Prediction of fetal hemoglobin in sickle cell anemia using an ensemble of genetic risk prediction models

Genetic Variation and Sickle Cell Disease Severity: A Systematic Review and Meta-Analysis

Importance

Sickle cell disease (SCD) is a monogenic disorder, yet clinical outcomes are influenced by additional genetic factors. Despite decades of research, the genetics of SCD remain poorly understood.

Objective

To assess all reported genetic modifiers of SCD, evaluate the design of associated studies, and provide guidelines for future analyses according to modern genetic study recommendations.

Data Sources

PubMed, Web of Science, and Scopus were searched through May 16, 2023, identifying 5290 publications.

Study Selection

At least 2 reviewers identified 571 original, peer-reviewed English-language publications reporting genetic modifiers of human SCD phenotypes, wherein the outcome was not treatment response, and the comparison was not between SCD subtypes or including healthy controls.

Data Extraction and Synthesis

Data relevant to all genetic modifiers of SCD were extracted, evaluated, and presented following STREGA and PRISMA guidelines. Weighted z score meta-analyses and pathway analyses were conducted.

Main Outcomes and Measures

Outcomes were aggregated into 25 categories, grouped as acute complications, chronic conditions, hematologic parameters or biomarkers, and general or mixed measures of SCD severity.

Results

The 571 included studies reported on 29 670 unique individuals (50% ≤ 18 years of age) from 43 countries. Of the 17 757 extracted results (4890 significant) in 1552 genes, 3675 results met the study criteria for meta-analysis: reported phenotype and genotype, association size and direction, variability measure, sample size, and statistical test. Only 173 results for 62 associations could be cross-study combined. The remaining associations could not be aggregated because they were only reported once or methods (eg, study design, reporting practice) and genotype or phenotype definitions were insufficiently harmonized. Gene variants regulating fetal hemoglobin and α-thalassemia (important markers for SCD severity) were frequently identified: 19 single-nucleotide variants in BCL11A, HBS1L-MYB, and HBG2 were significantly associated with fetal hemoglobin (absolute value of Z = 4.00 to 20.66; P = 8.63 × 10-95 to 6.19 × 10-5), and α-thalassemia deletions were significantly associated with increased hemoglobin level and reduced risk of albuminuria, abnormal transcranial Doppler velocity, and stroke (absolute value of Z = 3.43 to 5.16; P = 2.42 × 10-7 to 6.00 × 10-4). However, other associations remain unconfirmed. Pathway analyses of significant genes highlighted the importance of cellular adhesion, inflammation, oxidative and toxic stress, and blood vessel regulation in SCD (23 of the top 25 Gene Ontology pathways involve these processes) and suggested future research areas.

Conclusions and Relevance

The findings of this comprehensive systematic review and meta-analysis of all published genetic modifiers of SCD indicated that implementation of standardized phenotypes, statistical methods, and reporting practices should accelerate discovery and validation of genetic modifiers and development of clinically actionable genetic profiles.

Improving Pain Assessment using Vital Signs and Pain Medication for patients with Sickle Cell Disease: Retrospective Study (Preprint)

Background

Sickle cell disease (SCD) is the most common inherited blood disorder affecting millions of people worldwide. Most patients with SCD experience repeated, unpredictable episodes of severe pain. These pain episodes are the leading cause of emergency department visits among patients with SCD and may last for several weeks. Arguably, the most challenging aspect of treating pain episodes in SCD is assessing and interpreting a patient’s pain intensity level.

Objective

This study aims to learn deep feature representations of subjective pain trajectories using objective physiological signals collected from electronic health records.

Methods

This study used electronic health record data collected from 496 Duke University Medical Center participants over 5 consecutive years. Each record contained measures for 6 vital signs and the patient’s self-reported pain score, with an ordinal range from 0 (no pain) to 10 (severe and unbearable pain). We also extracted 3 features related to medication: medication type, medication status (given or applied, or missed or removed or due), and total medication dosage (mg/mL). We used variational autoencoders for representation learning and designed machine learning classification algorithms to build pain prediction models. We evaluated our results using an accuracy and confusion matrix and visualized the qualitative data representations.

