def plot_correlations(self):
# Figure that calculates the Euclidean distance between each EFM and
# the "experimental" flow, and overlays that information on the
# standard "Pareto" plot
exp_flux_df = self.fluxes_df.copy()
# remove the exchange reactions (xchg_*)
exp_flux_df = exp_flux_df.loc[
exp_flux_df.reaction_id.str.find('xchg') != 0, :]
exp_flux_df.reaction_id = exp_flux_df.reaction_id.apply(
D.FIX_REACTION_ID)
fig0, axs0 = plt.subplots(1, 2, figsize=(15, 7))
rates_df, params_df, km_df, enzyme_abundance_df = \
get_concatenated_raw_data('standard')
CORR_FLUX_L = 'correlation with exp fluxes'
LOG_LIKELIHOOD_L = 'log likelihood of flow'
figure_data = D.get_figure_data()
data = figure_data['standard']
data[CORR_FLUX_L] = rates_df.transpose().corr().loc[9999]
# calculate the likelihood of each EFM according to the measured flux
# distribution
data[LOG_LIKELIHOOD_L] = 0
joined_rates = rates_df.T
joined_rates['std'] = exp_flux_df[D.MEAS_STDEV_L]
joined_rates['std'] = joined_rates['std'].fillna(
0) + 1.0 # add a baseline stdev of 10%
for efm in data.index:
x = (joined_rates[efm] - joined_rates[9999]) / joined_rates['std']
log_likelihood = -(x**2).sum() / 2
data.loc[efm, LOG_LIKELIHOOD_L] = log_likelihood
data.loc[data[D.STRICTLY_ANAEROBIC_L],
D.GROWTH_RATE_L] = 0 # remove oxygen-sensitive EFMs
cmap = D.pareto_cmap(0.88)
D.plot_basic_pareto(data,
axs0[0],
x=D.YIELD_L,
y=D.GROWTH_RATE_L,
c=CORR_FLUX_L,
cmap=cmap,
vmin=0,
vmax=1,
linewidth=0,
s=20)
D.plot_basic_pareto(data,
axs0[1],
x=D.YIELD_L,
y=D.GROWTH_RATE_L,
c=LOG_LIKELIHOOD_L,
cmap=cmap,
linewidth=0,
s=20,
vmin=-100000,
vmax=0)
for ax in axs0:
for efm in D.efm_dict.keys():
xy = np.array(data.loc[efm,
[D.YIELD_L, D.GROWTH_RATE_L]].tolist())
xytext = xy + np.array((-1, 0.025))
ax.annotate(xy=xy,
s=D.efm_dict[efm]['label'],
xycoords='data',
xytext=xytext,
arrowprops=dict(facecolor='black',
shrink=0.05,
width=2,
headwidth=4))
ax.set_xlim(-1e-3, 1.1 * data[D.YIELD_L].max())
ax.set_ylim(-1e-3, 1.15 * data[D.GROWTH_RATE_L].max())
axs0[0].set_title('distance from measured fluxes (correlation)')
axs0[1].set_title('distance from measured fluxes (likelihood)')
fig0.tight_layout()
fig0.savefig(os.path.join(D.OUTPUT_DIR, 'Fig_flux_correlation.pdf'))
def plot_tsne_figure(figure_data, figsize=(15, 13)):
data = figure_data['standard']
