Anatole Chessel
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Anatole Chessel has a total of 216 co-authors. Here are the top co-authors by number of shared publications:
- Rafael Edgardo Carazo Salas
School of Cellular & Molecular Medicine, University of Bristol, BS8 1TD Bristol, UK
14 shared publications - Emmanuel Beaurepaire
Laboratoire d’Optique et Biosciences, Ecole polytechnique, CNRS, INSERM, Institut Polytechnique de Paris, Palaiseau, France
7 shared publications James Dodgson
The Gurdon Institute, University of Cambridge
5 shared publications- Attila Csikász-Nagy
Faculty of Information Technology and Bionics, Pázmány Péter Catholic University, Budapest, Hungary
4 shared publications - Ignacio Arganda-Carreras
Dept. of Computer Science and Artificial Intelligence, University of the Basque Country (UPV/EHU), San Sebastian, Spain
4 shared publications Marco Geymonat
The Gurdon Institute, University of Cambridge
4 shared publications
Latest Publications
- Open Access
- 3 November 2026
- Published by IOP Publishing in Biofabrication
- Vol. 18 (4) , 045020
Improved quality and reproducibility of cerebral cortical organoids under microfluidic culture conditions: a proof-of-concept study
Cerebral organoids have emerged as advanced three-dimensional in vitro models capable of recapitulating essential aspects of human brain development, thereby offering new opportunities for studying brain physiology and disease. Nonetheless, their use in preclinical settings remains limited by their high variability. Microfluidic devices offer a promising alternative to conventional culture supports by enabling improved recapitulation of the cellular microenvironment; however, most cerebral organoids-on-chips rely on custom-made academic prototypes, limiting their scalability and translatability. Here, we established a standardized brain organoid-on-chip model by combining a regionalized cortical organoid differentiation protocol with a commercially available microfluidic device (Duplex™, NETRI). Cortical organoid quality and reproducibility were evaluated using a previously established multi-criteria Quality Control (QC) framework based on a scoring system. To enhance objectivity and throughput, the non-invasive morphometric QC criteria were automated using deep learning-based image analysis. Using a single human induced pluripotent stem cell (hiPSC) line, we assessed whether microfluidic culture conditions could improve the quality and reproducibility of cortical organoids within a controlled genetic background. Compared with conventional cultures, on-chip cortical organoids displayed improved inter- and intra-batch reproducibility across multiple scales, including morphology, size, cytoarchitectural organization, and transcript expression, together with higher QC scores and reduced QC failure rates. Finally, the QC framework was adapted for neurotoxicity assessment using a decision tree to classify compounds according to their neurotoxic risk. While this study represents a proof-of-concept demonstration within a single genetic background, the integrated brain organoid-on-chip platform and standardized QC evaluations provide a flexible and translatable approach for preclinical and industrial studies and support future validation across multiple hiPSC lines.
- 3 November 2026
- Published by IOP Publishing in Biofabrication
- Vol. 18 (4) , 045020
Open AccessImproved quality and reproducibility of cerebral cortical organoids under microfluidic culture conditions: a proof-of-concept study
Cerebral organoids have emerged as advanced three-dimensional in vitro models capable of recapitulating essential aspects of human brain development, thereby offering new opportunities for studying brain physiology and disease. Nonetheless, their use in preclinical settings remains limited by their high variability. Microfluidic devices offer a promising alternative to conventional culture supports by enabling improved recapitulation of the cellular microenvironment; however, most cerebral organoids-on-chips rely on custom-made academic prototypes, limiting their scalability and translatability. Here, we established a standardized brain organoid-on-chip model by combining a regionalized cortical organoid differentiation protocol with a commercially available microfluidic device (Duplex™, NETRI). Cortical organoid quality and reproducibility were evaluated using a previously established multi-criteria Quality Control (QC) framework based on a scoring system. To enhance objectivity and throughput, the non-invasive morphometric QC criteria were automated using deep learning-based image analysis. Using a single human induced pluripotent stem cell (hiPSC) line, we assessed whether microfluidic culture conditions could improve the quality and reproducibility of cortical organoids within a controlled genetic background. Compared with conventional cultures, on-chip cortical organoids displayed improved inter- and intra-batch reproducibility across multiple scales, including morphology, size, cytoarchitectural organization, and transcript expression, together with higher QC scores and reduced QC failure rates. Finally, the QC framework was adapted for neurotoxicity assessment using a decision tree to classify compounds according to their neurotoxic risk. While this study represents a proof-of-concept demonstration within a single genetic background, the integrated brain organoid-on-chip platform and standardized QC evaluations provide a flexible and translatable approach for preclinical and industrial studies and support future validation across multiple hiPSC lines.
