基于图谱的超解析蛋白质-蛋白质相互作用空间邻近性预测单细胞中的抗癌药物反应

IF 2.3 4区 医学 Q3 BIOPHYSICS Cellular and molecular bioengineering Pub Date : 2024-10-06 eCollection Date: 2024-10-01 DOI:10.1007/s12195-024-00822-1
Nicholas Zhang, Shuangyi Cai, Mingshuang Wang, Thomas Hu, Frank Schneider, Shi-Yong Sun, Ahmet F Coskun
{"title":"基于图谱的超解析蛋白质-蛋白质相互作用空间邻近性预测单细胞中的抗癌药物反应","authors":"Nicholas Zhang, Shuangyi Cai, Mingshuang Wang, Thomas Hu, Frank Schneider, Shi-Yong Sun, Ahmet F Coskun","doi":"10.1007/s12195-024-00822-1","DOIUrl":null,"url":null,"abstract":"<p><strong>Purpose: </strong>Current bulk molecular assays fail to capture spatial signaling activities in cancers, limiting our understanding of drug resistance mechanisms. We developed a graph-based super-resolution protein-protein interaction (GSR-PPI) technique to spatially resolve single-cell signaling networks and evaluate whether higher resolution microscopy enhances the biological study of PPIs using deep learning classification models.</p><p><strong>Methods: </strong>Single-cell spatial proximity ligation assays (PLA, ≤ 9 PPI pairs) were conducted on EGFR mutant (EGFRm) PC9 and HCC827 cells (>10,000 cells) treated with 100 nM Osimertinib. Multiplexed PPI images were obtained using wide-field and super-resolution microscopy (Zeiss Airyscan, SRRF). Graph-based deep learning models analyzed subcellular protein interactions to classify drug treatment states and test GSR-PPI on clinical tissue samples. GSR-PPI triangulated PPI nodes into 3D relationships, predicting drug treatment labels. Biological discriminative ability (BDA) was evaluated using accuracy, AUC, and F1 scores. The method was also applied to 3D spatial proteomic molecular pixelation (PixelGen) data from T cells.</p><p><strong>Results: </strong>GSR-PPI outperformed baseline models in predicting drug responses from multiplexed PPI imaging in EGFRm cells. Super-resolution data significantly improved accuracy over localized wide-field imaging. GSR-PPI classified drug treatment states in cancer cells and human lung tissues, with performance improving as imaging resolution increased. It differentiated single and combination drug therapies in HCC827 cells and human tissues. Additionally, GSR-PPI accurately distinguished T-cell stimulation states, identifying key nodes such as CD44, CD45, and CD54.</p><p><strong>Conclusion: </strong>The GSR-PPI framework provides valuable insights into spatial protein interactions and drug responses, enhancing the study of signaling biology and drug resistance.</p><p><strong>Supplementary information: </strong>The online version contains supplementary material available at 10.1007/s12195-024-00822-1.</p>","PeriodicalId":9687,"journal":{"name":"Cellular and molecular bioengineering","volume":"17 5","pages":"467-490"},"PeriodicalIF":2.3000,"publicationDate":"2024-10-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11538221/pdf/","citationCount":"0","resultStr":"{\"title\":\"Graph-Based Spatial Proximity of Super-Resolved Protein-Protein Interactions Predicts Cancer Drug Responses in Single Cells.\",\"authors\":\"Nicholas Zhang, Shuangyi Cai, Mingshuang Wang, Thomas Hu, Frank Schneider, Shi-Yong Sun, Ahmet F Coskun\",\"doi\":\"10.1007/s12195-024-00822-1\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<p><strong>Purpose: </strong>Current bulk molecular assays fail to capture spatial signaling activities in cancers, limiting our understanding of drug resistance mechanisms. We developed a graph-based super-resolution protein-protein interaction (GSR-PPI) technique to spatially resolve single-cell signaling networks and evaluate whether higher resolution microscopy enhances the biological study of PPIs using deep learning classification models.</p><p><strong>Methods: </strong>Single-cell spatial proximity ligation assays (PLA, ≤ 9 PPI pairs) were conducted on EGFR mutant (EGFRm) PC9 and HCC827 cells (>10,000 cells) treated with 100 nM Osimertinib. Multiplexed PPI images were obtained using wide-field and super-resolution microscopy (Zeiss Airyscan, SRRF). Graph-based deep learning models analyzed subcellular protein interactions to classify drug treatment states and test GSR-PPI on clinical tissue samples. GSR-PPI triangulated PPI nodes into 3D relationships, predicting drug treatment labels. Biological discriminative ability (BDA) was evaluated using accuracy, AUC, and F1 scores. The method was also applied to 3D spatial proteomic molecular pixelation (PixelGen) data from T cells.</p><p><strong>Results: </strong>GSR-PPI outperformed baseline models in predicting drug responses from multiplexed PPI imaging in EGFRm cells. Super-resolution data significantly improved accuracy over localized wide-field imaging. GSR-PPI classified drug treatment states in cancer cells and human lung tissues, with performance improving as imaging resolution increased. It differentiated single and combination drug therapies in HCC827 cells and human tissues. Additionally, GSR-PPI accurately distinguished T-cell stimulation states, identifying key nodes such as CD44, CD45, and CD54.</p><p><strong>Conclusion: </strong>The GSR-PPI framework provides valuable insights into spatial protein interactions and drug responses, enhancing the study of signaling biology and drug resistance.</p><p><strong>Supplementary information: </strong>The online version contains supplementary material available at 10.1007/s12195-024-00822-1.</p>\",\"PeriodicalId\":9687,\"journal\":{\"name\":\"Cellular and molecular bioengineering\",\"volume\":\"17 5\",\"pages\":\"467-490\"},\"PeriodicalIF\":2.3000,\"publicationDate\":\"2024-10-06\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11538221/pdf/\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Cellular and molecular bioengineering\",\"FirstCategoryId\":\"5\",\"ListUrlMain\":\"https://doi.org/10.1007/s12195-024-00822-1\",\"RegionNum\":4,\"RegionCategory\":\"医学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"2024/10/1 0:00:00\",\"PubModel\":\"eCollection\",\"JCR\":\"Q3\",\"JCRName\":\"BIOPHYSICS\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Cellular and molecular bioengineering","FirstCategoryId":"5","ListUrlMain":"https://doi.org/10.1007/s12195-024-00822-1","RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"2024/10/1 0:00:00","PubModel":"eCollection","JCR":"Q3","JCRName":"BIOPHYSICS","Score":null,"Total":0}
引用次数: 0

