1
|
Bettancourt N, Pérez-Gallardo C, Candia V, Guevara P, Kalaidzidis Y, Zerial M, Segovia-Miranda F, Morales-Navarrete H. Virtual tissue microstructure reconstruction across species using generative deep learning. PLoS One 2024; 19:e0306073. [PMID: 38995963 PMCID: PMC11244806 DOI: 10.1371/journal.pone.0306073] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/08/2024] [Accepted: 06/11/2024] [Indexed: 07/14/2024] Open
Abstract
Analyzing tissue microstructure is essential for understanding complex biological systems in different species. Tissue functions largely depend on their intrinsic tissue architecture. Therefore, studying the three-dimensional (3D) microstructure of tissues, such as the liver, is particularly fascinating due to its conserved essential roles in metabolic processes and detoxification. Here, we present TiMiGNet, a novel deep learning approach for virtual 3D tissue microstructure reconstruction using Generative Adversarial Networks and fluorescence microscopy. TiMiGNet overcomes challenges such as poor antibody penetration and time-intensive procedures by generating accurate, high-resolution predictions of tissue components across large volumes without the need of paired images as input. We applied TiMiGNet to analyze tissue microstructure in mouse and human liver tissue. TiMiGNet shows high performance in predicting structures like bile canaliculi, sinusoids, and Kupffer cell shapes from actin meshwork images. Remarkably, using TiMiGNet we were able to computationally reconstruct tissue structures that cannot be directly imaged due experimental limitations in deep dense tissues, a significant advancement in deep tissue imaging. Our open-source virtual prediction tool facilitates accessible and efficient multi-species tissue microstructure analysis, accommodating researchers with varying expertise levels. Overall, our method represents a powerful approach for studying tissue microstructure, with far-reaching applications in diverse biological contexts and species.
Collapse
Affiliation(s)
- Nicolás Bettancourt
- Faculty of Biological Sciences, Department of Cell Biology, Universidad de Concepción, Concepción, Chile
- Faculty of Biological Sciences, Grupo de Procesos en Biología del Desarrollo (GDeP), Universidad de Concepción, Concepción, Chile
- Faculty of Engineering, Department of Electrical Engineering, Universidad de Concepción, Concepción, Chile
| | - Cristian Pérez-Gallardo
- Faculty of Biological Sciences, Department of Cell Biology, Universidad de Concepción, Concepción, Chile
- Faculty of Biological Sciences, Grupo de Procesos en Biología del Desarrollo (GDeP), Universidad de Concepción, Concepción, Chile
| | - Valeria Candia
- Faculty of Biological Sciences, Department of Cell Biology, Universidad de Concepción, Concepción, Chile
- Faculty of Biological Sciences, Grupo de Procesos en Biología del Desarrollo (GDeP), Universidad de Concepción, Concepción, Chile
| | - Pamela Guevara
- Faculty of Engineering, Department of Electrical Engineering, Universidad de Concepción, Concepción, Chile
| | - Yannis Kalaidzidis
- Max Planck Institute of Molecular Cell Biology and Genetics, Dresden, Germany
| | - Marino Zerial
- Max Planck Institute of Molecular Cell Biology and Genetics, Dresden, Germany
| | - Fabián Segovia-Miranda
- Faculty of Biological Sciences, Department of Cell Biology, Universidad de Concepción, Concepción, Chile
- Faculty of Biological Sciences, Grupo de Procesos en Biología del Desarrollo (GDeP), Universidad de Concepción, Concepción, Chile
| | - Hernán Morales-Navarrete
- Department of Systems Biology of Development, University of Konstanz, Konstanz, Germany
- Facultad de Ciencias Técnicas, Universidad Internacional Del Ecuador UIDE, Quito, Ecuador
| |
Collapse
|
2
|
Ibbini Z, Truebano M, Spicer JI, McCoy JCS, Tills O. Dev-ResNet: automated developmental event detection using deep learning. J Exp Biol 2024; 227:jeb247046. [PMID: 38806151 PMCID: PMC11152166 DOI: 10.1242/jeb.247046] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/24/2023] [Accepted: 04/22/2024] [Indexed: 05/30/2024]
Abstract
Delineating developmental events is central to experimental research using early life stages, permitting widespread identification of changes in event timing between species and environments. Yet, identifying developmental events is incredibly challenging, limiting the scale, reproducibility and throughput of using early life stages in experimental biology. We introduce Dev-ResNet, a small and efficient 3D convolutional neural network capable of detecting developmental events characterised by both spatial and temporal features, such as the onset of cardiac function and radula activity. We demonstrate the efficacy of Dev-ResNet using 10 diverse functional events throughout the embryonic development of the great pond snail, Lymnaea stagnalis. Dev-ResNet was highly effective in detecting the onset of all events, including the identification of thermally induced decoupling of event timings. Dev-ResNet has broad applicability given the ubiquity of bioimaging in developmental biology, and the transferability of deep learning, and so we provide comprehensive scripts and documentation for applying Dev-ResNet to different biological systems.
