def pathway_enrichment(self,
factor,
views=None,
genesets=None,
nprocesses=4,
permutation_num=0):
if genesets is None:
genesets = [
"c6.all.v7.1.symbols.gmt",
"c5.all.v7.1.symbols.gmt",
"h.all.v7.1.symbols.gmt",
"c2.all.v7.1.symbols.gmt",
]
if views is None:
views = ["methylation", "transcriptomics", "proteomics"]
df = pd.concat(
[
gseapy.ssgsea(
self.weights[v][factor],
processes=nprocesses,
permutation_num=permutation_num,
gene_sets=Enrichment.read_gmt(f"{DPATH}/pathways/{g}"),
no_plot=True,
).res2d.assign(geneset=g).assign(view=v).reset_index()
for v in views for g in genesets
],
ignore_index=True,
)
df = df.rename(columns={"sample1": "nes"}).sort_values("nes")
return df
("prot_culture_reps", "PC1"),
("prot_culture_reps", "PC2"),
("prot_broad_culture", "PC1"),
("prot_culture_reps_emt", "PC1"),
("prot_culture_reps_emt", "PC2"),
("prot_broad_culture_emt", "PC1"),
("prot_broad_culture_emt", "PC2"),
("prot_broad_culture_emt", "PC4"),
]
enr_pcs = pd.concat(
[
gseapy.ssgsea(
dsets_dred[dtype]["loadings"].loc[dtype_pc],
processes=4,
gene_sets=Enrichment.read_gmt(f"{DPATH}/pathways/{g}"),
no_plot=True,
).res2d.assign(geneset=g).assign(dtype=dtype).assign(
dtype_pc=dtype_pc).reset_index() for dtype, dtype_pc in enr_pcs
for g in genesets
],
ignore_index=True,
)
enr_pcs = enr_pcs.rename(columns={"sample1": "nes"}).sort_values("nes")
enr_pcs.to_csv(f"{RPATH}/DimRed_pcs_enr.csv.gz",
compression="gzip",
index=False)
# Plot
enr_pcs_plt = [
("prot", "PC1", "prot_broad", "PC1", 0.5),
"Transcriptomics ~ Copy number\n(Pearson's R)",
"Protein ~ Copy number\n(Pearson's R)",
)
plt.savefig(f"{RPATH}/ProteinAttenuation_attenuation_scatter.pdf",
bbox_inches="tight")
plt.savefig(f"{RPATH}/ProteinAttenuation_attenuation_scatter.png",
bbox_inches="tight")
plt.close("all")
# ### Pathway enrichement analysis of attenuated proteins
background = set(patt_corr.index)
sublist = set(patt_corr.query("cluster == 'High'").index)
enr_obj = Enrichment(gmts=["c5.all.v7.1.symbols.gmt"],
sig_min_len=15,
padj_method="fdr_bh")
enr = enr_obj.hypergeom_enrichments(sublist, background,
"c5.all.v7.1.symbols.gmt")
enr = enr[enr["adj.p_value"] < 0.01].head(30).reset_index()
enr["name"] = [i[3:].lower().replace("_", " ") for i in enr["gset"]]
_, ax = plt.subplots(1, 1, figsize=(2.0, 5.0), dpi=600)
sns.barplot(
-np.log10(enr["adj.p_value"]),
enr["name"],
orient="h",
color=CrispyPlot.PAL_DTRACE[2],
ax=ax,
# Discretise attenuated samples
gmm = GaussianMixture(n_components=2,
means_init=[[0],
[0.4]]).fit(satt_corr[["attenuation"]])
s_type, clusters = (
pd.Series(gmm.predict(satt_corr[["attenuation"]]),
index=satt_corr.index),
pd.Series(gmm.means_[:, 0], index=range(2)),
)
satt_corr["cluster"] = [
"High" if s_type[p] == clusters.argmax() else "Low"
for p in satt_corr.index
]
# Pathway enrichment
emt_sig = Enrichment.read_gmt(f"{DPATH}/pathways/emt.symbols.gmt",
min_size=0)
emt_enr = pd.Series({
s:
SSGSEA.gsea(gexp[s],
emt_sig["HALLMARK_EPITHELIAL_MESENCHYMAL_TRANSITION"])[0]
for s in gexp
})
proteasome_sig = Enrichment.read_gmt(
f"{DPATH}/pathways/proteasome.symbols.gmt", min_size=0)
proteasome_enr = pd.Series({
s: SSGSEA.gsea(prot[s].dropna(),
proteasome_sig["BIOCARTA_PROTEASOME_PATHWAY"])[0]
for s in prot
})
proteasome_enr_broad = pd.Series({