Development and application of a high-throughput microbial clone picking workstation based on machine vision

doi:10.12211/2096-8280.2025-038

Abstract

Abstract:

Microbial clone picking, a crucial step in genetic engineering and biological experiments, involves the accurate and rapid isolation of single colonies with desired characteristics from petri dishes teeming with numerous clones, followed by their inoculation into culture media for further propagation or analysis. In high-throughput settings, this task becomes burdensome due to its vast volume, complex record-keeping requirements, and the risk of cross-contamination, rendering manual operations impractical for achieving timely and precise results. To address this challenge, we present the design and manufacture of an automated clone picking workstation that performs efficient clone picking using 96-channel pneumatic pick-up pins, eliminating the need for consumables. The pins can be reused after ultrasonic cleaning and sterilization at high temperature following the previous picking cycle, making it more economical and environmentally friendly, compared with other methods that use disposable pipettes or picking needles. The pins can be replaced to adapt to different types of bacterial strains to meet various experimental requirements. The grab integrated on the picking head can rotate 360° and transfer the plates to different work positions.In the aspect of colony detection, the photos are automatically taken by an optical system, and the positioning and screening of colonies are achieved through the deep learning of numerous colony images by the software, which was designed independently. The precision image recognition technology is coupled with robotic and automated control technologies to enable seamless processes for picking, inoculating, cleaning, and drying. The High-Efficiency Particulate Air Filter and ultraviolet sterilization prevent cross-contamination, ensuring the experimental environment meets the required standards. This workstation is equipped with an independent operation computer and has developed a set of user-friendly software that enables personalized editing of multiple experimental protocols tailored to diverse microbial clone types. It can also communicate with external devices via TCP/IP protocols, facilitating the integration for conducting experiments such as fully automated synthetic biology. The validation experiment of bacterial colony picking was conducted by a prototype machine to test the selection efficiency. The success of the experiment suggests that the proposed system and method are feasible and effective, offering a valuable tool and a practical approach for the automation development of high-throughput laboratories. {L-End}

Key words: automation platform, deep learning, clone picking, machine vision, synthetic biology

摘要：

微生物克隆挑选是基因工程生物实验中的关键环节，需要从生长有大量菌落的培养皿中将符合质量要求的单克隆菌落准确、快速挑取出来并接种到培养基中，以便进一步扩大培养或检测。在高通量实验中，克隆挑选环节任务量大、记录繁复、容易交叉污染，依靠人工操作难以在短时间准确完成。针对这一难题，本项目成功研制出一种自动化克隆挑选工作站，通过菌落图像的深度学习实现克隆定位和筛选，并利用机器人技术完成挑取-接种-清洗-高温灭菌过程。在所研制的可视化工作界面中，工作站系统能够个性化编辑适用于多种微生物克隆的多项实验操作流程。通过样机验证实验结果，证明了所研制系统和方法的可行性和有效性，为高通量实验室自动化发展提供了有效工具和有益实践。

关键词: 自动化平台, 深度学习, 克隆挑选, 机器视觉, 合成生物学

CLC Number:

TP273

ZHANG Jiankang, WANG Wenjun, GUO Hongju, BAI Beichen, ZHANG Yafei, YUAN Zheng, LI Yanhui, LI Hang. Development and application of a high-throughput microbial clone picking workstation based on machine vision[J]. Synthetic Biology Journal, 2025, 6(4): 956-971.

张建康, 王文君, 郭洪菊, 白北辰, 张亚飞, 袁征, 李彦辉, 李航. 基于机器视觉的高通量微生物克隆挑选工作站研制及应用[J]. 合成生物学, 2025, 6(4): 956-971.

Figures/Tables 20

Fig. 1 Overall form of clone selection workstation

Fig. 2 System composition of clone picking workstation

Fig. 3 Electrical schematic diagram

Fig. 4 Arrangement of the work area for the clone picking workstation

Fig. 5 Problems existing in colony images that affect recognition

Fig. 6 Flowchart of colony identification and location

Fig. 7 Petri dish

Fig. 8 Dish training curve

Fig. 9 Identification and labeling of petri dishes

Table 1 Distribution of the dataset

数据集

Data set

训练集

Training set

测试集

Test set

完整菌落图像

Complete colony images

挑选出小图像块

Small image blocks selected

5160

1466

Fig. 10 Colony-training curve

Fig. 11 Grayscale image generated by reasoning

Fig. 12 Identification of qualified colonies

Fig. 13 UI design

Fig. 14 Control interface framework of the workstation

Fig. 15 Clone picking process

Fig. 16 Image comparison before and after picking

Fig. 17 Deep well plate containing colony culture medium

Fig. 18 Verification of sterilization effect

Table 2 A comparison of technical parameters of this device with other three clone picking workstations

