10x Genomics’ Post

We are excited to share our latest research introducing our new AI model, MISO (Multiscale Integration of Spatial Omics), available today as a preprint on bioRxiv & medRxiv. Trained on a new unpublished dataset of 72 10X Genomics Visium samples with corresponding digital pathology images, MISO enables near single-cell-resolution, spatially-resolved gene expression prediction from H&E-stained slides. With spatial transcriptomics remaining challenging to use routinely, our model represents a novel approach for augmenting multimodal datasets and scale up integration of spatial transcriptomics data with tumor morphology. 📑 Read our pre-print at https://lnkd.in/gsvdKk7p #AI #spatialomics

🍣 Super excited to share Owkin latest research introducing our new AI model, MISO (Multiscale Integration of Spatial Omics), available today as a preprint on bioRxiv & medRxiv. It is as umami as you think! 😋 Trained on a new unpublished dataset of our partner 72 10x Genomics Visium samples with corresponding digital pathology images, MISO enables near single-cell-resolution, spatially-resolved gene expression prediction from H&E-stained slides. With spatial transcriptomics remaining challenging to use routinely, our model represents a novel approach for augmenting multimodal datasets and scale up integration of spatial transcriptomics data with tumor morphology. 📑 Read our pre-print at https://lnkd.in/gsvdKk7p

We are excited to share our latest research introducing our new #AI model, MISO (Multiscale Integration of Spatial Omics), available today as a preprint on bioRxiv & medRxiv. Trained on a new unpublished dataset of 72 10X Genomics Visium samples with corresponding digital pathology images, MISO enables near single-cell-resolution, spatially-resolved gene expression prediction from H&E-stained slides. With #spatialomics techniques remaining challenging to use routinely, our model represents a novel approach for augmenting multimodal datasets and scale up integration of spatial transcriptomics data with tumor morphology. Read our pre-print at https://lnkd.in/dtWGR-aD

Dear All, I am presenting my year-long research (deep breath 😅) in delineating the spatial gene expression signatures that uniquely characterize both inter and intra-tumoral heterogeneity at the premier AACR 2024 conference. We model the single-cell spatial transcriptomic landscape of lung adenocarcinoma (LUAD) using graphs and train graph attention models to predict LUAD subtypes with 95% balanced accuracy. Our model further reveals the unique gene signatures in each tumor cell based on their spatial location and microenvironment interactions. We find that these genes form unique intra-tumoral clusters in complex acinar subtypes, while also serving as better predictors of survival and exhibiting inter-tumoral differences in micropapillary and solid tumors. The title of the poster is: "Delineating spatial expression signatures of lung adenocarcinoma subtypes from spatial single-cell transcriptomics using graph neural networks" If you are attending AACR and would like to chat about spatial transcriptomics or AI in general, please message me here :) Please find more details here: https://lnkd.in/gC7xsRQZ

📌 Using deep learning to quantify neuronal activation from single-cell and spatial transcriptomic data Bahl et al. presented NEUROeSTIMator, a versatile tool that estimates neuronal activity from transcriptome-wide single-cell gene expression data. Key points 📍Generation of an activity score that reflects whole-transcriptome response to stimulation 📍The rapid identification and prioritization of neurons displaying stimulus response 📍Performance and generalizability through capturing electrophysiological (e-phys) features 📍Detection of activation signatures across various stimulation protocols, neuron subtypes, species, and sequencing technologies, including spatial transcriptomics. ➡ More details: https://lnkd.in/gFPcEZt9 #spatialomics #spatialbiology #singlecellanalysis #singlecell #UniversityofIowa

#AI_in_Genomics: Accelerating Precision Medicine and DNA Analysis 📚For More Information - https://lnkd.in/dcAzFWue AI in Genomics refers to the use of artificial intelligence and machine learning technologies to analyze genomic data, aiding in the understanding of genetic structures and functions. AI models assist in identifying gene patterns, predicting disease risks, and personalizing treatments. By accelerating DNA sequencing analysis, AI enhances precision medicine and the development of novel therapies. Its applications span cancer genomics, rare disease diagnostics, and drug discovery, offering insights that were previously unattainable through traditional methods. AI also optimizes data handling in genomics, making the research process more efficient and accurate. #aiingenomics #genomics #artificialintelligence #precisionmedicine #geneticresearch #bioinformatics #dnaanalysis #machinelearning #healthcareinnovation #personalizedmedicine #drugdiscovery #genomicdata #medicalai #biotechnology #cancergenomics

