Multiethnic polygenic risk prediction in diverse populations through transfer learning

Bridging Genomic Research Disparities in Osteoporosis GWAS: Insights for Diverse Populations

PURPOSE OF REVIEW

Genome-wide association studies (GWAS) have significantly advanced osteoporosis research by identifying genetic loci associated with bone mineral density (BMD) and fracture risk. However, disparities persist due to the underrepresentation of non-European populations, limiting the applicability of polygenic risk scores (PRS). This review examines recent advancements in osteoporosis genetics, highlights existing disparities, and explores strategies for more inclusive research.

RECENT FINDINGS

European-focused GWAS have identified key loci for osteoporosis, including WNT signaling (SOST, LRP5) and RUNX2 transcriptional regulation. However, fewer than 40% of these variants can be replicated in Asian and African populations. Emerging studies in non-European groups reveal population-specific loci, sex-specific associations, and gene-environment interactions. Advances in machine learning (ML)-assisted GWAS and multi-omics integration are improving genetic discovery. Expanding GWAS in diverse populations, integrating multi-omics data, refining ML-based risk models, and standardizing biobank data are essential for equitable osteoporosis research. Future efforts must prioritize clinical translation to enhance personalized osteoporosis prevention and treatment.

Methodological opportunities in genomic data analysis to advance health equity

The causes and consequences of inequities in genomic research and medicine are complex and widespread. However, it is widely acknowledged that underrepresentation of diverse populations in human genetics research risks exacerbating existing health disparities. Efforts to improve diversity are ongoing, but an often-overlooked source of inequity is the choice of analytical methods used to process, analyse and interpret genomic data. This choice can influence all areas of genomic research, from genome-wide association studies and polygenic score development to variant prioritization and functional genomics. New statistical and machine learning techniques to understand, quantify and correct for the impact of biases in genomic data are emerging within the wider genomic research and genomic medicine ecosystems. At this crucial time point, it is important to clarify where improvements in methods and practices can, or cannot, have a role in improving equity in genomics. Here, we review existing approaches to promote equity and fairness in statistical analysis for genomics, and propose future methodological developments that are likely to yield the most impact for equity.

JointPRS: A data-adaptive framework for multi-population genetic risk prediction incorporating genetic correlation

Genetic risk prediction for non-European populations is hindered by limited Genome-Wide Association Study (GWAS) sample sizes and small tuning datasets. We propose JointPRS, a data-adaptive framework that leverages genetic correlations across multiple populations using GWAS summary statistics. It achieves accurate predictions without individual-level tuning data and remains effective in the presence of a small tuning set thanks to its data-adaptive approach. Through extensive simulations and real data applications to 22 quantitative and four binary traits in five continental populations evaluated using the UK Biobank (UKBB) and All of Us (AoU), JointPRS consistently outperforms six state-of-the-art methods across three data scenarios: no tuning data, same-cohort tuning and testing, and cross-cohort tuning and testing. Notably, in the Admixed American population, JointPRS improves lipid trait prediction in AoU by 6.46%-172.00% compared to the other existing methods.

Transfer learning for accelerated failure time model with microarray data

BACKGROUND

In microarray prognostic studies, researchers aim to identify genes associated with disease progression. However, due to the rarity of certain diseases and the cost of sample collection, researchers often face the challenge of limited sample size, which may prevent accurate estimation and risk assessment. This challenge necessitates methods that can leverage information from external data (i.e., source cohorts) to improve gene selection and risk assessment based on the current sample (i.e., target cohort).

METHOD

We propose a transfer learning method for the accelerated failure time (AFT) model to enhance the fit on the target cohort by adaptively borrowing information from the source cohorts. We use a Leave-One-Out cross validation based procedure to evaluate the relative stability of selected genes and overall predictive power.

CONCLUSION

In simulation studies, the transfer learning method for the AFT model can correctly identify a small number of genes, its estimation error is smaller than the estimation error obtained without using the source cohorts. Furthermore, the proposed method demonstrates satisfactory accuracy and robustness in addressing heterogeneity across the cohorts compared to the method that directly combines the target and the source cohorts in the AFT model. We analyze the GSE88770 and GSE25055 data using the proposed method. The selected genes are relatively stable, and the proposed method can make an overall satisfactory risk prediction.

