Skip to main content

Transfer learning for spatial transcriptomics data and single-cell RNA-seq data.

Project description

stTransfer

python >= 3.8

Installation

conda create -n stTranfer python=3.8
conda activate stTranfer
conda activate zt_stTransfer_2
conda install anaconda::h5py # if h5py install error
pip install torch==1.13.1 torchvision==0.14.1 torchaudio==0.13.1 --extra-index-url https://download.pytorch.org/whl/cu117

# install for cuda manylinux2014_aarch64
pip install torch-cluster==1.6.1 -f https://pytorch-geometric.com/whl/torch-1.13.1%2Bcu117.html
pip install torch-scatter==2.1.1 -f https://pytorch-geometric.com/whl/torch-1.13.1%2Bcu117.html
pip install torch-sparse==0.6.17 -f https://pytorch-geometric.com/whl/torch-1.13.1%2Bcu117.html
pip install torch-spline-conv==1.2.2 -f https://pytorch-geometric.com/whl/torch-1.13.1%2Bcu117.html
pip install pyg-lib==0.2.0 -f https://pytorch-geometric.com/whl/torch-1.13.1%2Bcu117.html
pip install torch-geometric

# install for cuda linux_x86_64
pip install torch-cluster==1.6.1+pt113cu117 -f https://pytorch-geometric.com/whl/torch-1.13.1%2Bcu117.html
pip install torch-scatter==2.1.1+pt113cu117 -f https://pytorch-geometric.com/whl/torch-1.13.1%2Bcu117.html
pip install torch-sparse==0.6.17+pt113cu117 -f https://pytorch-geometric.com/whl/torch-1.13.1%2Bcu117.html
pip install torch-spline-conv==1.2.2+pt113cu117 -f https://pytorch-geometric.com/whl/torch-1.13.1%2Bcu117.html
pip install pyg-lib==0.2.0+pt113cu117 -f https://pytorch-geometric.com/whl/torch-1.13.1%2Bcu117.html
pip install torch-geometric

# if jaxlib error if you need
conda install jaxlib

pip install git+https://github.com/zEpoch/stTransfer
# need to install again
pip install torch==1.13.1 torchvision==0.14.1 torchaudio==0.13.1 --extra-index-url https://download.pytorch.org/whl/cu117

# fix error you may need
pip install flax==0.7.2 
pip install pyro-ppl==1.8.6
pip install optax==0.1.7

And for my mechine, I need to install the following packages:

pip install wheel
git config --global url."https://mirror.ghproxy.com/https://github.com".insteadOf "https://github.com" 
pip install torch-cluster==1.6.1+pt113cu117 -f https://pytorch-geometric.com/whl/torch-1.13.1%2Bcu117.html
pip install torch-scatter==2.1.1+pt113cu117 -f https://pytorch-geometric.com/whl/torch-1.13.1%2Bcu117.html
pip install torch-sparse==0.6.17+pt113cu117 -f https://pytorch-geometric.com/whl/torch-1.13.1%2Bcu117.html
pip install torch-spline-conv==1.2.2+pt113cu117 -f https://pytorch-geometric.com/whl/torch-1.13.1%2Bcu117.html
pip install torch-geometric
git config --global url."https://mirror.ghproxy.com/https://github.com".insteadOf "https://github.com"
pip install git+https://github.com/zEpoch/stTransfer
pip install torch==1.13.1 torchvision==0.14.1 torchaudio==0.13.1 --extra-index-url https://download.pytorch.org/whl/cu117
pip install flax==0.7.2 
pip install pyro-ppl==1.8.6
pip install optax==0.1.7
from stTransfer import transfer

kwargs = {
    'sc_adata_path': '/data/work/sttransfer/stereoseq/script/adata.scvi.leiden.anno.h5ad',
    'sp_adata_path': '/data/work/sttransfer/cellbin_adatas/A01890F2_ot_left.h5ad',
    'sc_anno': 'anno',
    'sp_anno': 'annotation',
    'name': 'A01890F2_ot_left',
    'save_path': '/data/work/sttransfer/stereoseq/Result_3/',
    'sp_filter': True,
    'k_n_fold': 3, # for xgboost train
    'st_spatial_anno': 'spatial', # in the obsm
    'finetune_epochs': 50,
    'finutune_pca_dim': 0,
    'gpu': 0,
    'finutune_w_cls': 10,
    'finutune_w_gae': 1,
    'finutune_w_dae': 1,
'KD_T': 1,
'marker_genes':None
}
transfer(**kwargs)

import anndata as ad
adata = ad.read('/data/work/sttransfer/stereoseq/Result_3/spd_filtered.h5ad')
import pandas as pd
csv = pd.read_csv('/data/work/sttransfer/stereoseq/Result_3/celltype_label.h5ad')
csv.lolumns = ['0']
adata.obs['celltype'] = csv['0']

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

sttransfer-1.0.25.tar.gz (3.8 kB view details)

Uploaded Source

Built Distribution

stTransfer-1.0.25-py3-none-any.whl (21.6 kB view details)

Uploaded Python 3

File details

Details for the file sttransfer-1.0.25.tar.gz.

File metadata

  • Download URL: sttransfer-1.0.25.tar.gz
  • Upload date:
  • Size: 3.8 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/5.0.0 CPython/3.8.18

File hashes

Hashes for sttransfer-1.0.25.tar.gz
Algorithm Hash digest
SHA256 5152d04e958e32229eaeef328f64a9ef94afb8a290fb53f30d42aa9c3e3e6b2e
MD5 bd0d46cf63b55620bf940904b616696b
BLAKE2b-256 f743cfbc5d6fc36e2669fe57d136493723bf33e89c45e3d2ec57da63668aecb2

See more details on using hashes here.

File details

Details for the file stTransfer-1.0.25-py3-none-any.whl.

File metadata

  • Download URL: stTransfer-1.0.25-py3-none-any.whl
  • Upload date:
  • Size: 21.6 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/5.0.0 CPython/3.8.18

File hashes

Hashes for stTransfer-1.0.25-py3-none-any.whl
Algorithm Hash digest
SHA256 5a14a06a76a0a68138d305f454581c9edb42010f0f4684e64028d9261b73ca73
MD5 8bc81c331b4472cdd79a420e8df686e6
BLAKE2b-256 7fc36010b6b885fe07cb0d6c4b3005de3ecf0e082eefe92af45ebcce6c314a5e

See more details on using hashes here.

Supported by

AWS AWS Cloud computing and Security Sponsor Datadog Datadog Monitoring Fastly Fastly CDN Google Google Download Analytics Microsoft Microsoft PSF Sponsor Pingdom Pingdom Monitoring Sentry Sentry Error logging StatusPage StatusPage Status page