 exomes

  2024cites this paper
• Guidelines for releasing a variant effect predictor

  2024cites this paper
• Genetic evidence for involvement of β2-adrenergic receptor in brown adipose tissue thermogenesis in humans

  2024cites this paper
• Joint genotypic and phenotypic outcome modeling improves base editing variant effect quantification

  2024cites this paper
• Fine-tuning Protein Language Models with Deep Mutational Scanning improves Variant Effect Prediction

  2024cites this paper
• The global prevalence and genetic spectrum of primary carnitine deficiency

  2024cites this paper
• Understanding variants of unknown significance: the computational frontier

  2024cites this paper
• Critical assessment of missense variant effect predictors on disease-relevant variant data

  2024cites this paper
• Structural insight into the function of human peptidyl arginine deiminase 6

  2024cites this paper
• Rare variant effect estimation and polygenic risk prediction

  2024influential citation
• PHACTboost: A Phylogeny-Aware Pathogenicity Predictor for Missense Mutations via Boosting

  2024cites this paper
• Stratified analyses refine association between TLR7 rare variants and severe COVID-19

  2024cites this paper
• Large-scale genomic analysis of the domestic dog informs biological discovery

  2024cites this paper
• Machine learning-guided co-optimization of fitness and diversity facilitates combinatorial library design in enzyme engineering

  2024cites this paper
• Missing genetic diversity impacts variant prioritisation for rare disorders

  2024influential citation
• Human genetics and epigenetics of alcohol use disorder

  2024cites this paper
• High-speed whole-genome sequencing of a Whippet: Rapid chromosome-level assembly and annotation of an extremely fast dog’s genome

  2024cites this paper
• New insights shed light on the enigma of genetic diversity and species complexity

  2024cites this paper
• Variant Impact Predictor database (VIPdb), version 2: trends from three decades of genetic variant impact predictors

  2024cites this paper
• Variant scoring performance across selection regimes depends on variant-to-gene and gene-to-disease components

  2024cites this paper
• Promises and challenges of crop translational genomics

  2024influential citation
• Saturation mutagenesis-reinforced functional assays for disease-related genes.

  2024cites this paper
• varCADD: large sets of standing genetic variation enable genome-wide pathogenicity prediction

  2024cites this paper
• The Impact of Clinical and Molecular Variant Properties on Calibration and Performance of Variant Effect Prediction Tools

  2024cites this paper
• Toward trustable use of machine learning models of variant effects in the clinic.

  2024cites this paper
• Advancing evolutionary medicine with complete primate genomes and advanced biotechnologies.

  2024cites this paper
• Rare disease genomics and precision medicine

  2024cites this paper
• Ensemble and consensus approaches to prediction of recessive inheritance for missense variants in human disease

  2024cites this paper
• Analyses of Human Genetic Data to Identify Clinically Relevant Domains of Neuroligins

  2024cites this paper
• Pathogenicity patterns in cytochrome P450 family

  2024cites this paper
• A global catalog of whole-genome diversity from 233 primate species

  2023cites this paper
• Rare penetrant mutations confer severe risk of common diseases

  2023cites this paper
• Functional characterization of all CDKN2A missense variants and comparison to in silico models of pathogenicity

  2023influential citation