An Accurate Machine Learning Framework for Childhood Acute Myeloid Leukemia Subtype Identification by Integrating Bulk and Single-Cell Multi-Omics Data Within and Beyond the CCDI Ecosystem

通过整合 CCDI 生态系统内外的大量和单细胞多组学数据，构建准确的机器学习框架，用于儿童急性髓性白血病亚型识别

• 批准号: 10879909
• 负责人: Joann B. Sweasy
• 金额: $ 50万
• 依托单位: UNIVERSITY OF NEBRASKA MEDICAL CENTER
• 依托单位国家: 美国
• 财政年份: 1997
• 资助国家: 美国
• 起止时间: 1997-09-05 至 2026-08-31
• 项目状态: 未结题
• 来源: https://reporter.nih.gov/project-details/10879909
• 关键词: Acute Myelocytic Leukemia; Address; Administrative Supplement; Adolescent and Young Adult; Award; Bioinformatics; Biological Markers; Bone marrow failure; Cancer Center Support Grant; Cells; Childhood; Childhood Acute Myeloid Leukemia; Classification; Clinical; Clonal Expansion; Computational Biology; Consumption; Cytogenetic Analysis; Data; Detection; Diagnosis; Ecosystem; Epigenetic Process; Foundations; Gene Transfer; Genes; Genomics; Goals; Healthcare; Hematopathology; Hematopoiesis; Hematopoietic Neoplasms; Immunophenotyping; Impairment; Intelligence; International; Knowledge; Learning; Machine Learning; Malignant Childhood Neoplasm; Malignant Neoplasms; Medical Imaging; Methods; Modeling; Molecular; Molecular Profiling; Morphology; Multiomic Data; Mutation; Myelogenous; Neurosciences; Outcome; Parents; Patients; Performance; Positioning Attribute; Process; Prognosis; Research; Sampling; Selection for Treatments; Time; anticancer research; biomarker discovery; cancer subtypes; cancer type; cell type; cost; cost effective; deep learning; diverse data; epigenomics; experience; flexibility; genetic signature; image processing; improved; individualized medicine; kernel methods; leukemia; leukemia/lymphoma; machine learning framework; machine learning method; machine learning model; multidisciplinary; multimodality; multiple omics; next generation sequencing; novel; rare cancer; risk stratification; single cell analysis; single-cell RNA sequencing; specific biomarkers; therapy design; transcriptome sequencing; transcriptomics; treatment optimization

Abstract As a fatal childhood hematopoietic malignancy characterized by clonal expansion of immature myeloid precursors, acute myeloid leukemia (AML) usually leads to bone marrow failure and impaired hematopoiesis. AML has multiple distinct subtypes characterized by morphological, molecular, and genetic alterations. Identifying AML subtypes can facilitate downstream risk stratification and tailored treatment design. While various conventional methods like morphological analysis, cytogenetic analysis, immunophenotyping, or molecular profiling have been used for AML subtype identification, they are usually costly, time-consuming, labor-intensive, and sometimes inaccurate. Recent progress has witnessed the application of next generation sequencing (NGS) for identifying AML subtypes, but they are limited to bulk NGS data, or single omics data only. With tons of omics data being generated within and beyond the Childhood Cancer Data Initiative (CCDI) ecosystem, we hypothesize that integration of single-cell and bulk multi-omics data including genomics, transcriptomics, and epigenetics data will significantly facilitate subtype-specific biomarker discovery and boost the accuracy of AML subtype identification. Under our parent award (CA036727), in this supplemental project, we propose to develop an integrated machine learning (ML) framework for accurate and cost-effective AML subtype identification by combining bulk and single-cell multi-omics data within and beyond CCDI ecosystem. To achieve this, we plan to undertake two specific aims. In Aim 1, we will establish a knowledge-transfer ML model that leverages large-scale bulk and single-cell transcriptomics data for AML subtype identification. Besides identifying well-annotated AML subtypes, we will also explore novel AML subtypes by detecting rare cell types from large-scale single cell data, from which cluster-specific and rare-cell-type specific gene signatures can be transferred to the bulk transcriptomics data for improving performance of AML subtype identification. In Aim 2, we will develop a multi-kernel learning and a multi-modal deep learning framework to systematically and automatically integrate deep information related with AML subtypes from single-cell and bulk multi-omics data (including genomics, transcriptomics, epigenomics) to further boost AML subtype identification. Our model is flexible to tackle cases when only partial or incomplete multi-omics data are available for new patients. We believe successful completion of this study will have direct impacts on improving downstream childhood AML risk stratification, facilitating diagnosis and prognosis, and optimizing treatment selection. We also expect that our proposed framework in this study can be customized and extensible to identifying subtypes of other pediatric, adolescent, and young adult (AYA) cancers especially ultra-rare tumors.

抽象的 作为一种致命的儿童造血系统恶性肿瘤，其特征是未成熟骨髓细胞的克隆性扩张 急性髓系白血病（AML）通常会导致骨髓衰竭和造血功能受损。 AML 有多种不同的亚型，其特征是形态、分子和遗传改变。 识别 AML 亚型可以促进下游风险分层和定制治疗设计。虽然各种 常规方法，如形态学分析、细胞遗传学分析、免疫表型分析或分子分析 分析已被用于 AML 亚型识别，它们通常成本高昂、耗时、劳动密集型， 有时不准确。最新进展见证了下一代测序（NGS）的应用 用于识别 AML 亚型，但仅限于批量 NGS 数据或单个组学数据。拥有大量组学 数据是在儿童癌症数据倡议 (CCDI) 生态系统内部和外部生成的，我们 假设单细胞和大量多组学数据（包括基因组学、转录组学和 表观遗传学数据将显着促进亚型特异性生物标志物的发现并提高 AML 的准确性 亚型识别。根据我们的家长奖（CA036727），在这个补充项目中，我们建议 为准确且经济高效的 AML 子类型开发集成机器学习 (ML) 框架 通过结合 CCDI 生态系统内外的批量和单细胞多组学数据进行识别。 为了实现这一目标，我们计划实现两个具体目标。在目标 1 中，我们将建立知识转移 ML 该模型利用大规模批量和单细胞转录组数据进行 AML 亚型识别。除了 在识别注释良好的 AML 亚型的同时，我们还将通过检测稀有细胞类型来探索新的 AML 亚型 来自大规模单细胞数据，可以从中获得簇特异性和稀有细胞类型特异性基因特征 转移到大量转录组数据以提高 AML 亚型识别的性能。在目标 2 中， 我们将开发多内核学习和多模态深度学习框架来系统地、 自动集成来自单细胞和批量多组学数据的与 AML 亚型相关的深层信息 （包括基因组学、转录组学、表观基因组学）进一步促进 AML 亚型识别。我们的模型是 当新患者只有部分或不完整的多组学数据可用时，可以灵活地处理病例。我们 相信这项研究的成功完成将对改善下游儿童 AML 产生直接影响 风险分层，促进诊断和预后，优化治疗选择。我们也期望 我们在这项研究中提出的框架可以定制和扩展，以识别其他儿科的亚型， 青少年和青年 (AYA) 癌症，尤其是极其罕见的肿瘤。