Artificial intelligence for dementia genetics and omics

Alzheimer s & Dementia, Journal Year: 2023, Volume and Issue: 19(12), P. 5905 - 5921

Published: Aug. 22, 2023

Abstract Genetics and omics studies of Alzheimer's disease other dementia subtypes enhance our understanding underlying mechanisms pathways that can be targeted. We identified key remaining challenges: First, we genetic to address missing heritability? Can identify reproducible signatures differentiate between subtypes? high‐dimensional data improved biomarkers? How genetics inform causal status risk factors? And which biological processes are altered by dementia‐related variation? Artificial intelligence (AI) machine learning approaches give us powerful new tools in helping tackle these challenges, review possible solutions examples best practice. However, their limitations also need considered, as well the for coordinated multidisciplinary research diverse deeply phenotyped cohorts. Ultimately AI improve ability interrogate precision medicine. Highlights have five challenges studies. enable detection undiscovered patterns data. Enhanced more datasets still needed. Multidisciplinary collaborative efforts using boost research.

Language: Английский

---

The promise and challenges of genomics‐informed periodontal disease diagnoses

Periodontology 2000, Journal Year: 2024, Volume and Issue: 95(1), P. 194 - 202

Published: June 1, 2024

Abstract Recent advances in human genomics and the advent of molecular medicine have catapulted our ability to characterize health disease. Scientists healthcare practitioners can now leverage information on genetic variation gene expression at tissue or even individual cell level, an enormous potential exists refine diagnostic categories, assess risk unaffected individuals, optimize disease management among those affected. This review investigates progress made domains as they relate periodontology. The summarizes current evidence association between periodontal diseases, including state knowledge that approximately a third population variance periodontitis may be attributable several monogenic forms augmented by underlying cause. Finally, paper discusses utility polygenic scores testing for diagnosis future, light applications currently exist other areas healthcare.

Language: Английский

---

Systemic lupus erythematosus genetics: insights into pathogenesis and implications for therapy

Nature Reviews Rheumatology, Journal Year: 2024, Volume and Issue: 20(10), P. 635 - 648

Published: Sept. 4, 2024

Language: Английский

---

Ethical layering in AI-driven polygenic risk scores—New complexities, new challenges

Frontiers in Genetics, Journal Year: 2023, Volume and Issue: 14

Published: Jan. 26, 2023

Researchers aim to develop polygenic risk scores as a tool prevent and more effectively treat serious diseases, disorders conditions such breast cancer, type 2 diabetes mellitus coronary heart disease. Recently, machine learning techniques, in particular deep neural networks, have been increasingly developed create using electronic health records well genomic other data. While the use of artificial intelligence for may enable greater accuracy, performance prediction, it also presents range complex ethical challenges. The social issues many score applications medicine widely discussed. However, literature practice, implications their confluence with not yet sufficiently considered. Based on comprehensive review existing literature, we argue that this stands need urgent consideration research subsequent translation into clinical setting. Considering layers involved, will first give brief overview development intelligence-driven scores, associated implications, challenges ethics, finally, explore potential complexities driven by intelligence. We point out emerging complexity regarding fairness, building trust, explaining understanding regulatory uncertainties further strongly advocate taking proactive approach embedding ethics implementation processes

Language: Английский

---

Polygenic risk scores for disease risk prediction in Africa: current challenges and future directions

Genome Medicine, Journal Year: 2023, Volume and Issue: 15(1)

Published: Oct. 30, 2023

Early identification of genetic risk factors for complex diseases can enable timely interventions and prevent serious outcomes, including mortality. While the genetics underlying many Mendelian have been elucidated, it is harder to predict arising from combined effects variants with smaller individual on disease aetiology. Polygenic scores (PRS), which combine multiple contributing risk, potential influence implementation precision medicine. However, majority existing PRS were developed European data limited transferability African populations. Notably, populations diverse backgrounds, a genomic architecture haplotype blocks compared genomes. Subsequently, growing evidence shows that using large-scale ancestry cohorts as discovery development may generate more generalizable findings. Here, we (1) discuss poor in populations, (2) showcase novel Africa datasets development, (3) explore clinical utility (4) provide insight into future Africa.

