arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2502.02629q-bio.GNcs.AIcs.LG
收藏

面向肿瘤微环境的图结构学习:基于非空间 scRNA-seq 数据的细胞类型注释

Graph Structure Learning for Tumor Microenvironment with Cell Type Annotation from non-spatial scRNA-seq data

School of Computer Science, Northwestern Polytechnical University(西北工业大学计算机学院);Research & Development Institute of Northwestern Polytechnical University in Shenzhen(西北工业大学深圳研究院);School of Engineering, The University of Sydney(悉尼大学工程学院);College of Life Sciences, Northwest University(西北大学生命科学学院);Research Office, City University of Hong Kong (Dongguan)(香港城市大学(东莞)研究办公室)

Yu-An Huang, Yue-Chao Li, Hai-Ru You, Jie Pan, Xiyue Cao, Xinyuan Li, Zhi-An Huang, Zhu-Hong You

AI总结:

本文提出图神经网络模型 scGSL,利用非空间 scRNA-seq 数据提升肿瘤微环境中细胞类型注释与细胞间通讯推断性能,并在三类癌症数据集上验证了其优于现有方法的准确性和生物学可解释性。

摘要:

通过单细胞 RNA 测序(scRNA-seq)探索肿瘤微环境(TME)内的细胞异质性,对于理解癌症进展和治疗响应至关重要。然而,当前的 scRNA-seq 方法缺乏空间背景,并且依赖于不完整的配体-受体相互作用(LRIs)数据集,限制了准确的细胞类型注释和细胞间通讯(CCC)推断。本研究通过一种新颖的图神经网络(GNN)模型来应对这些挑战,该模型增强了细胞类型预测和细胞相互作用分析。我们的研究使用了一个包含 49,020 个细胞的数据集,这些细胞来自 19 名患者,涵盖三种癌症类型:白血病、乳腺浸润性癌和结直肠癌。所提出的 scGSL 模型表现出稳健的性能,在所有数据集上实现了平均准确率 84.83%、精确率 86.23%、召回率 81.51% 和 F1 分数 80.92%。这些指标相较于现有方法有显著提升,现有方法通常表现出较低的性能指标。此外,通过回顾 TME 内基因相互作用的现有文献,scGSL 模型被证明能够以无监督方式稳健地识别具有生物学意义的基因相互作用,并通过多种癌症中关键基因对的显著表达差异得到验证。本文使用的源代码和数据可在 https://github.com/LiYuechao1998/scGSL 中找到。

英文摘要:

The exploration of cellular heterogeneity within the tumor microenvironment (TME) via single-cell RNA sequencing (scRNA-seq) is essential for understanding cancer progression and response to therapy. Current scRNA-seq approaches, however, lack spatial context and rely on incomplete datasets of ligand-receptor interactions (LRIs), limiting accurate cell type annotation and cell-cell communication (CCC) inference. This study addresses these challenges using a novel graph neural network (GNN) model that enhances cell type prediction and cell interaction analysis. Our study utilized a dataset consisting of 49,020 cells from 19 patients across three cancer types: Leukemia, Breast Invasive Carcinoma, and Colorectal Cancer. The proposed scGSL model demonstrated robust performance, achieving an average accuracy of 84.83%, precision of 86.23%, recall of 81.51%, and an F1 score of 80.92% across all datasets. These metrics represent a significant enhancement over existing methods, which typically exhibit lower performance metrics. Additionally, by reviewing existing literature on gene interactions within the TME, the scGSL model proves to robustly identify biologically meaningful gene interactions in an unsupervised manner, validated by significant expression differences in key gene pairs across various cancers. The source code and data used in this paper can be found in https://github.com/LiYuechao1998/scGSL.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