Collapse
Affiliation(s)
- Ziad Ibbini
- Marine Biology and Ecology Research Centre, School of Biological and Marine Sciences, University of Plymouth, Drake Circus, Plymouth PL4 8AA, UK
| | - Manuela Truebano
- Marine Biology and Ecology Research Centre, School of Biological and Marine Sciences, University of Plymouth, Drake Circus, Plymouth PL4 8AA, UK
| | - John I. Spicer
- Marine Biology and Ecology Research Centre, School of Biological and Marine Sciences, University of Plymouth, Drake Circus, Plymouth PL4 8AA, UK
| | - Jamie C. S. McCoy
- Marine Biology and Ecology Research Centre, School of Biological and Marine Sciences, University of Plymouth, Drake Circus, Plymouth PL4 8AA, UK
| | - Oliver Tills
- Marine Biology and Ecology Research Centre, School of Biological and Marine Sciences, University of Plymouth, Drake Circus, Plymouth PL4 8AA, UK
| |
Collapse
|
3
|
Pomreinke AP, Müller P. Zebrafish nampt-a mutants are viable despite perturbed primitive hematopoiesis. Hereditas 2024; 161:14. [PMID: 38685093 PMCID: PMC11057069 DOI: 10.1186/s41065-024-00318-y] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/23/2024] [Accepted: 04/17/2024] [Indexed: 05/02/2024] Open
Abstract
BACKGROUND Nicotinamide phosphoribosyltransferase (Nampt) is required for recycling NAD+ in numerous cellular contexts. Morpholino-based knockdown of zebrafish nampt-a has been shown to cause abnormal development and defective hematopoiesis concomitant with decreased NAD+ levels. However, surprisingly, nampt-a mutant zebrafish were recently found to be viable, suggesting a discrepancy between the phenotypes in knockdown and knockout conditions. Here, we address this discrepancy by directly comparing loss-of-function approaches that result in identical defective transcripts in morphants and mutants. RESULTS Using CRISPR/Cas9-mediated mutagenesis, we generated nampt-a mutant lines that carry the same mis-spliced mRNA as nampt-a morphants. Despite reduced NAD+ levels and perturbed expression of specific blood markers, nampt-a mutants did not display obvious developmental defects and were found to be viable. In contrast, injection of nampt-a morpholinos into wild-type or mutant nampt-a embryos caused aberrant phenotypes. Moreover, nampt-a morpholinos caused additional reduction of blood-related markers in nampt-a mutants, suggesting that the defects observed in nampt-a morphants can be partially attributed to off-target effects of the morpholinos. CONCLUSIONS Our findings show that zebrafish nampt-a mutants are viable despite reduced NAD+ levels and a perturbed hematopoietic gene expression program, indicating strong robustness of primitive hematopoiesis during early embryogenesis.
Collapse
Affiliation(s)
- Autumn Penecilla Pomreinke
- Friedrich Miescher Laboratory of the Max Planck Society, Tübingen, Germany
- University of Hohenheim, Stuttgart, Germany
| | - Patrick Müller
- Friedrich Miescher Laboratory of the Max Planck Society, Tübingen, Germany.
- University of Konstanz, Konstanz, Germany.
| |
Collapse
|
4
|
Tang WH, Sim SR, Aik DYK, Nelanuthala AVS, Athilingam T, Röllin A, Wohland T. Deep learning reduces data requirements and allows real-time measurements in imaging FCS. Biophys J 2024; 123:655-666. [PMID: 38050354 PMCID: PMC10995408 DOI: 10.1016/j.bpj.2023.11.3403] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/29/2023] [Revised: 11/18/2023] [Accepted: 11/30/2023] [Indexed: 12/06/2023] Open
Abstract
Imaging fluorescence correlation spectroscopy (FCS) is a powerful tool to extract information on molecular mobilities, actions, and interactions in live cells, tissues, and organisms. Nevertheless, several limitations restrict its applicability. First, FCS is data hungry, requiring 50,000 frames at 1-ms time resolution to obtain accurate parameter estimates. Second, the data size makes evaluation slow. Third, as FCS evaluation is model dependent, data evaluation is significantly slowed unless analytic models are available. Here, we introduce two convolutional neural networks-FCSNet and ImFCSNet-for correlation and intensity trace analysis, respectively. FCSNet robustly predicts parameters in 2D and 3D live samples. ImFCSNet reduces the amount of data required for accurate parameter retrieval by at least one order of magnitude and makes correct estimates even in moderately defocused samples. Both convolutional neural networks are trained on simulated data, are model agnostic, and allow autonomous, real-time evaluation of imaging FCS measurements.
