High–throughput measurement of plant fitness traits with an object detection method using Faster R–CNN

Wang, Peipei; Meng, Fanrui; Donaldson, Paityn; Horan, Sarah; Panchy, Nicholas L.; Vischulis, Elyse; Winship, Eamon; Conner, Jeffrey K.; Krysan, Patrick J.; Shiu, Shin‐Han; Lehti‐Shiu, Melissa D.

doi:10.1111/nph.18056

Title: High–throughput measurement of plant fitness traits with an object detection method using Faster R–CNN

Journal Article · 24 February 2022 · New Phytologist

DOI: https://doi.org/10.1111/nph.18056 · OSTI ID:1876374

^[1];

^[2]; Donaldson, Paityn ^[2]; Horan, Sarah ^[2];

^[3]; Vischulis, Elyse ^[2];

^[2];

^[4];

^[5];

^[2];

^[2]

Michigan State Univ., East Lansing, MI (United States); Michigan State University Department of Plant Biology
Michigan State Univ., East Lansing, MI (United States)
Univ. of Tennessee, Knoxville, TN (United States)
Michigan State Univ., East Lansing, MI (United States); Michigan State Univ., Hickory Corners, MI (United States)
Univ. of Wisconsin, Madison, WI (United States)

Revealing the contributions of genes to plant phenotype is frequently challenging because loss-of-function effects may be subtle or masked by varying degrees of genetic redundancy. Such effects can potentially be detected by measuring plant fitness, which reflects the cumulative effects of genetic changes over the lifetime of a plant. However, fitness is challenging to measure accurately, particularly in species with high fecundity and relatively small propagule sizes such as Arabidopsis thaliana. An image segmentation-based method using the software ImageJ and an object detection-based method using the Faster Region-based Convolutional Neural Network (R-CNN) algorithm were used for measuring two Arabidopsis fitness traits: seed and fruit counts. The segmentation-based method was error-prone (correlation between true and predicted seed counts, r² = 0.849) because seeds touching each other were undercounted. By contrast, the object detection-based algorithm yielded near perfect seed counts (r² = 0.9996) and highly accurate fruit counts (r² = 0.980). Comparing seed counts for wild-type and 12 mutant lines revealed fitness effects for three genes; fruit counts revealed the same effects for two genes. Our study provides analysis pipelines and models to facilitate the investigation of Arabidopsis fitness traits and demonstrates the importance of examining fitness traits when studying gene functions.

View Accepted Manuscript (DOE)

Cite

Export

Save

Research Organization:: Michigan State Univ., East Lansing, MI (United States). Great Lakes Bioenergy Research Center

Sponsoring Organization:: USDOE Office of Science (SC), Biological and Environmental Research (BER)

Grant/Contract Number:: SC0018409

OSTI ID:: 1876374

Journal Information:: New Phytologist, Journal Name: New Phytologist Journal Issue: 4 Vol. 234; ISSN 0028-646X

Publisher:: WileyCopyright Statement

Country of Publication:: United States

Language:: English

References (41)

