PO.BCS01.02 · 生物信息与计算

用于无富集液体活检中罕见事件检测和单细胞表型分析的可扩展、无监督深度学习框架

Scalable, unsupervised deep learning frameworks for rare event detection and single cell phenotyping in enrichment free liquid biopsies

编号 1434 展板 28 时间 4/20 09:00–12:00 区域 Section 3 主讲 Dean Tessone, BS

分会场 Application of Bioinformatics to Cancer Biology 2

查看 PDF 下载 PDF 🔒 查看 / 下载完整 PDF 需登录并开通下载套餐 · 查看套餐 / 开通 AACR 官方页面

作者与单位 Authors & Affiliations

Dean Tessone¹, Amin Naghdloo², Javier Murgoitio-Esandi³, Jeremy Mason², Assad Oberai⁴, James B. Hicks⁵, Peter Kuhn⁶

¹Molecular and Computational Biology, University of Southern California, Los Angeles, CA,²USC - University of Southern California, Los Angeles, CA,³Aerospace and Mechanical Engineering, University of Southern California, Los Angeles, CA,⁴Viterbi School of Engineering, University of Southern California, Los Angeles, CA,⁵USC, Los Angeles, CA,⁶Assoc. Professor, Dept. of Cell Bio., University of Southern California, Los Angeles, CA

摘要 Abstract

中文摘要

液体活检提供了一种微创手段来探究肿瘤生物学；然而，循环肿瘤细胞 (CTC) 及相关细胞事件的极度稀有性和表型多样性仍是敏感检测和有意义分析的主要障碍。传统工作流程常依赖于生物物理富集或预定义的生物标志物组合，两者都可能使细胞回收产生偏倚并限制发现。因此，迫切需要能够直接分析数百万个单细胞观测值、并在不依赖先验标签的情况下提取生物学结构的可扩展计算方法。我们开发了基于深度学习的流程，用于分析从外周血中分离的有核细胞。对每位患者，通过白膜层制备获得约五百万个细胞，用五标志物荧光组合染色，并在不进行任何富集步骤的情况下通过全玻片显微成像。第一个流程是构建于去噪自编码器之上的无监督罕见事件检测器。应用于11名乳腺癌患者的样本时，该方法回收了91个额外事件——包括CTC、内皮细胞、癌相关成纤维细胞 (CAF) 和细胞外囊泡——在极少人工调整的情况下增加了超过50%。这种无标签的离群值检测形式可广泛推广至高内涵成像研究，其中对罕见或意外群体的无偏识别至关重要。第二个流程使用表示学习来推导稳定的单细胞嵌入。这些嵌入支持以92.64%的准确率进行表型分类，并且还能实现反映形态学和标志物表达内在变异的无监督聚类。值得注意的是，所学习的特征对成像伪影具有鲁棒性，确保了在异质数据集中一致的表型分析。总的来说，这些深度学习框架建立了一个用于液体活检中无富集罕见事件检测、聚类和细胞类型表征的集成策略，为生物标志物发现提供了可扩展的基础。

查看英文原文 English abstract

Liquid biopsy offers a minimally invasive means to interrogate tumor biology; however, the extreme rarity and phenotypic diversity of circulating tumor cells (CTCs) and related cellular events remain major obstacles to sensitive detection and meaningful analysis. Conventional workflows frequently rely on biophysical enrichment or predefined biomarker panels, both of which can bias cell recovery and constrain discovery. There is therefore a critical need for scalable computational approaches capable of analyzing millions of single-cell observations directly and extracting biological structure without dependence on prior labels. We developed deep learning-based pipelines to analyze nucleated cells isolated from peripheral blood. For each patient, approximately five million cells are obtained via buffy coat preparation, stained with a five-marker fluorescence panel, and imaged by whole-slide microscopy without any enrichment steps. The first pipeline is an unsupervised rare-event detector built on a denoising autoencoder. Applied to samples from 11 breast cancer patients, the method recovered 91 additional events-including CTCs, endothelial cells, cancer-associated fibroblasts (CAFs), and extracellular vesicles-representing a greater than 50% increase with minimal manual tuning. This form of label-free outlier detection is broadly generalizable to high-content imaging studies in which unbiased identification of infrequent or unexpected populations is essential. The second pipeline uses representation learning to derive stable single-cell embeddings. These embeddings support phenotype classification with 92.64% accuracy and also enable unsupervised clustering that reflects intrinsic variation in morphology and marker expression. Notably, the learned features are robust to imaging artifacts, ensuring consistent phenotyping across heterogeneous datasets. Collectively, these deep learning frameworks establish an integrated strategy for enrichment-free rare-event detection, clustering, and cell-type characterization in liquid biopsy, providing a scalable foundation for biomarker discovery

利益披露 Disclosure

D. Tessone, None.. J. Murgoitio-Esandi, None.

← 返回 AACR 2026 检索