Wang Lab

weights

open(ungated whole-human, organ-specific, and pan-cancer checkpoint folders)

data

closed(33 million pretraining cells described in the preprint with no corpus or reconstruction scripts released)

code

partial(fine-tuning, inference, and reference-mapping examples

license

MIT(OSI)

scGPT is an openly licensed checkpoint zoo with adaptation code, but the repository's own to-do list still carries the pretraining code, and the corpus was never released.

• https://raw.githubusercontent.com/bowang-lab/scGPT/main/LICENSE recorded 2026-10-21

  MIT License body covering the repository, read directly rather than from the license endpoint.

• https://raw.githubusercontent.com/bowang-lab/scGPT/main/README.md recorded 2026-10-21

  Lists eight downloadable pretrained checkpoint folders, describes pretraining on 33 million normal human cells without releasing the corpus, ships a fine-tuning example, and leaves "Provide the pretraining code with generative attention masking" unchecked.

No Hugging Face artifact exists for scGPT, since publishing to the Hub is still an open item in the repository, so GitHub stars are the fallback signal. The scgpt PyPI package is a separate, undeclared distribution channel whose download volume reads lower than the star count does; counting it would move this reading down rather than up, and that declaration has not been made.

• https://api.github.com/repos/bowang-lab/scGPT recorded 2026-09-10

  stargazers_count: 1626; archived: false; fork: false.

scGPT establishes three capability attributes, including multi-omic input: tutorials/Tutorial_Multiomics.ipynb and Tutorial_Perturbation.ipynb both ship in the repository, even though the project's own to-do list still marks multi-omic support unfinished. Gene and cell representations count as one scale, and the organ-specific checkpoints are separate models rather than a second scale.

• https://raw.githubusercontent.com/bowang-lab/scGPT/main/README.md recorded 2026-09-10

  Ships examples/finetune_integration.py for fine-tuning a pretrained checkpoint and names the model a generative pre-trained foundation model for single-cell multi-omics.

• https://scgpt.readthedocs.io/en/latest/introduction.html recorded 2026-09-10

  Describes generative pre-training on over 33 million cells, single-cell multi-omic data analysis, and downstream multi-omic integration and genetic perturbation prediction, with fine-tuning tutorials for each.