prism-grn 1.1.0

A Probabilistic Model for Recover GRNs with Multi-Omics Data https://github.com/Ying-Lab/PRISM

PRISM

A Probabilistic Bayesian Model to Recover Gene Regulatory Networks by Incorporating a Biologically Interpretable Structure and Effectively Utilizing Multi-Omics Data

Installation

git clone https://github.com/Ying-Lab/PRISM
cd PRISM
pip install -r requirements.txt 
python setup.py install

Example

from prism import model
from prism import utils
from utils import load_sc_data, load_sc_causal_data

args['flag'] = False
adj_train, feature, feature_ATAC, train_ids, val_ids, test_ids, train_labels, val_labels, test_labels = load_sc_data(Expression_data_path, Genescore_data_path, label_path)
adj_train = F.normalize(adj_train, p=1, dim=1)

scc = model.PRISM( nfeat=feature.shape[1],     ## the size of feature -> cell num
                    nhid=args['hidden'],         ## hidden layer size
                    dropout=args['dropout'],     
                    ns=args['ns'],               ## the size of VAE node embedding 
                    alpha=args['alpha'],         
                    flag=args['flag'],           ## causal or not
                    use_cuda= args['cuda']).to(device)

The more detailed usage is exemplified in demo.

Citation