scholarly journals Brain age prediction using deep learning uncovers associated sequence variants

2019 ◽  
Vol 10 (1) ◽  
Author(s):  
B. A. Jonsson ◽  
G. Bjornsdottir ◽  
T. E. Thorgeirsson ◽  
L. M. Ellingsen ◽  
G. Bragi Walters ◽  
...  
Keyword(s):  
Deep Learning ◽  
Genome Wide Association Study ◽  
Structural Mri ◽  
Machine Learning Algorithms ◽  
Age Difference ◽  
Sequence Variants ◽  
Uk Biobank ◽  
A Genome ◽  
The Uk ◽  
Brain Age

AbstractMachine learning algorithms can be trained to estimate age from brain structural MRI. The difference between an individual’s predicted and chronological age, predicted age difference (PAD), is a phenotype of relevance to aging and brain disease. Here, we present a new deep learning approach to predict brain age from a T1-weighted MRI. The method was trained on a dataset of healthy Icelanders and tested on two datasets, IXI and UK Biobank, utilizing transfer learning to improve accuracy on new sites. A genome-wide association study (GWAS) of PAD in the UK Biobank data (discovery set: $$N=12378$$N=12378, replication set: $$N=4456$$N=4456) yielded two sequence variants, rs1452628-T ($$\beta =-0.08$$β=−0.08, $$P=1.15\times{10}^{-9}$$P=1.15×10−9) and rs2435204-G ($$\beta =0.102$$β=0.102, $$P=9.73\times 1{0}^{-12}$$P=9.73×10−12). The former is near KCNK2 and correlates with reduced sulcal width, whereas the latter correlates with reduced white matter surface area and tags a well-known inversion at 17q21.31 (H2).

scholarly journals Deep learning based brain age prediction uncovers associated sequence variants

2019 ◽  
Author(s):  
B.A. Jonsson ◽  
G. Bjornsdottir ◽  
T.E. Thorgeirsson ◽  
L.M. Ellingsen ◽  
G. Bragi Walters ◽  
...  
Keyword(s):  
Deep Learning ◽  
Magnetic Resonance Images ◽  
Machine Learning Algorithms ◽  
Brain Diseases ◽  
Age Difference ◽  
Sequence Variants ◽  
Genome Wide Association Studies ◽  
Uk Biobank ◽  
Brain Ageing ◽  
Brain Age

AbstractMachine learning algorithms trained to recognize age-related structural changes in magnetic resonance images (MRIs) of healthy individuals can be used to predict biological brain age in independent samples. The difference between predicted and chronological age, predicted age difference (PAD), is a phenotype holding promise for the study of normal brain ageing and brain diseases, and genetic discoveryviagenome-wide association studies (GWASs). Here, we present a new deep learning approach to predict brain age from a T1-weighted MRI. The method was trained on a dataset of healthy Icelanders (N= 1264) and tested on two datasets, the IXI (N= 544) and UK Biobank (N= 12395) datasets, utilizing transfer learning to improve accuracy on new sites. A GWAS of PAD in the UK Biobank data (discovery set: N=12395, replication set: N=4453) yielded two sequence variants, rs1452628-T (β=-0.08,P= 1.15 · 10−9) and rs2435204-G (β=0.102,P= 9.73 · 10−12). The former is nearKCNK2and correlates with reduced sulcal width, whereas the latter correlates with reduced white matter surface area and tags a well-known inversion at 17q21.31 (H2). The genetic association analysis was also confined to variants known to associate with brain structure, yielding three additional sequence variants associating with PAD.

scholarly journals A novel variant in GLIS3 is associated with osteoarthritis

2018 ◽  
Vol 77 (4) ◽  
pp. 620-623 ◽  
Author(s):  
Elisabetta Casalone ◽  
Ioanna Tachmazidou ◽  
Eleni Zengini ◽  
Konstantinos Hatzikotoulas ◽  
Sophie Hackinger ◽  
...  
Keyword(s):  
Complex Disease ◽  
Genome Wide Association Study ◽  
Total Joint Replacement ◽  
Population Based ◽  
Uk Biobank ◽  
Proteomics Data ◽  
Glucose Levels ◽  
Genome Wide ◽  
A Genome ◽  
The Uk

