scGPT (v0.2.1) is a foundation model for single-cell biology, based on generative pre-trained transformers trained on a vast repository of over 33 million cells. The scGPT model demonstrates the ability to extract valuable biological insights and can be further optimized through transfer learning for various downstream applications, including cell-type annotation, multi-batch integration, genetic perturbation prediction, and gene network inference.

Example use case: For users who already have annotations for similar samples and want to transfer these annotations to newly collected samples quickly.

Technology: Transformers

Limitations:

Some parameters are kept as default please see the original tutorial here.

Before running this app, consider the following:

• Ensure gene column names are identical in both reference and test datasets. See the example dataset below.
• If the test dataset has a cell-type column, its name must match the one in the reference dataset.