Results

We designed a classification model using raw data and deep representational learning to predict subjective pain scores with average accuracies of 82.8%, 70.6%, 49.3%, and 47.4% for 2-point, 4-point, 6-point, and 11-point pain ratings, respectively. We observed that random forest classification models trained on deep represented features outperformed models trained on unrepresented data for all pain rating scales. We observed that at varying Likert scales, our models performed better when provided with medication data along with vital signs data. We visualized the data representations to understand the underlying latent representations, indicating neighboring representations for similar pain scores with a higher resolution of pain ratings.

Conclusions

Our results demonstrate that medication information (the type of medication, total medication dosage, and whether the medication was given or missed) can significantly improve subjective pain prediction modeling compared with modeling with only vital signs. This study shows promise in data-driven estimated pain scores that will help clinicians with additional information about the patient’s condition, in addition to the patient’s self-reported pain scores.

Multi-Locus Models to Address Hb F Variability in Portuguese β-Thalassemia Carriers

Hb F production is under the influence of major quantitative trait loci (QTL). The present study aims: i) to replicate the association with Hb F for representative genetic variants in the three major Hb F QTLs in a Portuguese sample of β-thalassemia (β-thal) carriers; and ii) to test different genetic multi-locus models to account for the genetic component of Hb F variation. A population sample of 79 Portuguese β-thal carriers (39 males, 40 females), aged between 2 to 70 years old, were genotyped for polymorphisms in the locus control region (LCR)-5' hypersensitive site 4 (5'HS4) rs16912979, XmnI-HBG2 rs7482144, BCL11A rs1427407 and HMIP rs66650371, using standard biomolecular procedures. Univariate linear regression models were used to test for genetic associations with Hb F. The minor alleles of the individual variants BCL11A rs1427407 (T) (0.165), HMIP rs66650371 (3 bp del) (0.247) and XmnI-HBG2 rs7482144 (T) (0.196), were found to be significantly associated with increased levels of Hb F (p = 0.029, p = 0.002 and p = 0.0004, respectively), explaining about 6.0, 12.0 and 15.0% of Hb F variation, respectively. In a multiple linear regression approach, the three loci accounted for about 30.0% of Hb F variance. Two genetic risk scores (GRS), rationalizing the number of minor alleles into a single genetic variable, explained about 30.0 and 32.0% of the Hb F variation. In conclusion, we replicated in β-thal carriers previously reported associations with Hb F. Multi-locus models combining three representative variants of Hb F influencing QTLs can explain a larger amount of Hb F variability.

Use of Mobile Health Apps and Wearable Technology to Assess Changes and Predict Pain During Treatment of Acute Pain in Sickle Cell Disease: Feasibility Study

BACKGROUND

Sickle cell disease (SCD) is an inherited red blood cell disorder affecting millions worldwide, and it results in many potential medical complications throughout the life course. The hallmark of SCD is pain. Many patients experience daily chronic pain as well as intermittent, unpredictable acute vaso-occlusive painful episodes called pain crises. These pain crises often require acute medical care through the day hospital or emergency department. Following presentation, a number of these patients are subsequently admitted with continued efforts of treatment focused on palliative pain control and hydration for management. Mitigating pain crises is challenging for both the patients and their providers, given the perceived unpredictability and subjective nature of pain.

OBJECTIVE

The objective of this study was to show the feasibility of using objective, physiologic measurements obtained from a wearable device during an acute pain crisis to predict patient-reported pain scores (in an app and to nursing staff) using machine learning techniques.

METHODS

For this feasibility study, we enrolled 27 adult patients presenting to the day hospital with acute pain. At the beginning of pain treatment, each participant was given a wearable device (Microsoft Band 2) that collected physiologic measurements. Pain scores from our mobile app, Technology Resources to Understand Pain Assessment in Patients with Pain, and those obtained by nursing staff were both used with wearable signals to complete time stamp matching and feature extraction and selection. Following this, we constructed regression and classification machine learning algorithms to build between-subject pain prediction models.

RESULTS

Patients were monitored for an average of 3.79 (SD 2.23) hours, with an average of 5826 (SD 2667) objective data values per patient. As expected, we found that pain scores and heart rate decreased for most patients during the course of their stay. Using the wearable sensor data and pain scores, we were able to create a regression model to predict subjective pain scores with a root mean square error of 1.430 and correlation between observations and predictions of 0.706. Furthermore, we verified the hypothesis that the regression model outperformed the classification model by comparing the performances of the support vector machines (SVM) and the SVM for regression.

CONCLUSIONS

The Microsoft Band 2 allowed easy collection of objective, physiologic markers during an acute pain crisis in adults with SCD. Features can be extracted from these data signals and matched with pain scores. Machine learning models can then use these features to feasibly predict patient pain scores.

