# Applications of AI to single-cell and spatial transcriptomics: current state-of-the-art and challenges

## TL;DR

This paper reviews how AI is used in analyzing single-cell and spatial transcriptomics data, comparing AI methods to traditional approaches.

## Contribution

The paper provides a comprehensive review of AI applications across ten key analysis tasks in single-cell and spatial transcriptomics.

## Key findings

- AI methods are widely used for tasks like dimensionality reduction and data integration in single-cell transcriptomics.
- Some AI algorithms are ready for general research use, while others require further development.
- The paper identifies which AI approaches are most useful for discovery researchers.

## Abstract

Artificial intelligence (AI) has become a common tool for bioinformatics, with hundreds of methods published in recent years. Due to the training data demands of deep-learning algorithms, high-throughput single-cell and spatial transcriptomics is one of the most popular areas for these applications. Here we review how AI is being used for single-cell and spatial transcriptomics analysis, and how these approaches compare to alternative statistical or heuristic-based methods. We explored 10 common analysis tasks: dimensionality reduction, cross-dataset integration, data denoising, data augmentation, deconvolution, cell-cell interactions, transcriptional velocity, transcriptomic-chromatin accessibility integration, and integrating single-cell and spatial transcriptomics modalities. We highlight which algorithms are likely to be useful for discovery researchers, and which are not yet ready for general research use.