ObjectivesOsteoarthritis (OA) is a complex disease, but its genetic aetiology remains poorly characterised. To identify novel susceptibility loci for OA, we carried out a genome-wide association study (GWAS) in individuals from the largest UK-based OA collections to date.MethodsWe carried out a discovery GWAS in 5414 OA individuals with knee and/or hip total joint replacement (TJR) and 9939 population-based controls. We followed-up prioritised variants in OA subjects from the interim release of the UK Biobank resource (up to 12 658 cases and 50 898 controls) and our lead finding in operated OA subjects from the full release of UK Biobank (17 894 cases and 89 470 controls). We investigated its functional implications in methylation, gene expression and proteomics data in primary chondrocytes from 12 pairs of intact and degraded cartilage samples from patients undergoing TJR.ResultsWe detect a genome-wide significant association at rs10116772 with TJR (P=3.7×10−8; for allele A: OR (95% CI) 0.97 (0.96 to 0.98)), an intronic variant in GLIS3, which is expressed in cartilage. Variants in strong correlation with rs10116772 have been associated with elevated plasma glucose levels and diabetes.ConclusionsWe identify a novel susceptibility locus for OA that has been previously implicated in diabetes and glycaemic traits.

scholarly journals A genome-wide association study finds genetic variants associated with neck or shoulder pain in UK Biobank

2020 ◽  
Vol 29 (8) ◽  
pp. 1396-1404 ◽  
Author(s):  
Weihua Meng ◽  
Brian W Chan ◽  
Cameron Harris ◽  
Maxim B Freidin ◽  
Harry L Hebert ◽  
...  
Keyword(s):  
Association Study ◽  
Shoulder Pain ◽  
Genetic Variants ◽  
Genome Wide Association Study ◽  
Genome Wide Association ◽  
Uk Biobank ◽  
Genome Wide ◽  
A Genome ◽  
Significant Locus ◽  
The Uk

Abstract Background Common types of musculoskeletal conditions include pain in the neck and shoulder areas. This study seeks to identify the genetic variants associated with neck or shoulder pain based on a genome-wide association approach using 203 309 subjects from the UK Biobank cohort and look for replication evidence from the Generation Scotland: Scottish Family Health Study (GS:SFHS) and TwinsUK. Methods A genome-wide association study was performed adjusting for age, sex, BMI and nine population principal components. Significant and independent genetic variants were then sent to GS:SFHS and TwinsUK for replication. Results We identified three genetic loci that were associated with neck or shoulder pain in the UK Biobank samples. The most significant locus was in an intergenic region in chromosome 17, rs12453010, having P = 1.66 × 10−11. The second most significant locus was located in the FOXP2 gene in chromosome 7 with P = 2.38 × 10−10 for rs34291892. The third locus was located in the LINC01572 gene in chromosome 16 with P = 4.50 × 10−8 for rs62053992. In the replication stage, among four significant and independent genetic variants, rs2049604 in the FOXP2 gene and rs62053992 in the LINC01572 gene were weakly replicated in GS:SFHS (P = 0.0240 and P = 0.0202, respectively). Conclusions We have identified three loci associated with neck or shoulder pain in the UK Biobank cohort, two of which were weakly supported in a replication cohort. Further evidence is needed to confirm their roles in neck or shoulder pain.

scholarly journals Genetic underpinnings of sociability in the UK Biobank

2019 ◽  
Author(s):  
J Bralten ◽  
CJHM Klemann ◽  
NR Mota ◽  
W De Witte ◽  
C Arango ◽  
...  
Keyword(s):  
Social Anxiety ◽  
Psychiatric Disorders ◽  
Genetic Correlation ◽  
Genome Wide Association Study ◽  
Autism Spectrum ◽  
Self Report ◽  
Uk Biobank ◽  
Genome Wide ◽  
A Genome ◽  
The Uk