摘要

目的:目前的大量分子检测无法捕捉癌症中的空间信号活动,限制了我们对耐药机制的了解。我们开发了一种基于图的超分辨率蛋白质-蛋白质相互作用(GSR-PPI)技术,从空间上解析单细胞信号转导网络,并利用深度学习分类模型评估更高分辨率的显微镜是否能加强PPIs的生物学研究:用100 nM Osimertinib处理表皮生长因子受体突变体(EGFRm)PC9和HCC827细胞(大于10,000个细胞),进行单细胞空间邻近连接试验(PLA,≤9个PPI对)。使用宽视场和超分辨率显微镜(Zeiss Airyscan、SRRF)获得了多重 PPI 图像。基于图的深度学习模型分析了亚细胞蛋白质相互作用,以对药物治疗状态进行分类,并在临床组织样本上测试 GSR-PPI。GSR-PPI 将 PPI 节点三角化为三维关系,预测药物治疗标签。使用准确率、AUC 和 F1 分数评估了生物鉴别能力(BDA)。该方法还应用于T细胞的三维空间蛋白质组分子像素化(PixelGen)数据:结果:GSR-PPI 在预测表皮生长因子受体(EGFRm)细胞中多重 PPI 成像的药物反应方面优于基线模型。超分辨率数据大大提高了局部宽视野成像的准确性。GSR-PPI 对癌细胞和人体肺组织中的药物治疗状态进行了分类,其性能随着成像分辨率的提高而提高。它能区分 HCC827 细胞和人体组织中的单一药物疗法和联合药物疗法。此外,GSR-PPI 还能准确区分 T 细胞刺激状态,识别 CD44、CD45 和 CD54 等关键节点:GSR-PPI框架为空间蛋白质相互作用和药物反应提供了宝贵的见解,加强了信号生物学和耐药性的研究:在线版本包含补充材料,可查阅 10.1007/s12195-024-00822-1。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
查看原文
分享 分享
微信好友 朋友圈 QQ好友 复制链接
本刊更多论文
Graph-Based Spatial Proximity of Super-Resolved Protein-Protein Interactions Predicts Cancer Drug Responses in Single Cells.