- Open Access
- 22 October 2026
- Published by Public Library of Science (PLoS) in PLOS ONE
- Vol. 21 (10) , e0328320
Machine learning quantitative OCT derived fibrosis indicators for corneal haze evaluation
Photorefractive Keratectomy (PRK) is a widely used laser-assisted refractive surgical technique. In some cases, it leads to temporary subepithelial fibrosis linked to visual haze, but objective and quantitative tools to monitor these symptoms are lacking. We here present a machine learning-based method for the classification of corneal images from spectral domain optical coherence tomography images recorded in vivo on standard clinical devices and use it to extract quantitative fibrosis indicators. Because of the transient nature and relative rarity of significant post-PRK haze, we trained the model on corneas presenting Fuchs’ Endothelial Corneal Dystrophy, causing similar, but permanent, fibrotic changes, and applied it to images from patients who have undergone PRK surgery. Our study shows that the model output (probability of pathological classification) combined with OCT-derived quantitative fibrosis descriptors provides an interpretable and explainable indicator of corneal healing for post-operative follow-up.
- 22 October 2026
- Published by Public Library of Science (PLoS) in PLOS ONE
- Vol. 21 (10) , e0328320
Open AccessMachine learning quantitative OCT derived fibrosis indicators for corneal haze evaluation
Photorefractive Keratectomy (PRK) is a widely used laser-assisted refractive surgical technique. In some cases, it leads to temporary subepithelial fibrosis linked to visual haze, but objective and quantitative tools to monitor these symptoms are lacking. We here present a machine learning-based method for the classification of corneal images from spectral domain optical coherence tomography images recorded in vivo on standard clinical devices and use it to extract quantitative fibrosis indicators. Because of the transient nature and relative rarity of significant post-PRK haze, we trained the model on corneas presenting Fuchs’ Endothelial Corneal Dystrophy, causing similar, but permanent, fibrotic changes, and applied it to images from patients who have undergone PRK surgery. Our study shows that the model output (probability of pathological classification) combined with OCT-derived quantitative fibrosis descriptors provides an interpretable and explainable indicator of corneal healing for post-operative follow-up.
- Open Access
- 23 November 2025
- Published by Springer Nature in Communications Biology
- Vol. 8 (1)
Label-free nonlinear microscopy probes cellular metabolism and myelin dynamics in live tissue
Metabolic coupling between neurons and glial cells plays a critical role in brain activity and myelin plasticity. Understanding its role in physiological and pathological contexts requires advanced methods to map metabolism and myelin in live tissue with high spatiotemporal resolution. Here, we present a label-free, multimodal, nonlinear optical microscopy platform integrated with an advanced image processing framework that simultaneously maps cellular metabolism and myelin distribution in organotypic cerebellar cultures. We combine third-harmonic generation microscopy for high-resolution myelin imaging with single axon precision with two-photon fluorescence lifetime microscopy of NAD(P)H metabolic biomarker to assess redox states with single-cell resolution. We introduce automated image analysis methods for cell segmentation and myelinated axon detection, enabling quantitative metabolic and myelin assessment in intact tissue during experimental myelination, demyelination and remyelination. Using this framework, we map the 3D myelin distribution in cerebellar folia and identify distinct metabolic signatures in neurons, oligodendrocytes, and microglia. Furthermore, we measure a metabolic shift in microglia along with myelin distribution changes during experimental demyelination. In conclusion, we establish label-free optical imaging as a powerful tool for the non-invasive characterization of neuro-glial metabolic coupling and myelin organization in living brain tissue, opening new perspectives for research in neuroinflammation and neurodegeneration.
