# matching samples between two different preps
matched_data = filter.filter_by_cpm(
data.loc[:, data.columns.str.contains('NSC')],
min_cpm=min_cpm,
min_n_samples=1)
matched_log_cpm = log_cpm(matched_data)
row_colours = pd.DataFrame(common.COLOUR_BREWERS[2][0],
index=matched_data.columns,
columns=['Library'])
row_colours.loc[row_colours.index.str.contains(
'smartseq')] = common.COLOUR_BREWERS[2][1]
# clustering plot
cg = clustering.plot_correlation_clustermap(matched_log_cpm,
row_colors=row_colours)
cg.gs.update(bottom=0.35, right=0.65)
cg.savefig(os.path.join(outdir, "cluster_log_cpm_corr_all_genes.png"),
dpi=200)
mad = transformations.median_absolute_deviation(
matched_log_cpm).sort_values(ascending=False)
cg = clustering.plot_correlation_clustermap(
matched_log_cpm.loc[mad.index[:3000]], row_colors=row_colours)
cg.gs.update(bottom=0.35, right=0.65)
cg.savefig(os.path.join(outdir, "cluster_log_cpm_corr_3000_genes.png"),
dpi=200)
# repeat with TMM norming
matched_log_cpm_n = transformations.edger_tmm_normalisation_cpm(
matched_data)
row_colours.loc[row_colours.index.str.contains('mDURA')] = 'k'
row_colours.loc[row_colours.index.str.contains(
'mDURA5_NSCmus_N3BE50.2')] = 'y'
row_colours.loc[row_colours.index.str.contains('mDURA6_NSCmus')] = 'y'
# Spearman distance
cor, pval = pairwise_correlation(log_dat_filt.transpose(),
method='spearman')
di = 1 - cor
for i in range(di.shape[0]):
di.iloc[i, i] = 0.
di = hc.distance.squareform(di)
cg = clustering.plot_correlation_clustermap(log_dat_filt,
row_colors=row_colours,
distance=di,
method='average')
cg.gs.update(bottom=0.3, right=0.7)
cg.savefig(os.path.join(outdir,
"log_tpm_spearman_distance_average_linkage.png"),
dpi=200)
# Euclidean distance
# cg2 = clustering.plot_correlation_clustermap(
# log_dat_filt,
# row_colors=row_colours,
# method='complete',
# metric='euclidean',
# )
# cg2.gs.update(bottom=0.3, right=0.7)
meta.loc[meta.index.str.contains('024'), 'subgroup'] = 'Unknown'
meta.loc[meta.index.str.contains('026'), 'subgroup'] = 'Unknown'
meta.loc[meta.index.str.contains('044'), 'subgroup'] = 'Mesenchymal'
meta.loc[meta.index.str.contains('GIBCO'), 'subgroup'] = 'NSC'
p = PCA(n_components=3)
p.fit(data.transpose())
y = p.transform(data.transpose())
pca.pca_plot_by_group_3d(y, meta.cell_type, plot_ellipsoids=False)
s = data.std(axis=1).sort_values(ascending=False)
# plot a correlation clustermap of GBM without 024 (which is a definite outlier)
clustering.plot_correlation_clustermap(
data.loc[s.index[:8000], (meta.cell_type == 'GBM') &
(~meta.index.str.contains('024'))])
ref_data, ref_meta = methylation_array.gse36278()
# only keep intersecting probes
probe_idx = ref_data.index.intersection(data.index)
sample_names = np.random.permutation(ref_data.columns)
n_train = 120
n_test = ref_data.shape[1] - n_train
ref_train = ref_data.loc[probe_idx, sample_names[:n_train]]
ref_test = ref_data.loc[probe_idx, sample_names[n_train:]]
ref_meta_train = ref_meta.loc[sample_names[:n_train]]
ref_meta_test = ref_meta.loc[sample_names[n_train:]]
out = sns.jointplot(np.log2(abs_diff + 1.),
rel_diff,
alpha=0.3,
stat_func=None)
out.ax_joint.set_ylim([0, 1])
out.ax_marg_y.set_ylim([0, 1])
ax = out.ax_joint
ax.set_xlabel("Log2 absolute difference")
ax.set_ylabel("Relative difference = absolute difference / mean")
ax.set_title(m)
plt.tight_layout()
ax.figure.savefig(os.path.join(outdir,
"abs_rel_difference_%s.png" % m),
dpi=200)
ax.figure.savefig(os.path.join(outdir,
"abs_rel_difference_%s.pdf" % m))
# list the genes for which one is zero
the_list = rnaseq_data.annotate(
twodata.loc[(twodata == 0).any(axis=1)],
annotate_by='Approved Symbol')
if the_list.size > 0:
print "%s. Genes for which one is zero and one >100: %s" % (
m, ', '.join(the_list.index))
cg = clustering.plot_correlation_clustermap(logdata)
cg.gs.update(bottom=0.25, right=0.7)
cg.fig.savefig(os.path.join(outdir, "clustermap_correlation_coeff.png"),
dpi=200)
cg.fig.savefig(os.path.join(outdir, "clustermap_correlation_coeff.pdf"))
meta_all = obj_all.meta