Purpose: Current bulk molecular assays fail to capture spatial signaling activities in cancers, limiting our understanding of drug resistance mechanisms. We developed a graph-based super-resolution protein-protein interaction (GSR-PPI) technique to spatially resolve single-cell signaling networks and evaluate whether higher resolution microscopy enhances the biological study of PPIs using deep learning classification models.

Methods: Single-cell spatial proximity ligation assays (PLA, ≤ 9 PPI pairs) were conducted on EGFR mutant (EGFRm) PC9 and HCC827 cells (>10,000 cells) treated with 100 nM Osimertinib. Multiplexed PPI images were obtained using wide-field and super-resolution microscopy (Zeiss Airyscan, SRRF). Graph-based deep learning models analyzed subcellular protein interactions to classify drug treatment states and test GSR-PPI on clinical tissue samples. GSR-PPI triangulated PPI nodes into 3D relationships, predicting drug treatment labels. Biological discriminative ability (BDA) was evaluated using accuracy, AUC, and F1 scores. The method was also applied to 3D spatial proteomic molecular pixelation (PixelGen) data from T cells.

Results: GSR-PPI outperformed baseline models in predicting drug responses from multiplexed PPI imaging in EGFRm cells. Super-resolution data significantly improved accuracy over localized wide-field imaging. GSR-PPI classified drug treatment states in cancer cells and human lung tissues, with performance improving as imaging resolution increased. It differentiated single and combination drug therapies in HCC827 cells and human tissues. Additionally, GSR-PPI accurately distinguished T-cell stimulation states, identifying key nodes such as CD44, CD45, and CD54.

Conclusion: The GSR-PPI framework provides valuable insights into spatial protein interactions and drug responses, enhancing the study of signaling biology and drug resistance.

Supplementary information: The online version contains supplementary material available at 10.1007/s12195-024-00822-1.

求助全文
通过发布文献求助,成功后即可免费获取论文全文。 去求助
来源期刊
CiteScore
5.60
自引率
3.60%
发文量
30
审稿时长
>12 weeks
期刊介绍: The field of cellular and molecular bioengineering seeks to understand, so that we may ultimately control, the mechanical, chemical, and electrical processes of the cell. A key challenge in improving human health is to understand how cellular behavior arises from molecular-level interactions. CMBE, an official journal of the Biomedical Engineering Society, publishes original research and review papers in the following seven general areas: Molecular: DNA-protein/RNA-protein interactions, protein folding and function, protein-protein and receptor-ligand interactions, lipids, polysaccharides, molecular motors, and the biophysics of macromolecules that function as therapeutics or engineered matrices, for example. Cellular: Studies of how cells sense physicochemical events surrounding and within cells, and how cells transduce these events into biological responses. Specific cell processes of interest include cell growth, differentiation, migration, signal transduction, protein secretion and transport, gene expression and regulation, and cell-matrix interactions. Mechanobiology: The mechanical properties of cells and biomolecules, cellular/molecular force generation and adhesion, the response of cells to their mechanical microenvironment, and mechanotransduction in response to various physical forces such as fluid shear stress. Nanomedicine: The engineering of nanoparticles for advanced drug delivery and molecular imaging applications, with particular focus on the interaction of such particles with living cells. Also, the application of nanostructured materials to control the behavior of cells and biomolecules.
期刊最新文献
Remote-Controlled Gene Delivery in Coaxial 3D-Bioprinted Constructs using Ultrasound-Responsive Bioinks. The 2024 Young Innovators of Cellular and Molecular Bioengineering. Novel 3-D Macrophage Spheroid Model Reveals Reciprocal Regulation of Immunomechanical Stress and Mechano-Immunological Response. Rational Design of HER2-Targeted Combination Therapies to Reverse Drug Resistance in Fibroblast-Protected HER2+ Breast Cancer Cells. Empowering High-Throughput High-Content Analysis of Microphysiological Models: Open-Source Software for Automated Image Analysis of Microvessel Formation and Cell Invasion.
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
现在去查看 取消
×
提示
确定
0
微信
客服QQ
Book学术公众号 扫码关注我们
反馈
×
意见反馈
请填写您的意见或建议
请填写您的手机或邮箱
已复制链接
已复制链接
快去分享给好友吧!
我知道了
×
扫码分享
扫码分享
Book学术官方微信
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术
文献互助 智能选刊 最新文献 互助须知 联系我们:info@booksci.cn
Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。
Copyright © 2023 Book学术 All rights reserved.
ghs 京公网安备 11010802042870号 京ICP备2023020795号-1