scvi-tools

You can perform batch correction on single-cell RNA-seq data by automating deep learning workflows with scvi-tools, which ensures robust model selection, training, and interpretation for integrating multiple data batches.

Yes, you can use deep learning for multi-modal analysis with ATAC-seq and CITE-seq data. The workflow supports various single-cell modalities including multi-ome data to integrate complex genomic datasets seamlessly.

The best way to choose a deep learning model for spatial transcriptomics is to use an automated model selection guide that matches your specific analysis requirements, simplifying the decision process for biologists.

You do not need to train models from scratch to start single-cell genomics analysis. You can access pre-trained models for various use cases, enabling quick analysis and interpretation without the overhead of training.

Deep learning integration handles existing single-cell datasets by seamlessly integrating with your current data, including scRNA-seq, CITE-seq, ATAC-seq, and multi-ome formats, ensuring robust data alignment and interpretation.