Machine learning optimized polygenic scores for blood cell traits identify sex-specific trajectories and genetic correlations with disease.
Ontology highlight
ABSTRACT:
SUBMITTER: Xu Y
PROVIDER: S-EPMC8758502 | biostudies-literature |
REPOSITORIES: biostudies-literature
Similar Datasets
Project description:Machine-learning techniques have helped solve a broad range of prediction problems, yet are not widely used to build polygenic risk scores for the prediction of complex traits. We propose a novel heuristic based on machine-learning techniques (GraBLD) to boost the predictive performance of polygenic risk scores. Gradient boosted regression trees were first used to optimize the weights of SNPs included in the score, followed by a novel regional adjustment for linkage disequilibrium. A calibration set with sample size of ~200 individuals was sufficient for optimal performance. GraBLD yielded prediction R 2 of 0.239 and 0.082 using GIANT summary association statistics for height and BMI in the UK Biobank study (N?=?130?K; 1.98?M SNPs), explaining 46.9% and 32.7% of the overall polygenic variance, respectively. For diabetes status, the area under the receiver operating characteristic curve was 0.602 in the UK Biobank study using summary-level association statistics from the DIAGRAM consortium. GraBLD outperformed other polygenic score heuristics for the prediction of height (p?<?2.2?×?10-16) and BMI (p?<?1.57?×?10-4), and was equivalent to LDpred for diabetes. Results were independently validated in the Health and Retirement Study (N?=?8,292; 688,398 SNPs). Our report demonstrates the use of machine-learning techniques, coupled with summary-level data from large genome-wide meta-analyses to improve the prediction of polygenic traits.
| S-EPMC5627249 | biostudies-literature
Project description:The popular statistics-based Genome-wide association studies (GWAS) have provided deep insights into the field of complex disorder genetics. However, its clinical applicability to predict disease/trait outcomes remains unclear as statistical models are not designed to make predictions. This study employs statistics-free machine-learning (ML)-optimized polygenic risk score (PRS) to complement existing GWAS and bring the prediction of disease/trait outcomes closer to clinical application. Rheumatoid Arthritis (RA) was selected as a model disease to demonstrate the robustness of ML in disease prediction as RA is a prevalent chronic inflammatory joint disease with high mortality rates, affecting adults at the economic prime. Early identification of at-risk individuals may facilitate measures to mitigate the effects of the disease. This study employs a robust ML feature selection algorithm to identify single nucleotide polymorphisms (SNPs) that can predict RA from a set of training data comprising RA patients and population control samples. Thereafter, selected SNPs were evaluated for their predictive performances across 3 independent, unseen test datasets. The selected SNPs were subsequently used to generate PRS which was also evaluated for its predictive capacity as a sole feature. Through robust ML feature selection, 9 SNPs were found to be the minimum number of features for excellent predictive performance (AUC > 0.9) in 3 independent, unseen test datasets. PRS based on these 9 SNPs was significantly associated with (P < 1 × 10-16) and predictive (AUC > 0.9) of RA in the 3 unseen datasets. A RA ML-PRS calculator of these 9 SNPs was developed ( https://xistance.shinyapps.io/prs-ra/ ) to facilitate individualized clinical applicability. The majority of the predictive SNPs are protective, reside in non-coding regions, and are either predicted to be potentially functional SNPs (pfSNPs) or in high linkage disequilibrium (r2 > 0.8) with un-interrogated pfSNPs. These findings highlight the promise of this ML strategy to identify useful genetic features that can robustly predict disease and amenable to translation for clinical application.
| S-EPMC9903430 | biostudies-literature
Project description:The efficient acquisition and transport of nutrients by plants largely depend on the root architecture. Due to the absence of complex microbial network interactions and soil heterogeneity in a restricted soilless medium, the architecture of roots is a function of genetics defined by the soilless matrix and exogenously supplied nutrients such as nitrogen (N). The knowledge of root trait combinations that offer the optimal nitrogen use efficiency (NUE) is far from being conclusive. The objective of this study was to define the root trait(s) that best predicts and correlates with vegetative biomass under differed N treatments. We used eight image-derived root architectural traits of 202 diverse spinach lines grown in two N concentrations (high N, HN, and low N, LN) in randomized complete blocks design. Supervised random forest (RF) machine learning augmented by ranger hyperparameter grid search was used to predict the variable importance of the root traits. We also determined the broad-sense heritability (H) and genetic (rg) and phenotypic (rp) correlations between root traits and the vegetative biomass (shoot weight, SWt). Each root trait was assigned a predicted importance rank based on the trait's contribution to the cumulative reduction in the mean square error (MSE) in the RF tree regression models for SWt. The root traits were further prioritized for potential selection based on the rg and SWt correlated response (CR). The predicted importance of the eight root traits showed that the number of root tips (Tips) and root length (RLength) under HN and crossings (Xsings) and root average diameter (RAvdiam) under LN were the most relevant. SWt had a highly antagonistic rg (- 0.83) to RAvdiam, but a high predicted indirect selection efficiency (- 112.8%) with RAvdiam under LN; RAvdiam showed no significant rg or rp to SWt under HN. In limited N availability, we suggest that selecting against larger RAvdiam as a secondary trait might improve biomass and, hence, NUE with no apparent yield penalty under HN.