cpm_all = data_all.divide(data_all.sum(axis=0), axis=1) * 1e6
keep = (cpm_all > .5).sum(axis=1) > 5
the_dat = np.log2(data_all.loc[keep] + 1)
fig = plt.figure(figsize=(10, 10))
ax = fig.add_subplot(111)
ax = corr.plot_correlation_coefficient_array(the_dat, vmin=0.4, ax=ax)
plt.setp(ax.xaxis.get_ticklabels(), rotation=90)
fig.tight_layout()
fig.savefig(os.path.join(outdir, 'corr_coeff.png'), dpi=200)
fig.savefig(os.path.join(outdir, 'corr_coeff.pdf'))
cg = clustering.plot_correlation_clustermap(the_dat)
cg.fig.savefig(os.path.join(outdir, 'corr_clustermap_all_genes.png'),
dpi=200)
cg.fig.savefig(os.path.join(outdir, 'corr_clustermap_all_genes.pdf'))
# correlation clustermap with only the CL57BL/6 samples
obj_all2 = rnaseq_data.MultipleBatchLoader(
[obj, obj64411, obj43916, obj86248, obj36114])
# remove some samples
to_remove = ['eNSC%dmouse' % i for i in (3, 5, 6)] + \
['mDura%smouse' % i for i in ('3N1', '5N24A', '6N6')] + \
['E14_Day4_RNA-seq', 'EmbryonicNSC1', 'EmbryonicNSC2']
meta2 = obj_all2.meta.drop(
to_remove,
axis=0,
)
cm.gs.update(bottom=0.3)
cm.savefig(os.path.join(outdir, fname.format(ext='png')), dpi=200)
fname = "all_samples_dendrogram_log_corr_top%d_by_mad.{ext}" % n_t
d = clustering.dendrogram_with_colours(
abg_log.loc[amad_log.index[:n_t]],
row_colours_all,
fig_kws={'figsize': (5.5, 10)},
vertical=False)
d['fig'].savefig(os.path.join(outdir, fname.format(ext='png')),
dpi=200)
fname = "all_samples_corrplot_log_top%d_by_mad.{ext}" % n_t
cm = clustering.plot_correlation_clustermap(
abg_log.loc[amad_log.index[:n_t]],
row_colors=row_colours_all,
n_gene=n_t,
)
plt.setp(cm.ax_heatmap.get_xticklabels(), rotation=90, fontsize=10)
plt.setp(cm.ax_heatmap.get_yticklabels(), rotation=0, fontsize=10)
cm.gs.update(bottom=0.35, right=0.65)
cm.savefig(os.path.join(outdir, fname.format(ext='png')), dpi=200)
# data subset: our data and Pten/P53 samples
mouse_data = rnaseq_data.mouse_nsc_salmon(units=units)
mouse_data_by_gene = general.ensembl_transcript_quant_to_gene(mouse_data,
tax_id=10090)
dat_pten = general.ensembl_transcript_quant_to_gene(
rnaseq_data.mouse_gbm_pten_p53(source='salmon', units=units),
metric='correlation',
method='average',
)
out['fig'].savefig(os.path.join(
outdir,
"gbm_nsc_correlation_dendrogram_logtransform_top%d.png" % NGENE),
dpi=200)
out['fig'].savefig(
os.path.join(
outdir,
"gbm_nsc_correlation_dendrogram_logtransform_top%d.pdf" %
NGENE))
cg = clustering.plot_correlation_clustermap(
log_data.loc[mad_log_srt.index[:NGENE]],
vmin=0.,
vmax=1.,
metric='correlation')
cg.gs.update(bottom=0.3, right=0.7)
cg.fig.savefig(os.path.join(
outdir,
"gbm_nsc_correlation_clustermap_logtransform_top%d.png" % NGENE),
dpi=200)
cg.fig.savefig(
os.path.join(
outdir,
"gbm_nsc_correlation_clustermap_logtransform_top%d.pdf" %
NGENE))
out = clustering.dendrogram_with_colours(
vst_data.loc[mad_vst_srt.index[:NGENE]],
ax.figure.savefig(os.path.join(outdir, "pca_ribozero_polya.pdf"))
# by cell line
subgroups = data_all_n.columns.str.replace(r'[^0-9]*', '')
ax = pca_plot_by_group_2d(y, subgroups=subgroups, ellipses=False, auto_scale=False)
ax.legend(loc='upper left', frameon=True, facecolor='w', edgecolor='b')
plt.tight_layout()
ax.figure.savefig(os.path.join(outdir, "pca_ribozero_polya_byline.png"), dpi=200)
ax.figure.savefig(os.path.join(outdir, "pca_ribozero_polya_byline.pdf"))
# hierarchical clustering
subgroups = pd.DataFrame(
['b'] * 3 + ['r'] * 2 + ['g'] * 5,
index=data_all_n.columns,
columns=['Prep type']
)
legend_lbl = {'FFPE': 'b', 'frozen': 'r', 'Poly(A)': 'g'}
res = clustering.dendrogram_with_colours(
comp_data,
subgroups,
legend_labels=legend_lbl,
metric='correlation',
method='average'
)
res['fig'].savefig(os.path.join(outdir, 'clustering_dendrogram.png'), dpi=200)
res['fig'].savefig(os.path.join(outdir, 'clustering_dendrogram.pdf'))
# can add n_gene kwarg here to pick top N genes by MAD:
cg = clustering.plot_correlation_clustermap(comp_data)
cg.savefig(os.path.join(outdir, 'clustering_corr_map.png'), dpi=200)
cg.savefig(os.path.join(outdir, 'clustering_corr_map.pdf'))
