1
|
Garcia Santa Cruz B, Slter J, Gomez-Giro G, Saraiva C, Sabate-Soler S, Modamio J, Barmpa K, Schwamborn JC, Hertel F, Jarazo J, Husch A. Generalising from conventional pipelines using deep learning in high-throughput screening workflows. Sci Rep 2022; 12:11465. [PMID: 35794231 PMCID: PMC9259641 DOI: 10.1038/s41598-022-15623-7] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/18/2021] [Accepted: 06/27/2022] [Indexed: 11/09/2022] Open
Abstract
The study of complex diseases relies on large amounts of data to build models toward precision medicine. Such data acquisition is feasible in the context of high-throughput screening, in which the quality of the results relies on the accuracy of the image analysis. Although state-of-the-art solutions for image segmentation employ deep learning approaches, the high cost of manually generating ground truth labels for model training hampers the day-to-day application in experimental laboratories. Alternatively, traditional computer vision-based solutions do not need expensive labels for their implementation. Our work combines both approaches by training a deep learning network using weak training labels automatically generated with conventional computer vision methods. Our network surpasses the conventional segmentation quality by generalising beyond noisy labels, providing a 25% increase of mean intersection over union, and simultaneously reducing the development and inference times. Our solution was embedded into an easy-to-use graphical user interface that allows researchers to assess the predictions and correct potential inaccuracies with minimal human input. To demonstrate the feasibility of training a deep learning solution on a large dataset of noisy labels automatically generated by a conventional pipeline, we compared our solution against the common approach of training a model from a small manually curated dataset by several experts. Our work suggests that humans perform better in context interpretation, such as error assessment, while computers outperform in pixel-by-pixel fine segmentation. Such pipelines are illustrated with a case study on image segmentation for autophagy events. This work aims for better translation of new technologies to real-world settings in microscopy-image analysis.
Collapse
Affiliation(s)
- Beatriz Garcia Santa Cruz
- National Department of Neurosurgery, Centre Hospitalier de Luxembourg, 4, Rue Ernest Barble, 1210, Luxembourg (City), Luxembourg. .,Interventional Neuroscience Group, Luxembourg Center for Systems Biomedicine, University of Luxembourg, 6, Avenue du Swing, 4367, Belvaux, Luxembourg.
| | - Jan Slter
- Interventional Neuroscience Group, Luxembourg Center for Systems Biomedicine, University of Luxembourg, 6, Avenue du Swing, 4367, Belvaux, Luxembourg
| | - Gemma Gomez-Giro
- Developmental and Cellular Biology, Luxembourg Center for Systems Biomedicine, University of Luxembourg, 6, Avenue du Swing, 4367, Belvaux, Luxembourg
| | - Claudia Saraiva
- Developmental and Cellular Biology, Luxembourg Center for Systems Biomedicine, University of Luxembourg, 6, Avenue du Swing, 4367, Belvaux, Luxembourg
| | - Sonia Sabate-Soler
- Developmental and Cellular Biology, Luxembourg Center for Systems Biomedicine, University of Luxembourg, 6, Avenue du Swing, 4367, Belvaux, Luxembourg
| | - Jennifer Modamio
- Developmental and Cellular Biology, Luxembourg Center for Systems Biomedicine, University of Luxembourg, 6, Avenue du Swing, 4367, Belvaux, Luxembourg
| | - Kyriaki Barmpa
- Developmental and Cellular Biology, Luxembourg Center for Systems Biomedicine, University of Luxembourg, 6, Avenue du Swing, 4367, Belvaux, Luxembourg
| | - Jens Christian Schwamborn
- Developmental and Cellular Biology, Luxembourg Center for Systems Biomedicine, University of Luxembourg, 6, Avenue du Swing, 4367, Belvaux, Luxembourg
| | - Frank Hertel
- National Department of Neurosurgery, Centre Hospitalier de Luxembourg, 4, Rue Ernest Barble, 1210, Luxembourg (City), Luxembourg.,Interventional Neuroscience Group, Luxembourg Center for Systems Biomedicine, University of Luxembourg, 6, Avenue du Swing, 4367, Belvaux, Luxembourg
| | - Javier Jarazo
- Developmental and Cellular Biology, Luxembourg Center for Systems Biomedicine, University of Luxembourg, 6, Avenue du Swing, 4367, Belvaux, Luxembourg.,OrganoTherapeutics SARL, 6A, avenue des Hauts-Fourneaux, 4365, Esch-sur-Alzette, Luxembourg
| | - Andreas Husch
- Interventional Neuroscience Group, Luxembourg Center for Systems Biomedicine, University of Luxembourg, 6, Avenue du Swing, 4367, Belvaux, Luxembourg. .,Systems Control Group, Luxembourg Centere for Systems Biomedicine, University of Luxembourg, 6, Avenue du Swing, 4367, Belvaux, Luxembourg.