- 23 November 2025
- Published by Springer Nature in Communications Biology
- Vol. 8 (1)
Open AccessLabel-free nonlinear microscopy probes cellular metabolism and myelin dynamics in live tissue
Metabolic coupling between neurons and glial cells plays a critical role in brain activity and myelin plasticity. Understanding its role in physiological and pathological contexts requires advanced methods to map metabolism and myelin in live tissue with high spatiotemporal resolution. Here, we present a label-free, multimodal, nonlinear optical microscopy platform integrated with an advanced image processing framework that simultaneously maps cellular metabolism and myelin distribution in organotypic cerebellar cultures. We combine third-harmonic generation microscopy for high-resolution myelin imaging with single axon precision with two-photon fluorescence lifetime microscopy of NAD(P)H metabolic biomarker to assess redox states with single-cell resolution. We introduce automated image analysis methods for cell segmentation and myelinated axon detection, enabling quantitative metabolic and myelin assessment in intact tissue during experimental myelination, demyelination and remyelination. Using this framework, we map the 3D myelin distribution in cerebellar folia and identify distinct metabolic signatures in neurons, oligodendrocytes, and microglia. Furthermore, we measure a metabolic shift in microglia along with myelin distribution changes during experimental demyelination. In conclusion, we establish label-free optical imaging as a powerful tool for the non-invasive characterization of neuro-glial metabolic coupling and myelin organization in living brain tissue, opening new perspectives for research in neuroinflammation and neurodegeneration.
- Open Access
- 28 July 2025
- Published by Springer Nature in Research Square
Fgfr3–Wnt signaling crosstalk is involved in maintaining cranial suture integrity.
Cranial suture formation is a dynamic process that requires precise cellular and molecular coordination to regulate bone growth and maintain suture homeostasis. The Fibroblast Growth Factor Receptor 3 (FGFR3) signaling pathway is among the major pathways disrupted in craniosynostosis; however, its precise role during cranial suture formation is still unknown. Using a relevant fgfr3 loss-of-function zebrafish model exhibiting abnormal suture morphology, we demonstrated for the first time that Fgfr3 plays a pleiotropic role in both the formation and maintenance of cranial sutures. Transmission electron microscopy and second harmonic generation imaging revealed that Fgfr3 is essential for the proper organization of the collagen network within the suture. Using specific transgenic reporter lines, we showed that Fgfr3 is crucial for regulating osteogenesis in this region. Specifically, Fgfr3 limits the number of osteoprogenitors at the osteogenic front and promotes osteoblast maturation at the suture edge. RNAscope analyses further revealed that loss of Fgfr3 led to significant upregulation of fgf18 expression and downregulation of the BMP antagonist grem1 within the suture. Finally, we investigated the Wnt/β-catenin signaling pathway and observed a marked overactivation in mutants compared to controls, notably evidenced by an upregulation of axin2. Pharmacological inhibition of this pathway during cranial suture development, using the β-catenin inhibitor XAV939, restored fgf18 expression, partially normalized grem1 levels, and led to a significant improvement in cranial suture morphology. In conclusion, these findings position Fgfr3 as a central regulator of cranial suture formation and homeostasis, acting through intricate cross-talk between the FGF, canonical Wnt, and possibly BMP signaling pathways. These data offer new insights into the biology of cranial suture and FGFR3-related craniosynostoses.
