单细胞ATAC实战02: 基因组下载和SnapATAC2安装

curl --proto '=https' --tlsv1.2 -sSf https://sh.rustup.rs | sh
rustup default nightly
source "$HOME/.cargo/env"
# 查看是否安装成功
which cargo

brew install cmake
# 查看是否安装成功
which cmake

xcode-select --install # Apple M2
brew install gcc
# 查看是否安装成功
which gcc

brew install --cask mambaforge #Apple M2
mamba create -n ATAC
mamba activate ATAC 
mamba install -y -c conda-forge  python=3.8 cython numpy notebook ipywidgets xgboost scanpy rustworkx polars tenacity pyarrow scvi-tools
mamba install -y -c bioconda harmonypy
mamba install -y -c plotly plotly
pip install SnapATAC2

# Apple 芯片的电脑 的 pytorch 使用gpu需要设置
mamba env config vars set PYTORCH_ENABLE_MPS_FALLBACK=1

which python
# /opt/homebrew/Caskroom/mambaforge/base/envs/ATAC/bin/python

wget https://codeload.github.com/macs3-project/MACS/tar.gz/refs/tags/v2.2.7.1
tar -xf MACS-2.2.7.1.tar.gz
cd MACS-2.2.7.1

## 修改setup.py文件
numpy_requires = '>=1.17'
install_requires = [f"numpy>={numpy_requires}",]
# 改为
numpy_requires = '>=1.17'
install_requires = [f"numpy{numpy_requires}",]

# 安装
python setup.py install

# line 255
count = pl.DataFrame(aggregate_X(data, groupby=groupby, normalize="RPKM"))
# 修改为
out_adata = aggregate_X(data, groupby=groupby, normalize="RPKM")
count = pl.DataFrame(out_adata.to_df().T)

# line 22
count = pl.DataFrame(aggregate_X(data, groupby=groupby, normalize="RPKM"))
# 修改为
out_adata = aggregate_X(data, groupby=groupby, normalize="RPKM")
count = pl.DataFrame(out_adata.to_df().T)

mkdir -p ~/DataHub/Genomics/GENCODE
cd ~/DataHub/Genomics/GENCODE
wget https://ftp.ebi.ac.uk/pub/databases/gencode/Gencode_human/release_43/gencode.v43.chr_patch_hapl_scaff.basic.annotation.gff3.gz
wget https://ftp.ebi.ac.uk/pub/databases/gencode/Gencode_human/release_43/GRCh38.primary_assembly.genome.fa.gz
gunzip GRCh38.primary_assembly.genome.fa.gz

https://cloud.tencent.com/developer/article/1624514
https://kzhang.org/SnapATAC2