Sickle cell disease in the era of precision medicine: looking to the future

Introduction

Sickle cell anemia is a mendelian disease that is noted for the heterogeneity of its clinical expression. Because of this, providing an accurate prognosis has been a longtime quest.

Areas covered

Reviewed are the benefits and shortcomings of testing for the major modulators of the severity of disease, like fetal hemoglobin and α thalassemia, along with studies that have attempted to link genetic variation with sub-phenotypes of disease in a predictive fashion. Induced pluripotent stem cells driven to differentiate into erythroid precursor cells provide another area for potential patient-specific drug testing.

Expert opinion

Fetal hemoglobin is the strongest modulator of sickle cell anemia but simply measuring its blood levels is an insufficient means of forecasting an individual's prognosis. A more precise method would be to know the distribution of fetal hemoglobin levels across the population of red cells, an assay not yet available. Prognostic measures have been developed using genetic and other signatures, but their predictive value is suboptimal. Widely applicable assays must be developed to allow a tailored approach to using the several new treatments that are likely to be available in the near future.

Genetic Modifiers of Fetal Haemoglobin in Sickle Cell Disease

Fetal haemoglobin (HbF) levels have a clinically beneficial effect on sickle cell disease (SCD). Patients with SCD demonstrate extreme variability in HbF levels (1-30%), a large part of which is likely genetically determined. The main genetic modifier loci for HbF persistence, HBS1L-MYB, BCL11A and the β-globin gene cluster in adults also act in SCD patients. Their effects are, however, modified significantly by a disease pathology that includes a drastically shortened erythrocyte lifespan with an enhanced survival of those red blood cells that carry HbF (F cells). We propose a model of how HbF modifier genes and disease pathology interact to shape HbF levels measured in patients. We review current knowledge on the action of these loci in SCD, their genetic architecture, and their putative functional components. At each locus, one strong candidate for a causative, functional DNA change has been proposed: Xmn1-HBG2 at the β-globin cluster, rs1427407 at BCL11A and the 3 bp deletion rs66650371 at HBS1L-MYB. These, however, explain only part of the impact of these loci and additional variants are yet to be identified. Further progress in understanding the genetic control of HbF levels requires that confounding factors inherent in SCD, such as ethnic complexity, the role of F cells and the influence of drugs, are suitably addressed. This will depend on international collaboration and on large, well-characterised patient cohorts with genome-wide single-nucleotide polymorphism or sequence data.

g(HbF): a genetic model of fetal hemoglobin in sickle cell disease

Fetal hemoglobin (HbF) is a strong modifier of sickle cell disease (SCD) severity and is associated with 3 common genetic loci. Quantifying the genetic effects of the 3 loci would specifically address the benefits of HbF increases in patients. Here, we have applied statistical methods using the most representative variants: rs1427407 and rs6545816 in BCL11A, rs66650371 (3-bp deletion) and rs9376090 in HMIP-2A, rs9494142 and rs9494145 in HMIP-2B, and rs7482144 (Xmn1-HBG2 in the β-globin locus) to create g(HbF), a genetic quantitative variable for HbF in SCD. Only patients aged ≥5 years with complete genotype and HbF data were studied. Five hundred eighty-one patients with hemoglobin SS (HbSS) or HbSβ⁰ thalassemia formed the "discovery" cohort. Multiple linear regression modeling rationalized the 7 variants down to 4 markers (rs6545816, rs1427407, rs66650371, and rs7482144) each independently contributing HbF-boosting alleles, together accounting for 21.8% of HbF variability (r²) in the HbSS or HbSβ⁰ patients. The model was replicated with consistent r² in 2 different cohorts: 27.5% in HbSC patients (N = 186) and 23% in 994 Tanzanian HbSS patients. g(HbF), our 4-variant model, provides a robust approach to account for the genetic component of HbF in SCD and is of potential utility in sickle genetic and clinical studies.