| |
Collapse
|
2
|
Sabate-Soler S, Nickels SL, Saraiva C, Berger E, Dubonyte U, Barmpa K, Lan YJ, Kouno T, Jarazo J, Robertson G, Sharif J, Koseki H, Thome C, Shin JW, Cowley SA, Schwamborn JC. Microglia integration into human midbrain organoids leads to increased neuronal maturation and functionality. Glia 2022; 70:1267-1288. [PMID: 35262217 PMCID: PMC9314680 DOI: 10.1002/glia.24167] [Citation(s) in RCA: 33] [Impact Index Per Article: 16.5] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/21/2022] [Revised: 02/25/2022] [Accepted: 02/28/2022] [Indexed: 01/29/2023]
Abstract
The human brain is a complex, three-dimensional structure. To better recapitulate brain complexity, recent efforts have focused on the development of human-specific midbrain organoids. Human iPSC-derived midbrain organoids consist of differentiated and functional neurons, which contain active synapses, as well as astrocytes and oligodendrocytes. However, the absence of microglia, with their ability to remodel neuronal networks and phagocytose apoptotic cells and debris, represents a major disadvantage for the current midbrain organoid systems. Additionally, neuroinflammation-related disease modeling is not possible in the absence of microglia. So far, no studies about the effects of human iPSC-derived microglia on midbrain organoid neural cells have been published. Here we describe an approach to derive microglia from human iPSCs and integrate them into iPSC-derived midbrain organoids. Using single nuclear RNA Sequencing, we provide a detailed characterization of microglia in midbrain organoids as well as the influence of their presence on the other cells of the organoids. Furthermore, we describe the effects that microglia have on cell death and oxidative stress-related gene expression. Finally, we show that microglia in midbrain organoids affect synaptic remodeling and increase neuronal excitability. Altogether, we show a more suitable system to further investigate brain development, as well as neurodegenerative diseases and neuroinflammation.