- 28 July 2025
- Published by Springer Nature in Research Square
Open AccessFgfr3–Wnt signaling crosstalk is involved in maintaining cranial suture integrity.
Cranial suture formation is a dynamic process that requires precise cellular and molecular coordination to regulate bone growth and maintain suture homeostasis. The Fibroblast Growth Factor Receptor 3 (FGFR3) signaling pathway is among the major pathways disrupted in craniosynostosis; however, its precise role during cranial suture formation is still unknown. Using a relevant fgfr3 loss-of-function zebrafish model exhibiting abnormal suture morphology, we demonstrated for the first time that Fgfr3 plays a pleiotropic role in both the formation and maintenance of cranial sutures. Transmission electron microscopy and second harmonic generation imaging revealed that Fgfr3 is essential for the proper organization of the collagen network within the suture. Using specific transgenic reporter lines, we showed that Fgfr3 is crucial for regulating osteogenesis in this region. Specifically, Fgfr3 limits the number of osteoprogenitors at the osteogenic front and promotes osteoblast maturation at the suture edge. RNAscope analyses further revealed that loss of Fgfr3 led to significant upregulation of fgf18 expression and downregulation of the BMP antagonist grem1 within the suture. Finally, we investigated the Wnt/β-catenin signaling pathway and observed a marked overactivation in mutants compared to controls, notably evidenced by an upregulation of axin2. Pharmacological inhibition of this pathway during cranial suture development, using the β-catenin inhibitor XAV939, restored fgf18 expression, partially normalized grem1 levels, and led to a significant improvement in cranial suture morphology. In conclusion, these findings position Fgfr3 as a central regulator of cranial suture formation and homeostasis, acting through intricate cross-talk between the FGF, canonical Wnt, and possibly BMP signaling pathways. These data offer new insights into the biology of cranial suture and FGFR3-related craniosynostoses.
- Open Access
- 23 July 2025
- Published by Wolters Kluwer Health in Cornea
- Vol. 45 (7) , 840-850
Machine Learning Model for Predicting Visual Acuity Improvement After Intrastromal Corneal Ring Surgery in Patients With Keratoconus
Background: Keratoconus is a progressive, degenerative corneal disease that can lead to significant visual impairment. The intrastromal ring segment implantation procedure is effective in reshaping the cornea and improving vision. However, vision does not improve postoperatively in all operated eyes, and the results vary widely among patients, making it challenging to predict postoperative visual gain. Purpose: This study investigated the potential of machine learning in predicting postoperative visual acuity in keratoconus patients undergoing intrastromal ring segment implantation with the aim of enhancing surgical decision-making. Methods: This retrospective study analyzed 120 eyes of 102 patients with keratoconus who underwent ring segment implantation (1 symmetric or asymmetric segment, 150–300 μm thick, 150 degrees, or 160 degrees-arc). Preoperative and postoperative refraction, corneal topography, and tomographic data were collected. Various models were trained to predict postoperative visual acuity improvements. Results: The models demonstrated excellent performance, with XGBoost achieving perfect results in predicting whether vision will improve after surgery (R 2 = 1.0, Youden Index = 1.0; all test observations being correctly classified). The CatBoost model achieved an R 2 of 0.59 [0.7-line mean absolute error (MAE)] for predicting postoperative visual acuity, an R 2 of 0.76 (MAE, 1.08 D) for predicting keratometry, and an R 2 of 0.54 (MAE, 0.29) for predicting corneal asphericity. Key features for accurate predictions included preoperative keratometry values (K1, K2, Kmax), corneal asphericity, and visual acuity, whereas segment characteristics featured low importance. Conclusions: This study shows the strong potential of machine learning for selecting candidates for surgery and predicting postoperative visual improvements after ring segment implantation in keratoconus eyes.
