scgpt
Towards Building a Foundation Model for Single-Cell Multi-omics Using Generative AI
Generative pre-trained models have achieved remarkable success in various domains such as natural language processing and computer vision. Specifically, the combination of large-scale diverse datasets and pre-trained transformers has emerged as a promising approach for developing foundation models. Drawing parallels between linguistic constructs and cellular biology - where texts comprise words, similarly, cells are defined by genes - our study probes the applicability of foundation models to advance cellular biology and genetics research. Utilizing the burgeoning single-cell sequencing data, we have pioneered the construction of a foundation model for single-cell biology, scGPT, which is based on generative pre-trained transformer across a repository of over 33 million cells. Our findings illustrate that scGPT, a generative pre-trained transformer, effectively distills critical biological insights concerning genes and cells. Through the further adaptation of transfer learning, scGPT can be optimized to achieve superior performance across diverse downstream applications. This includes tasks such as cell-type annotation, multi-batch integration, multi-omic integration, genetic perturbation prediction, and gene network inference.
Haotian Cui , Chloe Wang , Hassaan Maan , Kuan Pang , Fengning Luo , Bo Wang ,
Monthly downloads
1000
scGPT ¶
This is the official codebase for scGPT: Towards Building a Foundation Model for Single-Cell Multi-omics Using Generative AI.
!UPDATE: We have released several new pretrained scGPT checkpoints. Please see the Pretrained scGPT checkpoints section for more details.
Installation ¶
scGPT is available on PyPI. To install scGPT, run the following command:
$ pip install scgpt
[Optional] We recommend using wandb for logging and visualization.
$ pip install wandb
For developing, we are using the Poetry package manager. To install Poetry, follow the instructions here.
$ git clone this-repo-url
$ cd scGPT
$ poetry install
Note: The flash-attn dependency usually requires specific GPU and CUDA version. If you encounter any issues, please refer to the flash-attn repository for installation instructions. For now, May 2023, we recommend using CUDA 11.7 and flash-attn<1.0.5 due to various issues reported about installing new versions of flash-attn.
Pretrained scGPT Model Zoo ¶
Here is the list of pretrained models. Please find the links for downloading the checkpoint folders. We recommend using the whole-human model for most applications by default. If your fine-tuning dataset shares similar cell type context with the training data of the organ-specific models, these models can usually demonstrate competitive performance as well.
| Model name | Description | Download |
|---|---|---|
| whole-human (recommended) | Pretrained on 33 million normal human cells. | link |
| brain | Pretrained on 13.2 million brain cells. | link |
| blood | Pretrained on 10.3 million blood and bone marrow cells. | link |
| heart | Pretrained on 1.8 million heart cells | link |
| lung | Pretrained on 2.1 million lung cells | link |
| kidney | Pretrained on 814 thousand kidney cells | link |
| pan-cancer | Pretrained on 5.7 million cells of various cancer types | link |
Fine-tune scGPT for scRNA-seq integration ¶
Please see our example code in examples/finetune_integration.py. By default, the script assumes the scGPT checkpoint folder stored in the examples/save directory.
To-do-list ¶
- Upload the pretrained model checkpoint
- Publish to pypi
- Provide the pretraining code with generative attention masking
- Finetuning examples for multi-omics integration, cell type annotation, perturbation prediction, cell generation
- Example code for Gene Regulatory Network analysis
- Documentation website with readthedocs
- Bump up to pytorch 2.0
- New pretraining on larger datasets
- Reference mapping example
- Publish to huggingface model hub
Contributing ¶
We greatly welcome contributions to scGPT. Please submit a pull request if you have any ideas or bug fixes. We also welcome any issues you encounter while using scGPT.
Acknowledgements ¶
We sincerely thank the authors of following open-source projects:
Citing scGPT ¶
@article{cui2023scGPT,
title={scGPT: Towards Building a Foundation Model for Single-Cell Multi-omics Using Generative AI},
author={Cui, Haotian and Wang, Chloe and Maan, Hassaan and Pang, Kuan and Luo, Fengning and Wang, Bo},
journal={bioRxiv},
year={2023},
publisher={Cold Spring Harbor Laboratory}
}
Related notebook
BioTuring
Spatial transcriptomics (ST) technology has allowed to capture of topographical gene expression profiling of tumor tissues, but single-cell resolution is potentially lost. Identifying cell identities in ST datasets from tumors or other samples remains challenging for existing cell-type deconvolution methods. Spatial Cellular Estimator for Tumors (SpaCET) is an R package for analyzing cancer ST datasets to estimate cell lineages and intercellular interactions in the tumor microenvironment. Generally, SpaCET infers the malignant cell fraction through a gene pattern dictionary, then calibrates local cell densities and determines immune and stromal cell lineage fractions using a constrained regression model. Finally, the method can reveal putative cell-cell interactions in the tumor microenvironment. In this notebook, we will illustrate an example workflow for cell type deconvolution and interaction analysis on breast cancer ST data from 10X Visium. The notebook is inspired by SpaCET's vignettes and modified to demonstrate how the tool works on BioTuring's platform.
BioTuring
Required GPU
Cell2location is a principled Bayesian model that can resolve fine-grained cell types in spatial transcriptomic data and create comprehensive cellular maps of diverse tissues. Cell2location accounts for technical sources of variation and borrows statistical strength across locations, thereby enabling the integration of single cell and spatial transcriptomics with higher sensitivity and resolution than existing tools. This is achieved by estimating which combination of cell types in which cell abundance could have given the mRNA counts in the spatial data, while modelling technical effects (platform/technology effect, contaminating RNA, unexplained variance). This tutorial shows how to use cell2location method for spatially resolving fine-grained cell types by integrating 10X Visium data with scRNA-seq reference of cell types. Cell2location is a principled Bayesian model that estimates which combination of cell types in which cell abundance could have given the mRNA counts in the spatial data, while modelling technical effects (platform/technology effect, contaminating RNA, unexplained variance).
BioTuring
The recent development of experimental methods for measuring chromatin state at single-cell resolution has created a need for computational tools capable of analyzing these datasets. Here we developed Signac, a framework for the analysis of single-cell chromatin data, as an extension of the Seurat R toolkit for single-cell multimodal analysis. **Signac** enables an end-to-end analysis of single-cell chromatin data, including peak calling, quantification, quality control, dimension reduction, clustering, integration with single-cell gene expression datasets, DNA motif analysis, and interactive visualization. Furthermore, Signac facilitates the analysis of multimodal single-cell chromatin data, including datasets that co-assay DNA accessibility with gene expression, protein abundance, and mitochondrial genotype. We demonstrate scaling of the Signac framework to datasets containing over 700,000 cells.