Kidney disease is a leading cause of death worldwide.Currently,the diagnosis of kidney diseases and the grading of their severity are mainly based on clinical features,which do not reveal the underlying molecular path...Kidney disease is a leading cause of death worldwide.Currently,the diagnosis of kidney diseases and the grading of their severity are mainly based on clinical features,which do not reveal the underlying molecular pathways.More recent surge of∼omics studies has greatly catalyzed disease research.The advent of artificial intelligence(AI)has opened the avenue for the efficient integration and interpretation of big datasets for discovering clinically actionable knowledge.This review discusses how AI and multi-omics can be applied and integrated,to offer opportunities to develop novel diagnostic and therapeutic means in kidney diseases.The combination of new technology and novel analysis pipelines can lead to breakthroughs in expanding our understanding of disease pathogenesis,shedding new light on biomarkers and disease classification,as well as providing possibilities of precise treatment.展开更多
Genome-wide association studies(GWASs)have identified 30 independent genetic variants associated with IgA nephropathy(IgAN).A genetic risk score(GRS)represents the number of risk alleles carried and thus captures an i...Genome-wide association studies(GWASs)have identified 30 independent genetic variants associated with IgA nephropathy(IgAN).A genetic risk score(GRS)represents the number of risk alleles carried and thus captures an individual's genetic risk.However,whether and which polygenic risk score crucial for the evaluation of any potential personal or clinical utility on risk and prognosis are still obscure.We constructed different GRS models based on different sets of variants,which were top single nucleotide polymorphisms(SNPs)reported in the previous GWASs.The case–control GRS analysis included 3365 IgAN patients and 8842 healthy individuals.The association between GRS and clinical variability,including age at diagnosis,clinical parameters,Oxford pathology classification,and kidney prognosis was further evaluated in a prospective cohort of 1747 patients.Three GRS models(15 SNPs,21 SNPs,and 55 SNPs)were constructed after quality control.The patients with the top 20%GRS had 2.42—(15 SNPs,p=8.12×10^(-40)),3.89—(21 SNPs,p=3.40×10^(-80))and 3.73—(55 SNPs,p=6.86×10^(-81))fold of risk to develop IgAN compared to the patients with the bottom 20%GRS,with area under the receiver operating characteristic curve(AUC)of 0.59,0.63,and 0.63 in group discriminations,respectively.A positive correlation between GRS and microhematuria,mesangial hypercellularity,segmental glomerulosclerosis and a negative correlation on the age at diagnosis,body mass index(BMI),mean arterial pressure(MAP),serum C3,triglycerides can be observed.Patients with the top 20%GRS also showed a higher risk of worse prognosis for all three models(1.36,1.42,and 1.36 fold of risk)compared to the remaining 80%,whereas 21 SNPs model seemed to show a slightly better fit in prediction.Collectively,a higher burden of risk variants is associated with earlier disease onset and a higher risk of a worse prognosis.This may be informational in translating knowledge on IgAN genetics into disease risk prediction and patient stratification.展开更多
基金Support was provided by the National Science Foundation of China(82022010,82131430172,81970613)the Beijing Natural Science Foundation(Z190023)+3 种基金Academy of Medical Sciences-Newton Advanced Fellowship(NAFR13\1033)the Fok Ying Tung Education Foundation(171030)the Beijing Nova Program Interdisciplinary Cooperation Project(Z191100001119004)the Chinese Academy of Medical Sciences Research Unit(2019RU023).
文摘Kidney disease is a leading cause of death worldwide.Currently,the diagnosis of kidney diseases and the grading of their severity are mainly based on clinical features,which do not reveal the underlying molecular pathways.More recent surge of∼omics studies has greatly catalyzed disease research.The advent of artificial intelligence(AI)has opened the avenue for the efficient integration and interpretation of big datasets for discovering clinically actionable knowledge.This review discusses how AI and multi-omics can be applied and integrated,to offer opportunities to develop novel diagnostic and therapeutic means in kidney diseases.The combination of new technology and novel analysis pipelines can lead to breakthroughs in expanding our understanding of disease pathogenesis,shedding new light on biomarkers and disease classification,as well as providing possibilities of precise treatment.
基金supported by National Science Foundation of China(82022010,82370709,81970613,82070733,82000680)Beijing Natural Science Foundation(Z190023)+3 种基金Academy of Medical Sciences–Newton Advanced Fellowship(NAFR13\1033)Fok Ying Tung Education Foundation(171030)Chinese Academy of Medical Sciences(CAMS)Innovation Fund for Medical Sciences(2019-I2M-5–046,2020-JKCS-009)National High Level Hospital Clinical Research Funding(Interdisciplinary Clinical Research Project of Peking University First Hospital,2022CR41)。
文摘Genome-wide association studies(GWASs)have identified 30 independent genetic variants associated with IgA nephropathy(IgAN).A genetic risk score(GRS)represents the number of risk alleles carried and thus captures an individual's genetic risk.However,whether and which polygenic risk score crucial for the evaluation of any potential personal or clinical utility on risk and prognosis are still obscure.We constructed different GRS models based on different sets of variants,which were top single nucleotide polymorphisms(SNPs)reported in the previous GWASs.The case–control GRS analysis included 3365 IgAN patients and 8842 healthy individuals.The association between GRS and clinical variability,including age at diagnosis,clinical parameters,Oxford pathology classification,and kidney prognosis was further evaluated in a prospective cohort of 1747 patients.Three GRS models(15 SNPs,21 SNPs,and 55 SNPs)were constructed after quality control.The patients with the top 20%GRS had 2.42—(15 SNPs,p=8.12×10^(-40)),3.89—(21 SNPs,p=3.40×10^(-80))and 3.73—(55 SNPs,p=6.86×10^(-81))fold of risk to develop IgAN compared to the patients with the bottom 20%GRS,with area under the receiver operating characteristic curve(AUC)of 0.59,0.63,and 0.63 in group discriminations,respectively.A positive correlation between GRS and microhematuria,mesangial hypercellularity,segmental glomerulosclerosis and a negative correlation on the age at diagnosis,body mass index(BMI),mean arterial pressure(MAP),serum C3,triglycerides can be observed.Patients with the top 20%GRS also showed a higher risk of worse prognosis for all three models(1.36,1.42,and 1.36 fold of risk)compared to the remaining 80%,whereas 21 SNPs model seemed to show a slightly better fit in prediction.Collectively,a higher burden of risk variants is associated with earlier disease onset and a higher risk of a worse prognosis.This may be informational in translating knowledge on IgAN genetics into disease risk prediction and patient stratification.
