Unlocking the power of AI for phenotyping fruit morphology in Arabidopsis

Deep learning can revolutionise high-throughput image-based phenotyping by automating the measurement of complex traits, a task that is often la bour-intensi v e, time-consuming, and prone to human err or. Howev er, its pr ecision and adapta bility in accuratel y phenotyping organ-level tr aits, suc...

Descripción completa

Detalles Bibliográficos
Autores principales: Atkins, Kieran, Garzón Martínez, Gina A., Lloyd, Andrew, Doonan, John H., Chuan, Lu
Formato: article
Lenguaje:Inglés
Publicado: Oxford University Press 2025
Materias:
Acceso en línea:https://academic.oup.com/gigascience/article/doi/10.1093/gigascience/giae123/8010444
http://hdl.handle.net/20.500.12324/41152
https://doi.org/10.1093/gigascience/giae123
id RepoAGROSAVIA41152
record_format dspace
institution Corporación Colombiana de Investigación Agropecuaria
collection Repositorio AGROSAVIA
language Inglés
topic plant phenotyping
Arabidopsis
fruit morphology
instance segmentation
deep learning
QTL analysis
MAGIC population
Arabidopsi
Inteligencia artificial
Morfología vegetal
Fenotipado
Transversal
http://aims.fao.org/aos/agrovoc/c_33291
http://aims.fao.org/aos/agrovoc/c_27064
http://aims.fao.org/aos/agrovoc/c_13434
http://aims.fao.org/aos/agrovoc/c_45113221
spellingShingle plant phenotyping
Arabidopsis
fruit morphology
instance segmentation
deep learning
QTL analysis
MAGIC population
Arabidopsi
Inteligencia artificial
Morfología vegetal
Fenotipado
Transversal
http://aims.fao.org/aos/agrovoc/c_33291
http://aims.fao.org/aos/agrovoc/c_27064
http://aims.fao.org/aos/agrovoc/c_13434
http://aims.fao.org/aos/agrovoc/c_45113221
Atkins, Kieran
Garzón Martínez, Gina A.
Lloyd, Andrew
Doonan, John H.
Chuan, Lu
Unlocking the power of AI for phenotyping fruit morphology in Arabidopsis
description Deep learning can revolutionise high-throughput image-based phenotyping by automating the measurement of complex traits, a task that is often la bour-intensi v e, time-consuming, and prone to human err or. Howev er, its pr ecision and adapta bility in accuratel y phenotyping organ-level tr aits, suc h as fruit morphology, remain to be fully evaluated. Establishing the links between phenotypic and genotypic variation is essential for uncovering the genetic basis of traits and can also provide an orthologous test of pipeline effecti v eness. In this study, we assess the efficacy of deep learning for measuring variation in fruit morphology in Arabidopsis using ima ges fr om a m ultipar ent adv anced gener ation inter cr oss (MAGIC) mapping famil y. We tr ained an instance se gmentation model and developed a pipeline to phenotype Arabidopsis fruit morphology, based on the model outputs. Our model achieved strong perfor- mance with an av era ge pr ecision of 88.0% for detection and 55.9% for segmentation. Quantitati v e trait locus analysis of the derived phenotypic metrics of the MAGIC population identified significant loci associated with fruit morphology. This analysis, based on au- tomated phenotyping of 332,194 individual fruits, underscores the capability of deep learning as a robust tool for phenotyping large populations. Our pipeline for quantifying pod morphological traits is scala b le and provides high-quality phenotype data, facilitating genetic analysis and gene discov er y, as well as advancing crop breeding resear c h.
format article
author Atkins, Kieran
Garzón Martínez, Gina A.
Lloyd, Andrew
Doonan, John H.
Chuan, Lu
author_facet Atkins, Kieran
Garzón Martínez, Gina A.
Lloyd, Andrew
Doonan, John H.
