A knowledge map to find Alzheimer's disease drugs

一张知识图谱寻找阿尔茨海默病药物

基本信息

批准号：
10198233
负责人：
OLIVIER LICHTARGE
金额：
$ 38.66万
依托单位：
BAYLOR COLLEGE OF MEDICINE
依托单位国家：
美国
项目类别：
财政年份：
2018
资助国家：
美国
起止时间：
2018-09-30 至 2023-05-31
项目状态：
已结题

来源：
https://reporter.nih.gov/project-details/10198233
关键词：
2019-nCoV Address Algorithms Alzheimer&apos s Disease Alzheimer&apos s disease risk Alzheimer&apos s disease therapy Antigens Benchmarking Binding Biological Markers COVID-19 COVID-19 pandemic Calculi Catalysis Clinical Clustered Regularly Interspaced Short Palindromic Repeats Code Combined Modality Therapy Data Disease Disease Surveillance Docking Drug Targeting Emergency Situation Engineering Epitopes Evolution Funding Genes Genetic Code Genetic Markers Graph Human Human Genetics Immunotherapy Individual Infection Knowledge Lead Libraries Life Link Machine Learning Maps Measures Methods Mission Morbidity - disease rate Mutation Onset of illness Output Patient risk Peptide Synthesis Peptides Pharmaceutical Preparations Protein Region Proteins Proteome Research Risk Risk Assessment Site Solvents Speed Structure Surface Symptoms Testing Time Training Update Variant Viral Genes Virulence base biobank case control clinical risk disorder risk exome fitness genome-wide improved knowledge graph mimetics mortality novel novel strategies parent grant peptidomimetics prediction algorithm predictive marker prevent prospective prospective test protein function protein protein interaction protein structure prototype small molecule success support tools theories tool vaccine development web site

项目摘要

ABSTRACT. This Supplement extends Aims 1 and 2 of the parent grant on Alzheimer’s Disease (AD) by developing: prospective benchmarks for algorithms that predict biomarkers of disease risk (Aim 1) and new algorithms to support drug repositioning (Aim 2). Both extensions strengthen Aims 1 and 2 for AD but also have immediate applications for research on COVID-19 disease in keeping with NOT-AG-20-022. AIM 1 of the parent grant develops EA-ML, a Machine Learning (ML) pipeline to compare coding mutations in individuals with and without AD. The output is a list of genes with which to predict AD risk from their mutations. While the parent grant has multiple criteria for success, none are prospective given the vast lead-time between AD onset and symptoms. Supplemental Aim 1 adds prospective testing, using COVID-19. This is possible because the UK Biobank has begun to annotate its 50,000 public exomes with the COVID-19 status of individuals, including who had severe morbidity or mild symptoms at worst. The biobank will also add 150,000 more exomes by end 2020. Accordingly, we will apply EA-ML to the current UK biobank data to identify human genetic biomarkers that distinguish severe from mild cases and then test EA-ML predictions of COVID-19 virulence prospectively, on the exomes that are newly added to the biobank. As a further new benchmark, we will also compare EA-ML to a novel “EA-Wavelet” algorithm, also tested prospectively on COVID-19. EA- Wavelet sorts cases from controls by factoring EA over the entire network of human protein-protein interactions. The results will tell us which of EA-ML, EA-Wavelet, or combination thereof is the best at identifying critical biomarkers and clinical risk of AD, while also doing the same for COVID-19. Aim 2 of the parent grant develops drug repositioning for AD by linking target genes and drugs via knowledge maps of functional interactions. Here, we propose a complementary approach that connect genes to drugs via structural maps of binding epitopes. For this we will comprehensively map evolutionarily important sites in the structural proteome of genes that are associated with AD. The approach exploits EA theory to measure past and present evolutionary forces in fitness landscapes, and it takes into account current sequence variations to guard against any possible mutational escape from drugs that target these epitopes. The output will be surface accessible regions of proteins that can then be used for (i) computational docking of small molecules towards drug repurposing, combination therapy, and lead discovery for drug design3-5; (ii) engineering mimetic peptides or other molecules that can inhibit normal interactions6; and (iii) CRISPR engineering or peptide synthesis that create antigens for more effective vaccines7, 8. These automated mapping tools are general, and besides in SARS-CoV-2, will identify an entire new structural library of functional sites to target for AD therapy with repurposed drugs.

摘要：本补充方案将家长补助金的目标 1 和 2 延伸至阿尔茨海默病 (AD)。正在开发：预测疾病风险生物标志物的算法的前瞻性基准（目标 1）和新的支持药物重新定位的算法（目标 2）。这两个扩展都加强了 AD 的目标 1 和 2，但也有根据 NOT-AG-20-022 立即申请有关 COVID-19 疾病的研究。母基金的 AIM 1 开发了 EA-ML，这是一种机器学习 (ML) 管道，用于比较编码突变输出是一个基因列表，可通过其突变预测 AD 风险。虽然家长补助金有多种成功标准，但考虑到两者之间的漫长准备时间，没有一个是预期的。 AD 发病和症状补充目标 1 增加了使用 COVID-19 的前瞻性测试。因为英国生物银行已开始注释其 50,000 个公共外显子组，其 COVID-19 状态为个人，包括患有严重发病或最严重症状轻微的人，生物库还将增加 150,000 名。到 2020 年底，我们将获得更多外显子组。因此，我们将 EA-ML 应用于当前的英国生物库数据，以识别人类区分严重病例和轻度病例的遗传生物标志物，然后测试 EA-ML 对 COVID-19 的预测作为进一步的新基准，我们对新添加到生物库的外显子组进行了毒力预测。还将将 EA-ML 与新型“EA-Wavelet”算法进行比较，该算法也在 EA-19 上进行了前瞻性测试。小波通过在人类蛋白质-蛋白质相互作用的整个网络上分解 EA，对病例与对照进行分类。结果将告诉我们 EA-ML、EA-Wavelet 或其组合中哪一个最适合识别关键生物标志物和 AD 临床风险，同时也对 COVID-19 进行同样的研究。母基金的目标 2 通过知识将目标基因和药物联系起来，开发针对 AD 的药物重新定位在这里，我们提出了一种将基因与药物联系起来的补充方法。通过结合表位的结构图为此，我们将全面绘制进化上重要的位点。该方法利用 EA 理论来测量与 AD 相关的基因的结构蛋白质组。适应度景观中过去和现在的进化力量，并考虑了当前的序列变化以防止针对这些表位的药物发生任何可能的突变逃逸。输出将是表面的。蛋白质的可接近区域，然后可用于（i）小分子的计算对接药物再利用、联合治疗和药物设计的先导化合物发现3-5 (ii) 工程模拟肽；或其他可以抑制正常相互作用的分子6；以及 (iii) CRISPR 工程或肽合成为更有效的疫苗创建抗原7、8。这些自动绘图工具很通用，而且还可以用于 SARS-CoV-2 将确定一个全新的功能位点结构库，用于 AD 治疗重新利用药物。