DeepLearnMOR: a deep-learning framework for fluorescence image-based classification of organelle morphology

Li, Jiying; Peng, Jinghao; Jiang, Xiaotong; Rea, Anne C.; Peng, Jiajie; Hu, Jianping

doi:10.1093/plphys/kiab223

DeepLearnMOR: a deep-learning framework for fluorescence image-based classification of organelle morphology

Journal Article · Fri May 14 04:00:00 EDT 2021 · Plant Physiology (Bethesda)

DOI:https://doi.org/10.1093/plphys/kiab223· OSTI ID:1849998

^[1]; ^[2]; ^[3]; ^[3]; Peng, Jiajie ^[2]; ^[3]

Microsoft Corporation, Redmond, Washington 98052; OSTI
School of Computer Science, Northwestern Polytechnical University, Xi’an 710072, China
Department of Energy Plant Research Laboratory, Michigan State University, East Lansing, Michigan 48824

Abstract

The proper biogenesis, morphogenesis, and dynamics of subcellular organelles are essential to their metabolic functions. Conventional techniques for identifying, classifying, and quantifying abnormalities in organelle morphology are largely manual and time-consuming, and require specific expertise. Deep learning has the potential to revolutionize image-based screens by greatly improving their scope, speed, and efficiency. Here, we used transfer learning and a convolutional neural network (CNN) to analyze over 47,000 confocal microscopy images from Arabidopsis wild-type and mutant plants with abnormal division of one of three essential energy organelles: chloroplasts, mitochondria, or peroxisomes. We have built a deep-learning framework, DeepLearnMOR (Deep Learning of the Morphology of Organelles), which can rapidly classify image categories and identify abnormalities in organelle morphology with over 97% accuracy. Feature visualization analysis identified important features used by the CNN to predict morphological abnormalities, and visual clues helped to better understand the decision-making process, thereby validating the reliability and interpretability of the neural network. This framework establishes a foundation for future larger-scale research with broader scopes and greater data set diversity and heterogeneity.

Research Organization:: Michigan State Univ., East Lansing, MI (United States)

Sponsoring Organization:: USDOE Office of Science (SC)

DOE Contract Number:: FG02-91ER20021

OSTI ID:: 1849998

Journal Information:: Plant Physiology (Bethesda), Journal Name: Plant Physiology (Bethesda) Journal Issue: 4 Vol. 186; ISSN 0032-0889

Publisher:: American Society of Plant Biologists

Country of Publication:: United States

Language:: English

References (41)

