A visual–omics foundation model to bridge histopathology image with transcriptomics
Ontology highlight
ABSTRACT:
PROVIDER: PRJNA1243350 | ENA |
REPOSITORIES: ENA
Similar Datasets
Project description:Artificial intelligence has significantly advanced computational biology. Recent developments in omics technologies, such as single-cell RNA sequencing (scRNA-seq) and spatial transcriptomics (ST), provide detailed genomic data alongside tissue histology. However, current computational models often focus on either omics- or image-based analysis, lacking integration of both. To address this, we developed OmiCLIP, a visual-omics foundation model linking hematoxylin and eosin (H&E) images and transcriptomics using tissue patches from Visium data. For transcriptomics, we created 'sentences' by concatenating top-expressed gene symbols from tissue patches. We curated a dataset of 2.2 million paired tissue images and transcriptomic data across 32 organs to train OmiCLIP integrating histology and transcriptomics. Building on OmiCLIP, we created the Loki platform, which offers five key functions: tissue alignment, tissue annotation based on bulk RNA-seq or marker genes, cell type decomposition, image–transcriptomics retrieval, and ST gene expression prediction from H&E images. Compared with 22 state-of-the-art models on 5 simulations, 19 public, and 4 in-house experimental datasets, Loki demonstrated consistent accuracy and robustness in all tasks.
2025-04-01 | GSE293199 | GEO
Project description:The formation of the visual system is a complex multistep process that includes the establishment of proper connectivity of retinal ganglion cell (RGC) axon terminals with their relay neurons located in the brain. In mammals, the assembly of the different components of the visual circuit occurs at perinatal stages before eye opening. Upon reaching the target nuclei RGC axons extensively arborize and subsequently refine to establish the final connections. Spontaneous activity generated in the immature retina plays an essential role in the refinement of visual terminals at the main image-forming nuclei (IFN) that follow an eye-specific and retinotopic organization. However, the molecular mechanisms underlying spontaneous activity-dependent axon remodeling, and the influence of this activity in the connectivity of non-image forming nuclei (NIFN) that lack precise retinotopic maps and/or eye-specific segregation, are not well known. Here, by generating conditional mice with disturbed spontaneous retinal aneactivity and analyzing their retinal transcriptomic profiles, we identified novel players involved in axon refinement at the visual nuclei (e. g. Syt13). The analysis of visual projections in the NIFN of these mice revealed that correlated-retinal activity shapes final connectivity in non retinotopic or eye-specific segregating visual nuclei.
2024-10-09 | GSE193498 | GEO
Project description:We evaluated several foundation models in histopathology for image retrieval using a zero-shot approach. These models generated embeddings that were directly employed for retrieval without additional fine-tuning. Our experiments were conducted on diagnostic slides from The Cancer Genome Atlas (TCGA), which covers 23 organs and 117 cancer subtypes. We used Yottixel as the framework for whole-slide image (WSI) retrieval via patch-based embeddings. Retrieval performance was evaluated using macro-averaged F1 scores for top-1, top-3, and top-5 retrievals. The top-5 retrieval F1 scores indicated varying levels of performance: Yottixel-DenseNet (27% ± 13%), Yottixel-UNI (42% ± 14%), Yottixel-Virchow (40% ± 13%), Yottixel-GigaPath (41% ± 13%), and GigaPath WSI (40% ± 14%). These results demonstrate the potential and limitations of foundation models for histopathology image retrieval, underscoring the need for further advancements in embedding and retrieval techniques.
| S-EPMC11787325 | biostudies-literature
Project description:Perinatal correlated retinal activity is required for the wiring of visual axons in non-image forming nuclei
| PRJNA796364 | ENA
Project description:Artificial intelligence-based histopathology image analysis identifies a novel subset of endometrial cancers with distinct genomic features and unfavourable outcome
| PRJEB60600 | ENA
Project description:The development of mirror-image biology systems and related applications is hindered by the lack of effective methods to sequence mirror-image (D-) proteins. Although natural-chirality (L-) proteins can be sequenced by bottom–up liquid chromatography–tandem mass spectrometry (LC–MS/MS), the sequencing of long D-peptides and D-proteins with the same strategy requires digestion by a site-specific D-protease before mass analysis. Here we apply solid-phase peptide synthesis and native chemical ligation to chemically synthesize a mirror-image version of trypsin, a widely used protease for site-specific protein digestion. Using mirror-image trypsin digestion and LC–MS/MS, we sequence a mirror-image large subunit ribosomal protein (L25) and a mirror-image Sulfolobus solfataricus P2 DNA polymerase IV (Dpo4), and distinguish between different mutants of D-Dpo4. We also perform writing and reading of digital information in a long D-peptide of 50 amino acids. Thus, mirror-image trypsin digestion in conjunction with LC–MS/MS may facilitate practical applications of D-peptides and D-proteins as potential therapeutic and informational tools.
2024-01-19 | PXD046228 | Pride
Project description:Fast and selective isolation of single cells with unique spatial and morphological traits remains a technical challenge. We address this by establishing high speed image-enabled cell sorting (ICS), which records multicolor fluorescence images, and sorts cells based on measurements from image data at speeds up to 15,000 events per second. We combine ICS with CRISPR-pooled screens to identify novel regulators of the NF-κB pathway, enabling the completion of genome-wide image- based screens in around nine hours of run-time.
2022-01-20 | GSE167944 | GEO
Project description:This study examines the effect of four different image segmentation methods on the precision of the data. Keywords: other
2004-03-16 | GSE1054 | GEO
Project description:Visual deprivation, either in the form of dark rearing (DR) or monocular deprivation (MD) are established paradigms for studying cortical plasticity. We have used miRNA microarray to uncover miRNAs whose expression is altered in primary visual cortex following DR and/or MD. C57BL6 mice were reared in normal light and dark conditions (control) till P28, in complete darkness since birth (DR) till P28, or were grown in normal light/dark conditions from birth till P24 and then subjected to lid suturing of one eye till P28. Mice were euthanized at P28 and their primary visual cortex areas were excised and subjected to RNA isolation. In the case of MD mice only the contralateral to lid suture primary visual cortex was extracted. 100ng of total RNA (tested and quantified using the Agilent Bioanalyzer 2100) were labeled using the Agilent miRNA labeling system and hybridized to Agilent murine miRNA arrays. Microarrays were hybridized overnight at 64 ºC, scanned using an Agilent scanner and extracted with Agilent feature extractor 10.1.
2011-09-03 | E-GEOD-31536 | biostudies-arrayexpress
Project description:Hartwig Medical Foundation Benchmark Set
| PRJEB33197 | ENA