ABSTRACTDifficulties with sociability include a tendency to avoid social contacts and activities, and to prefer being alone rather than being with others. While sociability is a continuously distributed trait in the population, decreased sociability represent a common early manifestation of multiple neuropsychiatric disorders such as Schizophrenia (SCZ), Bipolar Disorder (BP), Major Depressive Disorder (MDD), Autism Spectrum Disorders (ASDs), and Alzheimer’s disease (AD). We aimed to investigate the genetic underpinnings of sociability as a continuous trait in the general population. In this respect, we performed a genome-wide association study (GWAS) using a sociability score based on 4 social functioning-related self-report questions in the UK Biobank sample (n=342,461) to test the effect of individual genetic variants. This was followed by LD score analyses to investigate the genetic correlation with psychiatric disorders (SCZ, BP, MDD, ASDs) and a neurological disorder (AD) as well as related phenotypes (Loneliness and Social Anxiety). The phenotypic data indeed showed that the sociability score was decreased in individuals with ASD, (probable) MDD, BP and SCZ, but not in individuals with AD. Our GWAS showed 604 genome-wide significant SNPs, coming from 18 independent loci (SNP-based h2=0.06). Genetic correlation analyses showed significant correlations with SCZ (rg=0.15, p=9.8e-23), MDD (rg=0.68, p=6.6e-248) and ASDs (rg=0.27, p=4.5e-28), but no correlation with BP (rg=0.01, p=0.45) or AD (rg=0.04, p=0.55). Our sociability trait was also genetically correlated with Loneliness (rg=0.45, p=2.4e-8) and Social Anxiety (rg=0.48, p=0.002). Our study shows that there is a significant genetic component to variation in population levels of sociability, which is relevant to some psychiatric disorders (SCZ, MDD, ASDs), but not to BP and AD.

scholarly journals A genome-wide association study identifies that the GDF5 and COL27A1 genes are associated with knee pain in UK Biobank (N = 171, 516)

2019 ◽  
Author(s):  
Weihua Meng ◽  
Mark J Adams ◽  
Colin NA Palmer ◽  
Jingchunzi Shi ◽  
Adam Auton ◽  
...  
Keyword(s):  
Knee Pain ◽  
Genome Wide Association Study ◽  
Meta Analysis ◽  
Genome Wide Association ◽  
Uk Biobank ◽  
Narrow Sense ◽  
Narrow Sense Heritability ◽  
Genome Wide ◽  
A Genome ◽  
The Uk

SUMMARYObjectiveKnee pain is one of the most common musculoskeletal complaints that brings people to medical attention. We sought to identify the genetic variants associated with knee pain in 171,516 subjects from the UK Biobank cohort and replicate them using cohorts from 23andMe, the Osteoarthritis Initiative (OAI), and the Johnston County Osteoarthritis Study (JoCo).MethodsWe performed a genome-wide association study of knee pain in the UK Biobank, where knee pain was ascertained through self-report and defined as “knee pain in the last month interfering with usual activities”. A total of 22,204 cases and 149,312 controls were included in the discovery analysis. We tested our top and independent SNPs (P < 5 × 10−8) for replication in 23andMe, OAI, and JoCo, then performed a joint meta-analysis between discovery and replication cohorts using GWAMA. We calculated the narrow-sense heritability of knee pain using Genome-wide Complex Trait Analysis (GCTA).ResultsWe identified 2 loci that reached genome-wide significance, rs143384 located in the GDF5 (P = 1.32 × 10−12), a gene previously implicated in osteoarthritis, and rs2808772, located near COL27A1 (P = 1.49 × 10−8). These findings were subsequently replicated in independent cohorts and increased in significance in the joint meta-analysis (rs143384: P = 4.64 × 10−18; rs2808772: P −11 = 2.56 × 10−1’). The narrow sense heritability of knee pain was 0.08.ConclusionIn this first reported genome-wide association meta-analysis of knee pain, we identified and replicated two loci in or near GDF5 and COL27A1 that are associated with knee pain.

