def manifold_plot(man,
fpkmMatrix,
samples,
standardize=3,
log=True,
show_text=False,
sep='_',
legend_loc='best',
legend_size=14):
# man: the instance of a manifold algorithm
## preprocessing of the fpkmMatrix
if log:
fpkmMatrix = np.log10(fpkmMatrix + 1.)
if standardize == 2: # standardize along rows/genes
fpkmMatrix = zscore(fpkmMatrix, axis=1)
elif standardize == 1: # standardize along cols/samples
fpkmMatrix = zscore(fpkmMatrix, axis=0)
fpkmMatrix = man.fit_transform(fpkmMatrix.T)
fig = plt.figure(figsize=(8, 8))
ax = fig.add_subplot(111)
scatter_proxies = []
labels_show = []
groups = {}
conditions = list(set([s.split(sep)[0] for s in samples]))
for row, label in zip(fpkmMatrix, samples):
label_show = label.split(sep)[0]
idx = conditions.index(label_show)
ax.scatter(row[0],
row[1],
label='label',
color=COLORS10[idx],
visible=not show_text,
s=50,
marker='o')
if label_show not in labels_show:
labels_show.append(label_show)
scatter1_proxy = Line2D([0], [0],
ls="none",
c=COLORS10[idx],
marker='o')
scatter_proxies.append(scatter1_proxy)
if show_text:
ax.text(row[0], row[1], label, \
ha='center', va='center', rotation=0, color=COLORS10[idx], size='large')
ax.legend(scatter_proxies,
labels_show,
numpoints=1,
frameon=True,
loc=legend_loc,
prop={'size': legend_size})
ax.set_xlabel('M1', fontsize=20)
ax.set_ylabel('M2', fontsize=20)
enlarge_tick_fontsize(ax, 14)
fig.tight_layout()
plt.show()
return
def PCA_plot(fpkmMatrix, samples, standardize=3, log=True, show_text=False, sep='_', legend_loc='best', legend_size=14):
# standardize: whether to a zscore transformation on the log10 transformed FPKM
pca = PCA(n_components=None)
## preprocessing of the fpkmMatrix
if log:
fpkmMatrix = np.log10(fpkmMatrix + 1.)
if standardize == 2: # standardize along rows/genes
fpkmMatrix = zscore(fpkmMatrix, axis=1)
elif standardize == 1: # standardize along cols/samples
fpkmMatrix = zscore(fpkmMatrix, axis=0)
## remove genes with NaNs
fpkmMatrix = fpkmMatrix[~np.isnan(np.sum(fpkmMatrix, axis=1))]
## get variance captured
pca.fit(fpkmMatrix.T)
variance_explained = pca.explained_variance_ratio_[0:3]
variance_explained *= 100
## compute PCA and plot
pca = PCA(n_components=2)
pca_transformed = pca.fit_transform(fpkmMatrix.T)
fig = plt.figure(figsize=(8,8))
ax = fig.add_subplot(111)
scatter_proxies = []
labels_show = []
groups = {}
conditions = list(set([s.split(sep)[0] for s in samples]))
colors = COLORS10
if len(conditions) > 10:
colors = COLORS20
if len(conditions) > 20:
r = lambda: random.randint(0,255)
colors = ['#%02X%02X%02X' % (r(),r(),r()) for i in range(len(conditions))]
for row, label in zip(pca_transformed, samples):
label_show = label.split(sep)[0]
idx = conditions.index(label_show)
ax.scatter(row[0], row[1], label='label', color=colors[idx], s=50, marker='o')
if label_show not in labels_show:
labels_show.append(label_show)
scatter1_proxy = Line2D([0],[0], ls="none", c=colors[idx], marker='o')
scatter_proxies.append(scatter1_proxy)
if show_text:
ax.text(row[0], row[1]-2, label.split(sep)[1], \
ha='center', va='center', rotation=0, color=colors[idx], size='large')
ax.legend(scatter_proxies, labels_show, numpoints=1, frameon=True,loc=legend_loc, prop={'size':legend_size})
ax.set_xlabel('PC1 (%.2f'%variance_explained[0] + '%' + ' variance captured)', fontsize=20)
ax.set_ylabel('PC2 (%.2f'%variance_explained[1] + '%' + ' variance captured)', fontsize=20)
enlarge_tick_fontsize(ax, 14)
fig.tight_layout()
plt.show()
def manifold_plot(man, fpkmMatrix, samples, standardize=3, log=True, show_text=False, sep='_', legend_loc='best', legend_size=14):
# man: the instance of a manifold algorithm
## preprocessing of the fpkmMatrix
if log:
fpkmMatrix = np.log10(fpkmMatrix + 1.)
