def calcTFs(
expr,
tf_names,
db,
prefix,
motif_path='../data/pySCENIC/ref/motifs-v9-nr.hgnc-m0.001-o0.0.tbl',
out_path='../data/pySCENIC',
ppn=8):
"""Computes motifs, regulons and trancriptional factor activation using pySCENIC.
Arguments
---------
expr: `pandas DataFrame`
cell X gene raw counts; FPKM; not TPM as coexpression will be calculated
tf_names: `list` (`str`)
curated human transcriptional factor downloaded from github: pySCENIC/ref/hs_hgnc_curated_tfs.txt
db: `list` (`FeatherRankingDatabase()`)
feather files, ranking genome [FeatherRankingDatabase(name="hg38__refseq-r80__10kb_up_and_down_tss")]
prefix: `str` (default: `None`)
Specify name to save files (eg, cell line names)
Returns
-------
Do not return but write files (the calc takes too long...)
"""
# Inference of co-expression modules
adjacencies = grnboost2(expr, tf_names=tf_names, verbose=True)
modules = list(modules_from_adjacencies(adjacencies, expr))
# Calculate a list of enriched motifs and the corresponding target genes for all modules.
with ProgressBar():
df = prune2df(db, modules, motif_path, num_workers=ppn)
# Create regulons from this table of enriched motifs.
regulons = df2regulons(df)
# Save the enriched motifs and the discovered regulons to disk.
with open('{}/{}_motifs.csv'.format(out_path, prefix), "wb") as f:
pickle.dump(regulons, f)
auc_mtx = aucell(expr, regulons, num_workers=ppn)
tfs = [tf.strip('(+)') for tf in auc_mtx.columns]
auc_mtx.to_csv('{}/{}_auc_mtx.csv'.format(out_path, prefix))
print('finished calculation for %s' % (prefix))
## Prune modules for targets with cis regulatory footprints (aka RcisTarget) ### Calculate a list of enriched motifs and the corresponding target genes for all modules. if not os.path.isfile(motifs_fname): df = prune2df(dbs, modules, motif_annotations, num_workers=n_cores) df.to_csv(motifs_fname) else: df = pd.read_csv(motifs_fname) del modules ### Create regulons from this table of enriched motifs. if not os.path.isfile(regulons_fname): regulons = df2regulons(df) pickle.dump(regulons, open(regulons_fname, 'wb')) else: regulons = pickle.load(open(regulons_fname, 'rb')) del df ## Cellular regulon enrichment matrices if not os.path.isfile(aucell_train_fname): auc_train = aucell(data_train, regulons, num_workers=n_cores) auc_train.to_csv(aucell_train_fname, sep=',', header=True, index=True, compression='gzip') else: auc_train = pd.read_csv(aucell_train_fname, index_col=0)
ex_matrix, tf_names=tf_names,
verbose=True) # runs improved GRNBoost instance of GENIE3
modules = list(modules_from_adjacencies(
adjacencies, ex_matrix)) # identifies modules from GENIE3
# save GRNBoost2 product so we don't have to repeat again
adjacencies.to_csv("grnboost_output.csv")
# load product in case something goes wrong
adjacencies = pd.read_csv("grnboost_output.csv", index_col=0)
# cisTarget process: IDs cis-regulatory footprints from motifs around the TSS
with ProgressBar(
): # calculate a list of enriched motifs and the corresponding target genes for all modules
df = prune2df(dbs, modules, "motifs-v9-nr-mgi.txt")
regulons = df2regulons(
df) # create regulons from this table of enriched motifs
# save the discovered motifs and regulons
df.to_csv(motifs_filename)
with open(regulons_filename, "wb") as f:
pickle.dump(regulons, f)
# load the discovered motifs and regulons if saved previously
df = load_motifs(motifs_filename)
with open(regulons_filename, "rb") as f:
regulons = pickle.load(f)
# AUCell process: finds enrichment of each discovered regulon
auc_matrix = aucell(ex_matrix, regulons, num_workers=4)
# export the product back to R for analysis
if __name__ =='__main__':
# #1. Inference of co-expression modules
# print('Inference...')
# df_adj=grnboost2(df_cnt, tf_names=tf_name, verbose=True)
# df_adj.to_csv(f'{fd_out}/adj.csv', index=False)
#2. prune
df_adj=pd.read_csv(f'{fd_out}/adj.csv') #if missing, always stuck at 98%
print('Prune...')
l_mod=list(modules_from_adjacencies(df_adj, df_cnt))
with ProgressBar():
df_prune = prune2df(l_db, l_mod, f_motif)
df_prune.to_csv(f'{fd_out}/prune.csv')
#3. create regulon
print('Regulon...')
regulon=df2regulons(df_prune)
#4. Save the enriched motifs and the discovered regulons
with open(f'{fd_out}/regulon.pkl', "wb") as f:
pickle.dump(regulon, f)
#5. auc
print('AUC...')
with open(f'{fd_out}/regulon.pkl', "rb") as f: #if missing, always stuck
regulon=pickle.load(f)
df_auc=aucell(df_cnt, regulon, num_workers=10)
df_auc.to_csv(f'{fd_out}/auc.csv')