# each one of the pareto zipfiles contains the rates of all the EFMs
# so we arbitrarily chose Fig3_pareto to get them.
rates_df, _, _, _ = get_concatenated_raw_data('standard')
X = rates_df.as_matrix()
model = TSNE(n_components=2)
np.set_printoptions(suppress=True)
X_new = model.fit_transform(X)
rates_df_new = pd.DataFrame(index=rates_df.index,
columns=('t-SNE dim 1', 't-SNE dim 2'))
rates_df_new.iloc[:, 0] = X_new[:, 0]
rates_df_new.iloc[:, 1] = X_new[:, 1]
data = rates_df_new.join(data)
#%%
fig, axs = plt.subplots(3, 3, figsize=figsize, sharex=True, sharey=True)
axs = list(axs.flat)
for i, ax in enumerate(axs):
ax.annotate(chr(ord('a') + i),
xy=(0.04, 0.98),
xycoords='axes fraction',
ha='left',
va='top',
size=20)
xdata = rates_df_new.iloc[:, 0]
ydata = rates_df_new.iloc[:, 1]
axs[0].scatter(xdata, ydata, s=15, c=(0.2, 0.2, 0.7), alpha=0.3)
for efm in D.efm_dict.keys():
xy = (xdata[efm], ydata[efm])
axs[0].annotate(s=D.efm_dict[efm]['label'],
xy=xy,
xycoords='data',
xytext=(30, 5),
textcoords='offset points',
arrowprops=dict(facecolor='black',
shrink=0.05,
width=2,
headwidth=4),
ha='left',
va='bottom')
plot_parameters = [
{
'c': D.YIELD_L,
'title': 'biomass yield'
},
{
'c': D.GROWTH_RATE_L,
'title': 'growth rate'
},
{
'c': D.OXYGEN_L,
'title': 'oxygen uptake'
},
{
'c': D.ACE_L,
'title': 'acetate secretion'
},
{
'c': D.NH3_L,
'title': 'ammonia uptake'
},
{
'c': D.SUCCINATE_L,
'title': 'succinate secretion'
},
{
'c': D.ED_L,
'title': 'ED pathway'
},
{
'c': D.PPP_L,
'title': 'pentose phosphate pathway',
},
]
for i, d in enumerate(plot_parameters):
d['ax'] = axs[i + 1]
D.plot_basic_pareto(data,
x=rates_df_new.columns[0],
y=rates_df_new.columns[1],
c=d['c'],
ax=d['ax'],
cmap='copper_r',
linewidth=0.2,
s=10)
d['ax'].set_title(d['title'])
fig.tight_layout()
return fig
def plot_sensitivity_for_reaction(self, reaction):
reaction_data_df = self.efm_data_df[self.efm_data_df['reaction'] ==
reaction]
draw_keq_sensitivity = (reaction_data_df['dmu/dKeq'] != 0).any()
substrates = self.stoich_df[
(self.stoich_df['reaction'] == reaction)
& (self.stoich_df['coefficient'] < 0)]['metabolite'].values
products = self.stoich_df[(self.stoich_df['reaction'] == reaction) & (
self.stoich_df['coefficient'] > 0)]['metabolite'].values
km_data = self.km_sensitivity_df[self.km_sensitivity_df['reaction'] ==
reaction]
n_subfigs = 1 + len(substrates) + len(products)
if draw_keq_sensitivity:
n_subfigs += 1
fig, axs = plt.subplots(1,
n_subfigs,
figsize=(4.5 * n_subfigs, 3),
sharey=True)
axs_stack = list(axs)
ax = axs_stack.pop(0)
D.plot_basic_pareto(reaction_data_df,
ax,
x=D.YIELD_L,
y=D.GROWTH_RATE_L,
c='dlnmu/dlnk',
cmap=D.pareto_cmap(0.83),
linewidth=0)
ax.set_title('sensitivity to $k_{cat}$ of %s' % reaction)
ax.set_ylim(-1e-3, None)
ax.set_xlim(-1e-3, None)
if draw_keq_sensitivity:
ax = axs_stack.pop(0)
D.plot_basic_pareto(reaction_data_df,
ax,
x=D.YIELD_L,
y=D.GROWTH_RATE_L,
c='dlnmu/dlnKeq',
cmap=D.pareto_cmap(0.11),
linewidth=0)
ax.set_title('sensitivity to $K_{eq}$ of %s' % reaction)
ax.get_yaxis().set_visible(False)
ax.set_xlim(-1e-3, 1.05 * reaction_data_df[D.YIELD_L].max())
ax.set_ylim(-1e-3, 1.05 * reaction_data_df[D.GROWTH_RATE_L].max())
for s in substrates:
ax = axs_stack.pop(0)
tmp_df = pd.merge(reaction_data_df,
km_data[km_data['metabolite'] == s],
on='efm')
D.plot_basic_pareto(tmp_df,
ax,
x=D.YIELD_L,
y=D.GROWTH_RATE_L,
c='dlnmu/dlnKm',
cmap=D.pareto_cmap(0.03),
linewidth=0)
ax.set_title('sensitivity to $K_S$ of %s : %s' % (reaction, s))
ax.get_yaxis().set_visible(False)