Language: Английский

---

Lessons and Applications of Omics Research in Diabetes Epidemiology

Current Diabetes Reports, Journal Year: 2024, Volume and Issue: 24(3), P. 27 - 44

Published: Jan. 31, 2024

Abstract Purpose of Review Recent advances in genomic technology and molecular techniques have greatly facilitated the identification disease biomarkers, advanced understanding pathogenesis different common diseases, heralded dawn precision medicine. Much these area diabetes been made possible through deep phenotyping epidemiological cohorts, analysis omics data relation to detailed clinical information. In this review, we aim provide an overview on how research could be incorporated into design current future studies. Findings We up-to-date review genetic, epigenetic, proteomic metabolomic markers for related outcomes, including polygenic risk scores. drawn key examples from literature, as well our own experience conducting using Hong Kong Diabetes Register Biobank, other illustrate potential diabetes. studies highlight opportunity, benefit, incorporate profiling set-up epidemiology studies, which can also advance heterogeneity Summary Learnings should facilitate researchers consider incorporating technologies their work field its co-morbidities. Insights would important development medicine

Language: Английский

---

Differences in polygenic score distributions in European ancestry populations: implications for breast cancer risk prediction

medRxiv (Cold Spring Harbor Laboratory), Journal Year: 2024, Volume and Issue: unknown

Published: Feb. 13, 2024

The 313-variant polygenic risk score (PRS313) provides a promising tool for breast cancer prediction. However, evaluation of the PRS313 across different European populations which could influence estimation has not been performed. Here, we explored distribution using genotype data from 94,072 females without cancer, European-ancestry 21 countries participating in Breast Cancer Association Consortium (BCAC) and 225,105 female participants UK Biobank. mean differed markedly countries, being highest south-eastern Europe lowest north-western Europe. Using overall to categorise individuals leads overestimation underestimation some respectively. Adjustment principal components explained most observed heterogeneity PRS. Country-specific PRS distributions may be used calibrate categories countries.

Language: Английский

---

Single nucleotide polymorphism-based biomarker in primary hypertension

European Journal of Pharmacology, Journal Year: 2024, Volume and Issue: 972, P. 176584 - 176584

Published: April 15, 2024

Language: Английский

---

Validation of a clinical breast cancer risk assessment tool combining a polygenic score for all ancestries with traditional risk factors

Genetics in Medicine, Journal Year: 2024, Volume and Issue: 26(7), P. 101128 - 101128

Published: June 3, 2024

PurposeWe previously described a combined risk score (CRS) that integrates multiple-ancestry polygenic (MA-PRS) with the Tyrer-Cuzick (TC) model to assess breast cancer (BC) risk. Here, we present longitudinal validation of CRS in real-world cohort.MethodsThis study included 130,058 patients referred for hereditary genetic testing and negative germline pathogenic variants BC-associated genes. Data were obtained by linking test results medical claims (median follow-up 12.1 months). calibration was evaluated ratio observed expected BCs.ResultsThree hundred forty BCs over 148,349 patient-years. well-calibrated demonstrated superior compared TC high-risk deciles. MA-PRS alone had greater discriminatory accuracy than TC, approximately 2-fold or TC. Among those classified as high 32.6% low CRS, 4.3% CRS. In cases where classifications disagreed, more accurate predicting incident BC.ConclusionCRS significantly improved BC stratification. Short-term suggests clinical implementation should improve outcomes all ancestries through personalized risk-based screening prevention.

Language: Английский

---

Integrative polygenic risk score improves the prediction accuracy of complex traits and diseases

medRxiv (Cold Spring Harbor Laboratory), Journal Year: 2023, Volume and Issue: unknown

Published: Feb. 26, 2023

Polygenic risk scores (PRS) are an emerging tool to predict the clinical phenotypes and outcomes of individuals. Validation transferability existing PRS across independent datasets diverse ancestries limited, which hinders practical utility exacerbates health disparities. We propose PRSmix, a framework that evaluates leverages corpus target trait improve prediction accuracy, PRSmix+, incorporates genetically correlated traits better capture human genetic architecture. applied PRSmix 47 32 diseases/traits in European South Asian ancestries, respectively. demonstrated mean accuracy improvement 1.20-fold (95% CI: [1.10; 1.3]; P-value = 9.17 × 10-5) 1.19-fold [1.11; 1.27]; 1.92 10-6), PRSmix+ improved by 1.72-fold [1.40; 2.04]; 7.58 10-6) 1.42-fold [1.25; 1.59]; 8.01 10-7) Compared previously established cross-trait-combination method with from pre-defined traits, we our can for coronary artery disease up 3.27-fold [2.1; 4.44]; after FDR correction 2.6 10-4). Our provides comprehensive benchmark leverage combined power maximal performance desired population.

Language: Английский

---