9e75f44f1a
Source-only snapshot of the cluster branch for WES execution. Large reference files (HPA/MANE/ensemble FASTA, model weights, ~597 MB) are omitted: they are baked into the container images at build time and mounted from the dreamdock-data PVC at runtime, and exceed the Gitea request size limit. Pipeline entry point is main.nf, which orchestrates the biotransformer, conplex and tissue modules as a single workflow. Ligand inputs are read from the eureka workspace; protein_zarr and chembl_db come from the dreamdock-data PVC.
40 lines
1.8 KiB
Python
40 lines
1.8 KiB
Python
import argparse
|
|
import pandas as pd
|
|
import numpy as np
|
|
|
|
def get_tissue_distribution(file_name):
|
|
#load protein expression per tissue
|
|
HPA = pd.read_csv('/home/omic/HPA_normal_ihc_data.tsv', sep = '\t')
|
|
#load enst symbol mapping data
|
|
MANE_all_transcipts = pd.read_csv('/home/omic/MANE_all_transcipts.csv')
|
|
|
|
#load interaction data
|
|
significant_interactions = pd.read_csv(file_name, sep = '\t')
|
|
|
|
#filter out tissues with low confidence
|
|
HPA = HPA[(HPA['Level'] == 'Medium') | (HPA['Level'] == 'High')]
|
|
|
|
#get protrin symbols from siginificant interactions
|
|
prot_enst = [i.split('_')[0] for i in pd.unique(significant_interactions['transcipt'])]
|
|
prot_symbol = [MANE_all_transcipts[MANE_all_transcipts['transcipt'] == i]['symbol'].iloc[0] for i in prot_enst]
|
|
prot_symbol = pd.unique(prot_symbol)
|
|
|
|
#get protein expression per tissue
|
|
tissue_per_prot_symbol = [list(pd.unique(HPA[HPA['Gene name'] == i]['Tissue'])) for i in prot_symbol]
|
|
#transform list do array
|
|
tissue_per_prot_symbol_array = np.array([[i in j for i in pd.unique(HPA['Tissue'])] for j in tissue_per_prot_symbol])
|
|
tissue_per_prot_symbol_pd = pd.DataFrame(tissue_per_prot_symbol_array)
|
|
tissue_per_prot_symbol_pd.columns = pd.unique(HPA['Tissue'])
|
|
tissue_per_prot_symbol_pd = tissue_per_prot_symbol_pd.set_index(prot_symbol)
|
|
|
|
#save
|
|
save_name = file_name.split('significant_interactions.tsv')[0] + 'tissue_distribution.tsv'
|
|
tissue_per_prot_symbol_pd.to_csv(save_name, sep = '\t')
|
|
|
|
if __name__ == "__main__":
|
|
parser = argparse.ArgumentParser(description="Get tissue distribution from *significant_interactions.tsv.")
|
|
parser.add_argument("--file_name", required=True, help="file_name")
|
|
args = parser.parse_args()
|
|
|
|
get_tissue_distribution(args.file_name)
|