Collapse
Affiliation(s)
- Sonia Sabate-Soler
- Luxembourg Centre for Systems Biomedicine (LCSB), Developmental and Cellular Biology, University of Luxembourg, Belvaux, Luxembourg
| | - Sarah Louise Nickels
- Luxembourg Centre for Systems Biomedicine (LCSB), Developmental and Cellular Biology, University of Luxembourg, Belvaux, Luxembourg
| | - Cláudia Saraiva
- Luxembourg Centre for Systems Biomedicine (LCSB), Developmental and Cellular Biology, University of Luxembourg, Belvaux, Luxembourg
| | - Emanuel Berger
- Luxembourg Centre for Systems Biomedicine (LCSB), Developmental and Cellular Biology, University of Luxembourg, Belvaux, Luxembourg
| | - Ugne Dubonyte
- Luxembourg Centre for Systems Biomedicine (LCSB), Developmental and Cellular Biology, University of Luxembourg, Belvaux, Luxembourg
| | - Kyriaki Barmpa
- Luxembourg Centre for Systems Biomedicine (LCSB), Developmental and Cellular Biology, University of Luxembourg, Belvaux, Luxembourg
| | - Yan Jun Lan
- Center for Integrative Medical Sciences, RIKEN, Yokohama, Kanagawa, Japan.,ETH Zurich, Institute of Pharmaceutical Sciences, Zurich, Switzerland
| | - Tsukasa Kouno
- Center for Integrative Medical Sciences, RIKEN, Yokohama, Kanagawa, Japan
| | - Javier Jarazo
- Luxembourg Centre for Systems Biomedicine (LCSB), Developmental and Cellular Biology, University of Luxembourg, Belvaux, Luxembourg.,OrganoTherapeutics SARL-S, Esch-sur-Alzette, Luxembourg
| | - Graham Robertson
- Luxembourg Centre for Systems Biomedicine (LCSB), Developmental and Cellular Biology, University of Luxembourg, Belvaux, Luxembourg
| | - Jafar Sharif
- Center for Integrative Medical Sciences, RIKEN, Yokohama, Kanagawa, Japan
| | - Haruhiko Koseki
- Center for Integrative Medical Sciences, RIKEN, Yokohama, Kanagawa, Japan
| | - Christian Thome
- Institute of Physiology and Pathophysiology, Heidelberg University, Heidelberg, Germany
| | - Jay W Shin
- Center for Integrative Medical Sciences, RIKEN, Yokohama, Kanagawa, Japan
| | - Sally A Cowley
- Oxford Parkinson's Disease Centre, James Martin Stem Cell Facility, Sir William Dunn School of Pathology, University of Oxford, Oxford, UK
| | - Jens C Schwamborn
- Luxembourg Centre for Systems Biomedicine (LCSB), Developmental and Cellular Biology, University of Luxembourg, Belvaux, Luxembourg
| |
Collapse
|
3
|
Zagare A, Barmpa K, Smajic S, Smits LM, Grzyb K, Grünewald A, Skupin A, Nickels SL, Schwamborn JC. Midbrain organoids mimic early embryonic neurodevelopment and recapitulate LRRK2-p.Gly2019Ser-associated gene expression. Am J Hum Genet 2022; 109:311-327. [PMID: 35077669 PMCID: PMC8874228 DOI: 10.1016/j.ajhg.2021.12.009] [Citation(s) in RCA: 16] [Impact Index Per Article: 8.0] [Reference Citation Analysis] [What about the content of this article? (0)] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/14/2021] [Accepted: 12/13/2021] [Indexed: 12/20/2022] Open
Abstract
Human brain organoid models that recapitulate the physiology and complexity of the human brain have a great potential for in vitro disease modeling, in particular for neurodegenerative diseases, such as Parkinson disease. In the present study, we compare single-cell RNA-sequencing data of human midbrain organoids to the developing human embryonic midbrain. We demonstrate that the in vitro model is comparable to its in vivo equivalents in terms of developmental path and cellular composition. Moreover, we investigate the potential of midbrain organoids for modeling early developmental changes in Parkinson disease. Therefore, we compare the single-cell RNA-sequencing data of healthy-individual-derived midbrain organoids to their isogenic LRRK2-p.Gly2019Ser-mutant counterparts. We show that the LRRK2 p.Gly2019Ser variant alters neurodevelopment, resulting in an untimely and incomplete differentiation with reduced cellular variability. Finally, we present four candidate genes, APP, DNAJC6, GATA3, and PTN, that might contribute to the LRRK2-p.Gly2019Ser-associated transcriptome changes that occur during early neurodevelopment.