scholarly journals Genome-wide Association Study of Pulmonary Function in Europeans and Africans from the UK Biobank Identifies Distinct Variants

2022 ◽  
Author(s):  
Musalula Sinkala ◽  
Samar S. M. Elsheikh ◽  
Mamana Mbiyavanga ◽  
Joshua Cullinan ◽  
Nicola Mulder
Keyword(s):  
Pulmonary Function ◽  
Genome Wide Association Study ◽  
Well Being ◽  
Genome Wide Association ◽  
Significant Finding ◽  
Uk Biobank ◽  
Chromosome 11 ◽  
Genome Wide ◽  
A Genome ◽  
The Uk

Pulmonary function is an indicator of well-being, and pulmonary pathologies are the third major cause of death worldwide. FEV1, FVC, and PEF are quantitively used to assess pulmonary function. We conducted a genome-wide association analysis of pulmonary function in 383,471 individuals of European and 5,978 African descent represented in the UK Biobank. Here, we report 817 variants in Europeans and 3 in Africans associated (p-values < 5 x 10-8) with three pulmonary function parameters; FEV1, FVC and PEF. In addition to 377 variants in Europeans previously reported to be associated with phenotypes related to pulmonary function, we identified 330 novel loci, including an ISX intergenic variant rs369476290 on chromosome 22 in Africans and a KDM2A intron variant rs12790261 on chromosome 11 in Europeans. Remarkably, we find no shared variants among Africans and Europeans. Enrichment analyses of variants separately for each ancestry background revealed significant enrichment for terms related to pulmonary phenotypes in Europeans but not Africans. Further analysis of studies of pulmonary phenotypes revealed individuals of European background are disproportionally overrepresented in datasets compared to Africans, with the gap widening over the past five years. Our findings offer a better understanding of the different variants that modify pulmonary function in Africans and Europeans, a significant finding for future GWAS studies and medicine.

scholarly journals Deep learning enables genetic analysis of the human thoracic aorta

2020 ◽  
Author(s):  
James P. Pirruccello ◽  
Mark D. Chaffin ◽  
Stephen J. Fleming ◽  
Alessandro Arduini ◽  
Honghuang Lin ◽  
...  
Keyword(s):  
Deep Learning ◽  
Aortic Aneurysm ◽  
Thoracic Aorta ◽  
Genetic Basis ◽  
Genome Wide Association Study ◽  
The Body ◽  
Aortic Diameter ◽  
Uk Biobank ◽  
Imaging Data ◽  
A Genome

The aorta is the largest blood vessel in the body, and enlargement or aneurysm of the aorta can predispose to dissection, an important cause of sudden death. While rare syndromes have been identified that predispose to aortic aneurysm, the common genetic basis for the size of the aorta remains largely unknown. By leveraging a deep learning architecture that was originally developed to recognize natural images, we trained a model to evaluate the dimensions of the ascending and descending thoracic aorta in cardiac magnetic resonance imaging. After manual annotation of just 116 samples, we applied this model to 3,840,140 images from the UK Biobank. We then conducted a genome-wide association study in 33,420 individuals, revealing 68 loci associated with ascending and 35 with descending thoracic aortic diameter, of which 10 loci overlapped. Integration of common variation with transcriptome-wide analyses, rare-variant burden tests, and single nucleus RNA sequencing prioritized SVIL, a gene highly expressed in vascular smooth muscle, that was significantly associated with the diameter of the ascending and descending aorta. A polygenic score for ascending aortic diameter was associated with a diagnosis of thoracic aortic aneurysm in the remaining 391,251 UK Biobank participants who did not undergo imaging (HR = 1.44 per standard deviation; P = 3.7·10−12). Defining the genetic basis of the diameter of the aorta may enable the identification of asymptomatic individuals at risk for aneurysm or dissection and facilitate the prioritization of potential therapeutic targets for the prevention or treatment of aortic aneurysm. Finally, our results illustrate the potential for rapidly defining novel quantitative traits derived from a deep learning model, an approach that can be more broadly applied to biomedical imaging data.

