Deep learning-assisted concentration gradient generation for the study of 3D cell cultures in hydrogel beads of varying stiffness
The study of dose-response relationships underpins analytical biosciences. Droplet microfluidics platforms can automate the generation of microreactors encapsulating varying concentrations of an assay component, providing datasets across a large chemical space in a single experiment. A classical met...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2024-04-01
|
| Series: | Frontiers in Bioengineering and Biotechnology |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/fbioe.2024.1364553/full |
| _version_ | 1797214259072991232 |
|---|---|
| author | Vasileios Anagnostidis Vasileios Anagnostidis Anuj Tiwari Fabrice Gielen Fabrice Gielen |
| author_facet | Vasileios Anagnostidis Vasileios Anagnostidis Anuj Tiwari Fabrice Gielen Fabrice Gielen |
| author_sort | Vasileios Anagnostidis |
| collection | DOAJ |
| description | The study of dose-response relationships underpins analytical biosciences. Droplet microfluidics platforms can automate the generation of microreactors encapsulating varying concentrations of an assay component, providing datasets across a large chemical space in a single experiment. A classical method consists in varying the flow rate of multiple solutions co-flowing into a single microchannel (producing different volume fractions) before encapsulating the contents into water-in-oil droplets. This process can be automated through controlling the pumping elements but lacks the ability to adapt to unpredictable experimental scenarios, often requiring constant human supervision. In this paper, we introduce an image-based, closed-loop control system for assessing and adjusting volume fractions, thereby generating unsupervised, uniform concentration gradients. We trained a shallow convolutional neural network to assess the position of the laminar flow interface between two co-flowing fluids and used this model to adjust flow rates in real-time. We apply the method to generate alginate microbeads in which HEK293FT cells could grow in three dimensions. The stiffnesses ranged from 50 Pa to close to 1 kPa in Young modulus and were encoded with a fluorescent marker. We trained deep learning models based on the YOLOv4 object detector to efficiently detect both microbeads and multicellular spheroids from high-content screening images. This allowed us to map relationships between hydrogel stiffness and multicellular spheroid growth. |
| first_indexed | 2024-04-24T11:11:19Z |
| format | Article |
| id | doaj.art-0615806d7a68430ba1ecc672d4f73efb |
| institution | Directory Open Access Journal |
| issn | 2296-4185 |
| language | English |
| last_indexed | 2024-04-24T11:11:19Z |
| publishDate | 2024-04-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Bioengineering and Biotechnology |
| spelling | doaj.art-0615806d7a68430ba1ecc672d4f73efb2024-04-11T12:50:16ZengFrontiers Media S.A.Frontiers in Bioengineering and Biotechnology2296-41852024-04-011210.3389/fbioe.2024.13645531364553Deep learning-assisted concentration gradient generation for the study of 3D cell cultures in hydrogel beads of varying stiffnessVasileios Anagnostidis0Vasileios Anagnostidis1Anuj Tiwari2Fabrice Gielen3Fabrice Gielen4Living Systems Institute, Faculty of Health and Life Sciences, University of Exeter, Exeter, United KingdomDepartment of Physics and Astronomy, Faculty of Environment, Science and Economy, University of Exeter, Exeter, United KingdomLiving Systems Institute, Faculty of Health and Life Sciences, University of Exeter, Exeter, United KingdomLiving Systems Institute, Faculty of Health and Life Sciences, University of Exeter, Exeter, United KingdomDepartment of Physics and Astronomy, Faculty of Environment, Science and Economy, University of Exeter, Exeter, United KingdomThe study of dose-response relationships underpins analytical biosciences. Droplet microfluidics platforms can automate the generation of microreactors encapsulating varying concentrations of an assay component, providing datasets across a large chemical space in a single experiment. A classical method consists in varying the flow rate of multiple solutions co-flowing into a single microchannel (producing different volume fractions) before encapsulating the contents into water-in-oil droplets. This process can be automated through controlling the pumping elements but lacks the ability to adapt to unpredictable experimental scenarios, often requiring constant human supervision. In this paper, we introduce an image-based, closed-loop control system for assessing and adjusting volume fractions, thereby generating unsupervised, uniform concentration gradients. We trained a shallow convolutional neural network to assess the position of the laminar flow interface between two co-flowing fluids and used this model to adjust flow rates in real-time. We apply the method to generate alginate microbeads in which HEK293FT cells could grow in three dimensions. The stiffnesses ranged from 50 Pa to close to 1 kPa in Young modulus and were encoded with a fluorescent marker. We trained deep learning models based on the YOLOv4 object detector to efficiently detect both microbeads and multicellular spheroids from high-content screening images. This allowed us to map relationships between hydrogel stiffness and multicellular spheroid growth.https://www.frontiersin.org/articles/10.3389/fbioe.2024.1364553/fullmicrofluidicsdeep learningconcentration gradient3D cell cultureobject detectionstiffness |
| spellingShingle | Vasileios Anagnostidis Vasileios Anagnostidis Anuj Tiwari Fabrice Gielen Fabrice Gielen Deep learning-assisted concentration gradient generation for the study of 3D cell cultures in hydrogel beads of varying stiffness Frontiers in Bioengineering and Biotechnology microfluidics deep learning concentration gradient 3D cell culture object detection stiffness |
| title | Deep learning-assisted concentration gradient generation for the study of 3D cell cultures in hydrogel beads of varying stiffness |
| title_full | Deep learning-assisted concentration gradient generation for the study of 3D cell cultures in hydrogel beads of varying stiffness |
| title_fullStr | Deep learning-assisted concentration gradient generation for the study of 3D cell cultures in hydrogel beads of varying stiffness |
| title_full_unstemmed | Deep learning-assisted concentration gradient generation for the study of 3D cell cultures in hydrogel beads of varying stiffness |
| title_short | Deep learning-assisted concentration gradient generation for the study of 3D cell cultures in hydrogel beads of varying stiffness |
| title_sort | deep learning assisted concentration gradient generation for the study of 3d cell cultures in hydrogel beads of varying stiffness |
| topic | microfluidics deep learning concentration gradient 3D cell culture object detection stiffness |
| url | https://www.frontiersin.org/articles/10.3389/fbioe.2024.1364553/full |
| work_keys_str_mv | AT vasileiosanagnostidis deeplearningassistedconcentrationgradientgenerationforthestudyof3dcellculturesinhydrogelbeadsofvaryingstiffness AT vasileiosanagnostidis deeplearningassistedconcentrationgradientgenerationforthestudyof3dcellculturesinhydrogelbeadsofvaryingstiffness AT anujtiwari deeplearningassistedconcentrationgradientgenerationforthestudyof3dcellculturesinhydrogelbeadsofvaryingstiffness AT fabricegielen deeplearningassistedconcentrationgradientgenerationforthestudyof3dcellculturesinhydrogelbeadsofvaryingstiffness AT fabricegielen deeplearningassistedconcentrationgradientgenerationforthestudyof3dcellculturesinhydrogelbeadsofvaryingstiffness |