Comparison of methods for building polygenic scores for diverse populations

Polygenic scores (PGSs) are a promising tool for estimating individual-level genetic risk of disease based on the results of genome-wide association studies (GWASs). However, their promise has yet to be fully realized because most currently available PGSs were built with genetic data from predominantly European-ancestry populations, and PGS performance declines when scores are applied to target populations different from the populations from which they were derived. Thus, there is a great need to improve PGS performance in currently under-studied populations. In this work we leverage data from two large and diverse cohorts the Million Veterans Program (MVP) and All of Us (AoU), providing us the unique opportunity to compare methods for building PGSs for multi-ancestry populations across multiple traits. We build PGSs for five continuous traits and five binary traits using both multi-ancestry and single-ancestry approaches with popular Bayesian PGS methods and both MVP META GWAS results and population-specific GWAS results from the respective African, European, and Hispanic MVP populations. We evaluate these scores in three AoU populations genetically similar to the respective African, Admixed American, and European 1000 Genomes Project superpopulations. Using correlation-based tests, we make formal comparisons of the PGS performance across the multiple AoU populations. We conclude that approaches that combine GWAS data from multiple populations produce PGSs that perform better than approaches that utilize smaller single-population GWAS results matched to the target population, and specifically that multi-ancestry scores built with PRS-CSx outperform the other approaches in the three AoU populations.

Advancements and limitations in polygenic risk score methods for genomic prediction: a scoping review

This scoping review aims to identify and evaluate the landscape of Polygenic Risk Score (PRS)-based methods for genomic prediction from 2013 to 2023, highlighting their advancements, key concepts, and existing gaps in knowledge, research, and technology. Over the past decade, various PRS-based methods have emerged, each employing different statistical frameworks aimed at enhancing prediction accuracy, processing speed and memory efficiency. Despite notable advancements, challenges persist, including unrealistic assumptions regarding sample sizes and the polygenicity of traits necessary for accurate predictions, as well as limitations in exploring hyper-parameter spaces and considering environmental interactions. We included studies focusing on PRS-based methods for risk prediction that underwent methodological evaluations using valid approaches and released computational tools/software. Additionally, we restricted our selection to studies involving human participants that were published in English language. This review followed the standard protocol recommended by Joanna Briggs Institute Reviewer's Manual, systematically searching Ovid MEDLINE, Ovid Embase, Scopus and Web of Science databases. Additionally, searches included grey literature sources like pre-print servers such as bioRxiv, and articles recommended by experts to ensure comprehensive and diverse coverage of relevant records. This study identified 34 studies detailing 37 genomic prediction methods, the majority of which rely on linkage disequilibrium (LD) information and necessitate hyper-parameter tuning. Nine methods integrate functional/gene annotation, while 12 are suitable for cross-ancestry genomic prediction, with only one considering gene-environment (GxE) interaction. While some methods require individual-level data, most leverage summary statistics, offering flexibility. Despite progress, challenges remain. These include computational complexity and the need for large sample sizes for high prediction accuracy. Furthermore, recent methods exhibit varying effectiveness across traits, with absolute accuracies often falling short of clinical utility. Transferability across ancestries varies, influenced by trait heritability and diversity of training data, while handling admixed populations remains challenging. Additionally, the absence of standard error measurements for individual PRSs, crucial in clinical settings, underscores a critical gap. Another issue is the lack of customizable graphical visualization tools among current software packages. While genomic prediction methods have advanced significantly, there is still room for improvement. Addressing current challenges and embracing future research directions will lead to the development of more universally applicable, robust, and clinically relevant genomic prediction tools.

Polygenic prediction for underrepresented populations through transfer learning by utilizing genetic similarity shared with European populations

Because current genome-wide association studies are primarily conducted in individuals of European ancestry and information disparities exist among different populations, the polygenic score derived from Europeans thus exhibits poor transferability. Borrowing the idea of transfer learning, which enables the utilization of knowledge acquired from auxiliary samples to enhance learning capability in target samples, we propose transPGS, a novel polygenic score method, for genetic prediction in underrepresented populations by leveraging genetic similarity shared between the European and non-European populations while explaining the trans-ethnic difference in linkage disequilibrium (LD) and effect sizes. We demonstrate the usefulness and robustness of transPGS in elevated prediction accuracy via individual-level and summary-level simulations and apply it to seven continuous phenotypes and three diseases in the African, Chinese, and East Asian populations of the UK Biobank and Genetic Epidemiology Research Study on Adult Health and Aging cohorts. We further reveal that distinct LD and minor allele frequency patterns across ancestral groups are responsible for the dissatisfactory portability of PGS.