Biomarker signatures of sickle cell disease severity

Identifying sickle cell disease patients at high risk of complications could lead to personalized treatment and better prognosis but despite many advances prediction of the clinical course of these patients remains elusive. We propose a system-type approach to discover profiles of multiple, common biomarkers that correlate with morbidity and mortality in sickle cell disease. We used cluster analysis to discover 17 signatures of 17 common circulating biomarkers in 2320 participants of the Cooperative Study of Sickle Cell Disease, and evaluated the association of these signatures with risk for stroke, pain, leg ulceration, acute chest syndrome, avascular necrosis, seizure, death, and trend of fetal hemoglobin and hemolysis using longitudinally collected data. The analysis shows that some of the signatures are associated with reduced risk for complications, while others are associated with increased risk for complications. We also show that these signatures repeat in two more contemporary studies of sickle cell disease and correlate with recently discovered biomarkers of pulmonary vascular disease. With replication and further study, these biomarker signatures could become an important and affordable precision medicine tool to aid treatment and management of the disease.

Improving Pain Management in Patients with Sickle Cell Disease from Physiological Measures Using Machine Learning Techniques

Pain management is a crucial part in Sickle Cell Disease treatment. Accurate pain assessment is the first stage in pain management. However, pain is a subjective response and hard to assess via objective approaches. In this paper, we proposed a system to map objective physiological measures to subjective self-reported pain scores using machine learning techniques. Using Multinomial Logistic Regression and data from 40 patients, we were able to predict patients' pain scores on an 11-point rating scale with an average accuracy of 0.578 at the intra-individual level, and an accuracy of 0.429 at the inter-individual level. With a condensed 4-point rating scale, the accuracy at the inter-individual level was further improved to 0.681. Overall, we presented a preliminary machine learning model that can predict pain scores in SCD patients with promising results. To our knowledge, such a system has not been proposed earlier within the SCD or pain domains by exploiting machine learning concepts within the clinical framework.

A deep convolutional neural network for classification of red blood cells in sickle cell anemia

Sickle cell disease (SCD) is a hematological disorder leading to blood vessel occlusion accompanied by painful episodes and even death. Red blood cells (RBCs) of SCD patients have diverse shapes that reveal important biomechanical and bio-rheological characteristics, e.g. their density, fragility, adhesive properties, etc. Hence, having an objective and effective way of RBC shape quantification and classification will lead to better insights and eventual better prognosis of the disease. To this end, we have developed an automated, high-throughput, ex-vivo RBC shape classification framework that consists of three stages. First, we present an automatic hierarchical RBC extraction method to detect the RBC region (ROI) from the background, and then separate touching RBCs in the ROI images by applying an improved random walk method based on automatic seed generation. Second, we apply a mask-based RBC patch-size normalization method to normalize the variant size of segmented single RBC patches into uniform size. Third, we employ deep convolutional neural networks (CNNs) to realize RBC classification; the alternating convolution and pooling operations can deal with non-linear and complex patterns. Furthermore, we investigate the specific shape factor quantification for the classified RBC image data in order to develop a general multiscale shape analysis. We perform several experiments on raw microscopy image datasets from 8 SCD patients (over 7,000 single RBC images) through a 5-fold cross validation method both for oxygenated and deoxygenated RBCs. We demonstrate that the proposed framework can successfully classify sickle shape RBCs in an automated manner with high accuracy, and we also provide the corresponding shape factor analysis, which can be used synergistically with the CNN analysis for more robust predictions. Moreover, the trained deep CNN exhibits good performance even for a deoxygenated dataset and distinguishes the subtle differences in texture alteration inside the oxygenated and deoxygenated RBCs.

Protective BCL11A and HBS1L-MYB polymorphisms in a cohort of 102 Congolese patients suffering from sickle cell anemia

BACKGROUND

We aimed to investigate the distribution of selected BCL11A and HMIP polymorphisms (SNP's), and to assess the correlation with HPFH in a cohort of sickle cell patients.

METHODS

A preliminary cross-sectional study was conducted in 102 patients. Group 1 was composed of patients with HPFH and Group 2 consisted of patients without HbF. We assessed 8 SNPs previously associated with HPFH in cohorts genetically close to the Congolese population. Observed frequencies were compared to expected frequencies.

RESULTS

In the group 1, at rs7606173, the observed frequency for the genotype GG was significantly higher and the genotype GC was significantly lower than their respective expected frequencies. At rs9399137, the observed frequency of the genotype TT was significantly lower than expected. Conversely, the observed frequency of the genotype TC was significantly higher than expected. The observed frequency of the genotype TT at rs11886868 was significantly lower than the expected whereas the frequency of the genotype TC was significantly higher than observed. The lowest HbF level was recorded in patients with genotype CC at rs11886868.