Chuan, Lu
author_sort Atkins, Kieran
title Unlocking the power of AI for phenotyping fruit morphology in Arabidopsis
title_short Unlocking the power of AI for phenotyping fruit morphology in Arabidopsis
title_full Unlocking the power of AI for phenotyping fruit morphology in Arabidopsis
title_fullStr Unlocking the power of AI for phenotyping fruit morphology in Arabidopsis
title_full_unstemmed Unlocking the power of AI for phenotyping fruit morphology in Arabidopsis
title_sort unlocking the power of ai for phenotyping fruit morphology in arabidopsis
publisher Oxford University Press
publishDate 2025
url https://academic.oup.com/gigascience/article/doi/10.1093/gigascience/giae123/8010444
http://hdl.handle.net/20.500.12324/41152
https://doi.org/10.1093/gigascience/giae123
work_keys_str_mv AT atkinskieran unlockingthepowerofaiforphenotypingfruitmorphologyinarabidopsis
AT garzonmartinezginaa unlockingthepowerofaiforphenotypingfruitmorphologyinarabidopsis
AT lloydandrew unlockingthepowerofaiforphenotypingfruitmorphologyinarabidopsis
AT doonanjohnh unlockingthepowerofaiforphenotypingfruitmorphologyinarabidopsis
AT chuanlu unlockingthepowerofaiforphenotypingfruitmorphologyinarabidopsis
_version_ 1842255962396688384
spelling RepoAGROSAVIA411522025-08-30T03:01:33Z Unlocking the power of AI for phenotyping fruit morphology in Arabidopsis Unlocking the power of AI for phenotyping fruit morphology in Arabidopsis Atkins, Kieran Garzón Martínez, Gina A. Lloyd, Andrew Doonan, John H. Chuan, Lu plant phenotyping Arabidopsis fruit morphology instance segmentation deep learning QTL analysis MAGIC population Arabidopsi Inteligencia artificial Morfología vegetal Fenotipado Transversal http://aims.fao.org/aos/agrovoc/c_33291 http://aims.fao.org/aos/agrovoc/c_27064 http://aims.fao.org/aos/agrovoc/c_13434 http://aims.fao.org/aos/agrovoc/c_45113221 Deep learning can revolutionise high-throughput image-based phenotyping by automating the measurement of complex traits, a task that is often la bour-intensi v e, time-consuming, and prone to human err or. Howev er, its pr ecision and adapta bility in accuratel y phenotyping organ-level tr aits, suc h as fruit morphology, remain to be fully evaluated. Establishing the links between phenotypic and genotypic variation is essential for uncovering the genetic basis of traits and can also provide an orthologous test of pipeline effecti v eness. In this study, we assess the efficacy of deep learning for measuring variation in fruit morphology in Arabidopsis using ima ges fr om a m ultipar ent adv anced gener ation inter cr oss (MAGIC) mapping famil y. We tr ained an instance se gmentation model and developed a pipeline to phenotype Arabidopsis fruit morphology, based on the model outputs. Our model achieved strong perfor- mance with an av era ge pr ecision of 88.0% for detection and 55.9% for segmentation. Quantitati v e trait locus analysis of the derived phenotypic metrics of the MAGIC population identified significant loci associated with fruit morphology. This analysis, based on au- tomated phenotyping of 332,194 individual fruits, underscores the capability of deep learning as a robust tool for phenotyping large populations. Our pipeline for quantifying pod morphological traits is scala b le and provides high-quality phenotype data, facilitating genetic analysis and gene discov er y, as well as advancing crop breeding resear c h. National Capability in Plant Phenotyping FoodBioSystems Doctoral Training Partnership - DTP 2025-08-29T16:41:33Z 2025-08-29T16:41:33Z 2025-02 2025 article Artículo científico http://purl.org/coar/resource_type/c_2df8fbb1 info:eu-repo/semantics/article https://purl.org/redcol/resource_type/ART http://purl.org/coar/version/c_970fb48d4fbd8a85 https://academic.oup.com/gigascience/article/doi/10.1093/gigascience/giae123/8010444 2047-217X