bmwoolf/leukomap-scvi

LeukoMap scVI Model

This is a trained scVI (single-cell Variational Inference) model for pediatric leukemia single-cell RNA-seq analysis.

Model Details

• Model Type: scVI (single-cell Variational Inference)
• Training Data: Caron et al. (2020) pediatric leukemia dataset
• Architecture: Variational Autoencoder for single-cell data
• Latent Dimensions: Unknown
• Training Epochs: Unknown

Usage

from scvi.model import SCVI
import scanpy as sc

# Load your AnnData object
adata = sc.read_h5ad("your_data.h5ad")

# Load the model
model = SCVI.load("your-username/leukomap-scvi", adata)

# Get latent representation
latent = model.get_latent_representation()

Dataset

This model was trained on the Caron et al. (2020) pediatric leukemia dataset:

• GEO Accession: GSE132509
• Paper: https://doi.org/10.1038/s41598-020-64929-x
• Original Analysis: https://github.com/CBC-UCONN/Single-Cell-Transcriptomics

Citation

If you use this model, please cite:

• Caron et al. (2020) Single-cell analysis of childhood leukemia reveals a link between developmental states and ribosomal protein expression as a source of intra-individual heterogeneity
• Lopez et al. (2018) Deep generative modeling for single-cell transcriptomics