Collapse
Affiliation(s)
- Wai Hoh Tang
- Department of Biological Sciences, National University of Singapore, Singapore, Singapore; NUS Centre for Bio-Imaging Sciences, National University of Singapore, Singapore, Singapore; Department of Statistics and Data Science, National University of Singapore, Singapore, Singapore; Institute of Digital Molecular Analytics and Science, National University of Singapore, Singapore, Singapore
| | - Shao Ren Sim
- Department of Biological Sciences, National University of Singapore, Singapore, Singapore; NUS Centre for Bio-Imaging Sciences, National University of Singapore, Singapore, Singapore
| | - Daniel Ying Kia Aik
- Department of Biological Sciences, National University of Singapore, Singapore, Singapore; NUS Centre for Bio-Imaging Sciences, National University of Singapore, Singapore, Singapore; Institute of Digital Molecular Analytics and Science, National University of Singapore, Singapore, Singapore; Department of Chemistry, National University of Singapore, Singapore, Singapore
| | - Ashwin Venkata Subba Nelanuthala
- Department of Biological Sciences, National University of Singapore, Singapore, Singapore; NUS Centre for Bio-Imaging Sciences, National University of Singapore, Singapore, Singapore
| | | | - Adrian Röllin
- Department of Statistics and Data Science, National University of Singapore, Singapore, Singapore
| | - Thorsten Wohland
- Department of Biological Sciences, National University of Singapore, Singapore, Singapore; NUS Centre for Bio-Imaging Sciences, National University of Singapore, Singapore, Singapore; Institute of Digital Molecular Analytics and Science, National University of Singapore, Singapore, Singapore; Department of Chemistry, National University of Singapore, Singapore, Singapore.
| |
Collapse
|
5
|
Demir R, Koc S, Ozturk DG, Bilir S, Ozata Hİ, Williams R, Christy J, Akkoc Y, Tinay İ, Gunduz-Demir C, Gozuacik D. Artificial intelligence assisted patient blood and urine droplet pattern analysis for non-invasive and accurate diagnosis of bladder cancer. Sci Rep 2024; 14:2488. [PMID: 38291121 PMCID: PMC10827787 DOI: 10.1038/s41598-024-52728-7] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/16/2023] [Accepted: 01/23/2024] [Indexed: 02/01/2024] Open
Abstract
Bladder cancer is one of the most common cancer types in the urinary system. Yet, current bladder cancer diagnosis and follow-up techniques are time-consuming, expensive, and invasive. In the clinical practice, the gold standard for diagnosis remains invasive biopsy followed by histopathological analysis. In recent years, costly diagnostic tests involving the use of bladder cancer biomarkers have been developed, however these tests have high false-positive and false-negative rates limiting their reliability. Hence, there is an urgent need for the development of cost-effective, and non-invasive novel diagnosis methods. To address this gap, here we propose a quick, cheap, and reliable diagnostic method. Our approach relies on an artificial intelligence (AI) model to analyze droplet patterns of blood and urine samples obtained from patients and comparing them to cancer-free control subjects. The AI-assisted model in this study uses a deep neural network, a ResNet network, pre-trained on ImageNet datasets. Recognition and classification of complex patterns formed by dried urine or blood droplets under different conditions resulted in cancer diagnosis with a high specificity and sensitivity. Our approach can be systematically applied across droplets, enabling comparisons to reveal shared spatial behaviors and underlying morphological patterns. Our results support the fact that AI-based models have a great potential for non-invasive and accurate diagnosis of malignancies, including bladder cancer.