- 23 July 2025
- Published by Wolters Kluwer Health in Cornea
- Vol. 45 (7) , 840-850
Open AccessMachine Learning Model for Predicting Visual Acuity Improvement After Intrastromal Corneal Ring Surgery in Patients With Keratoconus
Background: Keratoconus is a progressive, degenerative corneal disease that can lead to significant visual impairment. The intrastromal ring segment implantation procedure is effective in reshaping the cornea and improving vision. However, vision does not improve postoperatively in all operated eyes, and the results vary widely among patients, making it challenging to predict postoperative visual gain. Purpose: This study investigated the potential of machine learning in predicting postoperative visual acuity in keratoconus patients undergoing intrastromal ring segment implantation with the aim of enhancing surgical decision-making. Methods: This retrospective study analyzed 120 eyes of 102 patients with keratoconus who underwent ring segment implantation (1 symmetric or asymmetric segment, 150–300 μm thick, 150 degrees, or 160 degrees-arc). Preoperative and postoperative refraction, corneal topography, and tomographic data were collected. Various models were trained to predict postoperative visual acuity improvements. Results: The models demonstrated excellent performance, with XGBoost achieving perfect results in predicting whether vision will improve after surgery (R 2 = 1.0, Youden Index = 1.0; all test observations being correctly classified). The CatBoost model achieved an R 2 of 0.59 [0.7-line mean absolute error (MAE)] for predicting postoperative visual acuity, an R 2 of 0.76 (MAE, 1.08 D) for predicting keratometry, and an R 2 of 0.54 (MAE, 0.29) for predicting corneal asphericity. Key features for accurate predictions included preoperative keratometry values (K1, K2, Kmax), corneal asphericity, and visual acuity, whereas segment characteristics featured low importance. Conclusions: This study shows the strong potential of machine learning for selecting candidates for surgery and predicting postoperative visual improvements after ring segment implantation in keratoconus eyes.
- Open Access
Explainable machine learning for post PKR surgery follow-up
Photorefractive Keratectomy (PRK) is a widely used laser-assisted refractive surgical technique. In some cases, it leads to temporary subepithelial inflammation or fibrosis linked to visual haze. There are to our knowledge no physics based and quantitative tools to monitor these symptoms. We here present a comprehensive machine learning-based algorithm for the detection of fibrosis based on spectral domain optical coherence tomography images recorded in vivo on standard clinical devices. Because of the rarity of these phenomena, we trained the model on corneas presenting Fuchs’ dystrophy causing similar, but permanent, fibrosis symptoms, and applied it to images from patients who have undergone PRK surgery. Our study shows that the model output (probability of Fuchs’ dystrophy classification) provides a quantified and explainable indicator of corneal healing for post-operative follow-up.
Open AccessExplainable machine learning for post PKR surgery follow-up
Photorefractive Keratectomy (PRK) is a widely used laser-assisted refractive surgical technique. In some cases, it leads to temporary subepithelial inflammation or fibrosis linked to visual haze. There are to our knowledge no physics based and quantitative tools to monitor these symptoms. We here present a comprehensive machine learning-based algorithm for the detection of fibrosis based on spectral domain optical coherence tomography images recorded in vivo on standard clinical devices. Because of the rarity of these phenomena, we trained the model on corneas presenting Fuchs’ dystrophy causing similar, but permanent, fibrosis symptoms, and applied it to images from patients who have undergone PRK surgery. Our study shows that the model output (probability of Fuchs’ dystrophy classification) provides a quantified and explainable indicator of corneal healing for post-operative follow-up.
