Analyzes single-cell omics data using deep probabilistic models for integration, batch correction, and differential expression.
Provides comprehensive assistance for single-cell omics analysis using the scvi-tools suite. It streamlines the implementation of deep generative models like scVI, scANVI, and totalVI to handle complex tasks such as batch correction, data integration, and multimodal analysis including RNA-seq, ATAC-seq, and CITE-seq. Whether setting up AnnData objects, performing differential expression tests, or building custom model architectures, this skill offers the technical guidance and code patterns necessary to derive biological insights from high-dimensional single-cell datasets.
Key Features
010 GitHub stars
02Advanced differential expression and abundance analysis workflows
03Custom model development and extension of scvi-tools base classes
04Automated hyperparameter tuning and model optimization via scvi.autotune
05Implementation of scVI, scANVI, totalVI, MultiVI, and GIMVI models
06Batch correction and data integration for multi-modal single-cell experiments
Use Cases
01Analyzing multimodal data such as CITE-seq or spatial transcriptomics with deep generative models
02Integrating disparate single-cell datasets while correcting for technical batch effects
03Developing specialized variational autoencoder architectures for unique biological questions