Genetics of Latin American Diversity Project: Insights into population genetics and association studies in admixed groups in the Americas

Latin Americans are underrepresented in genetic studies, increasing disparities in personalized genomic medicine. Despite available genetic data from thousands of Latin Americans, accessing and navigating the bureaucratic hurdles for consent or access remains challenging. To address this, we introduce the Genetics of Latin American Diversity (GLAD) Project, compiling genome-wide information from 53,738 Latin Americans across 39 studies representing 46 geographical regions. Through GLAD, we identified heterogeneous ancestry composition and recent gene flow across the Americas. Additionally, we developed GLAD-match, a simulated annealing-based algorithm, to match the genetic background of external samples to our database, sharing summary statistics (i.e., allele and haplotype frequencies) without transferring individual-level genotypes. Finally, we demonstrate the potential of GLAD as a critical resource for evaluating statistical genetic software in the presence of admixture. By providing this resource, we promote genomic research in Latin Americans and contribute to the promises of personalized medicine to more people.

Improving GWAS performance in underrepresented groups by appropriate modeling of genetics, environment, and sociocultural factors

Genome-wide association studies (GWAS) and polygenic score (PGS) development are typically constrained by the data available in biobank repositories in which European cohorts are vastly overrepresented. Here, we increase the utility of non-European participant data within the UK Biobank (UKB) by characterizing the genetic affinities of UKB participants who self-identify as Bangladeshi, Indian, Pakistani, "White and Asian" (WA), and "Any Other Asian" (AOA), towards creating a more robust South Asian sample size for future genetic analyses. We assess the relationships between genetic structure and self-selected ethnic identities resulting in consistent patterns of clustering used to train a support vector machine (SVM). The SVM model was utilized to reassign n = 1,853 AOA and WA participants at the subcontinental level, and increase the sample size of the UKB South Asian group by 1,381 additional participants. We then leverage these samples to assess GWAS performance and PGS development. We further include environmental covariates in the height GWAS by implementing a rigorous covariate selection procedure, and compare the outputs of two GWAS models: GWASnull and GWASenv. We show that PGS performance derived from environmentally adjusted GWAS yields comparable prediction to PGS models developed with an order of magnitude larger training dataset (R 2=0.021 vs 0.026). Models with 7 - 8 environmental covariates double the variance explained by PGS alone. In summary, we demonstrate how GWAS performance can be improved by leveraging ambiguous ethnicity codes, ancestry matched imputation panels, and including environmental covariates.

Multi-ancestry polygenic risk scores for venous thromboembolism

Venous thromboembolism (VTE) is a significant contributor to morbidity and mortality, with large disparities in incidence rates between Black and White Americans. Polygenic risk scores (PRSs) limited to variants discovered in genome-wide association studies in European-ancestry samples can identify European-ancestry individuals at high risk of VTE. However, there is limited evidence on whether high-dimensional PRS constructed using more sophisticated methods and more diverse training data can enhance the predictive ability and their utility across diverse populations. We developed PRSs for VTE using summary statistics from the International Network against Venous Thrombosis (INVENT) consortium genome-wide association studies meta-analyses of European- (71 771 cases and 1 059 740 controls) and African-ancestry samples (7482 cases and 129 975 controls). We used LDpred2 and PRS-CSx to construct ancestry-specific and multi-ancestry PRSs and evaluated their performance in an independent European- (6781 cases and 103 016 controls) and African-ancestry sample (1385 cases and 12 569 controls). Multi-ancestry PRSs with weights tuned in European-ancestry samples slightly outperformed ancestry-specific PRSs in European-ancestry test samples (e.g. the area under the receiver operating curve [AUC] was 0.609 for PRS-CSx_combinedEUR and 0.608 for PRS-CSxEUR [P = 0.00029]). Multi-ancestry PRSs with weights tuned in African-ancestry samples also outperformed ancestry-specific PRSs in African-ancestry test samples (PRS-CSxAFR: AUC = 0.58, PRS-CSx_combined AFR: AUC = 0.59), although this difference was not statistically significant (P = 0.34). The highest fifth percentile of the best-performing PRS was associated with 1.9-fold and 1.68-fold increased risk for VTE among European- and African-ancestry subjects, respectively, relative to those in the middle stratum. These findings suggest that the multi-ancestry PRS might be used to improve performance across diverse populations to identify individuals at highest risk for VTE.