设备型号	通道数量	挑取方式	CCD分辨率/(Pixel/mm)	菌落识别尺寸/mm	菌落识别准确度/%	挑取准确率/%	有效像素/万
QPix 420	96	挑针	22	≥ 0.1	0.5～0.7mm菌落，>97%	＞ 98%	500
Hedylax T200智能微生物菌落挑选工作站	单通道或8通道	吸头	—	—	—	≥ 98%	2500
全自动菌落挑选工作站G3000	2或4	挑针	—	≥ 0.5	—	1 mm以上98%	600～2000
本设备	96	挑针	30	≥0.2	≥ 98%	≥ 98%	1000

References 32

[1]	MACARRÓN R, HERTZBERG R P. Design and implementation of high throughput screening assays[J]. Molecular Biotechnology, 2011, 47(3): 270-285.
[2]	HUGHES S R, BUTT T R, BARTOLETT S, et al. Design and construction of a first-generation high-throughput integrated robotic molecular biology platform for bioenergy applications[J]. SLAS Technology, 2011, 16(4): 292-307.
[3]	孙梦楚, 陆亮宇, 申晓林, 等. 基于荧光检测的高通量筛选技术和装备助力细胞工厂构建[J]. 合成生物学, 2023, 4(5): 947-965.
	SUN M C, LU L Y, SHEN X L, et al. Fluorescence detection-based high-throughput screening systems and devices facilitate cell factories construction[J]. Synthetic Biology Journal, 2023, 4(5): 947-965.
[4]	卢挥, 张芳丽, 黄磊. 合成生物学自动化装置iBioFoundry的构建与应用[J]. 合成生物学, 2023, 4(5): 877-891.
	LU H, ZHANG F L, HUANG L. Establishment of iBioFoundry for synthetic biology applications[J]. Synthetic Biology Journal, 2023, 4(5): 877-891.
[5]	STEPHENSON A, LASTRA L, NGUYEN B, et al. Physical laboratory automation in synthetic biology[J]. ACS Synthetic Biology, 2023, 12(11): 3156-3169.
[6]	PAVAN M. Setting up an automated biomanufacturing laboratory[J]. Methods in Molecular Biology, 2021, 2229: 137-155.
[7]	MARTIN V J J, PITERA D J, WITHERS S T, et al. Engineering a mevalonate pathway in Escherichia coli for production of terpenoids[J]. Nature Biotechnology, 2003, 21(7): 796-802.
[8]	WIN M N, SMOLKE C D. Higher-order cellular information processing with synthetic RNA devices[J]. Science, 2008, 322(5900): 456-460.
[9]	PADDON C J, WESTFALL P J, PITERA D J, et al. High-level semi-synthetic production of the potent antimalarial artemisinin[J]. Nature, 2013, 496(7446): 528-532.
[10]	CHAO R, MISHRA S, SI T, et al. Engineering biological systems using automated biofoundries[J]. Metabolic Engineering, 2017, 42: 98-108.
[11]	唐婷, 付立豪, 郭二鹏, 等. 自动化合成生物技术与工程化设施平台[J]. 科学通报, 2021, 66(3): 300-309.
	TANG T, FU L H, GUO E P, et al. Automation in synthetic biology using biological foundries[J]. Chinese Science Bulletin, 2021, 66(3): 300-309.
[12]	ZIMMERMANN M, ZIMMERMANN-KOGADEEVA M, WEGMANN R, et al. Mapping human microbiome drug metabolism by gut bacteria and their genes[J]. Nature, 2019, 570(7762): 462-467.
[13]	CERBINI T, LUO Y Q, RAO M S, et al. Transfection, selection, and colony-picking of human induced pluripotent stem cells TALEN-targeted with a GFP gene into the AAVS1 safe harbor[J]. Journal of Visualized Experiments, 2015(96): 52504.
[14]	DJATNA T, HADI M Z. Implementation of an ant colony approach to solve multi-objective order picking problem in beverage warehousing with drive-in rack system[C]//2017 International Conference on Advanced Computer Science and Information Systems (ICACSIS), 28-29 October 2017, Bali, Indonesia, 2017: 137-142.
[15]	HUANG C, HE K, LIU C L, et al. A colony picking robot with multi-pin synchronous manipulator[C]//2018 IEEE International Conference on Information and Automation(ICIA), 11-13 August 2018, Wuyi Mountain, Fujian, China, 2018: 7-12.
[16]	张依朗. 基于机器视觉的高通量自动菌落挑取系统研究[D]. 北京: 北京化工大学, 2021.