Arabidopsis gene knockout: phenotypes wanted Bouché, N. Current Opinion in Plant Biology, Vol. 4, Issue 2 https://doi.org/10.1016/S1369-5266(00)00145-X	journal	April 2001
Separase Promotes Microtubule Polymerization by Activating CENP-E-Related Kinesin Kin7 Moschou, Panagiotis N.; Gutierrez-Beltran, Emilio; Bozhkov, Peter V. Developmental Cell, Vol. 37, Issue 4 https://doi.org/10.1016/j.devcel.2016.04.015	journal	May 2016
NIH Image to ImageJ: 25 years of image analysis Schneider, Caroline A.; Rasband, Wayne S.; Eliceiri, Kevin W. Nature Methods, Vol. 9, Issue 7 https://doi.org/10.1038/nmeth.2089	journal	June 2012
Training instance segmentation neural network with synthetic datasets for crop seed phenotyping Toda, Yosuke; Okura, Fumio; Ito, Jun Communications Biology, Vol. 3, Issue 1 https://doi.org/10.1038/s42003-020-0905-5	journal	April 2020
The effect of cold priming on the fitness of Arabidopsis thaliana accessions under natural and controlled conditions Cvetkovic, Jelena; Müller, Klaus; Baier, Margarete Scientific Reports, Vol. 7, Issue 1 https://doi.org/10.1038/srep44055	journal	March 2017
Measurements of selection on floral traits in black mustard, Brassica nigra Conner, J. K.; Rush, S. Journal of Evolutionary Biology, Vol. 10, Issue 3 https://doi.org/10.1046/j.1420-9101.1997.10030327.x	journal	May 1997
Control of seed size in plants Sundaresan, Venkatesan Proceedings of the National Academy of Sciences, Vol. 102, Issue 50 https://doi.org/10.1073/pnas.0509021102	journal	December 2005
Large-effect flowering time mutations reveal conditionally adaptive paths through fitness landscapes in Arabidopsis thaliana Taylor, Mark A.; Wilczek, Amity M.; Roe, Judith L. Proceedings of the National Academy of Sciences, Vol. 116, Issue 36 https://doi.org/10.1073/pnas.1902731116	journal	August 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
Computer vision-based phenotyping for improvement of plant productivity: a machine learning perspective Mochida, Keiichi; Koda, Satoru; Inoue, Komaki GigaScience, Vol. 8, Issue 1 https://doi.org/10.1093/gigascience/giy153	journal	December 2018
SmartGrain : High-Throughput Phenotyping Software for Measuring Seed Shape through Image Analysis Tanabata, Takanari; Shibaya, Taeko; Hori, Kiyosumi Plant Physiology, Vol. 160, Issue 4 https://doi.org/10.1104/pp.112.205120	journal	October 2012
Alterations in Seed Development Gene Expression Affect Size and Oil Content of Arabidopsis Seeds Fatihi, Abdelhak; Zbierzak, Anna Maria; Dörmann, Peter Plant Physiology, Vol. 163, Issue 2 https://doi.org/10.1104/pp.113.226761	journal	September 2013
Salinity Is an Agent of Divergent Selection Driving Local Adaptation of Arabidopsis to Coastal Habitats Busoms, Silvia; Teres, Joana; Huang, Xin-Yuan Plant Physiology, Vol. 168, Issue 3 https://doi.org/10.1104/pp.15.00427	journal	June 2015
Phylogeny-Based Systematization of Arabidopsis Proteins with Histone H1 Globular Domain Kotliński, Maciej; Knizewski, Lukasz; Muszewska, Anna Plant Physiology, Vol. 174, Issue 1 https://doi.org/10.1104/pp.16.00214	journal	March 2017
pheno Seeder - A Robot System for Automated Handling and Phenotyping of Individual Seeds Jahnke, Siegfried; Roussel, Johanna; Hombach, Thomas Plant Physiology, Vol. 172, Issue 3 https://doi.org/10.1104/pp.16.01122	journal	September 2016
The Linker Histone GH1-HMGA1 Is Involved in Telomere Stability and DNA Damage Repair Charbonnel, Cyril; Rymarenko, Oleh; Da Ines, Olivier Plant Physiology, Vol. 177, Issue 1 https://doi.org/10.1104/pp.17.01789	journal	April 2018