Deep phenotyping: deep learning for temporal phenotype/genotype classification Taghavi Namin, Sarah; Esmaeilzadeh, Mohammad; Najafi, Mohammad Plant Methods, Vol. 14, Issue 1 https://doi.org/10.1186/s13007-018-0333-4	journal	August 2018
Theoretical analysis of an alphabetic confusion matrix Townsend, J. T. Perception & Psychophysics, Vol. 9, Issue 1 https://doi.org/10.3758/BF03213026	journal	January 1971
Organization and Regulation of Mitochondrial Respiration in Plants Millar, A. Harvey; Whelan, James; Soole, Kathleen L. Annual Review of Plant Biology, Vol. 62, Issue 1 https://doi.org/10.1146/annurev-arplant-042110-103857	journal	June 2011
Arabidopsis ARC6 Coordinates the Division Machineries of the Inner and Outer Chloroplast Membranes through Interaction with PDV2 in the Intermembrane Space Glynn, Jonathan M.; Froehlich, John E.; Osteryoung, Katherine W. The Plant Cell, Vol. 20, Issue 9 https://doi.org/10.1105/tpc.108.061440	journal	September 2008
DeepPhagy: a deep learning framework for quantitatively measuring autophagy activity in Saccharomyces cerevisiae Zhang, Ying; Xie, Yubin; Liu, Wenzhong Autophagy, Vol. 16, Issue 4 https://doi.org/10.1080/15548627.2019.1632622	journal	June 2019
Plant Peroxisomes: Biogenesis and Function Hu, Jianping; Baker, Alison; Bartel, Bonnie The Plant Cell, Vol. 24, Issue 6 https://doi.org/10.1105/tpc.112.096586	journal	June 2012
How Convolutional Neural Networks Diagnose Plant Disease Toda, Yosuke; Okura, Fumio Plant Phenomics, Vol. 2019 https://doi.org/10.34133/2019/9237136	journal	March 2019
What Does It Take to Be C ₄ ? Lessons from the Evolution of C ₄ Photosynthesis: Fig. 1. Edwards, Gerald E.; Furbank, Robert T.; Hatch, Marshall D. Plant Physiology, Vol. 125, Issue 1 https://doi.org/10.1104/pp.125.1.46	journal	January 2001
The PEROXIN11 Protein Family Controls Peroxisome Proliferation in Arabidopsis Orth, Travis; Reumann, Sigrun; Zhang, Xinchun The Plant Cell, Vol. 19, Issue 1 https://doi.org/10.1105/tpc.106.045831	journal	January 2007
Two small protein families, DYNAMIN-RELATED PROTEIN3 and FISSION1, are required for peroxisome fission in Arabidopsis Zhang, Xinchun; Hu, Jianping The Plant Journal, Vol. 57, Issue 1 https://doi.org/10.1111/j.1365-313X.2008.03677.x	journal	January 2009
Classification and mutation prediction from non–small cell lung cancer histopathology images using deep learning Coudray, Nicolas; Ocampo, Paolo Santiago; Sakellaropoulos, Theodore Nature Medicine, Vol. 24, Issue 10 https://doi.org/10.1038/s41591-018-0177-5	journal	September 2018
Structural variability of plant photosystem II megacomplexes in thylakoid membranes Nosek, Lukáš; Semchonok, Dmitry; Boekema, Egbert J. The Plant Journal, Vol. 89, Issue 1 https://doi.org/10.1111/tpj.13325	journal	December 2016
Interpretable classification of Alzheimer’s disease pathologies with a convolutional neural network pipeline Tang, Ziqi; Chuang, Kangway V.; DeCarli, Charles Nature Communications, Vol. 10, Issue 1 https://doi.org/10.1038/s41467-019-10212-1	journal	May 2019
An explainable deep machine vision framework for plant stress phenotyping Ghosal, Sambuddha; Blystone, David; Singh, Asheesh K. Proceedings of the National Academy of Sciences, Vol. 115, Issue 18 https://doi.org/10.1073/pnas.1716999115	journal	April 2018
Variations in chloroplast movement and chlorophyll fluorescence among chloroplast division mutants under light stress Dutta, Siddhartha; Cruz, Jeffrey A.; Imran, Saif M. Journal of Experimental Botany, Vol. 68, Issue 13 https://doi.org/10.1093/jxb/erx203	journal	June 2017
An introduction to ROC analysis Fawcett, Tom Pattern Recognition Letters, Vol. 27, Issue 8 https://doi.org/10.1016/j.patrec.2005.10.010	journal	June 2006
Predicting non-small cell lung cancer prognosis by fully automated microscopic pathology image features Yu, Kun-Hsing; Zhang, Ce; Berry, Gerald J. Nature Communications, Vol. 7, Issue 1 https://doi.org/10.1038/ncomms12474	journal	August 2016
Identifying Medical Diagnoses and Treatable Diseases by Image-Based Deep Learning Kermany, Daniel S.; Goldbaum, Michael; Cai, Wenjia Cell, Vol. 172, Issue 5 https://doi.org/10.1016/j.cell.2018.02.010	journal	February 2018
Deep learning LeCun, Yann; Bengio, Yoshua; Hinton, Geoffrey Nature, Vol. 521, Issue 7553 https://doi.org/10.1038/nature14539	journal	May 2015
Deep learning is combined with massive-scale citizen science to improve large-scale image classification Sullivan, Devin P.; Winsnes, Casper F.; Åkesson, Lovisa Nature Biotechnology, Vol. 36, Issue 9 https://doi.org/10.1038/nbt.4225	journal	October 2018
Non-invasive, whole-plant imaging of chloroplast movement and chlorophyll fluorescence reveals photosynthetic phenotypes independent of chloroplast photorelocation defects in chloroplast division mutants Dutta, Siddhartha; Cruz, Jeffrey A.; Jiao, Yuhua The Plant Journal, Vol. 84, Issue 2 https://doi.org/10.1111/tpj.13009	journal	October 2015
High-throughput fluorescence microscopy for systems biology Pepperkok, Rainer; Ellenberg, Jan Nature Reviews Molecular Cell Biology, Vol. 7, Issue 9, p. 690-696 https://doi.org/10.1038/nrm1979	journal	July 2006
