Integration of single-cell multi-omics data across space and time to unlock cellular trajectories
MULTIview-CELL aims to integrate multi-omics single-cell data using novel MML approaches to uncover spatiotemporal cell trajectories and molecular regulators, enhancing biological understanding and health outcomes.
Projectdetails
Introduction
The introduction of high-throughput single-cell sequencing has produced a flood of data at the resolution of the single cell, including spatiotemporal information and different molecular facets of a cell, a.k.a. multi-omics. Their integration through MultiModal Learning (MML), aimed at combining multiple complementary views, offers great promise to understand the spatiotemporal phenotypic evolution of a cell and its molecular regulators.
Computational Challenges
However, integrating multi-omics data across space and time is a huge computational challenge requiring radically new MML approaches.
Project Overview
MULTIview-CELL will infer multimodal spatiotemporal phenotypic cell trajectories by:
- Combining back-translation to allow the unsupervised dimensionality reduction of multimodal data.
- Utilizing a new Optimal Transport distance, allowing the spatiotemporal pairing of cells (Aim 1).
MULTIview-CELL will then pinpoint the molecular regulators of such trajectories by:
- Combining new Graph Convolutional Networks with topological evolutions.
- Utilizing Heterogeneous Multilayer Graphs, allowing the integration of graphs inferred from multimodal data (Aim 2).
Finally, all developed methods will be implemented in open-source software, with an emphasis on GPU-friendly scalable computations, a unique feature among existing single-cell tools (Aim 3).
Impact on Machine Learning and Biology
These core contributions will impact Machine Learning, but more importantly, will have profound biological implications.
Applications and Validation
The application of the tools developed to cutting-edge single-cell data from muscle stem cells will lead to new biological hypotheses on their heterogeneity and crosstalk, to be validated through wet-lab experiments (Transversal Tasks).
Long-term Goals
In addition, by allowing to answer longstanding questions on the spatiotemporal phenotypic evolution of a cell, MULTIview-CELL will catalyze the generation of crucial knowledge in fundamental biology. It will be key to preventing disease onset or therapy resistance, thus impacting health, society, and economy.
Financiële details & Tijdlijn
Financiële details
Subsidiebedrag | € 1.285.938 |
Totale projectbegroting | € 1.285.938 |
Tijdlijn
Startdatum | 1-4-2024 |
Einddatum | 31-3-2029 |
Subsidiejaar | 2024 |
Partners & Locaties
Projectpartners
- CENTRE NATIONAL DE LA RECHERCHE SCIENTIFIQUE CNRSpenvoerder
Land(en)
Vergelijkbare projecten binnen European Research Council
Project | Regeling | Bedrag | Jaar | Actie |
---|---|---|---|---|
Decoding the Multi-facets of Cellular Identity from Single-cell DataDevelop computational methods combining machine learning and dynamical systems to analyze single-cell data, uncovering cellular identities and interactions to enhance understanding of multicellular systems in health and disease. | ERC Starting... | € 1.484.125 | 2022 | Details |
Wasserstein FLOW Learning for multi-OmicsWOLF aims to develop a novel framework for multi-omics trajectory inference using non-Euclidean optimal transport flows, enhancing the understanding of cellular development and disease mechanisms. | ERC Advanced... | € 2.500.000 | 2024 | Details |
Learning and modeling the molecular response of single cells to drug perturbationsDeepCell aims to model cellular responses to drug perturbations using multiomics and deep learning, facilitating optimal treatment design and expediting drug discovery in clinical settings. | ERC Advanced... | € 2.497.298 | 2023 | Details |
Spatial Transcriptomics through the lenses of statistical modeling and AIThis project aims to integrate spatial transcriptomics with machine learning and statistical modeling to enhance understanding of gene expression and tissue organization for personalized medicine. | ERC Consolid... | € 1.979.375 | 2025 | Details |
Revealing cellular behavior with single-cell multi-omicsDevelop a single-cell multi-omics approach to analyze β-cell heterogeneity and metabolism, aiming to uncover insights into diabetes-related dysfunction and potential treatment targets. | ERC Starting... | € 2.499.864 | 2022 | Details |
Decoding the Multi-facets of Cellular Identity from Single-cell Data
Develop computational methods combining machine learning and dynamical systems to analyze single-cell data, uncovering cellular identities and interactions to enhance understanding of multicellular systems in health and disease.
Wasserstein FLOW Learning for multi-Omics
WOLF aims to develop a novel framework for multi-omics trajectory inference using non-Euclidean optimal transport flows, enhancing the understanding of cellular development and disease mechanisms.
Learning and modeling the molecular response of single cells to drug perturbations
DeepCell aims to model cellular responses to drug perturbations using multiomics and deep learning, facilitating optimal treatment design and expediting drug discovery in clinical settings.
Spatial Transcriptomics through the lenses of statistical modeling and AI
This project aims to integrate spatial transcriptomics with machine learning and statistical modeling to enhance understanding of gene expression and tissue organization for personalized medicine.
Revealing cellular behavior with single-cell multi-omics
Develop a single-cell multi-omics approach to analyze β-cell heterogeneity and metabolism, aiming to uncover insights into diabetes-related dysfunction and potential treatment targets.
Vergelijkbare projecten uit andere regelingen
Project | Regeling | Bedrag | Jaar | Actie |
---|---|---|---|---|
A multiplexed biomimetic imaging platform for assessing single cell plasticity (Plastomics) and scoring of tumour malignancyThe PLAST_CELL project aims to develop a microfluidics-based imaging platform to quantify cancer cell plasticity, enhancing diagnosis and treatment of metastasis and therapy resistance. | EIC Pathfinder | € 2.982.792 | 2022 | Details |
Instrument-free 3D molecular imaging with the VOLumetric UMI-Network EXplorerVOLUMINEX aims to revolutionize molecular imaging by providing an affordable 3D sequencing-based microscopy method for comprehensive spatial and transcriptomic data mapping. | EIC Pathfinder | € 2.999.999 | 2025 | Details |
A multiplexed biomimetic imaging platform for assessing single cell plasticity (Plastomics) and scoring of tumour malignancy
The PLAST_CELL project aims to develop a microfluidics-based imaging platform to quantify cancer cell plasticity, enhancing diagnosis and treatment of metastasis and therapy resistance.
Instrument-free 3D molecular imaging with the VOLumetric UMI-Network EXplorer
VOLUMINEX aims to revolutionize molecular imaging by providing an affordable 3D sequencing-based microscopy method for comprehensive spatial and transcriptomic data mapping.