A5087265062- Single-cell and spatial transcriptomics
- Cell Image Analysis Techniques
- Gene expression and cancer classification
- Molecular Biology Techniques and Applications
- Control Systems and Identification
- Neural Networks and Applications
- Congenital heart defects research
- Genetics, Aging, and Longevity in Model Organisms
- Metabolomics and Mass Spectrometry Studies
- AI in cancer detection
- Advanced Proteomics Techniques and Applications
- Microbial Community Ecology and Physiology
- Advanced biosensing and bioanalysis techniques
- interferon and immune responses
- Genomics and Chromatin Dynamics
- RNA regulation and disease
- Neuroscience and Neuropharmacology Research
- Geographic Information Systems Studies
- Image Processing Techniques and Applications
- Machine Learning in Bioinformatics
- Advanced Fluorescence Microscopy Techniques
- Medical Image Segmentation Techniques
- Lung Cancer Treatments and Mutations
- RNA modifications and cancer
- Cancer Genomics and Diagnostics
VIB-KU Leuven Center for Brain & Disease Research
2021-2025
KU Leuven
2021-2025
VIB-KU Leuven Center for Cancer Biology
2023-2025
Science for Life Laboratory
2017-2022
Uppsala University
2017-2022
University of Helsinki
2021
Image Intelligence (Sweden)
2018
Identifying cell-type-specific enhancers is critical for developing genetic tools to study the mammalian brain. We organized "Brain Initiative Cell Census Network (BICCN) Challenge: Predicting Functional Type-Specific Enhancers from Cross-Species Multi-Omics" evaluate machine learning and feature-based methods nominating enhancer sequences targeting mouse cortical cell types. Methods were assessed using in vivo data hundreds of adeno-associated virus (AAV)-packaged, retro-orbitally delivered...
Investigations of spatial cellular composition tissue architectures revealed by multiplexed in situ RNA detection often rely on inaccurate cell segmentation or prior biological knowledge from complementary single‐cell sequencing experiments. Here, we present spage2vec, an unsupervised segmentation‐free approach for decrypting the transcriptomic heterogeneity complex tissues at subcellular resolution. Spage2vec represents landscape samples as a graph and leverages powerful machine learning...
Visual assessment of scanned tissue samples and associated molecular markers, such as gene expression, requires easy interactive inspection at multiple resolutions. This smart handling image pyramids efficient distribution different types data across several levels detail.We present TissUUmaps, enabling fast visualization exploration millions points overlaying a sample. TissUUmaps can be used both web service or locally in any computer, regions interest well local statistics extracted shared...
Abstract Background Neuroanatomical compartments of the mouse brain are identified and outlined mainly based on manual annotations samples using features related to tissue cellular morphology, taking advantage publicly available reference atlases. However, this task is challenging since sliced sections rarely perfectly parallel or angled with respect in atlas organs from different individuals may vary size shape requires annotation. With advent situ sequencing technologies automated...
Recently, we have achieved a significant milestone with the creation of Fly Cell Atlas. This single-nuclei atlas encompasses entire fly, covering head and body, in addition to all major organs. catalogs many hundreds cell types, which annotated 250. Thus, large number clusters remain be fully characterized, particular brain. Furthermore, by applying sequencing, information about spatial location cells body possible subcellular localization mRNAs within these is lost. Spatial transcriptomics...
Recently, we have achieved a significant milestone with the creation of Fly Cell Atlas. This single-nuclei atlas encompasses entire fly, covering head and body, in addition to all major organs. catalogs many hundreds cell types, which annotated 250. Thus, large number clusters remain be fully characterized, particular brain. Furthermore, by applying sequencing, information about spatial location cells body possible subcellular localization mRNAs within these is lost. Spatial transcriptomics...
Abstract Recent advances in spatial omics methods are revolutionising biomedical research by enabling detailed molecular analyses of cells and their interactions native state. As most technologies capture only a specific type molecules, there is an unmet need to enable integration multiple spatial-omics datasets. This, however, presents several challenges as these typically operate on separate tissue sections at disparate resolutions. Here, we established multi-omics pipeline co-registration...
