IMAT-ITCR Collaboration: Artificial intelligence enhanced breast cancer dormancy cell classification-based organelle-morphology and topology

IMAT-ITCR 合作：人工智能增强乳腺癌休眠细胞分类的细胞器形态和拓扑

• 批准号: 10884759
• 负责人: Margarida Barroso
• 金额: $ 8.15万
• 依托单位: ALBANY MEDICAL COLLEGE
• 依托单位国家: 美国
• 财政年份: 2022
• 资助国家: 美国
• 起止时间: 2022-09-01 至 2024-08-31
• 项目状态: 已结题
• 来源: https://reporter.nih.gov/project-details/10884759
• 关键词: 3-Dimensional; 4T1; Acceleration; Algorithms; Artificial Intelligence; Biology; Biosensor; Breast Cancer Cell; Breast Cancer Model; Breast Cancer Patient; Breast Cancer cell line; Categories; Cell model; Cells; Cellular biology; Characteristics; Classification; Collaborations; Cytometry; Data; Development; Discriminant Analysis; Disease; Disseminated Malignant Neoplasm; Distant Metastasis; Endoplasmic Reticulum; Excision; Funding; Genetic; Genomics; Goals; Grant; Heterogeneity; Imaging Device; Immunofluorescence Immunologic; Individual; Informatics; Joints; Label; Location; Lysosomes; Machine Learning; Malignant Neoplasms; Metastatic breast cancer; Methodology; Methods; Mitochondria; Modeling; Morphology; Neoplasm Metastasis; Organelles; Patients; Pattern; Phenotype; Population; Primary Neoplasm; Proliferating; Proteomics; Recurrent Malignant Neoplasm; Regulator Genes; Resistance; Sampling; Signal Pathway; Spatial Distribution; Technology; Time; Tissues; analysis pipeline; analytical tool; anticancer research; cancer cell; cancer recurrence; cancer site; cancer type; classification algorithm; deep learning; diagnostic value; genetic manipulation; improved; in vivo; innovation; machine learning classifier; machine learning method; malignant breast neoplasm; monolayer; mortality; mouse model; multiplexed imaging; neoplastic cell; new technology; novel; novel strategies; prevent; prognostic value; protein biomarkers; random forest; rare cancer; success; synthetic biology; therapy development; tool; transcriptomics; tumor

ABSTRACT Breast cancer is a highly heterogenous disease, both phenotypically and genetically. The quantity and subcellular location of cancer protein biomarkers are used to classify breast cancer types. Transcriptomics, multiplexed imaging, or mass cytometry have been used to classify breast tumor cell heterogeneity with varying success. Although genomics and proteomics have been successful in the identification of tumor cell populations involved in metastatic progression, the ability to determine whether patient tumors contain metastatic subpopulations is still lacking. Recently, organelle morphology and function has been used as a direct readout of the functional phenotypic state of an individual cancer cell. We propose to use the spatial context of organelles, specifically their subcellular location and inter-organelle relationships (topology), to classify novel and distinct metastatic cancer cell subpopulations. We developed an Organelle Topology-based Cell Classification Pipeline (OTCCP) to quantify, for the first time, the topological features of subcellular organelles, defined as the distance between each organelle object and all its neighbors within a cell. Under RFA-CA-21-013 (Development of Innovative Informatics Methods and Algorithms for Cancer Research and Management), we will adapt or develop Machine learning and Deep Learning methodologies to accelerate and automate OTCCP-based organelle- based topology cancer cell classification to identify subpopulations of metastatic cells within heterogeneous primary tumors with potential diagnostic and prognostic value. This approach will also have major impact as a discovery tool to advance our understanding of cancer cell biology on a subcellular level.

抽象的 乳腺癌是一种在表型和遗传上都具有高度异质性的疾病。数量及 癌症蛋白生物标志物的亚细胞定位用于对乳腺癌类型进行分类。转录组学， 多重成像或质谱流式细胞仪已用于对乳腺肿瘤细胞异质性进行分类 成功。尽管基因组学和蛋白质组学已成功鉴定肿瘤细胞群 参与转移进展，确定患者肿瘤是否含有转移性肿瘤的能力 亚人群仍然缺乏。最近，细胞器形态和功能已被用作直接读数 单个癌细胞的功能表型状态。我们建议利用细胞器的空间背景， 特别是它们的亚细胞位置和细胞器间关系（拓扑），以对新颖和独特的进行分类 转移性癌细胞亚群。我们开发了基于细胞器拓扑的细胞分类流程 （OTCCP）首次量化亚细胞器的拓扑特征，定义为距离 细胞内每个细胞器对象与其所有邻居之间的关系。根据 RFA-CA-21-013（开发 用于癌症研究和管理的创新信息学方法和算法），我们将适应或开发 机器学习和深度学习方法可加速和自动化基于 OTCCP 的细胞器 基于拓扑癌细胞分类来识别异质内转移细胞的亚群 原发性肿瘤具有潜在的诊断和预后价值。这种方法也将产生重大影响 促进我们在亚细胞水平上理解癌细胞生物学的发现工具。