if standardize == 2: # standardize along rows/genes
fpkmMatrix = zscore(fpkmMatrix, axis=1)
elif standardize == 1: # standardize along cols/samples
fpkmMatrix = zscore(fpkmMatrix, axis=0)
fpkmMatrix = man.fit_transform(fpkmMatrix.T)
fig = plt.figure(figsize=(8,8))
ax = fig.add_subplot(111)
scatter_proxies = []
labels_show = []
groups = {}
conditions = list(set([s.split(sep)[0] for s in samples]))
for row, label in zip(fpkmMatrix, samples):
label_show = label.split(sep)[0]
idx = conditions.index(label_show)
ax.scatter(row[0], row[1], label='label', color=COLORS10[idx], visible=not show_text, s=50, marker='o')
if label_show not in labels_show:
labels_show.append(label_show)
scatter1_proxy = Line2D([0],[0], ls="none", c=COLORS10[idx], marker='o')
scatter_proxies.append(scatter1_proxy)
if show_text:
ax.text(row[0], row[1], label, \
ha='center', va='center', rotation=0, color=COLORS10[idx], size='large')
ax.legend(scatter_proxies, labels_show, numpoints=1, frameon=True,loc=legend_loc, prop={'size':legend_size})
ax.set_xlabel('M1', fontsize=20)
ax.set_ylabel('M2', fontsize=20)
enlarge_tick_fontsize(ax, 14)
fig.tight_layout()
plt.show()
return
def PCA_plot(fpkmMatrix, samples, standardize=3, log=True, show_text=False, sep='_', legend_loc='best', legend_size=14):
# standardize: whether to a zscore transformation on the log10 transformed FPKM
## perform PCA
variance_explained, pca_transformed = perform_PCA(fpkmMatrix, standardize=standardize, log=log)
fig = plt.figure(figsize=(8,8))
ax = fig.add_subplot(111)
scatter_proxies = []
labels_show = []
groups = {}
conditions = list(set([s.split(sep)[0] for s in samples]))
colors = COLORS10
if len(conditions) > 10:
colors = COLORS20
if len(conditions) > 20:
r = lambda: random.randint(0,255)
colors = ['#%02X%02X%02X' % (r(),r(),r()) for i in range(len(conditions))]
for row, label in zip(pca_transformed, samples):
label_show = label.split(sep)[0]
idx = conditions.index(label_show)
ax.scatter(row[0], row[1], label='label', color=colors[idx], s=50, marker='o')
if label_show not in labels_show:
labels_show.append(label_show)
scatter1_proxy = Line2D([0],[0], ls="none", c=colors[idx], marker='o')
scatter_proxies.append(scatter1_proxy)
if show_text:
ax.text(row[0], row[1]-2, label.split(sep)[1], \
ha='center', va='center', rotation=0, color=colors[idx], size='large')
ax.legend(scatter_proxies, labels_show, numpoints=1, frameon=True,loc=legend_loc, prop={'size':legend_size})
ax.set_xlabel('PC1 (%.2f'%variance_explained[0] + '%' + ' variance captured)', fontsize=20)
ax.set_ylabel('PC2 (%.2f'%variance_explained[1] + '%' + ' variance captured)', fontsize=20)
enlarge_tick_fontsize(ax, 14)
fig.tight_layout()
plt.show()
def PCA_plot2(fpkmMatrix, color_by, shape_by,
standardize=3, log=True, legend_loc='best', legend_size=14):
variance_explained, pca_transformed = perform_PCA(fpkmMatrix, standardize=standardize, log=log)
fig = plt.figure(figsize=(8,8))
ax = fig.add_subplot(111)
scatter_proxies = []
labels_show = [] # for legend and scatter proxies
color_uniq = list(set(color_by))
shape_uniq = list(set(shape_by))
colors = COLORS10
if len(color_uniq) > 10:
colors = COLORS20
if len(color_uniq) > 20:
r = lambda: random.randint(0,255)
colors = ['#%02X%02X%02X' % (r(),r(),r()) for i in range(len(color_uniq))]
shapes = 'osv^phd'
for row, label_c, label_s in zip(pca_transformed, color_by, shape_by):
idx_c = color_uniq.index(label_c)
idx_s = shape_uniq.index(label_s)
ax.scatter(row[0], row[1], label='label',
color=colors[idx_c], s=50, marker=shapes[idx_s])
label = '%s-%s' %(label_c, label_s)
if label not in labels_show:
labels_show.append(label)
scatter1_proxy = Line2D([0],[0], ls="none", c=colors[idx_c], marker=shapes[idx_s])
scatter_proxies.append(scatter1_proxy)