scholarly journals Machine Learning to Understand Genetic and Clinical Factors Associated with the Pulse Waveform Dicrotic Notch

2021 ◽  
Author(s):  
Jonathan W. Cunningham ◽  
Paolo Di Achille ◽  
Valerie N. Morrill ◽  
Lu-Chen Weng ◽  
Seung Hoan Choi ◽  
...  
Keyword(s):  
Machine Learning ◽  
Genome Wide Association Study ◽  
Polygenic Risk Score ◽  
Uk Biobank ◽  
Polygenic Risk ◽  
Continuous Trait ◽  
Dicrotic Notch ◽  
Digital Phenotyping ◽  
A Genome ◽  
The Uk

AbstractBackgroundAbsence of a dicrotic notch on finger photoplethysmography (PPG) is an easily ascertainable and inexpensive trait that has been associated with age and prevalent cardiovascular disease (CVD). However, the trait exists along a continuum, and little is known about its genetic underpinnings or prognostic value for incident CVD.MethodsIn 169,787 participants in the UK Biobank, we identified absent dicrotic notch on PPG and created a novel continuous trait reflecting notch smoothness using machine learning. Next, we determined the heritability, genetic basis, polygenic risk, and clinical relations for the binary absent notch trait and the newly derived continuous notch smoothness trait.ResultsHeritability of the continuous notch smoothness trait was 7.5%, compared with 5.6% for the binary absent notch trait. A genome wide association study of notch smoothness identified 15 significant loci, implicating genes including NT5C2 (P=1.2×10−26), IGFBP3 (P=4.8×10−18), and PHACTR1 (P=1.4×10−13), compared with 6 loci for the binary absent notch trait. Notch smoothness stratified risk of incident myocardial infarction or coronary artery disease, stroke, heart failure, and aortic stenosis. A polygenic risk score for notch smoothness was associated with incident CVD and all-cause death in UK Biobank participants without available PPG data.ConclusionWe found that a machine learning derived continuous trait reflecting dicrotic notch smoothness on PPG was heritable and associated with genes involved in vascular stiffness. Greater notch smoothness was associated with greater risk of incident CVD. Raw digital phenotyping may identify individuals at risk for disease via specific genetic pathways.

scholarly journals A genome-wide association study finds novel genetic associations with broadly-defined headache in UK Biobank (N = 223,773)

2017 ◽  
Author(s):  
Weihua Meng ◽  
Mark J Adams ◽  
Harry L Hebert ◽  
Ian J Deary ◽  
Andrew M McIntosh ◽  
...  
Keyword(s):  
Association Study ◽  
Genome Wide Association Study ◽  
Genetic Correlations ◽  
Genome Wide Association ◽  
Uk Biobank ◽  
Genetic Associations ◽  
Psychological Traits ◽  
Genome Wide ◽  
A Genome ◽  
The Uk

AbstractHeadache is the most common neurological symptom and a leading cause of years lived with disability. We sought to identify the genetic variants associated with a broadly-defined headache phenotype in 223,773 subjects from the UK Biobank cohort. We defined headache based on a specific question answered by the UK Biobank participants. We performed a genome-wide association study of headache as a single entity, using 74,461 cases and 149,312 controls. We identified 3,343 SNPs which reached the genome-wide significance level of P < 5 × 10−8. The SNPs were located in 28 loci, with the top SNP of rs11172113 in the LRP1 gene having a P value of 4.92 × 10−47. Of the 28 loci, 14 have previously been associated with migraine. Among 14 new loci, rs77804065 with a P value of 5.87 × 10−15 in the LINC02210-CRHR1 gene was the top SNP.Positive relationships (P < 0.001) between multiple brain tissues and genetic associations were identified through tissue expression analysis, whereas no vascular related tissues showed significant relationships. We identified several significant positive genetic correlations between headache and other psychological traits including neuroticism, depressive symptoms, insomnia, and major depressive disorder.Our results suggest that brain function is closely related to broadly-defined headache. In addition, we also found that many psychological traits have genetic correlations with headache.

Sign in / Sign up

Export Citation Format

Share Document