ax.set_xlim(-1e-3, 1.05 * reaction_data_df[D.YIELD_L].max())
ax.set_ylim(-1e-3, 1.05 * reaction_data_df[D.GROWTH_RATE_L].max())
for p in products:
ax = axs_stack.pop(0)
D.plot_basic_pareto(tmp_df,
ax,
x=D.YIELD_L,
y=D.GROWTH_RATE_L,
c='dlnmu/dlnKm',
cmap=D.pareto_cmap(0.58),
linewidth=0)
ax.set_title('sensitivity to $K_P$ of %s : %s' % (reaction, p))
ax.get_yaxis().set_visible(False)
ax.set_xlim(-1e-3, 1.05 * reaction_data_df[D.YIELD_L].max())
ax.set_ylim(-1e-3, 1.05 * reaction_data_df[D.GROWTH_RATE_L].max())
return fig
rcParams['font.family'] = 'sans-serif'
rcParams['font.sans-serif'] = 'Arial'
rcParams['legend.fontsize'] = 'medium'
rcParams['axes.labelsize'] = 14.0
rcParams['axes.titlesize'] = 14.0
rcParams['xtick.labelsize'] = 12.0
rcParams['ytick.labelsize'] = 12.0
# %% Figure 2c
fig2c, ax2c = plt.subplots(1, 1, figsize=(5, 5))
data = figure_data['standard']
# remove oxygen-sensitive EFMs
data.loc[data[D.STRICTLY_ANAEROBIC_L], D.GROWTH_RATE_L] = 0
D.plot_basic_pareto(data, ax2c, x=D.YIELD_L, y=D.GROWTH_RATE_L,
efm_dict=D.efm_dict,
facecolors=D.PARETO_NEUTRAL_COLOR, edgecolors='none')
ax2c.set_xlim(-1e-3, 1.1*data[D.YIELD_L].max())
ax2c.set_ylim(-1e-3, 1.15*data[D.GROWTH_RATE_L].max())
ax2c.set_title('glucose = 100 mM, O$_2$ = 3.7 mM')
fig2c.tight_layout()
fig2c.savefig(os.path.join(D.OUTPUT_DIR, 'Fig_web4.pdf'))
# %% histogram of all different EFM growth rates in a specific condition
fig5 = plt.figure(figsize=(5, 5))
ax5 = fig5.add_subplot(1, 1, 1)
efm = allocation_pie_chart(ax5, D.STD_CONC['glucoseExt'],
D.STD_CONC['oxygen'])
rates_df, full_df = get_concatenated_raw_data('sweep_glucose')
{'c': D.LACTATE_L, 'short_title': 'lactate secretion'},
{'c': D.SUCCINATE_L, 'short_title': 'succinate secretion'},
]
ax3 = list(ax3.flat)
data = figure_data['standard']
for i, d in enumerate(plot_parameters):
d['ax'] = ax3[i]
d['ax'].annotate(chr(ord('a')+i), xy=(0.02, 0.98),
xycoords='axes fraction', ha='left', va='top',
size=20)
d['ax'].set_title(d['short_title'])
d['ax'].set_xlim(-1e-3, 1.05*data[D.YIELD_L].max())
d['ax'].set_ylim(-1e-3, 1.05*data[D.GROWTH_RATE_L].max())
D.plot_basic_pareto(data, x=D.YIELD_L, y=D.GROWTH_RATE_L,
c=d['c'], ax=d['ax'], cmap='copper_r')
fig3.tight_layout(h_pad=0.2)
D.savefig(fig3, '3')
# %% Figure 4 - glucose & oxygen sweeps
fig4 = plt.figure(figsize=(15, 10))
ax4a = fig4.add_subplot(2, 3, 1, xscale='linear', yscale='linear')
ax4b = fig4.add_subplot(2, 3, 2, xscale='log', yscale='linear', sharey=ax4a)
ax4c = fig4.add_subplot(2, 3, 3, projection='3d')
ax4d = fig4.add_subplot(2, 3, 4, projection='3d')
ax4e = fig4.add_subplot(2, 3, 5, projection='3d')
ax4f = fig4.add_subplot(2, 3, 6, projection='3d')
import pareto_sampling
import seaborn as sns
figure_data = D.get_figure_data()
if __name__ == '__main__':
# %% Figure S1 - same as 3c, but compared to the biomass rate
# instead of growth rate
figS1, axS1 = plt.subplots(1, 2, figsize=(9, 4.5))
data = figure_data['standard']
# remove oxygen-sensitive EFMs
data.loc[data[D.STRICTLY_ANAEROBIC_L], D.GROWTH_RATE_L] = 0
D.plot_basic_pareto(data,
axS1[0],
x=D.YIELD_L,
y=D.BIOMASS_PROD_PER_ENZ_L,
facecolors=D.PARETO_NEUTRAL_COLOR,
edgecolors='none')
axS1[0].set_ylabel(
'enzyme-specific biomass production\n$r_{BM} = v_{BM}/E_{met}$ [gr dw h$^{-1}$ / gr enz]'
)
axS1[0].set_xlim(-1e-3, 1.1 * data[D.YIELD_L].max())
axS1[0].set_ylim(-1e-3, 1.15 * data[D.BIOMASS_PROD_PER_ENZ_L].max())
axS1[0].set_title('glucose = 100 mM, O$_2$ = 3.7 mM')
axS1[0].annotate('c',
xy=(0.02, 0.98),
xycoords='axes fraction',
ha='left',
va='top',
size=20)
for y in range(0, 14, 2):