Collapse
|
4
|
Jarazo J, Barmpa K, Modamio J, Saraiva C, Sabaté-Soler S, Rosety I, Griesbeck A, Skwirblies F, Zaffaroni G, Smits LM, Su J, Arias-Fuenzalida J, Walter J, Gomez-Giro G, Monzel AS, Qing X, Vitali A, Cruciani G, Boussaad I, Brunelli F, Jäger C, Rakovic A, Li W, Yuan L, Berger E, Arena G, Bolognin S, Schmidt R, Schröder C, Antony PMA, Klein C, Krüger R, Seibler P, Schwamborn JC. Parkinson's Disease Phenotypes in Patient Neuronal Cultures and Brain Organoids Improved by 2-Hydroxypropyl-β-Cyclodextrin Treatment. Mov Disord 2021; 37:80-94. [PMID: 34637165 PMCID: PMC9291890 DOI: 10.1002/mds.28810] [Citation(s) in RCA: 20] [Impact Index Per Article: 6.7] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/04/2021] [Revised: 09/07/2021] [Accepted: 09/10/2021] [Indexed: 12/13/2022] Open
Abstract
Background The etiology of Parkinson's disease (PD) is only partially understood despite the fact that environmental causes, risk factors, and specific gene mutations are contributors to the disease. Biallelic mutations in the phosphatase and tensin homolog (PTEN)‐induced putative kinase 1 (PINK1) gene involved in mitochondrial homeostasis, vesicle trafficking, and autophagy are sufficient to cause PD. Objectives We sought to evaluate the difference between controls' and PINK1 patients' derived neurons in their transition from neuroepithelial stem cells to neurons, allowing us to identify potential pathways to target with repurposed compounds. Methods Using two‐dimensional and three‐dimensional models of patients' derived neurons we recapitulated PD‐related phenotypes. We introduced the usage of midbrain organoids for testing compounds. Using Clustered Regularly Interspaced Short Palindromic Repeats (CRISPR)/CRISPR‐associated protein 9 (Cas9), we corrected the point mutations of three patients' derived cells. We evaluated the effect of the selected compound in a mouse model. Results PD patient‐derived cells presented differences in their energetic profile, imbalanced proliferation, apoptosis, mitophagy, and a reduced differentiation efficiency to tyrosine hydroxylase positive (TH+) neurons compared to controls' cells. Correction of a patient's point mutation ameliorated the metabolic properties and neuronal firing rates as well as reversing the differentiation phenotype, and reducing the increased astrocytic levels. Treatment with 2‐hydroxypropyl‐β‐cyclodextrin increased the autophagy and mitophagy capacity of neurons concomitant with an improved dopaminergic differentiation of patient‐specific neurons in midbrain organoids and ameliorated neurotoxicity in a mouse model. Conclusion We show that treatment with a repurposed compound is sufficient for restoring the impaired dopaminergic differentiation of PD patient‐derived cells. © 2021 The Authors. Movement Disorders published by Wiley Periodicals LLC on behalf of International Parkinson and Movement Disorder Society
Collapse
Affiliation(s)
- Javier Jarazo
- Developmental and Cellular Biology, Luxembourg Centre for Systems Biomedicine University of Luxembourg, Esch-sur-Alzette, Luxembourg.,OrganoTherapeutics société à responsabilité limitée simplifiée (SARL-S), Esch-sur-Alzette, Luxembourg
| | - Kyriaki Barmpa
- Developmental and Cellular Biology, Luxembourg Centre for Systems Biomedicine University of Luxembourg, Esch-sur-Alzette, Luxembourg
| | - Jennifer Modamio
- Developmental and Cellular Biology, Luxembourg Centre for Systems Biomedicine University of Luxembourg, Esch-sur-Alzette, Luxembourg
| | - Cláudia Saraiva
- Developmental and Cellular Biology, Luxembourg Centre for Systems Biomedicine University of Luxembourg, Esch-sur-Alzette, Luxembourg
| | - Sònia Sabaté-Soler
- Developmental and Cellular Biology, Luxembourg Centre for Systems Biomedicine University of Luxembourg, Esch-sur-Alzette, Luxembourg