- 29 April 2025
- Published by Springer Nature in Nature Methods
- Vol. 22 (6) , 1124-1126
BiaPy: accessible deep learning on bioimages
- 29 April 2025
- Published by Springer Nature in Nature Methods
- Vol. 22 (6) , 1124-1126
BiaPy: accessible deep learning on bioimages
- Open Access
Cranial suture integrity is maintained by Fgfr3 in zebrafish
Cranial suture formation is a dynamic process requiring precise cellular and molecular coordination to regulate bone growth and suture homeostasis. Despite the recognized role of Fibroblast Growth Factor Receptor 3 (FGFR3) in this process and its association with Muenke syndrome, one of the most common syndromic craniosynostoses, its precise function remains undefined. Through analyses of cranial suture formation and maintenance in a fgfr3 LoF zebrafish model displaying abnormal suture morphology, we demonstrate for the first time that Fgfr3 plays a pleiotropic role during these events. Transmission electron microscopy and second harmonic generation imaging revealed that Fgfr3 is involved in the proper organization of the collagen network within the suture. By employing specific transgenic reporter lines and studying gene expression of suture mesenchymal stem cell markers via RNAscope in situ hybridization, we show that Fgfr3 is crucial for regulating osteogenesis within the suture. Specifically, Fgfr3 limits the number of osteoprogenitors at the osteogenic front and promotes osteoblast maturation at the suture edge. Finally, our results reveal that Fgfr3-mediated regulation of osteogenesis involves cross-talk between FGF, canonical Wnt, and potentially BMP signaling pathways. In conclusion, these data position Fgfr3 as a central regulator of cranial suture formation and open new perspectives for understanding suture homeostasis and FGFR3-related craniosynostoses.
Open AccessCranial suture integrity is maintained by Fgfr3 in zebrafish
Cranial suture formation is a dynamic process requiring precise cellular and molecular coordination to regulate bone growth and suture homeostasis. Despite the recognized role of Fibroblast Growth Factor Receptor 3 (FGFR3) in this process and its association with Muenke syndrome, one of the most common syndromic craniosynostoses, its precise function remains undefined. Through analyses of cranial suture formation and maintenance in a fgfr3 LoF zebrafish model displaying abnormal suture morphology, we demonstrate for the first time that Fgfr3 plays a pleiotropic role during these events. Transmission electron microscopy and second harmonic generation imaging revealed that Fgfr3 is involved in the proper organization of the collagen network within the suture. By employing specific transgenic reporter lines and studying gene expression of suture mesenchymal stem cell markers via RNAscope in situ hybridization, we show that Fgfr3 is crucial for regulating osteogenesis within the suture. Specifically, Fgfr3 limits the number of osteoprogenitors at the osteogenic front and promotes osteoblast maturation at the suture edge. Finally, our results reveal that Fgfr3-mediated regulation of osteogenesis involves cross-talk between FGF, canonical Wnt, and potentially BMP signaling pathways. In conclusion, these data position Fgfr3 as a central regulator of cranial suture formation and open new perspectives for understanding suture homeostasis and FGFR3-related craniosynostoses.
- Open Access
- 6 March 2024
- Published by American Physical Society (APS) in Physical Review X
- Vol. 14 (1) , 011038
Modeling and Predicting Second-Harmonic Generation from Protein Molecular Structure
Polarization resolved second-harmonic generation (pSHG) microscopy is increasingly used for mapping organized arrays of noncentrosymmetric proteins such as collagen, myosin, and tubulin, and holds potential for probing their molecular structure and supramolecular organization in intact tissues. However, the contrast mechanism of pSHG is complex and the development of applications in the life sciences is hampered by the lack of models accurately relating the observed pSHG signals to the underlying molecular and macromolecular organization. In this work, we establish a general multiscale numerical framework relating the micrometer-scale SHG measurements to the atomic-scale and molecular structure of the proteins under study and their supramolecular arrangement. We first develop a new method to automatically analyze pSHG signals independently of the protein type and fiber orientation. We then characterize experimentally pSHG signals in live zebrafish larvae and show that they can be used to distinguish collagen, myosin, and tubulin structures in intact tissues. We then introduce a numerical model that considers the peptide bond (PB) as the elementary SHG source in proteins and takes into account the three-dimensional (3D) distribution of PBs to predict the second-order hyperpolarizability tensor