def run_embedding_proc(outdir,
plot_configs,
desc,
tsne_embeds_dict,
prefix=None):
'''Create a scatter plot for each embedding in tsne_embeds_dict
'''
plotting_df, legend_kwargs_list, default_kwargs = plot_configs
if plotting_df is None: return
for (pp, lr), embed_df in tsne_embeds_dict.items():
if prefix is None:
basename = 'tsne_embeds_pp_%d_lr_%d.png' % (pp, lr)
else:
basename = '%s_tsne_embeds_pp_%d_lr_%d.png' % (prefix, pp, lr)
outpath = os.path.join(outdir, basename)
title = '%s tSNE(perplexity=%d, learning_rate=%d)' % (desc.title(), pp,
lr)
fig, ax = plt.subplots()
plot_utils.plot_embeddings(embed_df,
plotting_df,
default_kwargs=default_kwargs,
legend_kwargs_list=legend_kwargs_list,
ax=ax,
title=title)
plot_utils.save(outpath, do_pdf=DO_PDF)
plt.close()
return
def plot_heatmap(outpath, df, sample_linkage, sample_colors, event_linkage,
desc, sample_color_lut):
assert desc.lower().startswith('altsplice') or desc.lower().startswith(
'expression')
is_altsplice = desc.lower().startswith('altsplice')
sys.setrecursionlimit(100000)
print "Plotting data ... "
graph = sns.clustermap(df.T,
col_colors=sample_colors,
col_linkage=sample_linkage,
row_linkage=event_linkage,
cmap=sns.cubehelix_palette(as_cmap=True))
graph.ax_heatmap.axis('off')
graph.ax_col_dendrogram.set_title("%s Clustering" %
' '.join(desc.split('_')).title())
graph.ax_heatmap.set_xlabel("Events")
graph.ax_heatmap.set_ylabel("Samples")
if is_altsplice: graph.cax.set_title("psi")
else: graph.cax.set_title("log(counts)")
add_legend(graph, sample_color_lut)
plot_utils.save(outpath)
return
plt.ylabel('$\Delta$ test accuracy')
plt.legend()
plt.tight_layout()
plt.title(
'ResNet-50 $\Delta$ test accuracy after {idx}{suffix} pruning iteration ({sparsity:.2%} sparsity)'
.format(
idx=it,
suffix=suffix_of_number(it),
sparsity=1 - density,
))
vals = plt.gca().get_yticks()
plt.gca().set_yticklabels(['{:,.2%}'.format(x) for x in vals])
ticks1 = np.linspace(0, 90, 11)
int_ticks1 = [round(i) for i in ticks1]
plt.gca().set_xticks(int_ticks1)
vals = plt.gca().get_xticks()
plt.gca().set_xticklabels(
[r'${} \times {}$'.format(int(x), it) if x > 0 else '0' for x in vals])
plt.tight_layout()
if plot_utils.save():
plt.savefig(
os.path.join('results_iterative',
'resnet50_{}'.format(it) + '.png'))
if plot_utils.show():
plt.show()
if not os.path.exists(outdir): os.makedirs(outdir)
desc = 'Expression'
if NORM: desc = 'Normalized ' + desc
try:
df = utils.load_large_df(path.replace('.tsv', ''))
except IOError:
df = pd.read_csv(path, sep='\t', index_col=0)
df.iloc[:] = np.minimum(df.values, np.percentile(df.values, 99, axis=0))
keep_cols = filter_to_high_var(df.values, df.columns, MAX_EVENTS)
df = df.iloc[:, keep_cols]
metadata_df = utils.load_metadata_df(config.metadata_path, df.index)
medians = collapse_to_median(df, metadata_df['cnc'])
heatmap_dists_with_dendro(medians, norm=NORM)
outpath = os.path.join(outdir, desc.lower().replace(' ', '_') +'_rep_dists_heatmap.png')
plot_utils.save(outpath, do_pdf=True)
# Add AltSplice
if False:
altsplice_event_list= ['alt_3prime', 'alt_5prime', 'intron_retention', 'exon_skip']
for event in altsplice_event_list:
path = os.path.join(config.embed_dir, 'altsplice', event, 'data.tsv')
outdir = os.path.join(config.plot_dir, 'altsplice', event, 'heatmap')
if not os.path.exists(outdir): os.makedirs(outdir)
desc = 'AltSplice %s'%event.title()
if NORM: desc = 'Normalized ' + desc
print desc
print "Loading %s" %path
try:
df = utils.load_large_df(path.replace('.tsv', ''))
except IOError:
def main(embed_dir, plot_dir, desc):
'''Runs all tasks on a single embedding.