| S-EPMC8100178 | biostudies-literature
Project description:The genetic basis of phenotypic variation across populations has not been well explained for most traits. Several factors may cause disparities, from variation in environments to divergent population genetic structure. We hypothesized that a population-level polygenic risk score (PRS) can explain phenotypic variation among geographic populations based solely on risk allele frequencies. We applied a population-specific PRS (psPRS) to 26 populations from the 1000 Genomes to four phenotypes: lactase persistence (LP), melanoma, multiple sclerosis (MS) and height. Our models assumed additive genetic architecture among the polymorphisms in the psPRSs, as is convention. Linear psPRSs explained a significant proportion of trait variance ranging from 0.32 for height in men to 0.88 for melanoma. The best models for LP and height were linear, while those for melanoma and MS were nonlinear. As not all variants in a PRS may confer similar, or even any, risk among diverse populations, we also filtered out SNPs to assess whether variance explained was improved using psPRSs with fewer SNPs. Variance explained usually improved with fewer SNPs in the psPRS and was as high as 0.99 for height in men using only 548 of the initial 4208 SNPs. That reducing SNPs improves psPRSs performance may indicate that missing heritability is partially due to complex architecture that does not mandate additivity, undiscovered variants or spurious associations in the databases. We demonstrated that PRS-based analyses can be used across diverse populations and phenotypes for population prediction and that these comparisons can identify the universal risk variants.
| S-EPMC8670062 | biostudies-literature
Project description:Evidence from both GWAS and clinical observation has suggested that certain psychiatric, metabolic, and autoimmune diseases are heterogeneous, comprising multiple subtypes with distinct genomic etiologies and Polygenic Risk Scores (PRS). However, the presence of subtypes within many phenotypes is frequently unknown. We present CLiP (Correlated Liability Predictors), a method to detect heterogeneity in single GWAS cohorts. CLiP calculates a weighted sum of correlations between SNPs contributing to a PRS on the case/control liability scale. We demonstrate mathematically and through simulation that among i.i.d. homogeneous cases generated by a liability threshold model, significant anti-correlations are expected between otherwise independent predictors due to ascertainment on the hidden liability score. In the presence of heterogeneity from distinct etiologies, confounding by covariates, or mislabeling, these correlation patterns are altered predictably. We further extend our method to two additional association study designs: CLiP-X for quantitative predictors in applications such as transcriptome-wide association, and CLiP-Y for quantitative phenotypes, where there is no clear distinction between cases and controls. Through simulations, we demonstrate that CLiP and its extensions reliably distinguish between homogeneous and heterogeneous cohorts when the PRS explains as low as 3% of variance on the liability scale and cohorts comprise 50, 000 - 100, 000 samples, an increasingly practical size for modern GWAS. We apply CLiP to heterogeneity detection in schizophrenia cohorts totaling > 50, 000 cases and controls collected by the Psychiatric Genomics Consortium. We observe significant heterogeneity in mega-analysis of the combined PGC data (p-value 8.54 × 0-4), as well as in individual cohorts meta-analyzed using Fisher's method (p-value 0.03), based on significantly associated variants. We also apply CLiP-Y to detect heterogeneity in neuroticism in over 10, 000 individuals from the UK Biobank and detect heterogeneity with a p-value of 1.68 × 10-9. Scores were not significantly reduced when partitioning by known subclusters ("Depression" and "Worry"), suggesting that these factors are not the primary source of observed heterogeneity.