Function Search in a Large Transcription Factor Gene Family in Arabidopsis: Assessing the Potential of Reverse Genetics to Identify Insertional Mutations in R2R3 MYB Genes Meissner, Ruth C.; Jin, Hailing; Cominelli, Eleonora The Plant Cell, Vol. 11, Issue 10 https://doi.org/10.1105/tpc.11.10.1827	journal	October 1999
Growth Stage-Based Phenotypic Analysis of Arabidopsis: A Model for High Throughput Functional Genomics in Plants Boyes, D. C. THE PLANT CELL ONLINE, Vol. 13, Issue 7 https://doi.org/10.1105/tpc.13.7.1499	journal	July 2001
An Improved Faster R-CNN for Small Object Detection Cao, Changqing; Wang, Bo; Zhang, Wenrui IEEE Access, Vol. 7 https://doi.org/10.1109/ACCESS.2019.2932731	journal	January 2019
Speed/Accuracy Trade-Offs for Modern Convolutional Object Detectors Huang, Jonathan; Rathod, Vivek; Sun, Chen 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) https://doi.org/10.1109/CVPR.2017.351	conference	July 2017
Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks Ren, Shaoqing; He, Kaiming; Girshick, Ross IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 39, Issue 6 https://doi.org/10.1109/TPAMI.2016.2577031	journal	June 2017
Measuring selection when parents and offspring interact Thomson, Caroline E.; Hadfield, Jarrod D. Methods in Ecology and Evolution, Vol. 8, Issue 6 https://doi.org/10.1111/2041-210X.12795	journal	November 2016
A dual‐targeted purple acid phosphatase in Arabidopsis thaliana moderates carbon metabolism and its overexpression leads to faster plant growth and higher seed yield Sun, Feng; Suen, Pui Kit; Zhang, Youjun New Phytologist, Vol. 194, Issue 1 https://doi.org/10.1111/j.1469-8137.2011.04026.x	journal	January 2012
Experimental Manipulation of Putative Selective Agents Provides Evidence for the role of Natural Enemies in the Evolution of Plant Defense Mauricio, Rodney; Rausher, Mark D. Evolution, Vol. 51, Issue 5 https://doi.org/10.1111/j.1558-5646.1997.tb01467.x	journal	October 1997
Fitness effects of mutation: testing genetic redundancy in Arabidopsis thaliana Rutter, M. T.; Wieckowski, Y. M.; Murren, C. J. Journal of Evolutionary Biology, Vol. 30, Issue 6 https://doi.org/10.1111/jeb.13081	journal	May 2017
Chromatin architectural proteins regulate flowering time by precluding gene looping Zhao, Bo; Xi, Yanpeng; Kim, Junghyun Science Advances, Vol. 7, Issue 24 https://doi.org/10.1126/sciadv.abg3097	journal	June 2021
A Role for the AKT1 Potassium Channel in Plant Nutrition Hirsch, R. E. Science, Vol. 280, Issue 5365 https://doi.org/10.1126/science.280.5365.918	journal	May 1998
The Molecular Basis of Adaptation: A Critical Review of Relevant Ideas and Observations McDonald, J. F. Annual Review of Ecology and Systematics, Vol. 14, Issue 1 https://doi.org/10.1146/annurev.es.14.110183.000453	journal	November 1983
Updated Methods for Seed Shape Analysis Cervantes, Emilio; Martín, José Javier; Saadaoui, Ezzeddine Scientifica, Vol. 2016 https://doi.org/10.1155/2016/5691825	journal	January 2016
Rapid analysis of seed size in Arabidopsis for mutant and QTL discovery Herridge, Rowan P.; Day, Robert C.; Baldwin, Samantha Plant Methods, Vol. 7, Issue 1 https://doi.org/10.1186/1746-4811-7-3	journal	January 2011
Image-based methods for phenotyping growth dynamics and fitness components in Arabidopsis thaliana Vasseur, François; Bresson, Justine; Wang, George Plant Methods, Vol. 14, Issue 1 https://doi.org/10.1186/s13007-018-0331-6	journal	July 2018