Prediction of progression to type 1 diabetes with dynamic biomarkers and risk scores

Identifying biomarkers of functional β-cell loss is an important step in the risk stratification of type 1 diabetes. Genetic risk scores (GRS), generated by profiling an array of single nucleotide polymorphisms, are a widely used type 1 diabetes risk-prediction tool. Type 1 diabetes screening studies have relied on a combination of biochemical (autoantibody) and GRS screening methodologies for identifying individuals at high-risk of type 1 diabetes. A limitation of these screening tools is that the presence of autoantibodies marks the initiation of β-cell loss, and is therefore not the best biomarker of progression to early-stage type 1 diabetes. GRS, on the other hand, represents a static biomarker offering a single risk score over an individual's lifetime. In this Personal View, we explore the challenges and opportunities of static and dynamic biomarkers in the prediction of progression to type 1 diabetes. We discuss future directions wherein newer dynamic risk scores could be used to predict type 1 diabetes risk, assess the efficacy of new and emerging drugs to retard, or prevent type 1 diabetes, and possibly replace or further enhance the predictive ability offered by static biomarkers, such as GRS.

Optimizing clinico-genomic disease prediction across ancestries: a machine learning strategy with Pareto improvement

BACKGROUND

Accurate prediction of an individual's predisposition to diseases is vital for preventive medicine and early intervention. Various statistical and machine learning models have been developed for disease prediction using clinico-genomic data. However, the accuracy of clinico-genomic prediction of diseases may vary significantly across ancestry groups due to their unequal representation in clinical genomic datasets.

METHODS

We introduced a deep transfer learning approach to improve the performance of clinico-genomic prediction models for data-disadvantaged ancestry groups. We conducted machine learning experiments on multi-ancestral genomic datasets of lung cancer, prostate cancer, and Alzheimer's disease, as well as on synthetic datasets with built-in data inequality and distribution shifts across ancestry groups.

RESULTS

Deep transfer learning significantly improved disease prediction accuracy for data-disadvantaged populations in our multi-ancestral machine learning experiments. In contrast, transfer learning based on linear frameworks did not achieve comparable improvements for these data-disadvantaged populations.

CONCLUSIONS

This study shows that deep transfer learning can enhance fairness in multi-ancestral machine learning by improving prediction accuracy for data-disadvantaged populations without compromising prediction accuracy for other populations, thus providing a Pareto improvement towards equitable clinico-genomic prediction of diseases.

MUSSEL: Enhanced Bayesian polygenic risk prediction leveraging information across multiple ancestry groups

Polygenic risk scores (PRSs) are now showing promising predictive performance on a wide variety of complex traits and diseases, but there exists a substantial performance gap across populations. We propose MUSSEL, a method for ancestry-specific polygenic prediction that borrows information in summary statistics from genome-wide association studies (GWASs) across multiple ancestry groups via Bayesian hierarchical modeling and ensemble learning. In our simulation studies and data analyses across four distinct studies, totaling 5.7 million participants with a substantial ancestral diversity, MUSSEL shows promising performance compared to alternatives. For example, MUSSEL has an average gain in prediction R2 across 11 continuous traits of 40.2% and 49.3% compared to PRS-CSx and CT-SLEB, respectively, in the African ancestry population. The best-performing method, however, varies by GWAS sample size, target ancestry, trait architecture, and linkage disequilibrium reference samples; thus, ultimately a combination of methods may be needed to generate the most robust PRSs across diverse populations.

Benchmarking multi-ancestry prostate cancer polygenic risk scores in a real-world cohort

Prostate cancer is a heritable disease with ancestry-biased incidence and mortality. Polygenic risk scores (PRSs) offer promising advancements in predicting disease risk, including prostate cancer. While their accuracy continues to improve, research aimed at enhancing their effectiveness within African and Asian populations remains key for equitable use. Recent algorithmic developments for PRS derivation have resulted in improved pan-ancestral risk prediction for several diseases. In this study, we benchmark the predictive power of six widely used PRS derivation algorithms, including four of which adjust for ancestry, against prostate cancer cases and controls from the UK Biobank and All of Us cohorts. We find modest improvement in discriminatory ability when compared with a simple method that prioritizes variants, clumping, and published polygenic risk scores. Our findings underscore the importance of improving upon risk prediction algorithms and the sampling of diverse cohorts.

Principles and methods for transferring polygenic risk scores across global populations

Polygenic risk scores (PRSs) summarize the genetic predisposition of a complex human trait or disease and may become a valuable tool for advancing precision medicine. However, PRSs that are developed in populations of predominantly European genetic ancestries can increase health disparities due to poor predictive performance in individuals of diverse and complex genetic ancestries. We describe genetic and modifiable risk factors that limit the transferability of PRSs across populations and review the strengths and weaknesses of existing PRS construction methods for diverse ancestries. Developing PRSs that benefit global populations in research and clinical settings provides an opportunity for innovation and is essential for health equity.

