logger.warn(
"%d genes in the %s signature do not match with the data index and will be dropped: %s.",
len(missing), k, ', '.join(missing))
genesets[k] = g_in
# check here whether there is any overlap
vs, vc = setops.venn_from_arrays(*genesets.values())
n_overlap = sum(
[vc[t] for t in setops.binary_combinations_sum_gte(len(genesets), 2)])
if n_overlap > 0:
logger.warn(
"The %d gene signatures used here have %d overlapping genes - please check this is OK.",
len(genesets), n_overlap)
# run ssGSEA then Z transform the results
es = gsva.ssgsea(rnaseq_dat, genesets)
es_z = z_transform(es, axis=1)
# export
for_export = es_z.transpose()
for_export.insert(for_export.shape[1], 'Verhaak classification',
rnaseq_meta.loc[for_export.index, 'expression_subclass'])
for_export.insert(for_export.shape[1], 'Wang classification',
rnaseq_meta.loc[for_export.index, 'wang_classification'])
for_export.to_excel(
os.path.join(outdir, "tcga_signature_scores_and_subgroups.xlsx"))
# boxplot by subgroup
if class_method == 'verhaak':
groups = rnaseq_meta.expression_subclass
# remove any small groups (e.g. a single G-CIMP instance)
to_export = the_list_mo.copy()
to_export.columns = ['Mouse BMDM', 'Mouse MG']
all_genes_in_set = setops.reduce_union(*the_list_hu.values())
# DEBUG: disable filtering genes - why would we need to?
if False:
# remove genes that have no appreciable expression level
# >=10 samples must have FPKM >= 1
to_keep = ((rnaseq_dat > fpkm_cutoff).sum(axis=1) > fpkm_min_samples) | (rnaseq_dat.index.isin(all_genes_in_set))
print "Keeping %d / %d genes that are sufficiently abundant" % (to_keep.sum(), to_keep.size)
rnaseq_dat = rnaseq_dat.loc[to_keep]
# run ssGSEA
rna_es = gsva.ssgsea(rnaseq_dat, rna_list_hu)
ffpe_es = gsva.ssgsea(ffpe_dat, rna_list_hu)
# scale using the Z transform
# TODO: previous operation had axis=None
rna_z = z_transform(rna_es, axis=1)
ffpe_z = z_transform(ffpe_es, axis=1)
fig = plt.figure(num="TCGA RNA-Seq")
ax = fig.add_subplot(111)
for g_name in the_list_hu:
sns.kdeplot(rna_z.loc[g_name], ax=ax)
ax.set_xlabel("Normalised ssGSEA score")
ax.set_ylabel("Density")
fig.savefig(os.path.join(outdir, 'rnaseq_ssgsea_score_tcga.png'), dpi=200)
fig.savefig(os.path.join(outdir, 'rnaseq_ssgsea_score_tcga.pdf'))