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
Required GPU
scVI-tools (single-cell variational inference tools) is a package for end-to-end analysis of single-cell omics data primarily developed and maintained by the Yosef Lab at UC Berkeley. scvi-tools has two components - Interface for easy use of a range of probabilistic models for single-cell omics (e.g., scVI, scANVI, totalVI). - Tools to build new probabilistic models, which are powered by PyTorch, PyTorch Lightning, and Pyro.
BioTuring
Mapping out the coarse-grained connectivity structures of complex manifolds Biological systems often change over time, as old cells die and new cells are created through differentiation from progenitor cells. This means that at any given time, not all cells will be at the same stage of development. In this sense, a single-cell sample could contain cells at different stages of differentiation. By analyzing the data, we can identify which cells are at which stages and build a model for their biological transitions. By quantifying the connectivity of partitions (groups, clusters) of the single-cell graph, partition-based graph abstraction (PAGA) generates a much simpler abstracted graph (PAGA graph) of partitions, in which edge weights represent confidence in the presence of connections. In this notebook, we will introduce the concept of single-cell Trajectory Analysis using PAGA (Partition-based graph abstraction) in the context of hematopoietic differentiation.
BioTuring
Required GPU
Advances in multi-omics have led to an explosion of multimodal datasets to address questions from basic biology to translation. While these data provide novel opportunities for discovery, they also pose management and analysis challenges, thus motivating the development of tailored computational solutions. `muon` is a Python framework for multimodal omics. It introduces multimodal data containers as `MuData` object. The package also provides state of the art methods for multi-omics data integration. `muon` allows the analysis of both unimodal omics and multimodal omics.