Deep Learning-Based Morphological Classification of Endoplasmic Reticulum Under Stress

被引:9
作者
Guo, Yuanhao [1 ,2 ]
Shen, Di [3 ]
Zhou, Yanfeng [1 ,2 ]
Yang, Yutong [1 ]
Liang, Jinzhao [1 ]
Zhou, Yating [1 ,2 ]
Li, Ningning [4 ]
Liu, Yu [3 ]
Yang, Ge [1 ,2 ]
Li, Wenjing [1 ,2 ]
机构
[1] Chinese Acad Sci, Inst Automat, Lab Computat Biol & Machine Intelligence, Natl Lab Pattern Recognit, Beijing, Peoples R China
[2] Univ Chinese Acad Sci, Sch Artificial Intelligence, Beijing, Peoples R China
[3] Chinese Acad Sci, Dalian Inst Chem Phys, CAS Key Lab Separat Sci Analyt Chem, Dalian, Peoples R China
[4] Sun Yat Sen Univ, Affiliated Hosp 7, Tomas Lindahl Lab, Shenzhen, Peoples R China
来源
FRONTIERS IN CELL AND DEVELOPMENTAL BIOLOGY | 2022年 / 9卷
关键词
ER stress; morphological classification; image biomarker; deep learning; homeostasis; UNFOLDED PROTEIN RESPONSE; MODULATES ER STRESS; MICROSCOPY IMAGES; IRE1-ALPHA; AUTOPHAGY; TRANSLATION; COMBINATION; EXPRESSION; DISCOVERY; APOPTOSIS;
D O I
10.3389/fcell.2021.767866
中图分类号
Q2 [细胞生物学];
学科分类号
071009 ; 090102 ;
摘要
Endoplasmic reticulum stress (ER stress) is a condition that is defined by abnormal accumulation of unfolded proteins. It plays an important role in maintaining cellular protein, lipid, and ion homeostasis. By triggering the unfolded protein response (UPR) under ER stress, cells restore homeostasis or undergo apoptosis. Chronic ER stress is implicated in many human diseases. Despite extensive studies on related signaling mechanisms, reliable image biomarkers for ER stress remain lacking. To address this deficiency, we have validated a morphological image biomarker for ER stress and have developed a deep learning-based assay to enable automated detection and analysis of this marker for screening studies. Specifically, ER under stress exhibits abnormal morphological patterns that feature ring-shaped structures called whorls (WHs). Using a highly specific chemical probe for unfolded and aggregated proteins, we find that formation of ER whorls is specifically associated with the accumulation of the unfolded and aggregated proteins. This confirms that ER whorls can be used as an image biomarker for ER stress. To this end, we have developed ER-WHs-Analyzer, a deep learning-based image analysis assay that automatically recognizes and localizes ER whorls similarly as human experts. It does not require laborious manual annotation of ER whorls for training of deep learning models. Importantly, it reliably classifies different patterns of ER whorls induced by different ER stress drugs. Overall, our study provides mechanistic insights into morphological patterns of ER under stress as well as an image biomarker assay for screening studies to dissect related disease mechanisms and to accelerate related drug discoveries. It demonstrates the effectiveness of deep learning in recognizing and understanding complex morphological phenotypes of ER.
引用
收藏
页数:13
相关论文
共 55 条
[1]   Discovery of 7-Methyl-5-(1-{[3-(trifluoromethyl)phenyl]acetyl}-2,3-dihydro-1H-indol-5-yl)-7H-pyrrolo[2,3-d]pyrimidin-4-amine (GSK2606414), a Potent and Selective First-in-Class Inhibitor of Protein Kinase R (PKR)-like Endoplasmic Reticulum Kinase (PERK) [J].
Axten, Jeffrey M. ;
Medina, Jesus R. ;
Feng, Yanhong ;
Shu, Arthur ;
Romeril, Stuart P. ;
Grant, Seth W. ;
Li, William Hoi Hong ;
Heerding, Dirk A. ;
Minthorn, Elisabeth ;
Mencken, Thomas ;
Atkins, Charity ;
Liu, Qi ;
Rabindran, Sridhar ;
Kumar, Rakesh ;
Hong, Xuan ;
Goetz, Aaron ;
Stanley, Thomas ;
Taylor, J. David ;
Sigethy, Scott D. ;
Tomberlin, Ginger H. ;
Hassell, Annie M. ;
Kahler, Kirsten M. ;
Shewchuk, Lisa M. ;
Gampe, Robert T. .