Collapse
Affiliation(s)
- Ramiz Demir
- Koç University Research Center for Translational Medicine (KUTTAM), Istanbul, Turkey
| | - Soner Koc
- Department of Computer Engineering, Koç University, Istanbul, Turkey
- KUIS AI Center, Koç University, Istanbul, Turkey
| | - Deniz Gulfem Ozturk
- Koç University Research Center for Translational Medicine (KUTTAM), Istanbul, Turkey
| | - Sukriye Bilir
- SUNUM Nanotechnology Research and Application Center, Istanbul, Turkey
| | | | - Rhodri Williams
- School of Engineering, University of Edinburgh, Edinburgh, UK
| | - John Christy
- School of Engineering, University of Edinburgh, Edinburgh, UK
| | - Yunus Akkoc
- Koç University Research Center for Translational Medicine (KUTTAM), Istanbul, Turkey
| | - İlker Tinay
- Anadolu Medical Center, Gebze, Kocaeli, Turkey
| | - Cigdem Gunduz-Demir
- Department of Computer Engineering, Koç University, Istanbul, Turkey.
- KUIS AI Center, Koç University, Istanbul, Turkey.
- School of Medicine, Koç University, Istanbul, Turkey.
| | - Devrim Gozuacik
- Koç University Research Center for Translational Medicine (KUTTAM), Istanbul, Turkey.
- SUNUM Nanotechnology Research and Application Center, Istanbul, Turkey.
- School of Medicine, Koç University, Istanbul, Turkey.
| |
Collapse
|
6
|
Kumar N, Marée R, Geurts P, Muller M. Recent Advances in Bioimage Analysis Methods for Detecting Skeletal Deformities in Biomedical and Aquaculture Fish Species. Biomolecules 2023; 13:1797. [PMID: 38136667 PMCID: PMC10742266 DOI: 10.3390/biom13121797] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/31/2023] [Revised: 12/05/2023] [Accepted: 12/09/2023] [Indexed: 12/24/2023] Open
Abstract
Detecting skeletal or bone-related deformities in model and aquaculture fish is vital for numerous biomedical studies. In biomedical research, model fish with bone-related disorders are potential indicators of various chemically induced toxins in their environment or poor dietary conditions. In aquaculture, skeletal deformities are affecting fish health, and economic losses are incurred by fish farmers. This survey paper focuses on showcasing the cutting-edge image analysis tools and techniques based on artificial intelligence that are currently applied in the analysis of bone-related deformities in aquaculture and model fish. These methods and tools play a significant role in improving research by automating various aspects of the analysis. This paper also sheds light on some of the hurdles faced when dealing with high-content bioimages and explores potential solutions to overcome these challenges.
Collapse
Affiliation(s)
- Navdeep Kumar
- Department of Computer Science and Electrical Engineering, Montefiore Institute, University of Liège, 4000 Liège, Belgium; (R.M.); (P.G.)
| | - Raphaël Marée
- Department of Computer Science and Electrical Engineering, Montefiore Institute, University of Liège, 4000 Liège, Belgium; (R.M.); (P.G.)
| | - Pierre Geurts
- Department of Computer Science and Electrical Engineering, Montefiore Institute, University of Liège, 4000 Liège, Belgium; (R.M.); (P.G.)
| | - Marc Muller
- Laboratory for Organogenesis and Regeneration (LOR), GIGA Institute, University of Liège, 4000 Liège, Belgium;
| |
Collapse
|
7
|
Method of the Year 2023: methods for modeling development. Nat Methods 2023; 20:1831-1832. [PMID: 38057526 DOI: 10.1038/s41592-023-02134-0] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 12/08/2023]
|
8
|
Toulany N, Morales-Navarrete H, Čapek D, Grathwohl J, Ünalan M, Müller P. Uncovering developmental time and tempo using deep learning. Nat Methods 2023; 20:2000-2010. [PMID: 37996754 PMCID: PMC10703695 DOI: 10.1038/s41592-023-02083-8] [Citation(s) in RCA: 1] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/19/2023] [Accepted: 10/15/2023] [Indexed: 11/25/2023]
Abstract
During animal development, embryos undergo complex morphological changes over time. Differences in developmental tempo between species are emerging as principal drivers of evolutionary novelty, but accurate description of these processes is very challenging. To address this challenge, we present here an automated and unbiased deep learning approach to analyze the similarity between embryos of different timepoints. Calculation of similarities across stages resulted in complex phenotypic fingerprints, which carry characteristic information about developmental time and tempo. Using this approach, we were able to accurately stage embryos, quantitatively determine temperature-dependent developmental tempo, detect naturally occurring and induced changes in the developmental progression of individual embryos, and derive staging atlases for several species de novo in an unsupervised manner. Our approach allows us to quantify developmental time and tempo objectively and provides a standardized way to analyze early embryogenesis.