http://hdl.handle.net/20.500.12324/41152 https://doi.org/10.1093/gigascience/giae123 reponame:Biblioteca Digital Agropecuaria de Colombia instname:Corporación colombiana de investigación agropecuaria AGROSAVIA eng GigaScience 14 1 1 14 Marsh JI, Hu H, Gill M, et al. Crop breeding for a changing climate: integrating phenomics and genomics with bioinformatics. Theor Appl Genet 2021;134(6):1677–90. https:// doi.org/ 10.1007/ s00122 - 021- 03820- 3 . Cucinotta M, Di Marzo M, Guazzotti A, et al. Gynoecium size and ovule number are interconnected traits that impact seed yield. J Exp Bot 2020;71(9):2479–89. https:// doi.org/ 10.1093/ jxb/ eraa050 . Vivian-Smith A, Luo M, Chaudhury A, et al. Fruit de v elopment is activ el y r estricted in the absence of fertilization in Ar abidopsis. De v elopment 2001;128(12):2321–31. https:// doi.org/ 10.1242/ dev. 128.12.2321 . Zhang L, Yang G, Liu P, et al. Genetic and correlation analysis of silique-traits in Brassica napus L. by quantitative trait locus mapping. Theor Appl Genet 2011;122(1):21–31. https:// doi.org/ 10 .1007/s00122- 010- 1419- 1 . Siles L, Hassall KL, Sanchis Gritsch C, et al. Uncovering trait as- sociations resulting in maximal seed yield in winter and spring oilseed r a pe. Fr ont Plant Sci 2021;12:697576. https:// doi.org/ 10.3 389/fpls.2021.697576 . Siles L, Hassall KL, Sanchis Gritsch C, et al. Uncovering trait as- sociations resulting in maximal seed yield in winter and spring oilseed r a pe. Fr ont Plant Sci 2021;12:697576. https:// doi.org/ 10.3 389/fpls.2021.697576 . Ton LB, Neik TX, Batley J. The use of genetic and gene technolo- gies in shaping modern rapeseed cultivars (Brassica napus L.). Genes 2020;11(10):1161 . https:// doi.org/ 10.3390/ genes11101161 . Berardini TZ, Reiser L, Li D, et al. The Arabidopsis information resource: making and mining the “gold standard”annotated ref- erence plant genome. Genesis 2015;53(8):474–85. https://doi.org/ 10.1002/dvg.22877 . Pierusc hka R, Sc hurr U. Plant phenotyping: past, pr esent, and future. Plant Phenomics 2019;2019:7507131. https:// doi.org/ 10.3 4133/2019/7507131 . Berry JC, Fahlgren N, Pokorny AA, et al. An automated, high- throughput method for standardizing image color profiles to im- pr ov e ima ge-based plant phenotyping. PeerJ 2018;6:e5727. https: // doi.org/ 10.7717/ peerj.5727 . Berry JC, Fahlgren N, Pokorny AA, et al. An automated, high- throughput method for standardizing image color profiles to im- pr ov e ima ge-based plant phenotyping. PeerJ 2018;6:e5727. https: // doi.org/ 10.7717/ peerj.5727 . He H, Ma X, Guan H. A calculation method of phenotypic traits of soybean pods based on image processing technology. Ecol In- form 2022;69:101676. https:// doi.org/ 10.1016/ j.ecoinf.2022.1016 76 . Zingaretti L, Monfort A, Pérez-Enciso M. Automatic fruit mor- phology phenome and genetic analysis: an application in the Octoploid Strawberry. Plant Phenomics 2021;2021:1–14. https: // doi.org/ 10.34133/2021/ 9812910 . Zingaretti L, Monfort A, Pérez-Enciso M. Automatic fruit mor- phology phenome and genetic analysis: an application in the Octoploid Strawberry. Plant Phenomics 2021;2021:1–14. https: // doi.org/ 10.34133/2021/ 9812910 . Gill T, Gill S, Chopra Y, et al. A compr ehensiv e r e vie w of high throughput phenotyping and machine learning for plant stress phenotyping. Plant Phenomics 2022;2:3. https:// doi.org/ 10.1007/ s43657- 022- 00048- z . Gill T, Gill S, Chopra Y, et al. A compr ehensiv e r e vie w of high throughput phenotyping and machine learning for plant stress phenotyping. Plant Phenomics 2022;2:3. https:// doi.org/ 10.1007/ s43657- 022- 00048- z . Morshed MS, Ahmed S, Ahmed T, et al. Fruit quality assessment with densely connected convolutional neural network. In: 2022 12th International Conference on Electrical and Computer En- gineering (ICECE). New York