Data Insights

Data Insights (Cycle 2)

This project will develop computational tools that will allow for fast and intuitive access to cell atlases through a web browser.

Data Insights (Cycle 3)

This project will develop automated computational tools to predict cell types and properties for single-cell data leveraging known hierarchical relationships.

Data Insights (Cycle 3)

This project will develop a spatial context aware cell-cell communication algorithm for de novo inference of in-situ cell signaling within tissue microenvironments characterized using protein-based highly multiplexed imaging of tissue samples.

Data Insights (Cycle 3)

This project will develop innovative computational methods to generate causal regulatory hypotheses from single-cell genomic data for advancing our understanding of cellular differentiation and disease.

Data Insights (Cycle 2)

This project will develop CytoSignal and VeloCytoSignal, two computational tools that detect cell-cell signaling interactions and their dynamics at single-cell resolution from spatial transcriptomic data.

Data Insights (Cycle 2)

This project will develop statistically robust and computationally efficient methods for performing differential expression analysis from single-cell RNA-sequencing data.

Data Insights (Cycle 2)

This project will develop robust computational tools for spatial transcriptomic analysis of human tissue pathology, with an initial focus in cancer biology.

Data Insights (Cycle 2)

This project will develop explainable AI techniques for single-cell regulatory genomics which will enable more rigorous and interpretable data-driven discoveries in single-cell regulatory genomics.

Data Insights (Cycle 3)

This project will develop specialized computational tools, based on the widely used Harmony algorithm, to make public single-cell data more accessible and easier to analyze.

Data Insights (Cycle 2)

This project will create and optimize new computational methods to significantly improve quantitative accuracy of single-cell proteomics data.

Data Insights (Cycle 3)

This project will investigate somatic mutation landscape in various human normal tissues from various sources of single-cell omics data.

Data Insights (Cycle 2)

This project will create and disseminate tools to enable cross-species and cross-measurement platform analysis of cell types and tissue environment-specific gene regulation in the muscle.

Data Insights (Cycle 3)

This project will develop methods for characterization of differentiation pathways and the cellular flow through those pathways from lineage tracing datasets of normal development and disease.

Data Insights (Cycle 2)

This project will predict, model, and compare gene regulatory networks and enhancer logic in brain and cancer cell types by re-using human and mouse single-cell multi-omics atlases.

Data Insights (Cycle 2)

This project will develop light and scalable approximations of cell atlases to democratize online access, web visualization, and machine learning, which will provide biological insights across organs and organisms.

Data Insights (Cycle 2)

This project will develop a publicly-available software package to integrate diverse spatial and nonspatial single-cell data modalities, creating a comprehensive spatial representation of a tissue of interest.

Data Insights (Cycle 3)

This project will analyze single-cell workflows used in biomedical literature through automated extraction to improve reproducibility and generalizability of computational single-cell analysis pipelines.

Data Insights (Cycle 3)

This project will develop machine tools for analyzing single-cell perturbation experiments, enabling integration of publicly available datasets and predicting single-cell responses to unseen perturbations.

Data Insights (Cycle 3)

This project will develop statistical methods for estimating gene-enhancer links from multi-modal single cell data and tensor decomposition methods for investigating regulatory variation among cell states.

Data Insights (Cycle 2)

This project will develop a spatially-aware unsupervised clustering algorithm and open-source software in R/Bioconductor scalable for analysis of large atlas-scale spatial transcriptomics data with multiple samples.

Data Insights (Cycle 3)

This project will engineer and train generative AI models that simulate realistic virtual cells with multiple species representations, and use it to model whole-organism consequences of rare disease perturbations.

Data Insights (Cycle 2)

This project will show how cell states can be understood as mosaic combinations of pathway-specific motifs and develop computational tools that make it possible to apply this framework to other cellular systems.

Data Insights (Cycle 3)

This project will develop a framework that enables broad disease, trait and biomarker prediction from single-cell data while simultaneously identifying relevant implicated cell types.

Data Insights (Cycle 2)

This project will build a 14 million blood cell reference cell atlas that will incorporate diverse healthy donors and 27 distinct disease states.

Data Insights (Cycle 2)

This project will develop CellTypist.org 2.0, an extended cross-tissue database accompanied by a cell type harmonization pipeline, which will automatically curate, standardize and annotate cell types across cell atlases.

Data Insights (Cycle 3)

This project will develop robust and scalable tools and pipelines for segmentation-free analysis on submicron resolution spatial transcriptomics, enabling harmonized analysis across existing cutting-edge technologies.

Data Insights (Cycle 2)

This project will develop a series of benchmarking frameworks for case-control and multi-perturbation studies that will increase the utilization of public single-cell data for precision medicine research.

Data Insights (Cycle 2)

This project will develop sequence-to-function neural network models for learning the relationship between regulatory genomic DNA sequence and dynamic cellular behavior at single cell resolution.

Data Insights (Cycle 3)

This project will establish a Metacell manifold vision-language(V-L) multimodal model to capture the intricacies of cellular dynamics for precise cellular mapping and annotation of CZ CELLxGENE sc/spatial omics data.

Data Insights (Cycle 2)

This project will characterize the genomic regulatory networks underlying ovarian aging in humans and vertebrate model organisms via integrative meta-analysis of ovarian single-cell RNA-seq datasets.

Data Insights (Cycle 3)

This project will build contextual cellular snapshots into existing cell atlases to better understand variables contributing to gene variation in health and disease.

Data Insights (Cycle 3)

This project will decipher circadian and cell cycle dynamics in cancer via context-dependent periodic manifold modeling, from regulation to new opportunities for chrono-treatments.

Data Insights (Cycle 2)

This project will enable interoperable multimodal spatial omics data storage and analysis by building open software and standards that join the imaging (napari, OME) and single-cell (scverse) communities.

Data Insights (Cycle 3)

This project will develop a generative AI toolkit for spatial proteomics able to virtually stain tissue images for various proteins, harmonizing existing data and creating a unified atlas of human cancer.

Data Insights (Cycle 3)

This project will develop a unified deep learning framework for analyzing paired and unpaired single-cell multi-omic datasets, and using the framework to drive local and long-range gene regulatory relationships.