Collapse
Affiliation(s)
- Nikan Toulany
- Systems Biology of Development, University of Konstanz, Konstanz, Germany
- Friedrich Miescher Laboratory of the Max Planck Society, Tübingen, Germany
- University Hospital and Faculty of Medicine, University of Tübingen, Tübingen, Germany
| | - Hernán Morales-Navarrete
- Systems Biology of Development, University of Konstanz, Konstanz, Germany
- Centre for the Advanced Study of Collective Behaviour, Konstanz, Germany
| | - Daniel Čapek
- Systems Biology of Development, University of Konstanz, Konstanz, Germany
| | - Jannis Grathwohl
- Systems Biology of Development, University of Konstanz, Konstanz, Germany
| | - Murat Ünalan
- Systems Biology of Development, University of Konstanz, Konstanz, Germany.
- Friedrich Miescher Laboratory of the Max Planck Society, Tübingen, Germany.
| | - Patrick Müller
- Systems Biology of Development, University of Konstanz, Konstanz, Germany.
- Friedrich Miescher Laboratory of the Max Planck Society, Tübingen, Germany.
- University Hospital and Faculty of Medicine, University of Tübingen, Tübingen, Germany.
- Centre for the Advanced Study of Collective Behaviour, Konstanz, Germany.
| |
Collapse
|
9
|
Wu C, Tan P, Chen X, Chang H, Chen Y, Su G, Liu T, Lu Z, Sun M, Wang Y, Zou Y, Wang J, Rao H. Machine Learning-Assisted High-Throughput Strategy for Real-Time Detection of Spermine Using a Triple-Emission Ratiometric Probe. ACS APPLIED MATERIALS & INTERFACES 2023; 15:48506-48518. [PMID: 37796018 DOI: 10.1021/acsami.3c09836] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 10/06/2023]
Abstract
In this study, we designed and fabricated a spermine-responsive triple-emission ratiometric fluorescent probe using dual-emissive carbon nanoparticles and quantum dots, which improve the sensor's accuracy and reduce interfering environmental effects. The probe is advantageous for the proportionate detection of spermine because it has good emission resolution, and the maximum points of the two emission peaks differ by 95 nm. As a proof of concept, cuvettes and a 96-well plate were combined with a smartphone and YOLO series algorithms to accomplish real-time, visual, and high-throughput detection of seafood and meat freshness. In addition, the reaction mechanism was verified by density functional theory and fundamental characterizations. Upon exposure to different amounts of spermine, the intensity of the fluorescent probe changed linearly, and the fluorescent color shifted from yellow-green to red, with a limit of detection of 0.33 μM. To enable visual identification of food-originated spermine, a hydrogel-based visual sensing platform was successfully developed utilizing the triple-emission fluorescent probe. Consequently, spermine could be identified and quantified without complicated equipment.
Collapse
Affiliation(s)
- Chun Wu
- College of Science, Sichuan Agricultural University, Xinkang Road, Yucheng District, Ya'an 625014, P. R. China
| | - Ping Tan
- College of Science, Sichuan Agricultural University, Xinkang Road, Yucheng District, Ya'an 625014, P. R. China
| | - Xianjin Chen
- College of Information Engineering, Sichuan Agricultural University, Xinkang Road, Yucheng District, Ya'an 625014, P. R. China
| | - Hongrong Chang
- College of Science, Sichuan Agricultural University, Xinkang Road, Yucheng District, Ya'an 625014, P. R. China
| | - Yuhui Chen
- College of Science, Sichuan Agricultural University, Xinkang Road, Yucheng District, Ya'an 625014, P. R. China
| | - Gehong Su
- College of Science, Sichuan Agricultural University, Xinkang Road, Yucheng District, Ya'an 625014, P. R. China
| | - Tao Liu
- College of Information Engineering, Sichuan Agricultural University, Xinkang Road, Yucheng District, Ya'an 625014, P. R. China
| | - Zhiwei Lu
- College of Science, Sichuan Agricultural University, Xinkang Road, Yucheng District, Ya'an 625014, P. R. China
| | - Mengmeng Sun
- College of Science, Sichuan Agricultural University, Xinkang Road, Yucheng District, Ya'an 625014, P. R. China
| | - Yanying Wang
- College of Science, Sichuan Agricultural University, Xinkang Road, Yucheng District, Ya'an 625014, P. R. China
| | - Yuanfeng Zou
- College of Veterinary Medicine, Sichuan Agricultural University, Huimin Road, Wenjiang District, Chengdu 611130, P. R. China
| | - Jian Wang
- College of Science, Sichuan Agricultural University, Xinkang Road, Yucheng District, Ya'an 625014, P. R. China
| | - Hanbing Rao
- College of Science, Sichuan Agricultural University, Xinkang Road, Yucheng District, Ya'an 625014, P. R. China
| |
Collapse
|