arc6, A Fertile Arabidopsis Mutant with Only Two Mesophyll Cell Chloroplasts Pyke, K. A.; Rutherford, S. M.; Robertson, E. J. Plant Physiology, Vol. 106, Issue 3 https://doi.org/10.1104/pp.106.3.1169	journal	November 1994
A primer on deep learning in genomics Zou, James; Huss, Mikael; Abid, Abubakar Nature Genetics, Vol. 51, Issue 1 https://doi.org/10.1038/s41588-018-0295-5	journal	November 2018
Stitching Organelles: Organization and Function of Specialized Membrane Contact Sites in Plants Pérez-Sancho, Jessica; Tilsner, Jens; Samuels, A. Lacey Trends in Cell Biology, Vol. 26, Issue 9 https://doi.org/10.1016/j.tcb.2016.05.007	journal	September 2016
DeepTetrad: high‐throughput image analysis of meiotic tetrads by deep learning in Arabidopsis thaliana Lim, Eun‐Cheon; Kim, Jaeil; Park, Jihye The Plant Journal, Vol. 101, Issue 2 https://doi.org/10.1111/tpj.14543	journal	October 2019
A Deep Learning-Based Approach for High-Throughput Hypocotyl Phenotyping Dobos, Orsolya; Horvath, Peter; Nagy, Ferenc Plant Physiology, Vol. 181, Issue 4 https://doi.org/10.1104/pp.19.00728	journal	October 2019
Micropilot: automation of fluorescence microscopy–based imaging for systems biology Conrad, Christian; Wünsche, Annelie; Tan, Tze Heng Nature Methods, Vol. 8, Issue 3 https://doi.org/10.1038/nmeth.1558	journal	January 2011
Using Co-Expression Analysis and Stress-Based Screens to Uncover Arabidopsis Peroxisomal Proteins Involved in Drought Response Li, Jiying; Hu, Jianping PLOS ONE, Vol. 10, Issue 9 https://doi.org/10.1371/journal.pone.0137762	journal	September 2015
Designing Network Design Spaces Radosavovic, Ilija; Kosaraju, Raj Prateek; Girshick, Ross 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) https://doi.org/10.1109/CVPR42600.2020.01044	conference	June 2020
A subcellular map of the human proteome Thul, Peter J.; Åkesson, Lovisa; Wiking, Mikaela Science, Vol. 356, Issue 6340 https://doi.org/10.1126/science.aal3321	journal	May 2017
Pheno-Deep Counter: a unified and versatile deep learning architecture for leaf counting Giuffrida, Mario Valerio; Doerner, Peter; Tsaftaris, Sotirios A. The Plant Journal, Vol. 96, Issue 4 https://doi.org/10.1111/tpj.14064	journal	September 2018
The Molecular Machinery of Chloroplast Division Chen, Cheng; MacCready, Joshua S.; Ducat, Daniel C. Plant Physiology, Vol. 176, Issue 1 https://doi.org/10.1104/pp.17.01272	journal	October 2017
Photorespiratory Metabolism: Genes, Mutants, Energetics, and Redox Signaling Foyer, Christine H.; Bloom, Arnold J.; Queval, Guillaume Annual Review of Plant Biology, Vol. 60, Issue 1 https://doi.org/10.1146/annurev.arplant.043008.091948	journal	June 2009
Deep learning of spontaneous arousal fluctuations detects early cholinergic defects across neurodevelopmental mouse models and patients Artoni, Pietro; Piffer, Arianna; Vinci, Viviana Proceedings of the National Academy of Sciences, Vol. 117, Issue 38 https://doi.org/10.1073/pnas.1820847116	journal	July 2019
Deep Learning for Plant Stress Phenotyping: Trends and Future Perspectives Singh, Asheesh Kumar; Ganapathysubramanian, Baskar; Sarkar, Soumik Trends in Plant Science, Vol. 23, Issue 10 https://doi.org/10.1016/j.tplants.2018.07.004	journal	October 2018
Development and Validation of a Deep Learning Algorithm for Detection of Diabetic Retinopathy in Retinal Fundus Photographs Gulshan, Varun; Peng, Lily; Coram, Marc JAMA, Vol. 316, Issue 22 https://doi.org/10.1001/jama.2016.17216	journal	December 2016
Mitochondrial Dynamics for Pollen Development Izumi, Masanori Plant Physiology, Vol. 180, Issue 2 https://doi.org/10.1104/pp.19.00335	journal	June 2019
Peroxisomes: versatile organelles with diverse roles in plants Pan, Ronghui; Liu, Jun; Wang, Saisai New Phytologist, Vol. 225, Issue 4 https://doi.org/10.1111/nph.16134	journal	September 2019
DeepPod: a convolutional neural network based quantification of fruit number in Arabidopsis Hamidinekoo, Azam; Garzón-Martínez, Gina A.; Ghahremani, Morteza GigaScience, Vol. 9, Issue 3 https://doi.org/10.1093/gigascience/giaa012	journal	March 2020
Plastoglobuli: Plastid Microcompartments with Integrated Functions in Metabolism, Plastid Developmental Transitions, and Environmental Adaptation van Wijk, Klaas J.; Kessler, Felix Annual Review of Plant Biology, Vol. 68, Issue 1 https://doi.org/10.1146/annurev-arplant-043015-111737	journal	April 2017

Similar Records

DeepLearnMOR: a deep-learning framework for fluorescence image-based classification of organelle morphology

Journal Article · Thu May 13 20:00:00 EDT 2021 · Plant Physiology (Bethesda) · OSTI ID:1811735

Peroxisomes: versatile organelles with diverse roles in plants

Journal Article · Thu Aug 22 20:00:00 EDT 2019 · New Phytologist · OSTI ID:1734850

Classifying Radio Galaxies with the Convolutional Neural Network

Journal Article · Thu Jun 01 00:00:00 EDT 2017 · Astrophysical Journal, Supplement Series · OSTI ID:22661117

Related Subjects

Plant Sciences

DeepLearnMOR: a deep-learning framework for fluorescence image-based classification of organelle morphology

Citation Formats

References (41)

Similar Records

Related Subjects