Detection and analysis of wheat spikes using Convolutional Neural Networks Hasan, Md Mehedi; Chopin, Joshua P.; Laga, Hamid Plant Methods, Vol. 14, Issue 1 https://doi.org/10.1186/s13007-018-0366-8	journal	November 2018
A high throughput method for quantifying number and size distribution of Arabidopsis seeds using large particle flow cytometry Morales, Alejandro; Teapal, J.; Ammerlaan, J. M. H. Plant Methods, Vol. 16, Issue 1 https://doi.org/10.1186/s13007-020-00572-x	journal	March 2020
The BELT and phenoSEED platforms: shape and colour phenotyping of seed samples Halcro, Keith; McNabb, Kaitlin; Lockinger, Ashley Plant Methods, Vol. 16, Issue 1 https://doi.org/10.1186/s13007-020-00591-8	journal	April 2020
A survey on Image Data Augmentation for Deep Learning Shorten, Connor; Khoshgoftaar, Taghi M. Journal of Big Data, Vol. 6, Issue 1 https://doi.org/10.1186/s40537-019-0197-0	journal	July 2019
High-Throughput Computer Vision Introduces the Time Axis to a Quantitative Trait Map of a Plant Growth Response Moore, Candace R.; Johnson, Logan S.; Kwak, Il-Youp Genetics, Vol. 195, Issue 3 https://doi.org/10.1534/genetics.113.153346	journal	August 2013
The Genetic Basis of Natural Variation in Seed Size and Seed Number and Their Trade-Off Using Arabidopsis thaliana MAGIC Lines Gnan, Sebastian; Priest, Anne; Kover, Paula X. Genetics, Vol. 198, Issue 4 https://doi.org/10.1534/genetics.114.170746	journal	October 2014
The Dominance of the Herbicide Resistance Cost in Several Arabidopsis thaliana Mutant Lines Roux, Fabrice; Gasquez, Jacques; Reboud, Xavier Genetics, Vol. 166, Issue 1 https://doi.org/10.1534/genetics.166.1.449	journal	January 2004
Lettuce (Lactuca sativa L.) seed quality evaluation using seed physical attributes, saturated salt accelerated aging and the seed vigour imaging system Penaloza, Patricia; Ramirez-Rosales, Gerardo; B. McDonald, Miller Electronic Journal of Biotechnology, Vol. 8, Issue 3 https://doi.org/10.2225/vol8-issue3-fulltext-11	journal	December 2005
Tomato Fruit Detection and Counting in Greenhouses Using Deep Learning Afonso, Manya; Fonteijn, Hubert; Fiorentin, Felipe Schadeck Frontiers in Plant Science, Vol. 11 https://doi.org/10.3389/fpls.2020.571299	journal	November 2020
Natural genetic variation in Arabidopsis thaliana defense metabolism genes modulates field fitness Kerwin, Rachel; Feusier, Julie; Corwin, Jason eLife, Vol. 4 https://doi.org/10.7554/eLife.05604	journal	April 2015

Similar Records

MYC transcription factors coordinate tryptophan–dependent defence responses and compromise seed yield in Arabidopsis

Journal Article · 2022 · New Phytologist · OSTI ID:1902048

Guo, Qiang; Major, Ian T.; Kapali, George; +1 more

Ecological trade-offs drive phenotypic and genetic differentiation of Arabidopsis thaliana in Europe

Journal Article · 2024 · Nature Communications · OSTI ID:2471815

Bastias, Cristina C.; Estarague, Aurélien; Vile, Denis; +5 more

Age-specific patterns of genetic variance in Drosophila melanogaster. II. Fecundity and its genetic covariance with age-specific mortality

Journal Article · 1996 · Genetics · OSTI ID:543023

Tatar, M; Promislow, D E.L.; Khazaeli, A A; +1 more

Related Subjects

59 BASIC BIOLOGICAL SCIENCES
Arabidopsis
deep learning
fitness traits
machine vision
object detection
segmentation

Title: High–throughput measurement of plant fitness traits with an object detection method using Faster R–CNN

Citation Formats

References (41)

Similar Records

Related Subjects