Applying polygenic risk score methods to pharmacogenomics GWAS: challenges and opportunities

Polygenic risk scores (PRSs) have emerged as promising tools for the prediction of human diseases and complex traits in disease genome-wide association studies (GWAS). Applying PRSs to pharmacogenomics (PGx) studies has begun to show great potential for improving patient stratification and drug response prediction. However, there are unique challenges that arise when applying PRSs to PGx GWAS beyond those typically encountered in disease GWAS (e.g. Eurocentric or trans-ethnic bias). These challenges include: (i) the lack of knowledge about whether PGx or disease GWAS/variants should be used in the base cohort (BC); (ii) the small sample sizes in PGx GWAS with corresponding low power and (iii) the more complex PRS statistical modeling required for handling both prognostic and predictive effects simultaneously. To gain insights in this landscape about the general trends, challenges and possible solutions, we first conduct a systematic review of both PRS applications and PRS method development in PGx GWAS. To further address the challenges, we propose (i) a novel PRS application strategy by leveraging both PGx and disease GWAS summary statistics in the BC for PRS construction and (ii) a new Bayesian method (PRS-PGx-Bayesx) to reduce Eurocentric or cross-population PRS prediction bias. Extensive simulations are conducted to demonstrate their advantages over existing PRS methods applied in PGx GWAS. Our systematic review and methodology research work not only highlights current gaps and key considerations while applying PRS methods to PGx GWAS, but also provides possible solutions for better PGx PRS applications and future research.

A new method for multiancestry polygenic prediction improves performance across diverse populations

Polygenic risk scores (PRSs) increasingly predict complex traits; however, suboptimal performance in non-European populations raise concerns about clinical applications and health inequities. We developed CT-SLEB, a powerful and scalable method to calculate PRSs, using ancestry-specific genome-wide association study summary statistics from multiancestry training samples, integrating clumping and thresholding, empirical Bayes and superlearning. We evaluated CT-SLEB and nine alternative methods with large-scale simulated genome-wide association studies (~19 million common variants) and datasets from 23andMe, Inc., the Global Lipids Genetics Consortium, All of Us and UK Biobank, involving 5.1 million individuals of diverse ancestry, with 1.18 million individuals from four non-European populations across 13 complex traits. Results demonstrated that CT-SLEB significantly improves PRS performance in non-European populations compared with simple alternatives, with comparable or superior performance to a recent, computationally intensive method. Moreover, our simulation studies offered insights into sample size requirements and SNP density effects on multiancestry risk prediction.

MUSSEL: Enhanced Bayesian Polygenic Risk Prediction Leveraging Information across Multiple Ancestry Groups

Polygenic risk scores (PRS) are now showing promising predictive performance on a wide variety of complex traits and diseases, but there exists a substantial performance gap across different populations. We propose MUSSEL, a method for ancestry-specific polygenic prediction that borrows information in the summary statistics from genome-wide association studies (GWAS) across multiple ancestry groups. MUSSEL conducts Bayesian hierarchical modeling under a MUltivariate Spike-and-Slab model for effect-size distribution and incorporates an Ensemble Learning step using super learner to combine information across different tuning parameter settings and ancestry groups. In our simulation studies and data analyses of 16 traits across four distinct studies, totaling 5.7 million participants with a substantial ancestral diversity, MUSSEL shows promising performance compared to alternatives. The method, for example, has an average gain in prediction R2 across 11 continuous traits of 40.2% and 49.3% compared to PRS-CSx and CT-SLEB, respectively, in the African Ancestry population. The best-performing method, however, varies by GWAS sample size, target ancestry, underlying trait architecture, and the choice of reference samples for LD estimation, and thus ultimately, a combination of methods may be needed to generate the most robust PRS across diverse populations.

Transfer Learning for Classification of Alzheimer's Disease Based on Genome Wide Data

Alzheimer's disease (AD) is a type of brain disorder that is regarded as a degenerative disease because the corresponding symptoms aggravate with the time progression. Single nucleotide polymorphisms (SNPs) have been identified as relevant biomarkers for this condition. This study aims to identify SNPs biomarkers associated with the AD in order to perform a reliable classification of AD. In contrast to existing related works, we utilize deep transfer learning with varying experimental analysis for reliable classification of AD. For this purpose, the convolutional neural networks (CNN) are firstly trained over the genome-wide association studies (GWAS) dataset requested from the AD neuroimaging initiative. We then employ the deep transfer learning for further training of our CNN (as base model) over a different AD GWAS dataset, to extract the final set of features. The extracted features are then fed into Support Vector Machine for classification of AD. Detailed experiments are performed using multiple datasets and varying experimental configurations. The statistical outcomes indicate an accuracy of 89% which is a significant improvement when benchmarked with existing related works.

