NPJ genomic medicine. 2025 Jun 14;10(1):48. doi: 10.1038/s41525-025-00507-2 Q14.82025

Integrating explainable machine learning and transcriptomics data reveals cell-type specific immune signatures underlying macular degeneration

可解释机器学习与转录组数据的整合揭示年龄相关黄斑变性背后细胞特异性免疫特征翻译改进

Khang Ma¹, Hosei Nakajima¹, Nipa Basak¹, Arko Barman^{2 3 4}, Rinki Ratnapriya^{5 6}

作者单位 +展开

作者单位

¹ Department of Ophthalmology, Baylor College of Medicine, Houston, TX, USA.

² Data to Knowledge Lab, Rice University, Houston, TX, USA.

³ Department of Electrical & Computer Engineering, Rice University, Houston, TX, USA.

⁴ Department of Statistics, Rice University, Houston, TX, USA.

⁵ Department of Ophthalmology, Baylor College of Medicine, Houston, TX, USA. rpriya@bcm.edu.

⁶ Department of Biochemistry and Molecular Pharmacology, Baylor College of Medicine, Houston, TX, USA. rpriya@bcm.edu.

DOI: 10.1038/s41525-025-00507-2 PMID: 40517179

摘要中英对照阅读

Genome-wide association studies (GWAS) have established key role of immune dysfunction in Age-related Macular Degeneration (AMD), though the precise role of immune cells remains unclear. Here, we develop an explainable machine-learning pipeline (ML) using transcriptome data of 453 donor retinas, identifying 81 genes distinguishing AMD from controls (AUC-ROC of 0.80, CI 0.70-0.92). Most of these genes were enriched in their expression within retinal glial c... ...点击完成人机验证后继续浏览

全基因组关联研究（GWAS）已经确立了免疫功能障碍在年龄相关性黄斑变性（AMD）中的关键作用，尽管免疫细胞的确切作用仍不清楚。在这里，我们使用453名捐赠者的视网膜转录组数据开发了一种可解释的机器学习管道（ML），识别出81个区分AMD和对照样本的基因（AUC-ROC为0.80，CI 0.70-0.92）。其中大多数基因在视网膜胶质细胞中的表达富集，尤其是小胶质细胞和星形胶质细胞。通过细胞去卷积进一步强化了这些基因在AMD中的作用，发现正常与AMD样本中小胶质细胞和星形胶质细胞存在显著差异。我们使用独立的单细胞数据验证了这一发现，其中几个机器学习基因表现出不同的表达水平。最后，整合AMD-GWAS数据识别出PLCG2上的调控变异rs4133124为新的AMD关联。总的来说，我们的研究提供了关于免疫功能障碍在AMD中反复出现的主题的分子见解，并强调了胶质细胞差异在AMD进展中的重要性。

翻译效果不满意？用Ai改进或寻求AI助手帮助，对摘要进行重点提炼

相关内容

期刊名：Npj genomic medicine

缩写：NPJ GENOM MED

ISSN：N/A

e-ISSN：2056-7944

IF/分区：4.8/Q1

文章目录更多期刊信息

全文链接

官方链接

PMC全文

引文链接

复制

已复制！

格式：

Integrating explainable machine learning and transcriptomics data reveals cell-type specific immune signatures underlying macular degeneration

可解释机器学习与转录组数据的整合揭示年龄相关黄斑变性背后细胞特异性免疫特征翻译改进

Using Explainable Machine Learning to Improve Intensive Care Unit Alarm Systems

使用可解释机器学习来改进重症监护室报警系统

A Fast and Minimal System to Identify Depression Using Smartphones: Explainable Machine Learning-Based Approach

一种快速且极简的基于智能手机识别抑郁症状的系统：可解释机器学习方法

Exploring the impact of socioeconomic and natural factors on pulmonary tuberculosis incidence in China (2013-2019) using explainable machine learning: A nationwide study

利用可解释机器学习探索2013-2019年中国结核病发病的社会经济和自然因素影响：一项全国性研究

Elucidating Key Characteristics of PFAS Binding to Human Peroxisome Proliferator-Activated Receptor Alpha: An Explainable Machine Learning Approach

揭示PFAS与人过氧化物酶体增殖物激活受体α结合的关键特性：一种可解释的机器学习方法

A novel method for detection of pancreatic Ductal Adenocarcinoma using explainable machine learning

利用可解释机器学习检测胰管腺癌的新方法

Using explainable machine learning to uncover the kinase-substrate interaction landscape

使用可解释机器学习揭示激酶-底物相互作用图谱

Toward Better Risk Stratification for Implantable Cardioverter-Defibrillator Recipients: Implications of Explainable Machine Learning Models

迈向植入式心脏除颤器接受者的更好的风险分层：可解释的机器学习模型的意义

Explainable machine learning for diffraction patterns

用于衍射图案的可解释机器学习

Validation and interpretation of a multimodal drowsiness detection system using explainable machine learning

基于可解释机器学习的多模态驾驶员疲劳检测系统的验证与分析研究

Integrating explainable machine learning and transcriptomics data reveals cell-type specific immune signatures underlying macular degeneration

可解释机器学习与转录组数据的整合揭示年龄相关黄斑变性背后细胞特异性免疫特征 翻译改进

Using Explainable Machine Learning to Improve Intensive Care Unit Alarm Systems

使用可解释机器学习来改进重症监护室报警系统

A Fast and Minimal System to Identify Depression Using Smartphones: Explainable Machine Learning-Based Approach

一种快速且极简的基于智能手机识别抑郁症状的系统：可解释机器学习方法

Exploring the impact of socioeconomic and natural factors on pulmonary tuberculosis incidence in China (2013-2019) using explainable machine learning: A nationwide study

利用可解释机器学习探索2013-2019年中国结核病发病的社会经济和自然因素影响：一项全国性研究

Elucidating Key Characteristics of PFAS Binding to Human Peroxisome Proliferator-Activated Receptor Alpha: An Explainable Machine Learning Approach

揭示PFAS与人过氧化物酶体增殖物激活受体α结合的关键特性：一种可解释的机器学习方法

A novel method for detection of pancreatic Ductal Adenocarcinoma using explainable machine learning

利用可解释机器学习检测胰管腺癌的新方法

Using explainable machine learning to uncover the kinase-substrate interaction landscape

使用可解释机器学习揭示激酶-底物相互作用图谱

Toward Better Risk Stratification for Implantable Cardioverter-Defibrillator Recipients: Implications of Explainable Machine Learning Models

迈向植入式心脏除颤器接受者的更好的风险分层：可解释的机器学习模型的意义

Explainable machine learning for diffraction patterns

用于衍射图案的可解释机器学习

Validation and interpretation of a multimodal drowsiness detection system using explainable machine learning

基于可解释机器学习的多模态驾驶员疲劳检测系统的验证与分析研究

可解释机器学习与转录组数据的整合揭示年龄相关黄斑变性背后细胞特异性免疫特征翻译改进