| S-EPMC7529195 | biostudies-literature
Project description:BackgroundAn increasing body of evidence suggests that neuroinflammation is one of the key drivers of late-onset Alzheimer's disease (LOAD) pathology. Due to the increased permeability of the blood-brain barrier (BBB) in older adults, peripheral plasma proteins can infiltrate the central nervous system (CNS) and drive neuroinflammation through interactions with neurons and glial cells. Because these inflammatory factors are heritable, a greater understanding of their genetic relationship with LOAD could identify new biomarkers that contribute to LOAD pathology or offer protection against it.MethodsWe used a genome-wide association study (GWAS) of 90 different plasma proteins (n = 17,747) to create polygenic scores (PGSs) in an independent discovery (cases = 1,852 and controls = 1,990) and replication (cases = 799 and controls = 778) cohort. Multivariate logistic regression was used to associate the plasma protein PGSs with LOAD diagnosis while controlling for age, sex, principal components 1-2, and the number of APOE-e4 alleles as covariates. After meta-analyzing the PGS-LOAD associations between the two cohorts, we then performed a two-sample Mendelian randomization (MR) analysis using the summary statistics of significant plasma protein level PGSs in the meta-analysis as an exposure, and a GWAS of clinically diagnosed LOAD (cases = 21,982, controls = 41,944) as an outcome to explore possible causal relationships between the two.ResultsWe identified four plasma protein level PGSs that were significantly associated (FDR-adjusted p < 0.05) with LOAD in a meta-analysis of the discovery and replication cohorts: CX3CL1, hepatocyte growth factor (HGF), TIE2, and matrix metalloproteinase-3 (MMP-3). When these four plasma proteins were used as exposures in MR with LOAD liability as the outcome, plasma levels of HGF were inferred to have a negative causal relationship with the disease when single-nucleotide polymorphisms (SNPs) used as instrumental variables were not restricted to cis-variants (OR/95%CI = 0.945/0.906-0.984, p = 0.005).ConclusionOur results show that plasma HGF has a negative causal relationship with LOAD liability that is driven by pleiotropic SNPs possibly involved in other pathways. These findings suggest a low transferability between PGS and MR approaches, and future research should explore ways in which LOAD and the plasma proteome may interact.
| S-EPMC11300309 | biostudies-literature
Project description:BackgroundThere is increasing evidence for shared genetic susceptibility between schizophrenia and bipolar disorder. Although genetic variants only convey subtle increases in risk individually, their combination into a polygenic risk score constitutes a strong disease predictor.AimsTo investigate whether schizophrenia and bipolar disorder polygenic risk scores can distinguish people with broadly defined psychosis and their unaffected relatives from controls.MethodUsing the latest Psychiatric Genomics Consortium data, we calculated schizophrenia and bipolar disorder polygenic risk scores for 1168 people with psychosis, 552 unaffected relatives and 1472 controls.ResultsPatients with broadly defined psychosis had dramatic increases in schizophrenia and bipolar polygenic risk scores, as did their relatives, albeit to a lesser degree. However, the accuracy of predictive models was modest.ConclusionsAlthough polygenic risk scores are not ready for clinical use, it is hoped that as they are refined they could help towards risk reduction advice and early interventions for psychosis.Declaration of interestR.M.M. has received honoraria for lectures from Janssen, Lundbeck, Lilly, Otsuka and Sunovian.
| S-EPMC6130805 | biostudies-literature
Project description:The COVID-19 pandemic is a global stressor with inter-individually differing influences on mental health trajectories. Polygenic Risk Scores (PRSs) for psychiatric phenotypes are associated with individual mental health predispositions. Elevated hair cortisol concentrations (HCC) and high PRSs are related to negative mental health outcomes. We analyzed whether PRSs and HCC are related to different mental health trajectories during the first COVID lockdown in Germany. Among 523 participants selected from the longitudinal resilience assessment study (LORA), we previously reported three subgroups (acute dysfunction, delayed dysfunction, resilient) based on weekly mental health (GHQ-28) assessment during COVID lockdown. DNA from blood was collected at the baseline of the original LORA study (n = 364) and used to calculate the PRSs of 12 different psychopathological phenotypes. An explorative bifactor model with Schmid-Leiman transformation was calculated to extract a general genetic factor for psychiatric disorders. Hair samples were collected quarterly prior to the pandemic for determining HCC (n = 192). Bivariate logistic regressions were performed to test the associations of HCC and the PRS factors with the reported trajectories. The bifactor model revealed 1 general factor and 4 sub-factors. Results indicate a significant association between increased values on the general risk factor and the allocation to the acute dysfunction class. The same was found for elevated HCC and the exploratorily tested sub-factor "childhood-onset neurodevelopmental disorders". Genetic risk and long-term cortisol secretion as a potential indicator of stress, indicated by PRSs and HCC, respectively, predicted different mental health trajectories. Results indicate a potential for future studies on risk prediction.