City, NY, United States: IEEE, 2022, 1–4. https:// doi.org/ 10.1109/ ICECE57408.2022.10088873 . Morshed MS, Ahmed S, Ahmed T, et al. Fruit quality assessment with densely connected convolutional neural network. In: 2022 12th International Conference on Electrical and Computer En- gineering (ICECE). New York City, NY, United States: IEEE, 2022, 1–4. https:// doi.org/ 10.1109/ ICECE57408.2022.10088873 . Bolya D, Zhou C, Xiao F, et al. Y OLA CT: real-time instance seg- mentation. In: 2019 IEEE/CVF International Conference on Com- puter Vision (ICCV). Seoul, Korea (South): IEEE, 2019, 9156–65. https:// doi.org/ 10.1109/ ICCV.2019.00925 . Bolya D, Zhou C, Xiao F, et al. Y OLA CT: real-time instance seg- mentation. In: 2019 IEEE/CVF International Conference on Com- puter Vision (ICCV). Seoul, Korea (South): IEEE, 2019, 9156–65. https:// doi.org/ 10.1109/ ICCV.2019.00925 . 20. Redmon J, Divvala S, Girshick R, et al. You only Redmon J, Divvala S, Girshick R, et al. You only look once: unified, real-time object detection. In: 2016 IEEE Conference on Com- puter Vision and Pattern Recognition (CVPR). Las Vegas, NV, USA: IEEE, 2016, 779–88. https:// doi.org/ 10.1109/ CVPR.2016.91 . Carr anza-García M, Torr es-Mateo J, Lar a-Benítez P, et al. On the performance of one-stage and two-stage object detectors in autonomous vehicles using camera data. Remote Sensing 2021;13(1):89. https:// doi.org/ 10.3390/ rs13010089 . He K, Gkioxari G, Dollar P, et al. Mask R-CNN. In: Proceedings of the IEEE International Conference on Computer Vision (ICCV). Venice, Italy: IEEE, 2017. Afzaal U, Bhattarai B, Pandeya YR, et al. An instance segmenta- tion model for strawberry diseases based on mask R-CNN. Sen- sors 2021;21(19):6565 . https:// doi.org/ 10.3390/ s21196565 . Toda Y, Okura F, Ito J, et al. Training instance segmentation neu- ral network with synthetic datasets for crop seed phenotyping. Commun Biol 2020;3:173. https:// doi.org/ 10.1038/ s42003- 020- 0 905-5 . Cheng B, Misra I, Schwing AG, et al. Masked-attention mask tr ansformer for univ ersal ima ge segmentation. In: Pr oceed- ings of the IEEE/CVF Conference on Computer Vision and Pat- tern Recognition (CVPR). New Orleans, LA, USA: IEEE, 2022, 1290–99. Gu W, Bai S, Kong L. A r e vie w on 2D instance segmen- tation based on deep neural networks. Image Vision Comput 2022;120:104401. https:// doi.org/ 10.1016/ j.imavis.2 022.104401 . Du R, Ma Z, Xie P, et al. PST: plant segmentation transformer for 3D point clouds of r a peseed plants at the podding stage. ISPRS J Photogramm Remote Sens 2023;195:380–92. https:// doi.org/ 10.1 016/j.ispr sjpr s.2022.11.022 . Cai Z, Vasconcelos N. Cascade R-CNN: high quality object detec- tion and instance segmentation. IEEE Trans Pattern Anal Mach Intell 2021;43(5):1483–98. https:// doi.org/ 10.1109/ TPAMI.2019.2 956516 . Wang X, Xuan H, Evers B, et al. High-throughput phenotyping with deep learning gives insight into the genetic arc hitectur e of flo w ering time in wheat. Gigascience 2019;8(11):giz120. https:// doi.org/ 10.1093/ gigascience/ giz120 . Xie E, Wang W, Yu Z, et al. SegFormer: simple and efficient de- sign for semantic segmentation with tr ansformers. In: Pr oceed- ings of the 35th International Conference on Neural Information Pr ocessing Systems. Vancouv er, Canada: Curr an Associates Inc., 2021. Geng Z, Lu Y, Duan L, et al. High-throughput phenotyping and deep learning to analyze dynamic panicle growth and dis- sect the genetic arc hitectur e of yield formation. Crop Environ 2024;3(1):1–11. https:// doi.org/ 10.1016/ j.crope.2023.10.005 . K o ver PX, Valdar W, Trakalo J, et al. A multiparent advanced gen- er ation inter-cr oss to fine-ma p quantitativ e tr aits in Ar abidopsis thaliana. PLoS Genet 2009;5(7):1–15. https:// doi.org/ 10.1371/ jour nal.pgen.1000551 . Biernaskie JM, Garzón-Martínez GA, Corke FMK, et al. Under re- vision, uncovering the hidden genetic basis of plant competitive- ness and group productivity. Proc R Soc B Biol Sci 2025. in press. Dutta A, Zisserman A. The VIA annotation softwar e for ima ges, audio and video. In: Proceedings of the 27th ACM International Conference on Multimedia. MM ’19. New York: ACM, 2019. https: // doi.org/ 10.1145/ 3343031.3350535 . Cor por ation CV AT .ai. Computer Vision Annotation T ool (CV AT). 