🚀 Introducing CELLama: Transforming Spatial Biology Discovery!🚀 We are delighted to announce the release of CELLama, our latest AI foundation model that's set to transform drug discovery from large data. CELLama is a leap forward in how we understand and utilize huge cell data. ✨ What makes CELLama unique? It's engineered to fully integrate gene expression information with meta-data and spatial details. This enables various tasks such as unprecedented precision in universal cell typing and understanding spatial relationships within tissues. 🔬  In Portrai, by securing spatial transcriptomics data of tens of millions of cells across various cancers, CELLama offers a robust platform for accelerating the discovery and development of our new drugs and biomarkers. 🌏  At Portrai, we're committed to pushing the boundaries of what's possible with spatial biology data to create real-world solutions. CELLama marks the beginning of a future driven forward by our innovative spirit in data-driven innovative drug development.Join us on this journey as we continue to revolutionize the approach to medical research and treatment development! Journal: https://lnkd.in/g8AkQNfT Github: https://lnkd.in/gW-SgZ5F #AI #Innovation #DrugDiscovery #SpatialTranscriptomics #SpatialBiology #Portrai #Cell

Our new work is out! With Celcomen, we introduce spatial causal disentanglement and identifiability in spatial transcriptomics to perform spatial counterfactuals 📖🔬 Check it out here: https://lnkd.in/dFutWauH. Our model can be prompted to generate spatial samples with spatial gene knockouts thereby giving access to experimentally inaccessible information. It does that by first learning to disentangle the intracellular vs intercellular forces that influence each cell. The causality theory behind celcomen guarantees the identifiability of these forces from the data. We validate our model using simulations, Xenium, and Visium data with actual spatially-resolved gene knock-outs. A huge thank you to Daniel Chen, Krzysztof Polanski, Moshe Eliasof, Carola-Bibiane Schonlieb, and Sarah Teichmann FMedSci FRS; Wellcome Sanger Institute, Cambridge Stem Cell Institute Cambridge Centre for AI in Medicine European Bioinformatics Institute | EMBL-EBI University of Cambridge

We're thrilled to share a fascinating research article titled "#Single-cell spatial transcriptome reveals cell-type organization in the macaque cortex" This groundbreaking study utilizes Stereo-seq technology to uncover gene expression and spatial information within the macaque cerebral cortex at an unprecedented subcellular resolution of 500 #nanometers. The findings shed light on the intricate organization of cell types within the macaque cortex, offering valuable insights into brain diseases and the molecular mechanisms of brain function in primates. 🔬Explore the full article: https://bit.ly/4akA3mz 🔬Learn more about our service: https://bit.ly/41Z6OTa #BGIGeneTest #update #cell #research #Stereoseq

🔬 Researchers from the Perelman School of Medicine at the University of Pennsylvania have developed an artificial intelligence (AI)-based medical imaging technique capable of analyzing the gene activity found within tissue microenvironments, which may have significant impacts on precision medicine and pathology, according to a study published last week in Nature Biotechnology. The tool, known as Inferring Super-Resolution Tissue Architecture (iStar), is designed to provide both detailed views of individual cells and a broader understanding of how a patient’s genes operate. The research team believes that the tool could help clinicians better diagnose and treat cancers that could go undetected using traditional methods.🌟 #CancerTreatment #PrecisionPathology #ArtificialIntelligence #MedicalInnovation #HealthTechRevolution #CancerCare #AIInHealthcare #InnovativeMedicine #HealthcareAdvancements #MedicalTechnology #FutureOfMedicine #DiscoverAI #MedicalBreakthroughs #TechInMedicine #HealthcareTransformation #PathologyRevolution #AIandHealth #InnovateToCure #CancerResearch #PrecisionMedicine #HealthcareEvolution #usa