	ZHANG Y L. Research on high throughput automatic colony picking sysetem based on machine vision[D]. Beijing: Beijing University of Chemical Technology, 2021.
[17]	CHEN W B, ZHANG C C. Automated bacterial colony counting for clonogenic assay[M]//Dental Computing and Applications. New York: IGI Global, 2009: 134-145.
[18]	GOROKHOV O, FAZYLOV R, KAZACHUK M, et al. Bacterial colony detection method for microbiological photographic images[C]//2022 International Joint Conference on Neural Networks (IJCNN). July 18-23, 2022, Padua, Italy. IEEE, 2022: 1-8.
[19]	ZHANG L. Phase contrast microscopy cell population segmentation: a survey[EB/OL]. arXiv, 2019: 1911.11111. (2019-11-29)[2025-03-01]. .
[20]	LAWLESS C, WILKINSON D J, YOUNG A, et al. Colonyzer: automated quantification of micro-organism growth characteristics on solid agar[J]. BMC Bioinformatics, 2010, 11: 287.
[21]	REHMAN A, SALEEM Z, AMJAD J, et al. A comparison of bacterial colonies count from petri dishes utilizing hough transform and traditional manual counting[EB/OL].arXiv, 2025: 2505.20365. (2025-05-26)[2025-06-01]. .
[22]	RUSS J C, NEAL F B. The image processing handbook[M/OL]. 7th ed. Boca Raton: CRC Press, 2016. (2018-09-03)[2025-06-25]. .
[23]	MOEN E, BANNON D, KUDO T, et al. Deep learning for cellular image analysis[J]. Nature Methods, 2019, 16(12): 1233-1246.
[24]	WAKABAYASHI R, AOYANAGI A, TOMINAGA T. Rapid counting of coliforms and Escherichia coli by deep learning-based classifier[J]. Journal of Food Safety, 2024, 44(4): e13158.
[25]	SHEN B Y, CHEN X, CAI D L, et al. Real-Space Imaging of the Ordered Small Molecule Orientations in Porous Frameworks by Electron Microscopy[EB/OL]. arXiv, 2020: 2001.09588.(2020-01-27)[2025-06-01]. .
[26]	AKBAR S ALI, GHAZALI K H, HASAN H, et al. Rapid bacterial colony classification using deep learning[J]. Indonesian Journal of Electrical Engineering and Computer Science, 2022, 26(1): 352.
[27]	ANDREINI P, BONECHI S, BIANCHINI M, et al. a deep learning approach to bacterial colony segmentation[C/OL]//KŮRKOVÁ V, MANOLOPOULOS Y, HAMMER B, et al. Artificial neural networks and machine learning-ICANN 2018. 27th International Conference on Artificial Neural Networks, Rhodes, Greece, October 4-7, 2018 , Proceedings, Part III. Cham: Springer, 2018. (2018-09-18)[2025-06-01]. .
[28]	RONNEBERGER O, FISCHER P, BROXET T, et al. U-Net: convolutional networks for biomedical image segmentation[EB/OL]. arXiv, 2015: 1505.04597. (2015-05-18)[2025-06-01]. .
[29]	OKTAY O, SCHLEMPER J, LE FOLGOC L, et al. Attention U-Net: learning where to look for the pancreas[EB/OL]. arXiv, 2018: 1804.03999. (2018-05-20)[2025-06-01]. .
[30]	HE K M, GKIOXARI G, DOLLÁRET P, et al. Mask R-CNN for object detection and instance segmentation[EB/OL]. arXiv, 2017: 1703.06870. (2018-01-24)[2025-06-01]. .
[31]	JHA D, SMEDSRUD P H, JOHANSEN D, et al. A comprehensive study on colorectal polyp segmentation with ResUNet++, conditional random field and test-time augmentation[J]. IEEE Journal of Biomedical and Health Informatics, 2021, 25(6): 2029-2040.
[32]	曹淑艳, 陈雪景, 张洵洋. 中国塑料行业绿色低碳发展研究报告[R/OL]. [2025-06-01]. .
	CAO S Y, CHEN X J, ZHANG X Y. Green and low carbon development of the plastics industry in China[R/OL]. [2025-06-01]. .