| | - Isabel Rosety
- Developmental and Cellular Biology, Luxembourg Centre for Systems Biomedicine University of Luxembourg, Esch-sur-Alzette, Luxembourg
| | | | | | - Gaia Zaffaroni
- Institute for Globally Distributed Open Research and Education, Gothenburg, Sweden
| | - Lisa M Smits
- Developmental and Cellular Biology, Luxembourg Centre for Systems Biomedicine University of Luxembourg, Esch-sur-Alzette, Luxembourg
| | - Jihui Su
- Institute of Health Sciences, China Medical University, Shenyang, China
| | - Jonathan Arias-Fuenzalida
- Developmental and Cellular Biology, Luxembourg Centre for Systems Biomedicine University of Luxembourg, Esch-sur-Alzette, Luxembourg
| | - Jonas Walter
- Developmental and Cellular Biology, Luxembourg Centre for Systems Biomedicine University of Luxembourg, Esch-sur-Alzette, Luxembourg
| | - Gemma Gomez-Giro
- Developmental and Cellular Biology, Luxembourg Centre for Systems Biomedicine University of Luxembourg, Esch-sur-Alzette, Luxembourg
| | - Anna S Monzel
- Developmental and Cellular Biology, Luxembourg Centre for Systems Biomedicine University of Luxembourg, Esch-sur-Alzette, Luxembourg
| | - Xiaobing Qing
- Developmental and Cellular Biology, Luxembourg Centre for Systems Biomedicine University of Luxembourg, Esch-sur-Alzette, Luxembourg
| | - Armelle Vitali
- Translational Neuroscience, Luxembourg Centre for Systems Biomedicine University of Luxembourg, Esch-sur-Alzette, Luxembourg
| | - Gerald Cruciani
- Translational Neuroscience, Luxembourg Centre for Systems Biomedicine University of Luxembourg, Esch-sur-Alzette, Luxembourg.,Disease Modeling and Screening Platform, Luxembourg Institute of Systems Biomedicine, University of Luxembourg and Luxembourg Institute of Health, Belvaux, Luxembourg
| | - Ibrahim Boussaad
- Translational Neuroscience, Luxembourg Centre for Systems Biomedicine University of Luxembourg, Esch-sur-Alzette, Luxembourg.,Disease Modeling and Screening Platform, Luxembourg Institute of Systems Biomedicine, University of Luxembourg and Luxembourg Institute of Health, Belvaux, Luxembourg
| | | | - Christian Jäger
- Metabolomics Platform, Enzymology and Metabolism, Luxembourg Centre for Systems Biomedicine University of Luxembourg, Esch-sur-Alzette, Luxembourg
| | | | - Wen Li
- Institute of Health Sciences, China Medical University, Shenyang, China
| | - Lin Yuan
- Institute of Health Sciences, China Medical University, Shenyang, China
| | - Emanuel Berger
- Developmental and Cellular Biology, Luxembourg Centre for Systems Biomedicine University of Luxembourg, Esch-sur-Alzette, Luxembourg
| | - Giuseppe Arena
- Translational Neuroscience, Luxembourg Centre for Systems Biomedicine University of Luxembourg, Esch-sur-Alzette, Luxembourg
| | - Silvia Bolognin
- Developmental and Cellular Biology, Luxembourg Centre for Systems Biomedicine University of Luxembourg, Esch-sur-Alzette, Luxembourg
| | | | | | - Paul M A Antony
- Translational Neuroscience, Luxembourg Centre for Systems Biomedicine University of Luxembourg, Esch-sur-Alzette, Luxembourg
| | - Christine Klein
- Institute of Neurogenetics, University of Lübeck, Lübeck, Germany
| | - Rejko Krüger
- Translational Neuroscience, Luxembourg Centre for Systems Biomedicine University of Luxembourg, Esch-sur-Alzette, Luxembourg.,Centre Hospitalier de Luxembourg, Parkinson Research Clinic, Luxembourg, Luxembourg.,Transversal Translational Medicine, Luxembourg Institute of Health, Strassen, Luxembourg
| | - Philip Seibler
- Institute of Neurogenetics, University of Lübeck, Lübeck, Germany
| | - Jens C Schwamborn
- Developmental and Cellular Biology, Luxembourg Centre for Systems Biomedicine University of Luxembourg, Esch-sur-Alzette, Luxembourg
| |
Collapse
|