Combining Machine Learning and Nanofluidic Technology for The Multiplexed Diagnosis of Pancreatic Adenocarcinoma

结合机器学习和纳流体技术进行胰腺癌的多重诊断

• 批准号: 10613226
• 负责人: Erica Carpenter
• 金额: $ 38.83万
• 依托单位: UNIVERSITY OF PENNSYLVANIA
• 依托单位国家: 美国
• 财政年份: 2023
• 资助国家: 美国
• 起止时间: 2023-06-01 至 2026-05-31
• 项目状态: 未结题
• 来源: https://reporter.nih.gov/project-details/10613226
• 关键词: Address; Algorithms; Benchmarking; Benign; Biological Assay; Biological Markers; Blinded; Blood; Blood specimen; CA-19-9 Antigen; Cancer Etiology; Cell Line; Cessation of life; Classification; Clinical; Data; Data Set; Detection; Development; Diagnosis; Diagnostic; Disease; Disease Progression; Distant Metastasis; Early Diagnosis; Elements; Endoscopic Biopsy; Endoscopy; Environment; Evaluation; Goals; Hour; Image; Individual; KRAS2 gene; Lesion; Localized Disease; Machine Learning; Magnetic Resonance Imaging; Magnetism; Malignant - descriptor; Malignant Neoplasms; Malignant neoplasm of pancreas; Membrane Proteins; Messenger RNA; Methods; MicroRNAs; Modeling; Molecular Profiling; Monitor; Mutation Detection; Neoplasm Metastasis; Nucleic Acids; Operative Surgical Procedures; Pancreas; Pancreatic Adenocarcinoma; Pancreatic Diseases; Pancreatic Ductal Adenocarcinoma; Pancreatitis; Patient-Focused Outcomes; Patients; Performance; Physicians; Plasma; Positron-Emission Tomography; Proteins; RNA; RNA Probes; Resectable; Role; Sampling; Sorting; Staging; Stream; Surface; Technology; Testing; Training; Tumor-Derived; Tumor-associated macrophages; United States; Validation; Vesicle; Work; X-Ray Computed Tomography; cell free DNA; cell type; clinical diagnostics; cohort; design; detection limit; detection sensitivity; diagnostic signature; diagnostic value; disorder control; drug efficacy; efficacious treatment; extracellular vesicles; improved; innovation; instrumentation; liquid biopsy; machine learning classification; machine learning classifier; manufacturability; microfluidic technology; multimodality; nanofluidic; nanoparticle; nanopore; nanoscale; neoplastic cell; next generation; noninvasive diagnosis; novel strategies; operation; physical property; predictive panel; prognostic signature; protein expression; screening; standard of care; treatment response; tumor; tumor DNA

Pancreatic ductal adenocarcinoma (PDAC) is the third leading cause of cancer-related death in the United States with an overall 5-year survival of 9%. Diagnosis and staging continue to rely on endoscopic biopsy and imaging, and as such most patients are diagnosed at an advanced stage. Sufficiently sensitive and specific screening tests for early disease remain elusive. Moreover, while curative-intent surgery is an option for patients whose disease is confined to the pancreas, distinguishing patients with metastases who are unlikely to benefit from surgery, remains challenging due to occult metastases not detectable by imaging. To address these challenges, several blood-based liquid biopsy biomarkers have been developed but show low sensitivity for detection of early-stage disease. We have recently shown that circulating tumor derived extracellular vesicles(EVs) can be isolated from blood and their RNA cargo used to diagnose early pancreatic cancer and stage disease. These findings suggest an opportunity to improve patient outcomes through development of a non-invasive diagnostic for pancreatic cancer. However, as has been well documented, EVs are highly heterogeneous in their expression of protein surface markers and their nucleic acid and protein cargo, and originate from multiple cell types in the tumor micro environment (TME) (e.g. tumor cells, tumor associated macrophages). The ultimate goal of this proposal is to address a fundamental technological unmet need in EV diagnostics, by further developing our new approach to EV subpopulation isolation using magnetic nanopores, which combines the benefits of nano-scale sorting with sufficiently fast flow rates (106x faster than typical nanofluidic approaches) to be practical for clinical diagnostics. In this R33, we develop this approach into a multiplexed EV assay that will allow multiple unique EV sub-populations - based on surface marker expression- to be isolated and their RNA cargo profiled. Building on our prior work that demonstrated the value of analyzing single EV-subpopulations, and improved sensitivity of a multi-analyte vs single analyte test, we will develop a multi-analyte EV-based assay that algorithmically combines tumor associated EV RNA from multiple circulating EV isolates from the TME, as well as Circulating cell-free DNA (ccfDNA) concentration, circulating tumor DNA-based KRAS mutation detection, and CA19-9 using machine learning.

胰腺导管腺癌 (PDAC) 是癌症相关死亡的第三大原因 美国的总体 5 年生存率为 9%。诊断和分期继续依赖 内窥镜活检和成像，因此大多数患者是在晚期诊断的 阶段。针对早期疾病的足够敏感和特异性的筛查测试仍然难以实现。 此外，虽然对于疾病仅限于以下疾病的患者来说，治愈性手术是一种选择 胰腺，区分不太可能从手术中受益的转移患者， 由于影像学无法检测到隐匿性转移，因此仍然具有挑战性。为了解决这些 挑战，已经开发了几种基于血液的液体活检生物标志物，但表现较低 检测早期疾病的敏感性。我们最近发现循环肿瘤 衍生的细胞外囊泡 (EV) 可以从血液中分离出来，其 RNA 货物可用于 诊断早期胰腺癌并分期疾病。这些发现表明有机会 通过开发胰腺非侵入性诊断方法改善患者治疗结果 癌症。然而，正如有充分证据表明的那样，电动汽车在其性能方面具有高度的异质性。 蛋白质表面标记及其核酸和蛋白质货物的表达，并起源 来自肿瘤微环境（TME）中的多种细胞类型（例如肿瘤细胞、肿瘤 相关巨噬细胞）。该提案的最终目标是解决一个根本问题 通过进一步开发我们的电动汽车新方法，解决电动汽车诊断中未满足的技术需求 使用磁性纳米孔进行亚群分离，结合了纳米级的优点 以足够快的流速（比典型纳米流体方法快 106 倍）进行分类 可用于临床诊断。在这款 R33 中，我们将这种方法开发成多路电动汽车 检测将允许多个独特的 EV 亚群 - 基于表面标记表达 - 进行分离并分析其 RNA 货物。以我们之前的工作为基础，展示了 分析单一 EV 亚群的价值，以及与多种分析物相比提高的灵敏度 单一分析物测试，我们将开发一种基于 EV 的多分析物检测，该检测通过算法 结合了来自 TME 的多种循环 EV 分离株的肿瘤相关 EV RNA，以及 作为循环游离 DNA (ccfDNA) 浓度、基于循环肿瘤 DNA 的 KRAS 使用机器学习进行突变检测和 CA19-9。