A polygenic risk score for Alzheimer's disease constructed using APOE-region variants has stronger association than APOE alleles with mild cognitive impairment in Hispanic/Latino adults in the U.S

INTRODUCTION

Polygenic Risk Scores (PRSs) are summaries of genetic risk alleles for an outcome.

METHODS

We used summary statistics from five GWASs of AD to construct PRSs in 4,189 diverse Hispanics/Latinos (mean age 63 years) from the Study of Latinos-Investigation of Neurocognitive Aging (SOL-INCA). We assessed the PRS associations with MCI in the combined set of people and in diverse subgroups, and when including and excluding the APOE gene region. We also assessed PRS associations with MCI in an independent dataset from the Mass General Brigham Biobank.

RESULTS

A simple sum of 5 PRSs ("PRSsum"), each constructed based on a different AD GWAS, was associated with MCI (OR = 1.28, 95% CI [1.14, 1.41]) in a model adjusted for counts of the APOE-[Formula: see text] and APOE-[Formula: see text] alleles. Associations of single-GWAS PRSs were weaker. When removing SNPs from the APOE region from the PRSs, the association of PRSsum with MCI was weaker (OR = 1.17, 95% CI [1.04,1.31] with adjustment for APOE alleles). In all association analyses, APOE-[Formula: see text] and APOE-[Formula: see text] alleles were not associated with MCI.

DISCUSSION

A sum of AD PRSs is associated with MCI in Hispanic/Latino older adults. Despite no association of APOE-[Formula: see text] and APOE-[Formula: see text] alleles with MCI, the association of the AD PRS with MCI is stronger when including the APOE region. Thus, APOE variants different than the classic APOE alleles may be important predictors of MCI in Hispanic/Latino adults.

Addressing the Challenge of Biomedical Data Inequality: An Artificial Intelligence Perspective

Artificial intelligence (AI) and other data-driven technologies hold great promise to transform healthcare and confer the predictive power essential to precision medicine. However, the existing biomedical data, which are a vital resource and foundation for developing medical AI models, do not reflect the diversity of the human population. The low representation in biomedical data has become a significant health risk for non-European populations, and the growing application of AI opens a new pathway for this health risk to manifest and amplify. Here we review the current status of biomedical data inequality and present a conceptual framework for understanding its impacts on machine learning. We also discuss the recent advances in algorithmic interventions for mitigating health disparities arising from biomedical data inequality. Finally, we briefly discuss the newly identified disparity in data quality among ethnic groups and its potential impacts on machine learning.

Leveraging trans-ethnic genetic risk scores to improve association power for complex traits in underrepresented populations

Trans-ethnic genome-wide association studies have revealed that many loci identified in European populations can be reproducible in non-European populations, indicating widespread trans-ethnic genetic similarity. However, how to leverage such shared information more efficiently in association analysis is less investigated for traits in underrepresented populations. We here propose a statistical framework, trans-ethnic genetic risk score informed gene-based association mixed model (GAMM), by hierarchically modeling single-nucleotide polymorphism effects in the target population as a function of effects of the same trait in well-studied populations. GAMM powerfully integrates genetic similarity across distinct ancestral groups to enhance power in understudied populations, as confirmed by extensive simulations. We illustrate the usefulness of GAMM via the application to 13 blood cell traits (i.e. basophil count, eosinophil count, hematocrit, hemoglobin concentration, lymphocyte count, mean corpuscular hemoglobin, mean corpuscular hemoglobin concentration, mean corpuscular volume, monocyte count, neutrophil count, platelet count, red blood cell count and total white blood cell count) in Africans of the UK Biobank (n = 3204) while utilizing genetic overlap shared in Europeans (n = 746 667) and East Asians (n = 162 255). We discovered multiple new associated genes, which had otherwise been missed by existing methods, and revealed that the trans-ethnic information indirectly contributed much to the phenotypic variance. Overall, GAMM represents a flexible and powerful statistical framework of association analysis for complex traits in underrepresented populations by integrating trans-ethnic genetic similarity across well-studied populations, and helps attenuate health inequities in current genetics research for people of minority populations.