def mutual_information(dataframe, measure1, measure2, report): name = '%s - %s' % (measure1, measure2) vector_list_x = ee.vectorize(dataframe[measure1]) vector_list_y = ee.vectorize(dataframe[measure2]) mutual_information = ee.mi(vector_list_x, vector_list_y) report_line = 'Informacion Mutua %s: %s\n'%(name, mutual_information) report.write(report_line) report.flush()
def mutualInformation(ImageStack,TimeRef,FlagROI,ROI):
MutualInfo = []
for z in range(TimeRef[0]+1,TimeRef[1]):
if FlagROI:
image1 = ImageStack[z-1,ROI[0]:ROI[1],ROI[2]:ROI[3]]
image2 = ImageStack[z,ROI[0]:ROI[1],ROI[2]:ROI[3]]
else:
image1 = ImageStack[z-1,:,:]
image2 = ImageStack[z,:,:]
c=ee.vectorize(image1.flatten())
d=ee.vectorize(image2.flatten())
mi=ee.mi(c,d)
MutualInfo.append(mi)
return MutualInfo
ax[0].set_xlabel('Percent White')
plt.tight_layout()
fig.savefig('figures/MN_GA_density.pdf')
plt.close('all')
sns.set_style('white')
fig, ax = plt.subplots(1, 2, figsize=(6, 2))
# bins=np.arange(-.1,1.1,.05)
mn = EE.kldiv(EE.vectorize(np.random.normal(.82, np.sqrt(.82 * (1 - .82) / 100), 1000)), EE.vectorize(MN_values),
k=20)
ga = EE.kldiv(EE.vectorize(np.random.normal(.55, np.sqrt(.55 * (1 - .55) / 100), 1000)), EE.vectorize(GA_values),
k=20)
objects = [mn, ga]
y_pos = np.arange(len(objects))
ax[0].bar(y_pos * 2 + 1, objects, align='center', color=['darkturquoise', 'magenta'])
# plt.xticks(y_pos, objects)
# plt.ylabel('Usage')
# plt.title('Programming language usage')
ax[0].set_xticks(y_pos * 2 + 1)
ax[0].set_xticklabels(['Minnesota', 'Georgia'])
ax[0].set_xlim([0, 4])
ax[1].bar(y_pos * 2 + 1, [9.2, 13.3], align='center', color=['darkturquoise', 'magenta'])
spearman = sp.spearmanr(
color_mat[:, 7, t][np.where(~np.isnan(color_mat[:, 5, t]))],
color_mat[:, 9, t][np.where(~np.isnan(color_mat[:, 5, t]))])[0]
if n < 2:
if n == 0:
if t == t_len - 1:
total_x_wt = np.append(total_x_wt, x.ravel())
total_y_wt = np.append(total_y_wt, y.ravel())
total_z_wt = np.append(total_z_wt, z.ravel())
if n == 1:
if t == t_len - 1:
total_x_c = np.append(total_x_c, x.ravel())
total_y_c = np.append(total_y_c, y.ravel())
total_z_c = np.append(total_z_c, z.ravel())
try:
info = ee.mi(ee.vectorize(y), ee.vectorize(z), k=3)
except:
info = 0
n_cells = len(np.where(~np.isnan(color_mat[:, 5, t]))[0])
df2 = pd.DataFrame({
'X': [np.std(x) / np.mean(x)],
'Y': [np.std(y) / np.mean(y)],
'Z': [np.std(z) / np.mean(z)],
'Information': [info],
'Correlation': [spearman],
'nCells': [n_cells],
'label': [tags[n]]
})
frames = [df, df2]
df = pd.concat(frames)
def main():
sns.set_style('white')
folder1 = 'Fig3_SourceData_1'
names1 = listdir(folder1)
if '.DS_Store' in names1:
names1.remove('.DS_Store')
names1 = sorted(names1, key=lambda x: int(x.split('.')[0]))
names1 = [folder1 + '/' + name for name in names1]
folder2 = 'Fig3_SourceData_2'
names2 = listdir(folder2)
if '.DS_Store' in names2:
names2.remove('.DS_Store')
names2 = sorted(names2, key=lambda x: int(x.split('.')[0]))
names2 = [folder2 + '/' + name for name in names2]
names = names1 + names2
df_mar = pd.DataFrame({
'X': [],
'Y': [],
'Z': [],
'Information': [],
'Correlation': [],
'nCells': [],
'label': []
})
tags = ['TX', 'TL']
n = 0
num_samps_each = 5
total_x_wt = np.array([])
total_x_c = np.array([])
total_y_wt = np.array([])
total_z_wt = np.array([])
total_y_c = np.array([])
total_z_c = np.array([])
for j, name in enumerate(names):
print(name)
mat_contents = sio.loadmat(name)
color_mat = mat_contents['data3D']
t_len = mat_contents['data3D'].shape[2]
for t in range(t_len):
x = color_mat[:, 5, t][np.where(~np.isnan(color_mat[:, 5, t]))]
y = color_mat[:, 7, t][np.where(~np.isnan(color_mat[:, 5, t]))]
z = color_mat[:, 9, t][np.where(~np.isnan(color_mat[:, 5, t]))]
spearman = sp.spearmanr(
color_mat[:, 7, t][np.where(~np.isnan(color_mat[:, 5, t]))],
color_mat[:, 9, t][np.where(~np.isnan(color_mat[:, 5, t]))])[0]
if n < 2:
