cnv = cnv_obj.filter(subset=list(prot))
cnv_norm = np.log2(cnv.divide(prot_obj.ss.loc[cnv.columns, "ploidy"]) + 1)
LOG.info(f"Copy number: {cnv.shape}")
# Overlaps
#
samples = list(set.intersection(set(prot), set(gexp), set(cnv)))
genes = list(
set.intersection(set(prot.index), set(gexp.index), set(cnv.index),
set(prot_broad.index)))
LOG.info(f"Genes: {len(genes)}; Samples: {len(samples)}")
# Data tranformations
#
gexp_t = pd.DataFrame(
{i: Utils.gkn(gexp.loc[i].dropna()).to_dict()
for i in genes}).T
##
#
s_corr = pd.DataFrame({
s1: {
s2: two_vars_correlation(prot[s1], gexp[s2])["corr"]
for s2 in samples
}
for s1 in samples
})
s_corr.to_csv(
"/Users/Downloads/Proteomics_Transcriptomics_Corr_Matrix.csv")
# Sample-wise Protein/Gene correlation with CopyNumber - Attenuation
stromal_count != 1].index)]
# Import proteomics data-sets
#
dmatrix, ms_type, ctypes = [], [], []
for ctype, dfile in CPTAC_DATASETS:
df = pd.read_csv(f"{CPTAC_DPATH}/linkedomics/{dfile}",
sep="\t",
index_col=0)
if "COADREAD" in dfile:
df = df.replace(0, np.nan)
df = df.pipe(np.log2)
df = pd.DataFrame(
{i: Utils.gkn(df.loc[i].dropna()).to_dict()
for i in df.index}).T
# Simplify barcode
df.columns = [i[:12].replace(".", "-") for i in df]
# Cancer type
ctypes.append(pd.Series(ctype, index=df.columns))
# MS type
ms_type.append(
pd.Series("LF" if "COADREAD" in dfile else "TMT",
index=df.columns))
dmatrix.append(df)