2023. https://github.com/cv at-ai/cv at . Accessed 14 December 2024. Kirillov A, Mintun E, Ravi N, et al. Segment Anything. In: 2023 IEEE/CVF International Conference on Computer Vision (ICCV). P aris, Fr ance: IEEE, 2023, 3992–4003. Li K, Malik J. Amodal instance segmentation. In: Computer Vi- sion –ECCV 2016. ECCV 2016. Lecture Notes in Computer Sci- ence. Amsterdam, The Netherlands: Springer nature, 2016. Radosa vo vic I, K osar aju RP, Girshic k R, et al. Designing network design spaces. In: 2020 IEEE/CVF Conference on Computer Vi- sion and Pattern Recognition (CVPR) Seattle, WA, USA: IEEE, 2020. Lin TY, Maire M, Belongie S et al., Microsoft COCO: common ob- jects in context. In: Fleet D, Pajdla T, Schiele B, et al. eds. Computer Vision–ECCV 2014. Cham: Springer International Publish- ing; 2014:740–55. Gilmer J, Ghorbani B, Garg A, et al. A loss curv atur e perspectiv e on training instability in deep learning. In: The Tenth Interna- tional Conference on Learning Representations ICLR 2022. Vir- tual Event: OpenReview.net, 2021. Zhang TY, Suen CY. A fast parallel algorithm for thinning digital patterns. Commun ACM 1984;27(3):236–39. https:// doi.org/ 10.1 145/357994.358023 . Berardini TZ, Mundodi S, Reiser L, et al. Functional annota- tion of the Arabidopsis genome using controlled vocabularies. Plant Physiol 2004;135(2):745–55. https:// doi.org/ 10.1104/ pp.104 .040071 . Chen K, Wang J, Pang J et al., MMDetection: open MMLab de- tection toolbox and benc hmark. Tec hnical Report. 2019. https: //ar xiv.or g/abs/1906.07155 . Accessed 14 December 2024. P aszke A, Gr oss S, Massa F, et al. PyTorc h: an imper ativ e style, high-performance deep learning libr ary. In: Pr oceedings of the 33rd International Conference on Neural Information Process- ing Systems, vol. 33, Red Hook, NY, USA: Curran Associates Inc., 2019:721. van der Walt S, Schönberger JL, Nunez-Iglesias J, et al. scikit- ima ge: ima ge pr ocessing in Python. PeerJ 2014;2:e453. https://do i.org/ 10.7717/ peerj.453 . Br adski G. The OpenCV Libr ary. Dr Dobb’s Journal of Software Tools 2000. Broman KW, Gatti DM, Simecek P, et al. R/qtl2: software for ma pping quantitativ e tr ait loci with high-dimensional data and m ulti-par ent populations. Genetics 2019;211(2):495–502. https: // doi.org/ 10.1534/ genetics.118.301595 . Tav ar es H. atMAGIC: Data pac ka ge with R/qtl2 objects for the Arabidopsis MAGIC lines. 2024. R package version 0.1.0, commit 0b8e985975a0d0277cdc0bb4cc7a0dc39393070b. https://github.c om/tavareshugo/atMAGIC . Accessed 14 December 2024. Torii KU, Mitsukawa N, Oosumi T, et al. The Arabidopsis ERECTA gene encodes a putative receptor protein kinase with extra- cellular leucine-rich repeats. Plant Cell 1996;8(4):735–46. https: // doi.org/ 10.1105/ tpc.8.4.735 . Gegas VC, Nazari A, Griffiths S, et al. A genetic frame- work for grain size and shape variation in wheat. Plant Cell 2010;22(4):1046–56. https:// doi.org/ 10.1105/ tpc.110.074153 . Pan Y, Wang Y, McGregor C, et al. Genetic arc hitectur e of fruit size and shape variation in cucurbits: a comparative perspec- tive . T heor Appl Genet 2020;133:1–21. https:// doi.org/ 10.1007/ s0 0122- 019- 03481- 3 . Hussain Q, Zhan J, Liang H, et al. Key genes and mechanisms underl ying natur al v ariation of silique length in oilseed r a pe (Br assica na pus L.) germplasm. Cr op J 2022;10(3):617–26. https: // doi.org/ 10.1016/ j.cj.2021.08.010 . Hong Y, Zhang M, Zhu J, et al. Genome-wide association studies r e v eal nov el loci for gr ain size in two-r owed barley (Hordeum vulgare L.). Theor Appl Genet 2024;137(3):58. https:// doi.org/ 10 .1007/s00122- 024- 04562- 8 . Zhang W, Chen K, Zhang B, et al. Postharvest responses of Chi- nese bayberry fruit. Postharvest Biol Technol 2005;37(3):241–51. https:// doi.org/ 10.1016/ j.postharvbio .2005.05.005 . Ghahremani M, Williams K, Corke F, et al. Direct and accurate featur e extr action fr om 3D point clouds of plants using RANSAC. Comput Electron Agric 2021;187:106240. https:// doi.org/ 10.101 6/j.compag.2021.106240 . Ghahremani M, Williams K, Corke FMK, et al. Deep segmentation of point clouds of wheat. Front Plant Sci 2021;12:608732. https: // doi.org/ 10.3389/ fpls.2021.608732 . Zhao X, Yu K, Pang C, et al. QTL anal ysis of fiv e silique-r elated traits in brassica napus L. across multiple environments. Front Plant Sci 2021;12:766271. https:// doi.org/ 10.3389/ fpls.2021.7662 71 . Jiao Y, Zhang K, Cai G, et al. Fine mapping and candidate gene analysis of a major locus controlling ovule abortion and seed number per silique in Brassica napus L. Theor Appl Genet 2021;134(8):2517–30. https:// doi.org/ 10.1007/ s00122-021 - 03839- 6 . Yu P, Gao Z, Hua Z. Contrasting impacts of ubiquitin over- expr ession on ar abidopsis gr owth and de v elopment. Plants 2024;13(11):1485. https:// doi.org/ 10.3390/ plants13111485 . Esvelt Klos K, Yimer B A, Ho w arth CJ, et al. The genetic architec- ture of milling quality in spring oat lines of the collabor ativ e oat r esearc h enter prise. Foods 2021;10(10):2479. https:// doi.org/ 10.3 390/foods10102479 . Macua JI, Lahoz I, Bozal JM, et al. Industrial quality of cherry tomato varieties in Navarre. Acta Hortic. 2007;758:181–84. https: // doi.org/ 10.17660/ActaHortic.2007.758.20 . Sun S, Liu Z, Wang X, et al. Genetic control of thermomorpho- genesis in tomato inflor escences. Nat Comm un 2024;15(1):1472. https:// doi.org/ 10.1038/ s41467- 024- 45722- 0 . González-Suárez P, Walker CH, Lock T, et al. FLOWERING LO- CUS T-mediated thermal signalling regulates age-dependent inflor escence de v elopment in Ar abidopsis thaliana. J Exp Bot 2024;75(14):4400–14. https:// doi.org/ 10.1093/ jxb/ erae094 . Mor phPod. Mor phPod (v ersion 1.0). 2024. https://github.com/kie ranatkins/silique-detector /r eleases/tag/v1.0.0 . Accessed 14 De- cember 2024. Atkins K, Garzón Martínez GA, Lloyd A et al. Unlocking the po w er of AI for phenotyping fruit morphology in Ara- bidopsis (Version 1), [Computer softw are]. Softw are Her- ita ge. 2024. https://arc hive.softwar eheritage.or g/swh:1:snp: ae0de35e2b49271b5a8f6dc682a957ac882c2cf2;origin=https: // github.com/kieranatkins/ gimp- image- annotator. Accessed 14 December 2024. GI À. GIMP Image Annotator (GI À) (version 1.0). GitHub. 2024. https:// github.com/kieranatkins/ gimp- image- annotator /r elea ses/ tag/ v1.0.0 . Accessed 14 December 2024. Atkins K. GIMP Image Annotator. WorkflowHub. 2024. https://do i.org/10.48546/WORKFLOWHUB.WORKFLOW.1229.1 . Accessed 14 December 2024. Atkins K, Garzón Martínez GA, Lloyd A, et al. Data for: unlocking the Po w er of AI for fruit phenotyping: a genetic validation study in Arabidopsis [data set]. Zenodo. 2024. https:// doi.org/ 10.20391 /283ce324- 6a96- 4cc8- 8168- 51f 48354f 7cf . Accessed 14 Decem- ber 2024. Atkins K, Garzón Martínez GA, Lloyd A, et al. Unlocking the po w er of AI for phenotyping fruit morphology in Arabidop- sis [DOME-ML Annotations]. DOME-ML Registry. 2024. https://re gistry.dome-ml.or g/re view/a8q3rb7qrv . Accessed 14 December 2024. Atribución-NoComercial-CompartirIgual 4.0 Internacional http://creativecommons.org/licenses/by-nc-sa/4.0/ application/pdf application/pdf Oxford University Press GigaScience; Vol. 14, Núm. 1 (2025): GigaScience (Feb);p. 55 -66.