Recently, we have achieved a significant milestone with the creation of Fly Cell Atlas. This single-nuclei atlas encompasses entire fly, covering head and body, in addition to all major organs. catalogs many hundreds cell types, which annotated 250. Thus, large number clusters remain be fully characterized, particular brain. Furthermore, by applying sequencing, information about spatial location cells body possible subcellular localization mRNAs within these is lost. Spatial transcriptomics...
Recently, we have achieved a significant milestone with the creation of Fly Cell Atlas. This single-nuclei atlas encompasses entire fly, covering head and body, in addition to all major organs. catalogs hundreds thousands cell types, which annotated 250. still leaves many clusters be fully characterized, particular brain. Furthermore, sequencing, information about spatial location cells mRNAs within these is lost. Here, provide solution this problem. In proof concept study, applied...
Identifying cell type-specific enhancers in the brain is critical to building genetic tools for investigating mammalian brain. Computational methods functional enhancer prediction have been proposed and validated fruit fly not yet We organized 'Brain Initiative Cell Census Network (BICCN) Challenge: Predicting Functional Type-Specific Enhancers from Cross-Species Multi-Omics' assess machine learning feature-based designed nominate DNA sequences target types mouse cortex. Methods were...
ABSTRACT Spatial organization of tissue characterizes biological function, and spatially resolved gene expression has the power to reveal variations features with high resolution. Here, we propose a novel graph-based in situ sequencing decoding approach that improves recall, enabling precise spatial analysis. We apply our method on data from mouse brain sections, identify compartments correspond known regions, relate them morphology.
ABSTRACT Investigation of spatial cellular composition tissue architectures revealed by multiplexed in situ RNA detection often rely on inaccurate cell segmentation or prior biological knowledge from complementary single sequencing experiments. Here we present spage2vec, an unsupervised free approach for decrypting the transcriptomic heterogeneity complex tissues at subcellular resolution. Spage2vec represents landscape samples as a functional network and leverages powerful machine learning...
Deep learning has proven to successfully learn variations in tissue and cell morphology. Training of such models typically relies on expensive manual annotations. Here we conjecture that spatially resolved gene expression, e.i., the transcriptome, can be used as an alternative In particular, trained five convolutional neural networks with patches different size extracted from locations defined by expression. The network is classify morphology related two genes, general tissue, well...
With the emergence of high throughput single cell techniques, understanding molecular and cellular diversity mammalian organs have rapidly increased. In order to understand spatial organization this diversity, data is often integrated with create probabilistic maps. However, targeted typing approaches relying on existing achieve incomplete biased maps that could mask true present in a tissue slide. Here we applied de novo technique spatially resolve characterize situ sequencing during human...
Fusion genes are both useful cancer biomarkers and important drug targets. Finding relevant fusion is challenging due to genomic instability resulting in a high number of passenger events. To reveal prioritize gene events we have developed FUsionN Gene Identification toolset (FUNGI) that uses an ensemble detection algorithms with prioritization visualization modules.We applied FUNGI ovarian dataset 107 tumor samples from 36 patients. Ten out 11 detected prioritized were validated. Many...
Image-based multiplexed in situ RNA detection makes it possible to map the spatial gene expression of hundreds thousands genes parallel, and thus discern at same time a large numbers different cell types better understand tissue development, heterogeneity, disease. Fluorescent signals are detected over multiple fluorescent channels imaging rounds decoded order identify molecules their morphological context. Here we present graph-based decoding approach that models process as network flow...
Recently, we have achieved a significant milestone with the creation of Fly Cell Atlas. This single-nuclei atlas encompasses entire fly, covering head and body, in addition to all major organs. catalogs many hundreds cell types, which annotated 250. Thus, large number clusters remain be fully characterized, particular brain. Furthermore, by applying sequencing, information about spatial location cells body possible subcellular localization mRNAs within these is lost. Spatial transcriptomics...