if n == 0:
if t == t_len - 1:
total_x_wt = np.append(total_x_wt, x.ravel())
total_y_wt = np.append(total_y_wt, y.ravel())
total_z_wt = np.append(total_z_wt, z.ravel())
if n == 1:
if t == t_len - 1:
total_x_c = np.append(total_x_c, x.ravel())
total_y_c = np.append(total_y_c, y.ravel())
total_z_c = np.append(total_z_c, z.ravel())
try:
info = ee.mi(ee.vectorize(y), ee.vectorize(z), k=3)
except:
info = 0
n_cells = len(np.where(~np.isnan(color_mat[:, 5, t]))[0])
df2 = pd.DataFrame({
'X': [np.std(x) / np.mean(x)],
'Y': [np.std(y) / np.mean(y)],
'Z': [np.std(z) / np.mean(z)],
'Information': [info],
'Correlation': [spearman],
'nCells': [n_cells],
'label': [tags[n]]
})
frames = [df_mar, df2]
df_mar = pd.concat(frames)
if (j + 1) % num_samps_each == 0:
n += 1
f3, ax3 = plt.subplots(1, 2, figsize=(10, 3))
ax3[0].set_xlim([-10, 300])
sns.set_style('white')
colors = ['salmon', 'darkblue']
tags = ['TX', 'TL']
tvect = np.linspace(0, 400, 1000)
recs = []
ax30 = ax3[0].twinx()
for j, color in enumerate(colors):
x, y = df_mar.loc[df_mar.label == tags[j]].nCells, df_mar.loc[
df_mar.label == tags[j]].X
x, y2 = df_mar.loc[df_mar.label == tags[j]].nCells, df_mar.loc[
df_mar.label == tags[j]].Information
ys = df_mar.loc[df_mar.label == tags[j]].Y
zs = df_mar.loc[df_mar.label == tags[j]].Z
nbins = 15
bins = np.linspace(0, 275, nbins)
idx = np.digitize(x, bins)
means = [0]
errors = [0]
means2 = []
errors2 = []
for i in range(nbins):
if j == 0:
ax3[0].errorbar(bins[i] + (200 / (2 * nbins)),
np.mean(y[idx == i + 1]),
fmt='o',
color=color)
ax3[1].errorbar(bins[i] + (200 / (2 * nbins)),
np.mean(y2[idx == i + 1]),
fmt='o',
color=color)
else:
ax30.errorbar(bins[i] + (200 / (2 * nbins)),
np.mean(y[idx == i + 1]),
fmt='o',
color=color)
ax3[1].errorbar(bins[i] + (200 / (2 * nbins)),
np.mean(y2[idx == i + 1]),
fmt='o',
color=color)
# ax.errorbar(bins[i]+(200/(2*nbins)),np.mean(y[idx==i+1]),yerr=np.std(y[idx==i+1]),fmt='o',color=color)
means.append(np.mean(y[idx == i + 1]))
errors.append(sp.sem(y[idx == i + 1]))
means2.append(np.mean(y2[idx == i + 1]))
errors2.append(sp.sem(y2[idx == i + 1]))
means = np.asarray(means)
errors = np.asarray(errors)
xvect = bins + (200 / (2 * nbins))
xvect = np.insert(xvect, 0, 0)
if j == 0:
ax3[0].fill_between(xvect,
means - errors,
means + errors,
color=color,
alpha=0.5)
else:
ax30.fill_between(xvect,
means - errors,
means + errors,
color=color,
alpha=0.5)
means2 = np.asarray(means2)
errors2 = np.asarray(errors2)
ax3[1].fill_between(bins + (200 / (2 * nbins)),
means2 - errors2,
means2 + errors2,
color=color,
alpha=0.5)
recs.append(mpatches.Rectangle((0, 0), 1, 1, fc=colors[j]))
ax3[0].legend(recs[::-1], ['MarA Fusion', 'WT MarA'],
title='Strain',
loc=4)
ax3[1].legend(recs[::-1], ['MarA Fusion', 'WT MarA'],
title='Strain',
loc=4)
ax3[0].set_ylabel('Coefficient of Variation')
ax3[0].set_title('Activator Variance over Time')
ax3[0].set_xlabel('Number of Cells in Microcolony')
ax3[1].set_xlabel('Number of Cells in Microcolony')
ax3[1].set_title('Downstream coordination over time')
ax3[1].set_ylabel('Infromation (bits)')
ax3[0].set_ylim([0, 0.25])
plt.tight_layout()
f3.savefig('figures/modified_marA_TS.pdf', bbox_inches='tight')
# = H(T) # In this case, I use the average entropy # over the training examples iXT1.append(t1_ent / h_cnt) print(iXT1) iXT2.append(t2_ent / h_cnt) print(iXT2) iXT3.append(t3_ent / h_cnt) print(iXT3) iXT4.append(t4_ent / h_cnt) print(iXT4) # Estimate the continuous mutual information using the # k-nearst neighbors estimator # https://github.com/gregversteeg/NPEET ys = ee.vectorize(ys) iTY1.append(ee.mi(t1s, ys)) print(iTY1) iTY2.append(ee.mi(t2s, ys)) print(iTY2) iTY3.append(ee.mi(t3s, ys)) print(iTY3) iTY4.append(ee.mi(t4s, ys)) print(iTY4) xs = [] ys = [] t1s = [] t2s = [] t3s = [] t4s = []
def scoreDependence(X, Y):
dep = ee.mi(ee.vectorize(X), ee.vectorize(Y))
return dep