CONCLUSION

In this preliminary study, the results demonstrate that alleles of some of the 8 studied SNPs are not randomly distributed among patients with or without HPFH in this cohort.

Original Research: A case-control genome-wide association study identifies genetic modifiers of fetal hemoglobin in sickle cell disease

Sickle cell disease (SCD) is a group of inherited blood disorders that have in common a mutation in the sixth codon of the β-globin (HBB) gene on chromosome 11. However, people with the same genetic mutation display a wide range of clinical phenotypes. Fetal hemoglobin (HbF) expression is an important genetic modifier of SCD complications leading to milder symptoms and improved long-term survival. Therefore, we performed a genome-wide association study (GWAS) using a case-control experimental design in 244 African Americans with SCD to discover genetic factors associated with HbF expression. The case group consisted of subjects with HbF≥8.6% (133 samples) and control group subjects with HbF≤£3.1% (111 samples). Our GWAS results replicated SNPs previously identified in an erythroid-specific enhancer region located in the second intron of the BCL11A gene associated with HbF expression. In addition, we identified SNPs in the SPARC, GJC1, EFTUD2 and JAZF1 genes as novel candidates associated with HbF levels. To gain insights into mechanisms of globin gene regulation in the HBB locus, linkage disequilibrium (LD) and haplotype analyses were conducted. We observed strong LD in the low HbF group in contrast to a loss of LD and greater number of haplotypes in the high HbF group. A search of known HBB locus regulatory elements identified SNPs 5' of δ-globin located in an HbF silencing region. In particular, SNP rs4910736 created a binding site for a known transcription repressor GFi1 which is a candidate protein for further investigation. Another HbF-associated SNP, rs2855122 in the cAMP response element upstream of Gγ-globin, was analyzed for functional relevance. Studies performed with siRNA-mediated CREB binding protein (CBP) knockdown in primary erythroid cells demonstrated γ-globin activation and HbF induction, supporting a repressor role for CBP. This study identifies possible molecular determinants of HbF production.

Genomic approaches to identifying targets for treating β hemoglobinopathies

Sickle cell disease and β thalassemia are common severe diseases with little effective pathophysiologically-based treatment. Their phenotypic heterogeneity prompted genomic approaches to identify modifiers that ultimately might be exploited therapeutically. Fetal hemoglobin (HbF) is the major modulator of the phenotype of the β hemoglobinopathies. HbF inhibits deoxyHbS polymerization and in β thalassemia compensates for the reduction of HbA. The major success of genomics has been a better understanding the genetic regulation of HbF by identifying the major quantitative trait loci for this trait. If the targets identified can lead to means of increasing HbF to therapeutic levels in sufficient numbers of sickle or β-thalassemia erythrocytes, the pathophysiology of these diseases would be reversed. The availability of new target loci, high-throughput drug screening, and recent advances in genome editing provide the opportunity for new approaches to therapeutically increasing HbF production.

Hashimoto's thyroiditis and acute chest syndrome revealing sickle cell anemia in a 32 years female patient

Sickle cell anemia results from a single amino acid substitution in the gene encoding the β-globin subunit. Polymerization of deoxygenated sickle hemoglobin leads to decreased deformability of red blood cells. Hashimoto's thyroiditis is a common thyroid disease now recognized as an auto-immune thyroid disorder, it is usually thought to be haemolytic autoimmune anemia. We report the case of a 32 years old women admitted for chest pain and haemolysis anemia in which Hashimoto's thyroiditis and sickle cell anemia were found. In our observation the patient is a young woman whose examination did not show signs of goitre but the analysis of thyroid function tests performed before an auto-immune hemolytic anemia (confirmed by a high level of unconjugated bilirubin and a Coombs test positive for IgG) has found thyroid stimulating hormone (TSH) and positive thyroid antibody at rates in excess of 4.5 times their normal value. In the same period, as the hemolytic anemia, and before the atypical chest pain and anguish they generated in the patient, the search for hemoglobinopathies was made despite the absence of a family history of haematological disease or painful attacks in childhood. Patient electrophoresis's led to research similar cases in the family. The mother was the first to be analyzed with ultimately diagnosed with sickle cell trait have previously been ignored. This case would be a form with few symptoms because the patient does not describe painful crises in childhood or adolescence.