| S-EPMC9490720 | biostudies-literature
Project description:BACKGROUND:This study aimed at estimating genetic parameters of sex-influenced production traits, evaluating the impact of genotype-by-sex interaction, and identifying the selection criteria that could be included in multiple-trait genetic evaluation to increase the rate of genetic improvement in both sexes. To achieve this goal, we used 10 male and 10 female phenotypes, which were measured in a population of 2111 Australian Brahman cattle genotyped at high-density. RESULTS:Heritability estimates ranged from very low (0.03?±?0.03 for cows' days to calving at first calving opportunity, DC1), to moderate (0.33?±?0.08 for cows' adult body weight, AWTc), and to high (0.95?±?0.07 for cows' hip height, HHc). Genetic correlation (rg) estimates between male and female homologous traits were favorable and ranged from moderate to high values, which indicate that selection for any of the traits in one sex would lead to a correlated response with the equivalent phenotype in the other sex. However, the estimated direct response was greater than the indirect response. Moreover, Pearson correlations between estimated breeding values obtained from each sex separately and from female and male homologous traits combined into a single trait in univariate analysis ranged from 0.74 to 0.99, which indicate that small ranking variation might appear if male and female traits are included as single or separate phenotypes. Genetic correlations between male growth and female reproductive traits were not significant, ranging from -?0.07?±?0.13 to 0.45?±?0.65. However, selection to improve HHc and AWTc in cows may reduce the percentage of normal sperm at 24 months of age (PNS24), possibly due to correlated effects in the same traits in males, which are related to late maturing animals. CONCLUSIONS:Hip height in cows and PNS24, as well as blood insulin-like growth factor 1 (IGF1) concentration in bulls at 6 months of age are efficient selection criteria to improve male growth and female reproductive traits, simultaneously. In the presence of genotype-by-sex interactions, selection for traits in each sex results in high rates of genetic improvement, however, for the identification of animals with the highest breeding value, data for males and females may be considered a single trait.
| S-EPMC6651968 | biostudies-literature
Project description:The genetic protective factors for cognitive decline in aging remain unknown. Predicting an individual's rate of cognitive decline-or with better cognitive resilience-using genetics will allow personalized intervention for cognitive enhancement and the optimal selection of target samples in clinical trials. Here, using genome-wide polygenic scores (GPS) of cognitive capacity as the genomic indicators for variations of human intelligence, we analyzed the 18-year records of cognitive and behavioral data of 8511 European-ancestry adults from the Wisconsin Longitudinal Study (WLS), specifically focusing on the cognitive assessments that were repeatedly administered to the participants with their average ages of 64.5 and 71.5. We identified a significant interaction effect between age and cognitive capacity GPS, which indicated that a higher cognitive capacity GPS significantly correlated with a slower cognitive decline in the domain of immediate memory recall (β = 1.86 × 10-1, p-value = 1.79 × 10-3). The additional phenome-wide analyses identified several associations between cognitive capacity GPSs and cognitive/behavioral phenotypes, such as similarities task (β = 1.36, 95% CI = (1.22, 1.51), p-value = 3.59 × 10-74), number series task (β = 0.94, 95% CI = (0.85, 1.04), p-value = 2.55 × 10-78), IQ scores (β = 1.42, 95% CI = (1.32, 1.51), p-value = 7.74 × 10-179), high school classrank (β = 1.86, 95% CI = (1.69, 2.02), p-value = 3.07 × 10-101), Openness from the BIG 5 personality factor (p-value = 2.19 × 10-14, β = 0.57, 95% CI = (0.42, 0.71)), and leisure activity of reading books (β = 0.50, 95% CI = (0.40, 0.60), p-value = 2.03 × 10-21), attending cultural events, such as concerts, plays, or museums (β = 0.60, 95% CI = (0.49, 0.72), p-value = 2.06 × 10-23), and watching TV (β = -0.48, 95% CI = (-0.59, -0.37), p-value = 4.16 × 10-18). As the first phenome-wide analysis of cognitive and behavioral phenotypes, this study presents the novel genetic protective effects of cognitive ability on the decline of memory recall in an aging population.
| S-EPMC9331374 | biostudies-literature