embed_dir: location of pca & tsne embeddings
plot_dir: directory to write plots
desc: identifies embedding (used for e.g. plot titles)
'''
assert os.path.exists(embed_dir), embed_dir
if not os.path.exists(plot_dir): os.makedirs(plot_dir)
rnadeg_df = utils.load_rnadeg(config.rnadeg_path) if DEGSCORE else None
libsize_df = utils.load_libsize(config.libsize_path) if LIBSIZE else None
pca_model, pca_embeds, tsne_embeds_dict = utils.load_embeds(
embed_dir,
whitelist=WHITELIST,
pp_set=TSNE_PP_PLOT_SET,
lr_set=TSNE_LR_PLOT_SET)
metadata_df = utils.load_metadata_df(config.metadata_path,
pca_embeds.index)
metadata_df, subtype_names = utils.append_subtype(config.subtype_path,
metadata_df)
if ALL_TASKS or COLOR_CNC:
outdir = os.path.join(plot_dir, 'complete')
if not os.path.exists(outdir): os.makedirs(outdir)
plot_configs = plot_args.cnc_plotting_args(metadata_df)
run_embedding_proc(outdir, plot_configs, desc, tsne_embeds_dict)
if ALL_TASKS or HL_CNC is not None:
if ALL_TASKS or HL_CNC == 'all':
cnc_list = np.unique(metadata_df['cnc'].values)
else:
cnc_list = HL_CNC
cnc_groups = metadata_df.groupby('cnc')
for cnc in cnc_list:
cnc_index = cnc_groups.get_group(cnc).index
other_index = np.setdiff1d(metadata_df.index, cnc_index)
for subtype in subtype_names:
if DEBUG: print cnc, subtype
subtype_configs = plot_args.load_subtype_color_tumor_marker_kwargs(
metadata_df, subtype, cnc)
outdir = os.path.join(plot_dir, 'highlights_subtype', cnc)
if not os.path.exists(outdir): os.makedirs(outdir)
subtype_desc = ' '.join([subtype, desc])
run_embedding_proc(outdir,
subtype_configs,
subtype_desc,
tsne_embeds_dict,
prefix=subtype)
pass
if ALL_TASKS or TUMOR_NORMAL:
if DEBUG: print "start tumor normal"
tn_configs = plot_args.tumor_normal_plotting_args(metadata_df)
outdir = os.path.join(plot_dir, 'complete_tumor_normal')
if not os.path.exists(outdir): os.makedirs(outdir)
tn_desc = '%s Tumor/Normal' % desc
run_embedding_proc(outdir, tn_configs, tn_desc, tsne_embeds_dict)
if ALL_TASKS or LIBSIZE:
if DEBUG: print " start libsize"
cbar_title = libsize_df.columns[0]
outdir = os.path.join(plot_dir, 'qc', 'libsize')
if not os.path.exists(outdir): os.makedirs(outdir)
for (pp, lr), embed_df in tsne_embeds_dict.items():
outpath = os.path.join(outdir,
'tsne_embeds_pp_%d_lr_%d.png' % (pp, lr))
axis_title = '%s Library Size Effects\ntSNE(perplexity=%d, learning_rate=%d)' % (
desc.title(), pp, lr)
fig, ax = plt.subplots()
plot_utils.plot_continuous_color_embeddings(embed_df,
libsize_df.iloc[:, 0],
ax=ax,
axis_title=axis_title,
cbar_title=cbar_title)
plot_utils.save(outpath, do_pdf=DO_PDF)
if ALL_TASKS or DEGSCORE:
if DEBUG: print " start degscore"
outdir = os.path.join(plot_dir, 'qc', 'degscore')
if not os.path.exists(outdir): os.makedirs(outdir)
cbar_title = rnadeg_df.columns[0]
for (pp, lr), embed_df in tsne_embeds_dict.items():
outpath = os.path.join(outdir,
'tsne_embeds_pp_%d_lr_%d.png' % (pp, lr))
fig, ax = plt.subplots()
axis_title = '%s RNADeg Effects\ntSNE(perplexity=%d, learning_rate=%d)' % (
desc.title(), pp, lr)
plot_utils.plot_continuous_color_embeddings(embed_df,
rnadeg_df.iloc[:, 0],
ax=ax,
axis_title=axis_title,
cbar_title=cbar_title)
plot_utils.save(outpath, do_pdf=DO_PDF)