Evaluation of an ensemble of genetic models for prediction of a quantitative trait

Many genetic markers have been shown to be associated with common quantitative traits in genome-wide association studies. Typically these associated genetic markers have small to modest effect sizes and individually they explain only a small amount of the variability of the phenotype. In order to build a genetic prediction model without fitting a multiple linear regression model with possibly hundreds of genetic markers as predictors, researchers often summarize the joint effect of risk alleles into a genetic score that is used as a covariate in the genetic prediction model. However, the prediction accuracy can be highly variable and selecting the optimal number of markers to be included in the genetic score is challenging. In this manuscript we present a strategy to build an ensemble of genetic prediction models from data and we show that the ensemble-based method makes the challenge of choosing the number of genetic markers more amenable. Using simulated data with varying heritability and number of genetic markers, we compare the predictive accuracy and inclusion of true positive and false positive markers of a single genetic prediction model and our proposed ensemble method. The results show that the ensemble of genetic models tends to include a larger number of genetic variants than a single genetic model and it is more likely to include all of the true genetic markers. This increased sensitivity is obtained at the price of a lower specificity that appears to minimally affect the predictive accuracy of the ensemble.

The genetics of hemoglobin A2 regulation in sickle cell anemia

Hemoglobin A2 , a tetramer of α- and δ-globin chains, comprises less than 3% of total hemoglobin in normal adults. In northern Europeans, single nucleotide polymorphisms (SNPs) in the HBS1L-MYB locus on chromosome 6q and the HBB cluster on chromosome 11p were associated with HbA2 levels. We examined the genetic basis of HbA2 variability in sickle cell anemia using genome-wide association studies. HbA2 levels were associated with SNPs in the HBS1L-MYB interval and SNPs in BCL11A. These effects are mediated by the association of these loci with γ-globin gene expression and fetal hemoglobin (HbF) levels. The association of polymorphisms downstream of the β-globin gene (HBB) cluster on chromosome 11 with HbA2 was not mediated by HbF. In sickle cell anemia, levels of HbA2 appear to be modulated by trans-acting genes that affect HBG expression and perhaps also elements within the β-globin gene cluster. HbA2 is expressed pancellularly and can inhibit HbS polymerization. It remains to be seen if genetic regulators of HbA2 can be exploited for therapeutic purposes.

C-reactive Protein and Disease Outcome in Nigerian Sickle Cell Disease Patients

Background:

Evidence suggests that sickle cell disease (SCD) is associated with a chronic inflammatory state. C-reactive protein (CRP) is known to modulate inflammation. Its role in the chronic inflammation of SCD may make it valuable as a therapeutic target.

Aim:

The aim was to determine CRP levels in SCD subjects in asymptomatic steady state (ASS) and crisis and correlate these with severity scores in the ASS.

Subjects and Methods:

We measured the level of CRP in 30 hemoglobin SS (HbSS) individuals in ASS and seven in crisis. As controls, we measured CRP in 50 individuals each who were hemoglobin AS and hemoglobin AA respectively, using enzyme linked immunoabsorbent assay based commercially available kits from East Wing Diagnostic Limited Full blood count (white blood cell [WBC]) was done for the ASS HbSS individuals using a cell counter and their disease severity calculated by an objective scoring method.

Results:

Our results showed that ASS HbSS individuals had significantly higher CRP levels compared with the controls. The HbSS individuals in crisis also had a significantly higher level of CRP compared to the ASS HbSS individuals. Disease severity and WBC were found to be negatively correlated with CRP levels (P = 0.17; and 0.73, respectively).

Conclusion:

Our results suggest that increased levels of CRP in ASS HbSS individuals may play a protective role in SCD leading to better disease outcome, and may have value as a therapeutic target.

Integrating genetics and social science: genetic risk scores

The sequencing of the human genome and the advent of low-cost genome-wide assays that generate millions of observations of individual genomes in a matter of hours constitute a disruptive innovation for social science. Many public use social science datasets have or will soon add genome-wide genetic data. With these new data come technical challenges, but also new possibilities. Among these, the lowest-hanging fruit and the most potentially disruptive to existing research programs is the ability to measure previously invisible contours of health and disease risk within populations. In this article, we outline why now is the time for social scientists to bring genetics into their research programs. We discuss how to select genetic variants to study. We explain how the polygenic architecture of complex traits and the low penetrance of individual genetic loci pose challenges to research integrating genetics and social science. We introduce genetic risk scores as a method of addressing these challenges and provide guidance on how genetic risk scores can be constructed. We conclude by outlining research questions that are ripe for social science inquiry.