JOURNAL OF MEDICINAL CHEMISTRY, 2012, 55 (16) :7193-7207
[2]   VCP inhibitors induce endoplasmic reticulum stress, cause cell cycle arrest, trigger caspase-mediated cell death and synergistically kill ovarian cancer cells in combination with Salubrinal [J].
Bastola, Prabhakar ;
Neums, Lisa ;
Schoenen, Frank J. ;
Chien, Jeremy .
MOLECULAR ONCOLOGY, 2016, 10 (10) :1559-1574
[3]   Autophagy counterbalances endoplasmic reticulum expansion during the unfolded protein response [J].
Bernales, Sebastian ;
McDonald, Kent L. ;
Walter, Peter .
PLOS BIOLOGY, 2006, 4 (12) :2311-2324
[4]   Protein Folding and Modification in the Mammalian Endoplasmic Reticulum [J].
Braakman, Ineke ;
Bulleid, Neil J. .
ANNUAL REVIEW OF BIOCHEMISTRY, VOL 80, 2011, 80 :71-99
[5]   Both thapsicorain- and tunicamucin-induced endoplasmic reticulum stress increases expression of Hrd1 in IRE1-dependent fashion [J].
Dibdiakova, Katarina ;
Saksonova, Simona ;
Pilchova, Ivana ;
Klacanova, Katarina ;
Tatarkova, Zuzana ;
Racay, Peter .
NEUROLOGICAL RESEARCH, 2019, 41 (02) :177-188
[6]   The ER in 3D: a multifunctional dynamic membrane network [J].
Friedman, Jonathan R. ;
Voeltz, Gia K. .
TRENDS IN CELL BIOLOGY, 2011, 21 (12) :709-717
[7]   A novel specific PERK activator reduces toxicity and extends survival in Huntington's disease models [J].
Ganz, Javier ;
Shacham, Talya ;
Kramer, Maria ;
Shenkman, Marina ;
Eiger, Hagit ;
Weinberg, Nitai ;
Iancovici, Ori ;
Roy, Somnath ;
Simhaev, Luba ;
Da'adoosh, Benny ;
Engel, Hamutal ;
Perets, Nisim ;
Barhum, Yael ;
Portnoy, Moshe ;
Offen, Daniel ;
Lederkremer, Gerardo Z. .
SCIENTIFIC REPORTS, 2020, 10 (01)
[8]   Allosteric Inhibition of the IRE1α RNase Preserves Cell Viability and Function during Endoplasmic Reticulum Stress [J].
Ghosh, Rajarshi ;
Wang, Likun ;
Wang, Eric S. ;
Perera, B. Gayani K. ;
Igbaria, Aeid ;
Morita, Shuhei ;
Prado, Kris ;
Thamsen, Maike ;
Caswell, Deborah ;
Macias, Hector ;
Weiberth, Kurt F. ;
Gliedt, Micah J. ;
Alavi, Marcel V. ;
Hari, Sanjay B. ;
Mitra, Arinjay K. ;
Bhhatarai, Barun ;
Schuerer, Stephan C. ;
Snapp, Erik L. ;
Gould, Douglas B. ;
German, Michael S. ;
Backes, Bradley J. ;
Maly, Dustin J. ;
Oakes, Scott A. ;
Papa, Feroz R. .
CELL, 2014, 158 (03) :534-548
[9]   A multi-scale convolutional neural network for phenotyping high-content cellular images [J].
Godinez, William J. ;
Hossain, Imtiaz ;
Lazic, Stanley E. ;
Davies, John W. ;
Zhang, Xian .
BIOINFORMATICS, 2017, 33 (13) :2010-2019
[10]   IRE1α Kinase Activation Modes Control Alternate Endoribonuclease Outputs to Determine Divergent Cell Fates [J].
Han, Dan ;
Lerner, Alana G. ;
Vande Walle, Lieselotte ;
Upton, John-Paul ;
Xu, Weihong ;
Hagen, Andrew ;
Backes, Bradley J. ;
Oakes, Scott A. ;
Papa, Feroz R. .
CELL, 2009, 138 (03) :562-575