ax.legend(scatter_proxies, labels_show, numpoints=1, frameon=True,loc=legend_loc, prop={'size':legend_size})
ax.set_xlabel('PC1 (%.2f'%variance_explained[0] + '%' + ' variance captured)', fontsize=20)
ax.set_ylabel('PC2 (%.2f'%variance_explained[1] + '%' + ' variance captured)', fontsize=20)
enlarge_tick_fontsize(ax, 14)
fig.tight_layout()
return fig
def PCA_plot2(fpkmMatrix,
color_by,
shape_by,
standardize=3,
log=True,
legend_loc='best',
legend_size=14):
variance_explained, pca_transformed = perform_PCA(fpkmMatrix,
standardize=standardize,
log=log)
fig = plt.figure(figsize=(8, 8))
ax = fig.add_subplot(111)
scatter_proxies = []
labels_show = [] # for legend and scatter proxies
color_uniq = list(set(color_by))
shape_uniq = list(set(shape_by))
colors = COLORS10
if len(color_uniq) > 10:
colors = COLORS20
if len(color_uniq) > 20:
r = lambda: random.randint(0, 255)
colors = [
'#%02X%02X%02X' % (r(), r(), r()) for i in range(len(color_uniq))
]
shapes = 'osv^phd'
for row, label_c, label_s in zip(pca_transformed, color_by, shape_by):
idx_c = color_uniq.index(label_c)
idx_s = shape_uniq.index(label_s)
ax.scatter(row[0],
row[1],
label='label',
color=colors[idx_c],
s=50,
marker=shapes[idx_s])
label = '%s-%s' % (label_c, label_s)
if label not in labels_show:
labels_show.append(label)
scatter1_proxy = Line2D([0], [0],
ls="none",
c=colors[idx_c],
marker=shapes[idx_s])
scatter_proxies.append(scatter1_proxy)
ax.legend(scatter_proxies,
labels_show,
numpoints=1,
frameon=True,
loc=legend_loc,
prop={'size': legend_size})
ax.set_xlabel('PC1 (%.2f' % variance_explained[0] + '%' +
' variance captured)',
fontsize=20)
ax.set_ylabel('PC2 (%.2f' % variance_explained[1] + '%' +
' variance captured)',
fontsize=20)
enlarge_tick_fontsize(ax, 14)
fig.tight_layout()
plt.show()
return
def PCA_plot(fpkmMatrix,
samples,
standardize=3,
log=True,
show_text=False,
sep='_',
legend_loc='best',
legend_size=14):
# standardize: whether to a zscore transformation on the log10 transformed FPKM
pca = PCA(n_components=None)
## preprocessing of the fpkmMatrix
if log:
fpkmMatrix = np.log10(fpkmMatrix + 1.)
if standardize == 2: # standardize along rows/genes
fpkmMatrix = zscore(fpkmMatrix, axis=1)
elif standardize == 1: # standardize along cols/samples
fpkmMatrix = zscore(fpkmMatrix, axis=0)
## remove genes with NaNs
fpkmMatrix = fpkmMatrix[~np.isnan(np.sum(fpkmMatrix, axis=1))]
## get variance captured
pca.fit(fpkmMatrix.T)
variance_explained = pca.explained_variance_ratio_[0:3]
variance_explained *= 100
## compute PCA and plot
pca = PCA(n_components=2)
pca_transformed = pca.fit_transform(fpkmMatrix.T)
fig = plt.figure(figsize=(8, 8))
ax = fig.add_subplot(111)
scatter_proxies = []
labels_show = []
groups = {}
conditions = list(set([s.split(sep)[0] for s in samples]))
colors = COLORS10
if len(conditions) > 10:
colors = COLORS20
if len(conditions) > 20:
r = lambda: random.randint(0, 255)
colors = [
'#%02X%02X%02X' % (r(), r(), r()) for i in range(len(conditions))
]
for row, label in zip(pca_transformed, samples):
label_show = label.split(sep)[0]
idx = conditions.index(label_show)
ax.scatter(row[0],
row[1],
label='label',
color=colors[idx],
s=50,
marker='o')
if label_show not in labels_show:
labels_show.append(label_show)
scatter1_proxy = Line2D([0], [0],
ls="none",
c=colors[idx],
marker='o')
scatter_proxies.append(scatter1_proxy)
if show_text:
ax.text(row[0], row[1]-2, label.split(sep)[1], \
ha='center', va='center', rotation=0, color=colors[idx], size='large')
ax.legend(scatter_proxies,
labels_show,
numpoints=1,
frameon=True,
loc=legend_loc,
prop={'size': legend_size})
ax.set_xlabel('PC1 (%.2f' % variance_explained[0] + '%' +
' variance captured)',
fontsize=20)
ax.set_ylabel('PC2 (%.2f' % variance_explained[1] + '%' +
' variance captured)',
fontsize=20)
enlarge_tick_fontsize(ax, 14)
fig.tight_layout()
plt.show()