This repository is a curated list of research papers focusing on the application of deep learning techniques to single-cell analysis. It serves as a valuable resource for researchers and practitioners in bioinformatics and computational biology seeking to leverage advanced machine learning for understanding cellular data. The collection aims to keep pace with the rapidly evolving field by categorizing papers by specific analytical tasks.

How It Works

The repository functions as an organized, community-driven bibliography. It categorizes papers based on common tasks in single-cell analysis, such as representation learning, batch effect correction, cell type annotation, and multimodal integration. This structured approach allows users to quickly find relevant literature for specific deep learning applications within single-cell genomics.

Highlighted Details

• Comprehensive coverage of deep learning applications in single-cell analysis, including foundation models, GANs/diffusion models, multimodal learning, and interpretability.
• Extensive categorization of papers by specific tasks, providing a granular view of the research landscape.
• Includes links to a survey paper, foundational models, and various tools and courses related to single-cell analysis.
• Features papers on emerging areas like spatial transcriptomics, RNA velocity, and perturbation analysis.

Maintenance & Community

The project encourages community contributions through issues and pull requests for error correction or missed papers. It cites a comprehensive survey paper on Deep Learning in Single-cell Analysis.

Licensing & Compatibility

The repository itself does not contain code or data, but rather links to external research papers. The licensing of the linked papers varies by publication.

Limitations & Caveats

This is a curated list of papers and does not provide any code, tools, or datasets for direct use. Its value is purely informational, requiring users to access and evaluate the cited research independently.