Single cell multi-omics cross modal generation, multi-omics simulation and perturbation
Project description
scCross
A Deep Learning-Based Model for the integration, cross-dataset cross-modality generation, self augmentation and matched multi-omics simulation of single-cell multi-omics data. Our model excels at maintaining in-silico perturbations during cross-modality generation and harnessing these perturbations to identify key genes.
For detailed instructions, comprehensive documentation, and helpful tutorials, please visit:
Overview
Key Capabilities
-
Combine more than three single-cell multi-omics datasets, whether they are matched or unmatched, into a unified latent space. This space can be used for downstream analysis, even when dealing with over 4 million cells of varying types.
-
Generate cross-compatible single-cell data between two or more different omics. Trained and tested on independent referenced multi-omics datasets is also feasible.
-
Augment single-cell omics data through self-improvement techniques.
-
Simulate single-cell multi-omics data that match a specific cellular state, irrespective of the type and quantity of omics data involved.
-
Accurately identify key genes by comparing two different cell clusters using in-silico perturbation methods.
-
Maintain genomic integrity during omics perturbations and cross-generations effectively.
Installation
You may install scCross by the following command:
pip install sccross
Project details
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.