of proteins, as well as the SHG efficiency and pSHG response of an arbitrary macromolecular assembly. We show that this model accurately reproduces pSHG measurements obtained from collagen, myosin, microtubule, and actin structures, revealing the precise dependence of SHG signals on the 3D distribution of PBs within protein assemblies. We then use our model to analyze pSHG from a 3D distribution of microtubule assemblies as a function of out-of-plane angles, angular disorder, and polarity. Finally, we demonstrate that our model predicts SHG from different molecular conformations of tubulin that are highly relevant from a biomedical point of view as associated with microtubules (de)polymerization. By bridging scales from the molecular bonds to the optical wavelength, our model provides an accurate interpretation of SHG signals in terms of protein structure and supramolecular organization.- 6 March 2024
- Published by American Physical Society (APS) in Physical Review X
- Vol. 14 (1) , 011038
Open AccessModeling and Predicting Second-Harmonic Generation from Protein Molecular Structure
Polarization resolved second-harmonic generation (pSHG) microscopy is increasingly used for mapping organized arrays of noncentrosymmetric proteins such as collagen, myosin, and tubulin, and holds potential for probing their molecular structure and supramolecular organization in intact tissues. However, the contrast mechanism of pSHG is complex and the development of applications in the life sciences is hampered by the lack of models accurately relating the observed pSHG signals to the underlying molecular and macromolecular organization. In this work, we establish a general multiscale numerical framework relating the micrometer-scale SHG measurements to the atomic-scale and molecular structure of the proteins under study and their supramolecular arrangement. We first develop a new method to automatically analyze pSHG signals independently of the protein type and fiber orientation. We then characterize experimentally pSHG signals in live zebrafish larvae and show that they can be used to distinguish collagen, myosin, and tubulin structures in intact tissues. We then introduce a numerical model that considers the peptide bond (PB) as the elementary SHG source in proteins and takes into account the three-dimensional (3D) distribution of PBs to predict the second-order hyperpolarizability tensor of proteins, as well as the SHG efficiency and pSHG response of an arbitrary macromolecular assembly. We show that this model accurately reproduces pSHG measurements obtained from collagen, myosin, microtubule, and actin structures, revealing the precise dependence of SHG signals on the 3D distribution of PBs within protein assemblies. We then use our model to analyze pSHG from a 3D distribution of microtubule assemblies as a function of out-of-plane angles, angular disorder, and polarity. Finally, we demonstrate that our model predicts SHG from different molecular conformations of tubulin that are highly relevant from a biomedical point of view as associated with microtubules (de)polymerization. By bridging scales from the molecular bonds to the optical wavelength, our model provides an accurate interpretation of SHG signals in terms of protein structure and supramolecular organization. - Open Access
BiaPy: Accessible deep learning on bioimages
BiaPy is an open-source library and application that streamlines the use of common deep learning approaches for bioimage analysis. Designed to simplify technical complexities, it offers an intuitive interface, zero-code notebooks, and Docker integration, catering to both users and developers. While focused on deep learning workflows for 2D and 3D image data, it enhances performance with multi-GPU capabilities, memory optimization, and scalability for large datasets. Although BiaPy does not encompass all aspects of bioimage analysis, such as visualization and manual annotation tools, it empowers researchers by providing a ready-to-use environment with customizable templates that facilitate sophisticated bioimage analysis workflows.
Open AccessBiaPy: Accessible deep learning on bioimages
BiaPy is an open-source library and application that streamlines the use of common deep learning approaches for bioimage analysis. Designed to simplify technical complexities, it offers an intuitive interface, zero-code notebooks, and Docker integration, catering to both users and developers. While focused on deep learning workflows for 2D and 3D image data, it enhances performance with multi-GPU capabilities, memory optimization, and scalability for large datasets. Although BiaPy does not encompass all aspects of bioimage analysis, such as visualization and manual annotation tools, it empowers researchers by providing a ready-to-use environment with customizable templates that facilitate sophisticated bioimage analysis workflows.