Deep Learning Based Genetic Risk Prediction for Type 1 Diabetes

基于深度学习的 1 型糖尿病遗传风险预测

• 批准号: 10189573
• 负责人: Paul Tran
• 金额: $ 4.16万
• 依托单位: AUGUSTA UNIVERSITY
• 依托单位国家: 美国
• 财政年份: 2019
• 资助国家: 美国
• 起止时间: 2019-07-10 至 2022-07-09
• 项目状态: 已结题
• 来源: https://reporter.nih.gov/project-details/10189573
• 关键词: Adopted; Alleles; Alternative Splicing; Area; Autoimmune Diseases; Autoimmune Responses; Bioinformatics; Biological; Child; Childhood; Communities; Complex; Data; Data Analyses; Data Set; Decision Making; Development; Diabetes Mellitus; Disease; Enhancers; Enrollment; Environmental Risk Factor; Future; Genes; Genetic; Genetic Population Study; Genetic Predisposition to Disease; Genetic Risk; Genotype; HLA Antigens; Individual; Insulin-Dependent Diabetes Mellitus; Intervention; Islets of Langerhans; Logistic Regressions; Longitudinal Studies; Measures; Medical; Modeling; Molecular; Neural Network Simulation; Newborn Infant; Pathogenesis; Pathway Analysis; Population; Prediabetes syndrome; Premature Birth; Prevention Research; Prevention trial; Publishing; Quantitative Trait Loci; Receiver Operating Characteristics; Research; Risk; Sensitivity and Specificity; Statistical Models; Testing; Time; Training; Variant; base; case control; deep learning; feedforward neural network; genome wide association study; high risk; improved; molecular subtypes; neural network; new therapeutic target; novel; predictive modeling; prevent; prevention clinical trial; promoter; recruit; risk prediction; statistical and machine learning

Project Summary Type I diabetes (T1D) is an autoimmune disease of childhood caused by a combination of genetic and environmental factors. In a subset of individuals with a genetic predisposition to T1D, environmental triggers instigate an autoimmune response which targets and damages pancreatic islets, leading to pre-diabetes and ultimately diabetes. A critical barrier in T1D prevention research is to identify and directly enroll children with a strong genetic predisposition for developing T1D into prevention trials. A robust genetic risk score (GRS) would allow for the identification of children at high-risk of T1D, their recruitment into T1D prevention trials, and subsequent testing of novel interventions. I aim to 1) optimize a multi-layer feedforward neural network genetic risk predictor that can be used to enroll newborns directly into T1D prevention trials; and 2) identify putative, novel T1D-causing SNPs, and their interactions. Completion of aim 1 would provide a better GRS to the T1D research community, which can be used to identify children with higher genetic risk of T1D development, increasing the statistical power of future T1D prevention clinical trials. Completion of aim 2 will provide a deeper biological understanding of the molecular drivers of T1D development, and potential new therapeutic targets for T1D prevention trials. Successful completion of this project will both help understand the genetic causes of type 1 diabetes and help prevent the disease.

项目概要 I 型糖尿病 (T1D) 是一种由遗传和遗传因素共同引起的儿童期自身免疫性疾病。 环境因素。在具有 T1D 遗传易感性的个体子集中，环境触发因素 引发针对胰岛并损害胰岛的自身免疫反应，导致糖尿病前期 最终患上糖尿病。 T1D 预防研究的一个关键障碍是识别并直接招募儿童 具有将 T1D 纳入预防试验的强烈遗传倾向。强大的遗传风险评分 (GRS) 将允许识别 T1D 高危儿童，并招募他们参与 T1D 预防工作 试验以及随后对新干预措施的测试。我的目标是 1）优化多层前馈神经网络 网络遗传风险预测器，可用于将新生儿直接纳入 T1D 预防试验；和 2) 识别推定的、新颖的 T1D 致病 SNP 及其相互作用。完成目标 1 将提供 为 T1D 研究界提供更好的 GRS，可用于识别具有较高遗传风险的儿童 T1D 发展的统计能力，增加未来 T1D 预防临床试验的统计能力。完成 目标 2 将提供对 T1D 发展的分子驱动因素更深入的生物学理解，以及 T1D 预防试验的潜在新治疗靶点。该项目的顺利完成将 帮助了解 1 型糖尿病的遗传原因并帮助预防该疾病。

项目成果

Comparative analysis of transcriptomic profile, histology, and IDH mutation for classification of gliomas.

• DOI: 10.1038/s41598-020-77777-6
• 发表时间: 2020-11-26
• 期刊: Scientific reports
• 影响因子: 4.6
• 作者: Tran PMH;Tran LKH;Nechtman J;Dos Santos B;Purohit S;Satter KB;Dun B;Kolhe R;Sharma S;Bollag R;She JX
• 通讯作者: She JX

Are There Survival Differences Between Women with Equivalent Residual Disease After Interval Cytoreductive Surgery Compared with Primary Cytoreductive Surgery for Advanced Ovarian and Peritoneal Cancer?

• DOI: 10.1245/s10434-020-09304-w
• 发表时间: 2020-11-05
• 期刊: ANNALS OF SURGICAL ONCOLOGY
• 影响因子: 3.7
• 作者: Mysona, David Pierce;Ghamande, Sharad;Gehrig, Paola A.
• 通讯作者: Gehrig, Paola A.

A combined score of clinical factors and serum proteins can predict time to recurrence in high grade serous ovarian cancer.

• DOI: 10.1016/j.ygyno.2018.12.015
• 发表时间: 2019-03
• 期刊: GYNECOLOGIC ONCOLOGY
• 影响因子: 4.7
• 作者: Mysona, David;Pyrzak, Adam;Purohit, Sharad;Zhi, Wenbo;Sharma, Ashok;Tran, Lynn;Tran, Paul;Bai, Shan;Rungruang, Bunja;Ghamande, Sharad;She, Jin-Xiong
• 通讯作者: She, Jin-Xiong

T1DMicro: A Clinical Risk Calculator for Type 1 Diabetes Related Microvascular Complications.

• DOI: 10.3390/ijerph182111094
• 发表时间: 2021-10-21
• 期刊: International journal of environmental research and public health
• 作者: Tran PMH;Kim E;Tran LKH;Khaled BS;Hopkins D;Gardiner M;Bryant J;Bernard R;Morgan J;Bode B;Reed JC;She JX;Purohit S
• 通讯作者: Purohit S

Retrospective Validation of a 168-Gene Expression Signature for Glioma Classification on a Single Molecule Counting Platform.

• DOI: 10.3390/cancers13030439
• 发表时间: 2021-01-25
• 期刊: Cancers
• 影响因子: 5.2
• 作者: Tran PMH;Tran LKH;Satter KB;Purohit S;Nechtman J;Hopkins DI;Dos Santos B;Bollag R;Kolhe R;Sharma S;She JX
• 通讯作者: She JX